This paper presents a novel neural-fuzzy-based adaptive sliding mode automatic steering control strategy to improve the driving performance of vision-based unmanned electric vehicles with time-varying and uncertain pa...This paper presents a novel neural-fuzzy-based adaptive sliding mode automatic steering control strategy to improve the driving performance of vision-based unmanned electric vehicles with time-varying and uncertain parameters.Primarily,the kinematic and dynamic models which accurately express the steering behaviors of vehicles are constructed,and in which the relationship between the look-ahead time and vehicle velocity is revealed.Then,in order to overcome the external disturbances,parametric uncertainties and time-varying features of vehicles,a neural-fuzzy-based adaptive sliding mode automatic steering controller is proposed to supervise the lateral dynamic behavior of unmanned electric vehicles,which includes an equivalent control law and an adaptive variable structure control law.In this novel automatic steering control system of vehicles,a neural network system is utilized for approximating the switching control gain of variable structure control law,and a fuzzy inference system is presented to adjust the thickness of boundary layer in real-time.The stability of closed-loop neural-fuzzy-based adaptive sliding mode automatic steering control system is proven using the Lyapunov theory.Finally,the results illustrate that the presented control scheme has the excellent properties in term of error convergence and robustness.展开更多
Based on the developed neural-fuzzy control system for anaerobic hybrid reactor （AHR） in wastewater treatment and biogas production, the neural network with backpropagation algorithm for prediction of the variables ...Based on the developed neural-fuzzy control system for anaerobic hybrid reactor （AHR） in wastewater treatment and biogas production, the neural network with backpropagation algorithm for prediction of the variables pH, alkalinity （Alk） and total volatile acids （TVA） at present day time t was used as input data for the fuzzy logic to calculate the influent feed flow rate that was applied to control and monitor the process response at different operations in the initial, overload influent feeding and the recovery phases. In all three phases, this neural-fuzzy control system showed great potential to control AHR in high stability and performance and quick response. Although in the overloading operation phase II with two fold calculating influent flow rate together with a two fold organic loading rate （OLR）, this control system had rapid response and was sensitive to the intended overload. When the influent feeding rate was followed by the calculation of control system in the initial operation phase I and the recovery operation phase III, it was found that the neural-fuzzy control system application was capable of controlling the AHR in a good manner with the pH close to 7, TVA/Alk 〈 0.4 and COD removal 〉 80% with biogas and methane yields at 0.45 and 0.30 m^3/kg COD removed.展开更多
Iran is located on a silver, lead, and zinc belt and according to the latest studies holds 11 million tons of lead, zinc, and silver stones which constitute 4 percent of global resources. Considering that mineral mate...Iran is located on a silver, lead, and zinc belt and according to the latest studies holds 11 million tons of lead, zinc, and silver stones which constitute 4 percent of global resources. Considering that mineral materials are explored in an uncertain space, exploration investment risk is an inseparable part of these activities. The important fact is to minimize the effect of this undesired factor in exploration. To achieve this, it is required that exploration activities and withdrawals are performed in a certain framework in which risk minimization is considered. Using mineral potential modelling for determining promising zones which should be taken into consideration in more detailed stages could make achieving the purpose possibly. This work is aimed at applying fuzzy neural network and TOPSIS methods simultaneously in order to explore zinc and lead resources. In this article, geological, telemetry, geophysics, and geochemistry data is integrated using fuzzy-neural network (neuro fuzzy) and using TOPSIS method rating for lead and zinc ore deposit potential mapping in Isfahan-Khomein strip which has been introduced as one of zinc and leads mineral scopes in Iran. This area which is composed of several zinc and lead ore deposits has been considered as the target area. Fuzzy integration results of zinc and lead mineralization witness layers confirm the relatively high potential of lead and zinc mineralization in this region having a northwest-southeast trend and involving more than 90 percent of the known indices and ore deposits of the region. In this research, it was shown that the results of TOPSIS-Neuro-Fuzzy integrated model (a combination of neural network and fuzzy logic) have increased the resolution of talented areas from the areas with no mineralization potential in comparison with the fuzzy method individually.展开更多
Robot learning in unstructured environments has been proved to be an extremely challenging problem, mainly because of many uncertainties always present in the real world. Human beings, on the other hand, seem to cope ...Robot learning in unstructured environments has been proved to be an extremely challenging problem, mainly because of many uncertainties always present in the real world. Human beings, on the other hand, seem to cope very well with uncertain and unpredictable environments, often relying on perception-based information. Furthermore, humans beings can also utilize perceptions to guide their learning on those parts of the perception-action space that are actually relevant to the task. Therefore, we conduct a research aimed at improving robot learning through the incorporation of both perception-based and measurement-based information. For this reason, a fuzzy reinforcement learning (FRL) agent is proposed in this paper. Based on a neural-fuzzy architecture, different kinds of information can be incorporated into the FRL agent to initialise its action network, critic network and evaluation feedback module so as to accelerate its learning. By making use of the global optimisation capability of GAs (genetic algorithms), a GA-based FRL (GAFRL) agent is presented to solve the local minima problem in traditional actor-critic reinforcement learning. On the other hand, with the prediction capability of the critic network, GAs can perform a more effective global search. Different GAFRL agents are constructed and verified by using the simulation model of a physical biped robot. The simulation analysis shows that the biped learning rate for dynamic balance can be improved by incorporating perception-based information on biped balancing and walking evaluation. The biped robot can find its application in ocean exploration, detection or sea rescue activity, as well as military maritime activity.展开更多
基金Supported by National Basic Research Project of China(Grant No.2016YFB0100900)National Natural Science Foundation of China(Grant No.61803319)+2 种基金Shenzhen Municipal Science and Technology Projects of China(Grant No.JCYJ20180306172720364)Fundamental Research Funds for the Central Universities of China(Grant No.20720190015)State Key Laboratory of Automotive Safety and Energy of China(Grant No.KF2011).
文摘This paper presents a novel neural-fuzzy-based adaptive sliding mode automatic steering control strategy to improve the driving performance of vision-based unmanned electric vehicles with time-varying and uncertain parameters.Primarily,the kinematic and dynamic models which accurately express the steering behaviors of vehicles are constructed,and in which the relationship between the look-ahead time and vehicle velocity is revealed.Then,in order to overcome the external disturbances,parametric uncertainties and time-varying features of vehicles,a neural-fuzzy-based adaptive sliding mode automatic steering controller is proposed to supervise the lateral dynamic behavior of unmanned electric vehicles,which includes an equivalent control law and an adaptive variable structure control law.In this novel automatic steering control system of vehicles,a neural network system is utilized for approximating the switching control gain of variable structure control law,and a fuzzy inference system is presented to adjust the thickness of boundary layer in real-time.The stability of closed-loop neural-fuzzy-based adaptive sliding mode automatic steering control system is proven using the Lyapunov theory.Finally,the results illustrate that the presented control scheme has the excellent properties in term of error convergence and robustness.
基金the Thailand Graduate Institute of Science and Technology(No. TGIST 01-47-038)the National Science and Technology Development Agency(NSTDA) for Ph.D.Scholarship to Mr. Chaiwat Waewsakthe National Research Council of Thailand for research grant under Fiscal Year 2008 Budget to King Mongkut’s University of Technology Thonburi
文摘Based on the developed neural-fuzzy control system for anaerobic hybrid reactor （AHR） in wastewater treatment and biogas production, the neural network with backpropagation algorithm for prediction of the variables pH, alkalinity （Alk） and total volatile acids （TVA） at present day time t was used as input data for the fuzzy logic to calculate the influent feed flow rate that was applied to control and monitor the process response at different operations in the initial, overload influent feeding and the recovery phases. In all three phases, this neural-fuzzy control system showed great potential to control AHR in high stability and performance and quick response. Although in the overloading operation phase II with two fold calculating influent flow rate together with a two fold organic loading rate （OLR）, this control system had rapid response and was sensitive to the intended overload. When the influent feeding rate was followed by the calculation of control system in the initial operation phase I and the recovery operation phase III, it was found that the neural-fuzzy control system application was capable of controlling the AHR in a good manner with the pH close to 7, TVA/Alk 〈 0.4 and COD removal 〉 80% with biogas and methane yields at 0.45 and 0.30 m^3/kg COD removed.
文摘Iran is located on a silver, lead, and zinc belt and according to the latest studies holds 11 million tons of lead, zinc, and silver stones which constitute 4 percent of global resources. Considering that mineral materials are explored in an uncertain space, exploration investment risk is an inseparable part of these activities. The important fact is to minimize the effect of this undesired factor in exploration. To achieve this, it is required that exploration activities and withdrawals are performed in a certain framework in which risk minimization is considered. Using mineral potential modelling for determining promising zones which should be taken into consideration in more detailed stages could make achieving the purpose possibly. This work is aimed at applying fuzzy neural network and TOPSIS methods simultaneously in order to explore zinc and lead resources. In this article, geological, telemetry, geophysics, and geochemistry data is integrated using fuzzy-neural network (neuro fuzzy) and using TOPSIS method rating for lead and zinc ore deposit potential mapping in Isfahan-Khomein strip which has been introduced as one of zinc and leads mineral scopes in Iran. This area which is composed of several zinc and lead ore deposits has been considered as the target area. Fuzzy integration results of zinc and lead mineralization witness layers confirm the relatively high potential of lead and zinc mineralization in this region having a northwest-southeast trend and involving more than 90 percent of the known indices and ore deposits of the region. In this research, it was shown that the results of TOPSIS-Neuro-Fuzzy integrated model (a combination of neural network and fuzzy logic) have increased the resolution of talented areas from the areas with no mineralization potential in comparison with the fuzzy method individually.
文摘Robot learning in unstructured environments has been proved to be an extremely challenging problem, mainly because of many uncertainties always present in the real world. Human beings, on the other hand, seem to cope very well with uncertain and unpredictable environments, often relying on perception-based information. Furthermore, humans beings can also utilize perceptions to guide their learning on those parts of the perception-action space that are actually relevant to the task. Therefore, we conduct a research aimed at improving robot learning through the incorporation of both perception-based and measurement-based information. For this reason, a fuzzy reinforcement learning (FRL) agent is proposed in this paper. Based on a neural-fuzzy architecture, different kinds of information can be incorporated into the FRL agent to initialise its action network, critic network and evaluation feedback module so as to accelerate its learning. By making use of the global optimisation capability of GAs (genetic algorithms), a GA-based FRL (GAFRL) agent is presented to solve the local minima problem in traditional actor-critic reinforcement learning. On the other hand, with the prediction capability of the critic network, GAs can perform a more effective global search. Different GAFRL agents are constructed and verified by using the simulation model of a physical biped robot. The simulation analysis shows that the biped learning rate for dynamic balance can be improved by incorporating perception-based information on biped balancing and walking evaluation. The biped robot can find its application in ocean exploration, detection or sea rescue activity, as well as military maritime activity.
