Entity

Time filter

Source Type


Zhang W.,Beijing University of Technology | Zhang W.,Beijing Key Laboratory of Computational Intelligence and Intelligence System | Qiao J.-F.,Beijing University of Technology | Qiao J.-F.,Beijing Key Laboratory of Computational Intelligence and Intelligence System
Proceedings of the World Congress on Intelligent Control and Automation (WCICA) | Year: 2015

In this paper, a direct adaptive neural network control (DANNC) method is developed to deal with the multi-variable (dissolved oxygen concentration and nitrate concentration) tracking control problem in wastewater treatment processes (WWTPs), which avoids the perplex issue of establishing the plant model of WWTP and has the excellent adaptive ability. The DANNC system is composed of neural controller and compensation controller. The neural controller is employed to approximate an ideal control law, and the compensation controller is designed to offset the network approximation error. The controller parameters' adaptive laws are deduced by the Lyapunov theorem. Simulation results, based on the international benchmark simulation model No.1 (BSM1), show that the control accuracy and dynamic performance of the DANNC method are improved nicely. © 2014 IEEE. Source


Qiao J.,Beijing University of Technology | Qiao J.,Beijing Key Laboratory of Computational Intelligence and Intelligence System | Zhang W.,Beijing University of Technology | Zhang W.,Henan Polytechnic University | And 3 more authors.
Journal of Intelligent and Fuzzy Systems | Year: 2016

In order to improve the accuracy and adaptive ability of dissolved oxygen concentration control in the wastewater treatment process (WWTP), a self-organizing fuzzy control (SOFC) method is developed in this paper. The main feature of this control system is that the fuzzy controller can extract fuzzy rules automatically using a self-organizing fuzzy neural network (FNN), which can adjust the network structure during the process based on the growing-pruning-combining algorithm. Furthermore, to ensure the convergence of the system, a compensation controller is designed to dispel the FNN approximation error, and the parameter compensation is also considered while adjusting the network structure. Finally, simulation results, based on the international benchmark simulation model No.1 (BSM1), demonstrate that the proposed method can achieve better control performance and superior adaptive ability compared with PID, model predictive control and conventional fuzzy logic controller. © 2016 - IOS Press and the authors. All rights reserved. Source


Pei F.-J.,Beijing University of Technology | Pei F.-J.,Beijing Key Laboratory of Computational Intelligence and Intelligence System | Yang D.,Beijing University of Technology | Yang D.,Beijing Key Laboratory of Computational Intelligence and Intelligence System | And 2 more authors.
Beijing Gongye Daxue Xuebao/Journal of Beijing University of Technology | Year: 2015

Bending, noise, fluid fluctuation are the main features of pipline in ship. Aiming at these problems, this paper proposed a ship pipeline leakage detection system using linear Sagnac optical fiber interferometer. This system designed a optical fiber sensor by selecting the length of eliminated blind optical fiber to find out the optimal optical fiber position. The design process of this system was based on four key elements: eliminating blind area of zero frequency, avoiding repeating zero frequency, easy to emerging of zero frequency, and preventing noise frequency pollution. Moreover, this paper integrated circuit, optical path and detector into monitor case, and made a detection system into instrument. Experiment results show that leak signal can be precisely detected by instrument in time. This monitor instrument can effectively solve how to detect the complexity ship pipline precisely in excellent stability. ©, 2015, Beijing University of Technology. All right reserved. Source


Li W.,Beijing University of Technology | Li W.,Beijing Key Laboratory of Computational Intelligence and Intelligence System | Han H.,Beijing University of Technology | Han H.,Beijing Key Laboratory of Computational Intelligence and Intelligence System | And 2 more authors.
IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CICA 2014: 2014 IEEE Symposium on Computational Intelligence in Control and Automation, Proceedings | Year: 2015

This paper proposes a novel input-output clustering approach for structure identification of T-S fuzzy neural networks. This approach consists of two phases. Firstly, k-means clustering method is applied to the input data to provide the initial clusters of the input space. Secondly, check whether the sub-clustering is needed for each input cluster by considering the corresponding output variation and then apply the k-means method to further partition those input clusters needed sub-clustering. Applying the above process recursively leads to the structure identification of a T-S fuzzy neural network and then the parameter identification is completed by using the gradient learning algorithm. The experiments by applying the proposed method to several benchmark problems show better performance compared with many existing methods and then verify the effectiveness and usefulness of the proposed method. © 2014 IEEE. Source


Pei F.-J.,Beijing University of Technology | Pei F.-J.,Beijing Key Laboratory of Computational Intelligence and Intelligence System | Cheng Y.-H.,Beijing University of Technology | Cheng Y.-H.,Beijing Key Laboratory of Computational Intelligence and Intelligence System | And 4 more authors.
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | Year: 2015

To solve the problem of the simultaneous localization and mapping (SLAM) under the complex circumstance, a distributed algorithm of the SLAM based on partition of space-region is proposed considering the respective advantages of centralized configuration and distributed structure. The region is formed according to the angle between two landmarks and the robot, which is designed in case of the collinearity between two landmarks. The landmarks in each region are combined to establish the corresponding observation model. Besides, the position of the robot is obtained by applying the distributed unscented particle filter and the positions of the landmarks are estimated simultaneously by employing the Kalman filter. Meanwhile, the accuracy and the stability are improved through constructing the adjustment of particle distribution during the dynamic reconfiguration process. Eventually, the better real-time capability and filter accuracy of the proposed SLAM algorithm are proved through simulation experiments which are supported by actual data. ©, 2015, Chinese Institute of Electronics. All right reserved. Source

Discover hidden collaborations