Shenyang Institute of Automation,Chinese Academy Of Sciences
Not a member yet
23582 research outputs found
Sort by
A Surrogate-Assisted Many-Objective Evolutionary Algorithm Using Multi- Classification and Coevolution for Expensive Optimization Problems
No full textSurrogate-assisted evolutionary algorithms have received a surge of attentions for their promising ability of solving expensive optimization problems. Existing surrogate-assisted evolutionary algorithms usually adopt the regression models and the binary classification models to guide the evolution of the population for solving the multiobjective optimization problems. However, the regression models will make the algorithm to be increasingly computation-expensive as the number of objectives increases, while the use of the binary classification models might suffer from the poor diversity since the diversified information of solutions cannot be reflected in these classification models. For this issue, this paper proposes a surrogate-assisted many-objective evolutionary algorithm using the cooperation of the multi-classification and regression models to improve the search quality while reducing the computational cost. Our approach includes two parts: At the model training stage, a multi-classification model is constructed to divide the whole population into several classes for ensuring diversity, a distance regression model and an angle regression model are used to select solutions with better convergence and diversity in each class; At the evolution stage, a coevolutionary framework is used to guide the evolution according to a new selection criterion. Experimental results verify the effectiveness of the proposed algorithm on a set of expensive test problems with up to 10 objectives.</p
Mechatronics design of self-adaptive under-actuated climbing robot for pole climbing and ground moving
No full textClimbing robots have broad application prospects in aerospace equipment inspection, forest farm monitoring, and pipeline maintenance. Different types of climbing robots in existing research have different advantages. However, the self-adaptability and stability have not been achieved at the same time. In order to realize the self-adaptability of holding and climbing stability, this work proposes a new type of climbing robot under the premise of minimizing the driving source. The robot realizes stable multifinger holding and wheeled movement through two motors. At the same time, the robot has two different working modes, namely pole climbing and ground crawling. The holding adaptability and climbing stability are realized by underactuated holding mechanism and model reference adaptive controller (MRAC). On the basis of model design and parameter analysis, a prototype of the climbing robot is built. Experiments prove that the proposed climbing robot has the ability to stably climb poles of different shapes. The holding and climbing stability, self-adaptability, and climbing and crawling speed of the proposed climbing robot are verified by experiments
Accurate and robust feature description and dense point-wise matching based on feature fusion for endoscopic images
No full textDespite the rapid technical advancement of augmented reality (AR) and mixed reality (MR) in minimally invasive surgery (MIS) in recent years, monocular-based 2D/3D reconstruction still remains technically challenging in AR/MR guided surgery navigation nowadays. In principle, soft tissue surface is smooth and watery with sparse texture, specular reflection, and frequent deformation. As a result, we frequently obtain only sparse feature points that give rise to incorrect matching results with conventional image processing methods. To ameliorate, in this paper we enunciate an accurate and robust description and matching method for dense feature points in endoscopic videos. Our new method first extracts contours of the low-rank image sequences based on the adaptive robust principal component analysis (RPCA) decomposition. Then we propose a multi-scale dense geometric feature description approach, which simultaneously extracts dense feature descriptors of the contours in the original Euclidean coordinate space, the accompanying 3D color coordinate space, and the derived curvature-gradient coordinate space. Finally, we devise a new algorithm for both global and local point-wise matching based on feature fusion. For global matching, we employ the fast Fourier transform (FFT) to reduce the dimension of the dense feature descriptors. For local feature point matching, in order to enhance the robustness and accuracy of the matching, we cluster multiple contour points to form "super-point" based on dense feature descriptors and their spatio-temporal continuity. The comprehensive experimental results confirm that our novel approach can overcome the highlight influence, and robustly describe contours from image sequences of soft tissue surfaces. Compared with the state-of-the-art feature point description and matching methods, our analysis framework shows the key advantages of both robustness and accuracy in dense point-wise matching, even when the severe soft tissue deformation occurs. Our new approach is expected to have high potential in 2D/3D reconstruction in endoscopy
Sensor fault estimation and fault tolerant control for IT2 fuzzy system via sliding mode approach
No full textThe point of this article is the sensor fault estimation and fault-tolerant controller design for IT2 fuzzy systems via sliding mode approach. In order to estimate accurately the system states and sensor faults, a novel proportional and derivative sliding mode observer is introduced, which provide more design freedom and eliminate the effects of sensor faults. By splitting the operating domain and estimating the membership functions, a set of relaxation stability conditions subject to the information of membership functions and system states are obtained. Then, a sliding mode controller in form of IT2 fuzzy model is designed to stabilize the closed-loop systems. An example of bolt-tightening tool model is considered to demonstrate the validity of the proposed results
Special issue on cyber-physical systems and intelligent control in honor of the 65th birthday of Professor Bijoy K. Ghosh
No full textIt is our great pleasure to organize this special issue in Control Theory and Technology in honor of the 65th birthday of Professor Bijoy K. Ghosh, who has made many truly outstanding contributions to the field of systems and control through the years, which include robust and nonlinear control, robotics and machine vision in his earlier research period, and his recent focus on biology and biomedical modeling, learning control and multi-agent systems to name a few.</p
Distributed Secure State Estimation for Cyber-Physical Systems Against Replay Attacks via Multisensor Method
No full textThis article investigates the distributed secure state estimation problem for cyber-physical systems under replay attacks. The main purpose is to design the distributed observers such that the estimation error system is stable. First, a detection algorithm is proposed to not only expose the behavior of the attacker but also identify which sensor is tampered. Then, the distributed observers are designed and the adverse effects are eliminated. Moreover, in view of the linear matrix inequality technique, a sufficient condition is presented, which ensures that the estimation error system is stable and achieves an property. Finally, a practical inverted pendulum example is employed to elaborate the effectiveness and superiority of the presented design and detection method.</p
Steady-state sequence optimization with incremental input constraints in two-layer model predictive control
No full textSteady-state optimization is of vital importance in two-layer model predictive control for bringing better steady-state and dynamic performance. However, the global optimality of steady-state sequences provided by local steady-state optimization cannot be guaranteed. Therefore, a new steady-state sequence optimization approach is proposed in the paper, to improve the global optimality of steadystate sequences. First, the non-global optimality of local steady-state sequences is discussed using an example. Subsequently, aiming at improving the global optimality, a novel sequence optimization strategy designed for steady-state optimization is proposed. Its basic formulation is given and the lower bound of the introduced parameter is analyzed. Then, the relation and difference between the proposed steady-state sequence optimization and the existing global steady-state optimization and local steady-state optimization are discussed. Finally, the steady-state performance, dynamic performance, and computational burden of the proposed approach are studied. The proposed approach provides engineers a brand-new way to realize steady-state optimization and effectively improves the global optimality of calculated steady-state sequences. Extensive simulations verify the effectiveness and reliability of the proposed method.</p
Fault Diagnosis Based on RseNet-LSTM for Industrial Process
No full textAiming at the problems that conventional data-driven diagnosis methods are difficult to adaptively extract effective features from industrial process data, and do not make full use of the time series characteristics of process data, in this paper, a fault diagnosis method based on residual convolutional neural networks and long short-term memory networks (ResNet-LSTM) is developed. Firstly, the local spatial features of process data are captured by the deep residual convolution network. Then, the time series characteristics of process data are extracted by LSTM. Finally, the output of the fault category is performed through the softmax classifier. This method can extract features adaptively, more fully extract features in time series fault data, and effectively reduce the difficulty of deep neural network training. The benchmark Tennessee-Eastman (TE) process is used to validate performance of the proposed method. The ResNet-LSTM model is compared with the CNN, LSTM, ResNets, CNN-LSTM models, and the experiment results show that the ResNet-LSTM method achieves better performance
Review of snake robots in constrained environments
No full textSnake robots have advantages of terrain adaptability over wheeled mobile robots and traditional articulated robot arms because of their limbless thin body structure and high flexibility. They have extensive applications in tasks such as rescue, disaster recovery, inspection and minimally invasive surgery. Current research on snake robots is mainly focused on snake-like locomotion and the embodiment of these motion gaits for different applications. Modular structure and real-time control algorithms are two key aspects for snake robots operating in constrained environments. This review will attempt to address both. First, a review on the snake motion and the body structure is provided, which outlines the biological foundation of all snake robots. This is followed by the mechanical structure of snake robots, especially the structure of elemental snake modules. Finally, control algorithms for variant terrain contours and obstacle avoidance are discussed. The review also outlines emerging application areas and potential future directions of snake robots.</p
Queue assignment for fixed-priority real-time flows in time-sensitive networks: Hardness and algorithm
No full textTime sensitive networks (TSNs) enable deterministic real-time communication over Ethernet networks. According to IEEE 802.1Qbv standards, TSN switches use gates between queues and their corresponding egress ports to facilitate timing-deterministic communications. Management of switch resources, such as queues, has a significant impact on the schedulability of real-time flows. In this paper, we look into the theoretical foundation of queue management in TSN switches. We prove that the queue assignment problem for real-time flows on time sensitive networks under static priority scheduling is NP-hard in the strong sense, even if the number of queues per port is 3. Then we formulate the problem as a satisfiability modulo theories (SMT) specification. Besides, we propose a worst case response time analysis and a fast heuristic algorithms by eliminating scheduling conflicts. Experiments with randomly generated workload demonstrate the effectiveness of our algorithms for queue assignment of real-time flows.</p