Kongzhi yu Juece/Control and Decision (ISSN:1001-0920) is a monthly peer-reviewed scopus indexed journal originally founded in 1986. It is sponsored by the Ministry of Education, china and Northeastern University, china. Kongzhi yu Juece/Control and Decision (ISSN:1001-0920) has always adhered to the correct purpose of running the journal, and has been committed to gathering and disseminating excellent academic achievements, inspiring technological innovation, and promoting the development of disciplines in my country.Aiming at major national needs and international frontiers, this journal has published a large number of original and high-level research result. The journal was selected into the "China Science and Technology Journal Excellence Action Plan Project" in December 2019.In the future, it will strive to build an open innovation, collaborative integration.
This paper proposes an adaptive optimal control method for active suspension systems subject to unknown dynamics and multiple performance indices. dynamics. Then, a cost function concerning the ride comfort, suspension stroke and control input is established, which aims at achieving a compromise between the performance indices. Furthermore, a single layer neural network (NN) is used to estimate the optimal, cost f by which the Hamiltonian function can be derived. To obtain the online solution, a novel adaptive law driven by the parameter estimation error is developed to update the unknown N
This paper presents a distributed multi-objective model predictive control (MPC) strategy for multi-objective control problems of nonlinear vehicle platoon systems subject to state and control constraints. Based on the predecessor-follower communication topology, the nonlinear longitudinal cruise control models of connected vehicle platoons are established. The lexicographic method is applied to formulate the distributed multi-objective optimization problem. Moreover, together with the triple elements of MPC, the constraints on string stability and contractive are designed to guarantee stab
This paper investigates the finite time prescribed performance control strategy for the trajectory tracking problem of quadrotor UAVs with time-vary disturbance, model uncertainty and constraint of the output error. Firstly, the UAVs dynamic model is decoupled into an sub atitude system and. Then, the finite time convergence of the conversion error is realized, and the output error of the original system is limited by introducing the error conversion function, performance constraint function and designing the fast terminal sliding surface reasonably. The designed controller can guarantee th
Aiming at the problems of low segmentation accuracy of small targets, high computational complexity, and slow convergence in the U-Net, an U-Net network based on dilated convolution and reconstructed sampling units (DSU-Net) is constructed. In the DSU-Net, in order to increase the receptive field of image feature extraction and fuse multi-scale information, dilated convolutional layers with different dilation rates are designed; in view of the shortcoming of losing a large amount of semantic information during the pooling process, sampling units which combine pooling and convolution are con
Accurate prediction of key parameters in tobacco primary processing plays a key role in its precise optimization and control. Existing prediction methods usually do not consider time dynamic characteristics, and the performance of multi-step prediction is not good, which cannot meet the actual index needs of tobacco primary processing. In response to the above problems, a multi-step prediction method for key parameters of tobacco primary processing based on the time-varying attention-temporal convolutional network (TVA-TCN) is proposed. Firstly, for the key information in the input variable