Reconstructing dynamical networks based on time series of nodal states is of significant interest in many fields of science and engineering. Despite recent progress in network reconstruction, most research focuses on static structures, rather than on dynamic ones with unknown switching instants and number of subnetworks. Therefore, this paper develops a method for reconstructing switching networks, where a new sparse Bayesian learning algorithm is proposed to estimate switching instants. The proposed method is theoretically proved to be convergent. Experimental results are elaborated to demonstrate the effectiveness and superiority of the proposed method.

Energy costs associated with the consumption of nonrenewable energy sources have become an important issue in improving the international competitiveness of agriculture. Wind power, as a renewable energy source, can replace nonrenewable energy sources to reduce energy costs and improve the sustainability of agricultural. However, the inherent intermittency, randomness, and volatility within weather conditions and wind speed present a substantial challenge in accurately predicting wind power generation. This work proposes a novel YJQR-LSTM algorithm that leverages Yeo-Johnson quantile regression (YJQR) with a long short-term memory (LSTM) network for nonparametric probabilistic forecasting of wind power generation via the Intelligent Internet of Things. First, an improved YJQR model based on the YJ transformation is designed to obtain a more precise characterization of wind uncertainty, providing a more flexible probability density function for wind power generation. Then, utilizing the unique structure of the LSTM network to learn the parameters of the YJQR model, temporal features can be extracted from time-series data. To mitigate the impact of outliers in the raw data on accuracy and improve computational efficiency, a novel logarithmic-likelihood function is developed as the loss function utilized in the training phase. The effectiveness of the proposed algorithm is validated using a real-world dataset from five wind farms from the Global Energy Forecasting Competition. Numerical results demonstrate that the algorithm provides more accurate wind power prediction results in complex wind power data environments, which is important for making full use of wind energy and thus reducing the consumption of nonrenewable energy in agriculture.

Periodical time-delay scenario is often encountered in industrial manufacturing processes. However, the presence of time delays and periodical coefficients brings challenges to controller design and system analysis, which thereby hinders the performance improvement of such systems. In this work, the dynamics of milling systems are transformed into a time-invariant finite-dimensional uncertain model described by Fourier series and Padé approximation. An adaptive active control law is accordingly designed to stabilize such complex dynamics. With the assistance of LaSalle–Yoshizawa theorem, conditions are derived to guarantee sufficiently large stability regions of the corresponding closed-loop system. A numerical case study is conducted on a standard two degrees of freedom milling perturbation system to substantiate the superiority of the proposed adaptive active control technique in terms of enlarged stable operational regions.

Imbalanced vibration is an urgent yet challenging problem in active magnetic bearings (AMBs) rotor manufacturing due to the rotor mass imbalance effect. The virtue of active control in AMB systems lies in enabling substantial online mitigation of imbalanced vibrations. However, in practice, due to the lack of speed sensors in most of the existing AMB-rotor systems, efficient rotational speed feedback is still on the way. As a remedy, this article proposes a rotational speed sensor-free synchronous signal processor (SSP) with the double inputs:$x$- and$y$-axes direction displacement measurements of radial AMBs. The proposed SSP is capable of estimating the rotational speed and accordingly generating synchronous signals of the imbalanced vibrations by filtering noise in both directions. Such signals are afterward implemented as a feedforward compensator for eliminating the periodical imbalance effects. With the assistance of the Lyapunov theory, the conditions of the proposed SSP method together with the feedforward imbalance compensator are derived to guarantee the stability of the closed-loop AMB-rotor system. Extensive experimental results substantiate the effectiveness and superiority of the proposed SSP method in terms of imbalanced vibration suppression.

This article proposes a distributed cooperative manipulation control scheme for multirobot systems to track reference trajectories with unknown payload dynamics, grasp positions, and external disturbances. An online learning module is established to estimate the payload dynamics. Then a wrench-synthetic trajectory tracking control protocol is thereby developed to manipulate an object under unknown external disturbances no matter where the grasping points are. Moreover, sufficient conditions are derived to guarantee the uniform boundedness of the tracking errors of the closed-loop cooperative manipulation system. Finally, numerical simulations are conducted to substantiate the effectiveness of the proposed cooperative manipulation control scheme.

Sparse representation has been widely applied to image classification, where the key issue is to extract a suitable discriminative dictionary. To this end, we propose a joint dictionary and classifier learning algorithm based on a parameterized Bayesian model. Therein, the Gaussian priors of a dictionary endow it with the capability of discrimination and representation. Moreover, we introduce a multivariate Gaussian prior for the sparse codes to achieve group sparsity, thereby substantially improving the classification performance. Furthermore, the sparse codes are estimated by a group-sparse Bayesian learning (GSBL) method, and the dictionary atoms are updated sequentially by maximizing a posterior. Moreover, to avoid manual parameter adjustment, the hyperparameters are optimized by an evidence maximization method. Accordingly, we develop a classification scheme via GSBL. Finally, extensive experiments are conducted on six benchmark datasets of face classification, object recognition, handwritten recognition, and scene categorization to substantiate the effectiveness and superiority of the proposed method.

Chatter is a typical kind of unstable dynamics often encountered in machining processes, which often results in overcut and rapid tool wear. Hence, chatter phenomenon worsens the surface quality and reduces productivity in milling systems as well. Recent years have witnessed a surging industrial demand of high quality and high efficiency machining. Specifically, for low radial immersion milling situation, large depth of cuts is inevitably needed so as to increase the machining efficiency. To fulfill such a task, this paper develops a robust active control method to mitigate the chatter dynamics of low radial immersion milling processes. The present approach increases the axial depth of cuts, and the improvement is inversely proportional to the radial immersion ratio. Finally, case studies are conducted to show the substantially enlarged stable region in the stability lobe diagram (SLD) spanned by spindle rotational speed and axial depth of cut. Thus, the method can be expected to improve the efficiency of milling processes.