Jiahan Bao

Model predictive control (MPC) is increasingly applied in quadrotor unmanned aerial vehicle (UAV) control due to its ability to explicitly handle constraints and its other advantages. However, existing research has yet to consider the impact of aligning the prediction horizon with the real-time velocity of the UAV on trajectory tracking control performance. To address this issue, this paper first analyzes how the prediction horizon influences tracking accuracy under various speed conditions. Based on this analysis, an adaptive prediction horizon model predictive control (APH-MPC) strategy is proposed. This approach determines the optimal prediction horizon parameters for MPC at different target velocities using the grey relational analysis (GRA), and derives the optimal prediction horizon control law via third-order polynomial fitting. Furthermore, an event-triggered mechanism is introduced to enhance the real-time performance of MPC. Experimental results demonstrate that APH-MPC maintains accurate trajectory tracking for UAVs under varying speed conditions while reducing computational cost. This study improves the robustness of MPC in UAV trajectory tracking control.

1. With the continuous increase in global demand for coal resources, belt conveyors have assumed the primary role in transportation, and their scope of application continues to expand (Zrnić et al....

It is meaningful to learn fault-related information from multi-sensor signals automatically and provide accurate diagnostic results. To further improve the multi-sensor information fusion effect, reduce the discrepancy between the real value and predicted value, and improve the rolling bearing fault diagnosis accuracy, in this paper, a novel ensemble learning-based multi-sensor information fusion method is proposed. Firstly, a multi-scale convolutional neural network (MSCNN) is constructed as a base learning model to learn multi-scale features of raw vibration signals. Secondly, based on the ensemble learning framework, a multi-branch MSCNN is built to realize the simultaneous extraction of multiple sensor signal features and output the decision score of each sensor. Then, considering the confidence of multiple different sensors, fuzzy rank is utilized to fuse the decision scores of each sensor, minimizing the discrepancy between the real value and predicted value. Finally, the usefulness and robustness of proposed method are validated on two different types of rolling bearing datasets. The dataset and code are available under request and the contact e-mail is pantc2006@163.com.

Transfer learning can meet the challenge of cross-condition fault diagnosis. However, the diagnostic effectiveness of transfer learning in actual applications is unsatisfactory, mainly due to the great unbalance in labeling between testing and training samples. A one-dimensional dual residual squeeze-and-excitation transfer learning network (1D-DRSETL) is proposed for an unsupervised accurate intelligent diagnosis under cross-condition in this paper for unlabeled small sample. First, a special block is designed to obtain transferable features by adaptively focusing on fault-sensitive information. Second, the joint maximum mean discrepancy is utilized to deal with the feature matching problem under cross-conditions. Then, speed up model training with AdaBelief optimizer. Finally, cross-conditions transfer diagnosis experiments are designed to demonstrate the superiority of the method based on a self-made dataset and the publicly available rolling bearings dataset. The experimental results show that the proposed method can achieve higher fault diagnosis accuracy and better robustness under cross-conditions than the contrasting methods.

It is important to study the vibration of rolling mills to improve the stability of rolling production. A dynamic rolling process model is established by considering the elastic recovery of the exit strip and the influence of multiroll equilibrium, and the accuracy of the model is verified by experimental data. On this basis, based on the distribution of friction force in the deformation zone, the rolling force and rolling torque are nonlinearized. In addition, a rolling mill structure model is established by considering the structure gap and a piecewise nonlinear horizontal‐vertical‐torsional vibration model of the rolling mill is established by combining the structure model and dynamic rolling process model. Finally, the amplitude‐frequency characteristics of the work roll under different external excitation amplitude and the dynamic bifurcation characteristics of the work roll under different gaps are analyzed. The study indicates that, by reducing excitation amplitude and structure gap, the system vibration can be reduced. The research results can provide a theoretical reference for further exploration of the coupling vibration of hot rolling mills.

Multiscale fuzzy entropy (MFE), as an enhanced multiscale sample entropy (MSE) method, is an effective nonlinear method for measuring the complexity of time series. In this paper, an improved MFE algorithm termed composite interpolation-based multiscale fuzzy entropy (CIMFE) is proposed by using cubic spline interpolation of the time series over different scales to overcome the drawbacks of the coarse-grained MFE process. The proposed CIMFE method is compared with MSE and MFE by analyzing simulation signals and the result indicates that CIMFE is more robust than MSE and MFE in analyzing short time series. Taking this into account, a new fault diagnosis method for rolling bearing is presented by combining CIMFE for feature extraction with Laplacian support vector machine for fault feature classification. Finally, the proposed fault diagnosis method is applied to the experiment data of rolling bearing by comparing with the MSE, MFE and other existing methods, and the recognition rate of the proposed method is 98.71%, 98.71%, 98.71%, 98.71% and 100% under different training samples (5, 10, 15, 20 and 25), which is higher than that of the existing methods.