This work is focused on an underwater manipulator. To solve its nonlinear dynamics and hydrodynamics when it operates underwater, model reference adaptive control (MRAC) is applied. The output of the reference model represents the expected transient response. Adaptive controller parameters are adjusted on-line in real time according to the error between the reference model output and the system output and the outputs of the state filters, using an adaptive parameter regulator. The system control input is thus achieved such that the system output can track the reference model output. Simulation results demonstrate that the proposed control scheme has accurate tracking ability and can greatly improve the dynamic and static properties of the system. The MRAC for the underwater manipulator is also fairly robust to load disturbance and system parameter variation.

The existing rolling bearing fault diagnosis method based on the deep convolutional neural network has the issues of insufficient feature extraction ability, poor anti-noise ability, and a large number of model parameters. A lightweight bearing fault diagnosis method based on depthwise separable convolutions is proposed. The proposed method can simultaneously extract different features from vibration signals in different directions to enhance the stability of the diagnosis model. The lightweight unit based on depthwise separable convolutions in the feature extraction layer reduces the size of the model and the number of parameters that need to be learned. The vibration signals of bearings in different directions are converted into time-frequency signals by the short-time Fourier transform (STFT) and then into pictures as the input of the model. In order to verify the effectiveness and generalization of the method, this paper uses the gearbox data set of Southeast University and the CWRU (Case Western Reserve University) bearing data set for experiments. Comparisons of bearing fault diagnosis results using the proposed model with other classical deep learning models are implemented. The results show that the proposed model is superior to other classical deep learning models; thus, it has a smaller model size, higher accuracy, and less computation burden. Compared with using a single-direction vibration signal as input, the proposed model that uses multiple vibration signals in different directions as input has more accuracy.

In this article, an attitude tracking controller is designed for a quadrotor unmanned aerial vehicle (UAV) subject to lumped disturbances. Firstly, the attitude dynamical model of the quadrotor under external disturbances is established. Subsequently, an improved sliding mode control (SMC) strategy is designed based on the linear extended state observer (LESO). In this control scheme, the SMC will guarantee the sliding surface is finite time reachable and the LESO will estimate and compensate for the lumped disturbances. Then, the robustness and asymptotic stability of the proposed controller are proved by the stability analyses. Finally, three numerical simulation cases and comparative flight experiments validate the effectiveness of the developed controller.

Automatic milking systems (AMSs) for medium and large dairy farms in China require manual assistance to attach the teat cup, which greatly affects the milking efficiency and labor costs. In this regard, it is necessary to realize the automatic completion of cow teat attachment work. To address this issue, the authors developed a teat cup attachment robot for an AMS based on the theory of the solution of inventive problems (TRIZ). Specifically, we developed an enhanced algorithm for teat detection and designed a six-degree-of-freedom manipulator with integrated drive control. The design parameters were simulated and analyzed to validate their efficacy, while the rationality of the manipulator’s movement during teat cup attachment was verified. The maximum displacement and angle error of the cup was 1.625 mm and 1.216 mm, respectively, as verified by the teat cup attachment error test. A dynamic response test showed that the manipulator could follow the teat of the cow in real time. The attachment time for teat cups was 21 s per cow, with a success rate of 98%. The performance of the teat cup attachment robot was capable of meeting the automatic attachment teat cup needs for medium and large dairy farms during milking.

Charged droplets driven by Coulomb force are an important part of a droplet-based micro reactor. In this study, we realized the rapid oscillatory motion of droplets both in oil and on superhydrophobic surface by injecting charges through corona discharge. Distinct from the oscillatory motion of water droplets under a DC electric field, charge injection can make the motion of water droplets more flexible. A droplet in the oil layer can move up and down regularly under the action of corona discharge, and the discharge voltage can control the movement period and height of the droplet. In addition, the left–right translation of droplets on a superhydrophobic surface can be achieved by injecting charges into the hydrophobic film surface through corona discharge. Two kinds of droplet motion behaviors are systematically analyzed, and the mechanism of droplet motion is explained. The present results could help establish new approaches to designing efficient machines in microfluidics and micromechanical equipment.

Missing values in time series data present a significant challenge, often degrading the performance of downstream tasks such as classification and forecasting. Traditional approaches address this issue by first imputing the missing values and then independently solving the predictive tasks. Recent methods have leveraged self-attention models to enhance imputation quality and accelerate inference. These models, however, predict values based on all input observations—including the missing values—thereby potentially compromising the fidelity of the imputed data. In this paper, we propose the Uncertainty-Aware Self-Attention (UASA) model to overcome these limitations. Our approach introduces two novel techniques: (i) A self-attention mechanism with a partially observed diagonal that effectively captures complex non-local dependencies in time series data—a characteristic also observed in fractional-order systems. This approach draws inspiration from fractional calculus, where non-integer-order derivatives better characterize complex dynamical systems with long-memory effects, providing a more comprehensive mathematical framework for handling temporal data. And (ii) uncertainty quantification in data imputation to better inform downstream tasks. The UASA model comprises an upstream component for data imputation and a downstream component for time series prediction, trained jointly in an end-to-end fashion to optimize both imputation accuracy and task-specific objectives simultaneously. For classification tasks, the UASA model demonstrates remarkable performance even under high missing data rates, achieving a ROC-AUC of $99.5\%$, a PR-AUC of $58.5\%$, and an F1-SCORE of $49.3\%$. For forecasting tasks on the AUST-Gait dataset, the UASA model achieves a Mean Squared Error (MSE) of 0.72 under $0\%$ missing data conditions (i.e., complete data input). Under the end-to-end training strategy evaluated across all missing data rates, the model achieves an average MSE of 0.74, showcasing its adaptability and robustness across diverse missing data scenarios.