Search

• Systematic scheme for designing high-order S-curve trajectories. • Efficient algorithm to find time-optimal solutions with kinematic constraints. • Frequency shaping of trajectories for multimode vibration elimination. • Combination of adjustable robustness and high-frequency attenuation. • Effectiveness of the method is validated numerically and experimentally. The generation of optimal reference trajectories poses a challenging problem for industrial machines due to the trade-off between execution speed and vibration amplitude. This paper presents a novel method for systematically planning smooth and robust S-curve trajectories of arbitrary order adapted to vibratory behaviour for high-speed operations. In particular, the minimum time trajectory featuring good continuity under kinematic bounds is designed utilizing an improved procedure based on the existence prediction of trajectory segments. A complete analytical solution for trajectories of orders up to five is then derived. Moreover, through an analysis of the dynamic response characteristics, a parameter tuning strategy based on modal properties is established, enabling further shaping of the acceleration profiles to remove the energy content around the resonances with lower sensitivity to modelling errors. Due to the embedded filtering effect, the optimized trajectories combine specific vibration cancellation with high-frequency attenuation while providing flexibility to balance competing objectives. Comparative experiments conducted on a robot transferring flexible beams demonstrate the effectiveness and robustness of the proposed methodology in reducing residual vibration and settling time under system uncertainties. [ABSTRACT FROM AUTHOR]

• An expert-knowledge attention network (EKANet) was designed to classify four tachyarrhythmia on electrocardiogram (ECG) signals. • Two attention modules in EKANet are explored for abnormal rhythm representation and multiple leads selection. They are guided by the knowledge of cardiology clinicians. • The two attention modules in EKANet required no extra training process. The low complex structure increases the generalization and robustness of EKANet. • EKANet can be more generalized and robust to different ECG datasets than the comparison methods. An expert-knowledge attention network (EKANet) was designed to improve the accuracy of arrhythmia diagnosis and reduce the recheck time. This network classifies four tachyarrhythmia on electrocardiogram (ECG) signals, encompassing most arrhythmia diseases. In the EKANet, two attention modules based on the knowledge of cardiology can rapidly capture the ECG rhythm and P waves in multiple leads without any training. This mechanism is performed to reduce the computational time of re-building a model. The EKANet integrates a six-layer convolutional neural network (CNN) and a gated recurrent unit (GRU) as the classifier to realise the tachyarrhythmia classification. The EKANet outperformed 1D CNN and ArrhythmiaNet on the MIT-BIH datasets by 3.1% on average accuracy. Furthermore, the EKANet achieved approximately 8.5% and 3.9% average F 1-score increases on the dataset of China ECG challenge contest compared with time-incremental CNN (TI-CNN) and attention-based TI-CNN, respectively. Meanwhile, the EKANet has a much lower complexity than that of the other typical models with a competitive accuracy. [ABSTRACT FROM AUTHOR]