A human in-hand motion (HIM) recognition system based on multi-modal perception information fusion is proposed in this paper, which can observe the state information between the object and the hand by using customized ten kinds of HIM manipulation in order to recognize the complex HIMs. First, combined with the characteristics of HIM capture, ten kinds of HIM sets are designed, and finger trajectory, contact force and electromyographic signal data are acquired synchronously through the multi-modal data acquisition platform; second, motion segmentation is realized through the threshold segmentation method, the multi-modal signal preprocessing is realized by Empirical Mode Decomposition (EMD), and multi-modal signal feature extraction is realized by Maximum Lyapunov Exponent (MLE); then, a detailed non-linear data analysis is carried out. A detailed analysis and discussion are presented from the results of the Random Forest (RF) recognizing HIMs, the comparison results of motion recognition rates of different subjects, the comparison results of motion recognition rates of different perceptrons, and the comparison results of the motion recognition rates of different machine learning methods. The experimental results show that the multi-modal perception information based HIM recognition system proposed in this paper can effectively recognize ten different HIMs, with an accuracy rate of 93.72%.

The bipedal robot should be able to maintain standing balance even in the presence of disturbing forces. The control schemes of bipedal robot are conventionally developed based on system models or fixed torque-ankle states, which often lack robustness. In this paper, a variable impedance control based on artificial muscle activation is investigated for bipedal robotic standing balance to address this limitation. The robustness was improved by applying the artificial muscle activation model to adjust the impedance parameters. In particular, an ankle variable impedance model was used to obtain the antidisturbance torque which combined with the ankle dynamic torque to estimate the desired ankle torque for robotic standing balance. The simulation and prototype experimentation results demonstrate that the control method improves the robustness of bipedal robotic standing balance control.

Vacuum degree is a key parameter determining the breaking and insulation performance of vacuum circuit breakers (VCBs). Its deterioration over time can lead to performance failure. Therefore, achieving high-precision online monitoring of the vacuum degree is essential for ensuring the operational reliability of VCBs. This study employs electromagnetic radiation waves generated by vacuum discharge as indirect indicators of vacuum degree and investigates their physical mechanism and detectable lower limits under different conditions. On this basis, a classification model integrating temporal convolutional network (TCN), bidirectional gated recurrent unit (BiGRU), and an attention mechanism is developed to learn discharge event features from the waveforms and classify internal pressure states. Experimental results show that the method supports vacuum degree monitoring from $1.0\times 10^{-3}$ to 10 Pa, achieves 92% precision, and outperforms support vector machine (SVM), kernel extreme learning machine (KELM), and back propagation neural network (BP-NN). This approach provides a practical and efficient solution for real-time condition monitoring of VCBs.