Flexible pressure sensors have drawn growing attention in areas like human physiological signal monitoring and human–computer interaction. Nevertheless, it still remains a significant challenge to guarantee their long-term stability while attaining a wide detection range, a minute pressure testing limit, and high sensitivity. Inspired by the wrinkles on animal skins, this paper introduces a flexible pressure sensor with wrinkled microstructures. This sensor is composed of a composite of reduced graphene oxide (rGO), single-walled carbon nanotubes (SWCNTs), and polydimethylsiloxane (PDMS). After optimizing the proportion of the composite materials, the flexible pressure sensor was manufactured using highly efficient heat-shrinkable films. It has a sensitivity as high as 15.364 kPa⁻¹. Owing to the wrinkled microstructures, the sensor can achieve an ultra-wide pressure detection range, with the maximum reaching 1150 kPa, and is capable of detecting water wave vibrations at the minimum level. Moreover, the wrinkled microstructures were locked by PDMS. The sensor acquired waterproof performance and its mechanical stability was enhanced. Even after 18,000 cycles of repeated loading and unloading, its performance remained unchanged. By combining with an artificial neural network, high-precision recognition of different sounds and postures when grasping different objects was realized, with the accuracies reaching 98.3333% and 99.1111%, respectively. Through the integration of flexible WIFI, real-time wireless transmission of sensing data was made possible. In general, the studied sensor can facilitate the application of flexible pressure sensors in fields such as drowning monitoring, remote traditional Chinese medicine, and intelligent voice.

Magnetic microswarms exhibit great potential for targeted delivery because of their excellent controllability and environmental adaptability. Enabling label-free cargo delivery and controllable release while endowing microswarms with resistance to environmental disturbances is key to expanding their application scope. In this study, we present a label-free microcargo delivery strategy based on a magnetic microswarm actuated by a magnetic tweezers system. In this approach, high-frequency magnetic fields enable autonomous cargo capture, while low-frequency fields trigger controlled release, forming a simple yet effective frequency-switching mechanism. Owing to the high-intensity magnetic field produced by the magnetic tweezers system, the microswarm exhibits significantly improved anti-interference capability, ensuring stable transport even under dynamic flow conditions. Leveraging visual feedback, the microswarm autonomously captures and stably transports various microscale cargos, including polystyrene microspheres and cell spheroids up to 400 µm in diameter. In complex structures and flowing fluid environments, microswarms that carry cargo successfully resist fluid impacts and achieve autonomous navigation. Furthermore, the controllable release of nonmagnetic cargos is realized through a frequency-switching mechanism. When a microswarm carries multiple cargos, small cargos are usually discharged first, indicating the potential of this release mechanism to sequentially release multiple cargos. This strategy circumvents the risks associated with permanent magnetic labeling and enhances the microswarm’s anti-interference capability, providing essential technical support for the practical translation and clinical application of magnetic microrobots.

A piezoelectric actuator (PEA) is a fundamental part of a high-precision motion system, yet its performance is critically constrained by inherent nonlinearities such as the velocity dead zone and hysteresis. To overcome these limitations and the associated time-varying dynamics, this study introduces a novel control framework for a dual-mode standing wave PEA. The framework integrates a Global Linearized Sparse Prediction (GLSP) model with an Adaptive Kalman Observer-based Model Predictive Control (AKOBMPC) strategy, specifically designed for velocity dead-zone compensation. The GLSP model employs Koopman operator theory to lift the complex, nonlinear electromechanical and contact dynamics into a linear invariant subspace. Incorporated with a deep learning-based structured pruning mechanism, the model achieves an effective balance between prediction accuracy and computational efficiency, facilitating real-time implementation. Leveraging this high-fidelity model, the AKOBMPC algorithm is developed to estimate unmeasurable disturbances and optimize the control sequence for precise velocity tracking. Experimental results demonstrate the GLSP model’s accurate prediction of system behavior under varying loads and excitation frequencies. The proposed controller effectively suppresses the velocity dead zone, achieving tracking errors within ±0.35 mm/s for a 40.00 mm/s trapezoidal reference and within ±0.50 mm/s for sinusoidal tracking. These results confirm the superior performance of the AKOBMPC scheme over conventional methods, offering a robust solution for high-precision velocity regulation in PEA system and contributing to the advancement of next-generation precision actuator.

This paper proposes a data-driven model predictive control (MPC) framework for high-precision speed control of rotary traveling wave ultrasonic motors (RTWUSMs) under temperature drift. To address the strong nonlinearity and time-varying thermal characteristics of RTWUSMs, a Koopman–convolutional neural network–long short-term memory (Koopman–CNN–LSTM) prediction model with radial basis function (RBF) observable features is constructed. The model maps the nonlinear electromechanical coupling and friction-driven dynamics of the motor into a linear invariant subspace, achieving high prediction accuracy while maintaining low computational complexity. On this basis, a data-driven MPC scheme is designed, which eliminates the dependence on accurate analytical plant models and compensates for thermal-induced speed drift through online driving frequency adjustment. The experimental results show that under 900 s of continuous operation, the proposed scheme achieves a relative steady-state speed error of 0.37%, which is significantly better than typical temperature drift compensation methods. This scheme can also provide stable tracking performance under load torques of 0.5 N·m and 1.0 N·m, providing a practical solution for the long-term stable speed regulation of RTWUSM in precision drive applications.