With the advancement of flexible electronics and machine learning (ML), the collection and analysis of athletic big data using self-powered sensors have become increasingly important in intelligent sports. However, accurate quantification of the rotation direction, a critical parameter in ball games, remains largely underexplored. This study proposes an ML-assisted, intelligent motion-feedback table tennis paddle integrated with a triboelectric nanogenerator (TENG) for simultaneous velocity and rotation direction sensing. By leveraging a well-intercalated MXene/bacterial cellulose (MXBC) composite thin film, the developed sensor exhibits improved tensile strength, excellent conductivity, good processability, and lightweight characteristics. Consequently, the MXBC-based TENG generates distinct and rich feature signals corresponding to rotational motions, enabling its use as a self-powered intelligent feedback sensor. To enhance detection sensitivity and accuracy, a hybrid long short-term memory network–support vector machine (LSTM–SVM) model is constructed, coupled with effective denoising technique. Using the optimized LSTM–SVM modal, the proposed sensor achieves table tennis ball rotation direction and velocity recognition with an accuracy of 99.8%, representing a 48.5% improvement over the conventional SVM method. This study is the first to achieve self-powered rotation direction detection in table tennis, demonstrating significant potential for ball sports training and opening new avenues for the advancement of intelligent sports.

Flexible thermoelectric generators (f-TEGs) can directly convert low-grade thermal energy from the human body and surrounding environment into electricity, showing great promise for wearable power systems and self-sustained sensors. However, conventional inorganic thermoelectric materials still face significant constraints in balancing flexibility, structural stability, and energy conversion efficiency. In this work, high-performance Bi₂Te₃/hydroxypropyl methylcellulose (HPMC)@paper composite thermoelectric films were fabricated via a vacuum filtration method, realizing a synergistic enhancement in both flexibility and thermoelectric performance. The obtained p-type and n-type films exhibited Seebeck coefficients of 182.96 and −229.98 μV·K⁻¹, respectively, and maintained stable output under repeated bending. Based on these films, both planar and multilayer stacked f-TEG architectures were designed to achieve multidimensional energy harvesting. The Level-III stacked f-TEG reached an ultrahigh device-level Seebeck coefficient (S_device) of 11,330.25 μV·K⁻¹ and a maximum output power of 617.4 nW, demonstrating outstanding conversion capability and structural robustness. When integrated with an Ecoflex substrate, the device maintained stable operation under bending, twisting, and conformal attachment to curved surfaces. A smart wristband built from this system continuously drove a low-power pedometer during human-wear testing, validating its feasibility for wearable thermoelectric energy harvesting. This study proposes an inorganic–organic hybrid thermoelectric film design that combines high flexibility with excellent thermoelectric performance, offering a new strategy for flexible energy devices and showing broad prospects in wearable electronics.

Technologies for evaporation-driven electricity generation and solar-driven steam generation exhibit significant potential for addressing energy crises and freshwater shortages. Nevertheless, it is still a challenge to develop multifunctional materials for efficient energy generation and seawater desalination via economical and simple methods. Here, we propose a Chinese ink-coated viscose fiber composite (Ink@VF), suitable for direct applications in evaporation-driven electricity generators (EEGs) and solar-driven steam generators (SSGs). The Ink@VF prepared by a simple dip-dyeing method exhibits excellent mechanical properties (Young’s modulus of 18.1 GPa), hydrophilicity, electrical conductivity (36.51 Ω/sq), and photothermal conversion properties. Based on the synergy of water evaporation, capillary effect, and electric double layer (EDL) electrokinetic effect, the Ink@VF-based EEG can achieve a maximum open-circuit voltage (V_oc) of 0.65 V and an optimal power density of 43.72 mW/m² with 1 mol/L NaCl solution. It can also be integrated in series to develop a self-powered bracelet. Simultaneously, the evaporation rate and solar energy conversion efficiency of the Ink@VF-based SSG can reach 1.32 kg/(m²·h) and 84.9% under 1 sun irradiation, respectively. Through utilizing the evaporation-condensation mechanism, it can achieve freshwater generation at a rate of 1.49 kg/(m²·h) and metal ion removal in excess of 99.9%. This study provides a low-cost and efficient solution to the energy crisis and freshwater shortage in resource-poor remote areas by utilizing inexhaustible natural resources.

Smart actuators have a wide range of applications in bionics and energy conversion. The ability to reconfigure shape is essential for soft actuators to achieve various shapes and deformations, which is a crucial feature for next-generation actuators. Nonetheless, it is still an enormous challenge to establish a straightforward approach to creating programmable and reconfigurable actuators. MXene-cellulose nanofiber composite film (MCCF) with a brick-and-mortar hierarchical structure was produced through a vacuum filtration process. MCCF demonstrates impressive mechanical properties such as a tensile stress of 68 MPa and a Young’s modulus of 4.65 GPa. Besides, the MCCF highlights its potential for water-assisted shaping/welding due to the abundance of hydrogen bonds between MXene and cellulose nanofibers. MCCF also showcases capabilities as a humidity-driven actuator with a rapid response rate of 550 °·s⁻¹. Using the methods of water-assisted shaping/welding, several bionic actuators (such as flower, butterfly, and muscle) based on MCCF were designed, highlighting their versatility in applications of smart actuators. The research showcases the impressive capabilities of MXene-based actuators and offers beneficial insights for the advancement of future intelligent materials.