We propose the planetary flywheel inerter, which is a new type of ball screw inerter. A planetary flywheel consists of several planetary gears mounted on a flywheel bracket. When the flywheel bracket is driven by a screw and rotating, each planetary gear meshing with an outer ring gear generates a compound motion composed of revolution and rotation. Theoretical analysis shows that the output force of the planetary flywheel inerter is proportional to the relative acceleration of one terminal of the inerter to the other. Optimizing the gear ratio of the planetary gears to the ring gear allows the planetary flywheel to be lighter than its traditional counterpart, without any loss on the inertance. According to the structure of the planetary flywheel inerter, nonlinear factors of the inerter are analyzed, and a nonlinear dynamical model of the inerter is established. Then the parameters in the model are identified and the accuracy of the model is validated by experiment. Theoretical analysis and experimental data show that the dynamical characteristics of a planetary flywheel inerter and those of a traditional flywheel inerter are basically the same. It is concluded that a planetary flywheel can completely replace a traditional flywheel, making the inerter lighter.

The planetary flywheel can significantly reduce the weight of the flywheel, allowing the inerter to be lightweight. When a planetary flywheel ball screw inerter-based active actuator is used in a vehicle suspension system, the nonlinear features of the actuator affect vehicle performance. The planetary flywheel inerter actuator’s nonlinear dynamic model is constructed in this study based on the dynamic features of the planetary flywheel ball screw inerter and the electromagnetic torque generating mechanism of the permanent magnet synchronous motor. The impact of ball screw–nut friction, transmission clearance, planetary gear friction, and gear backlash on the performance of an active tuned inerter damper suspension is then investigated. As a result, the impact and sensitivity of numerous nonlinear parameters on suspension performance are shown, providing a theoretical foundation for the design of planetary flywheel inerter actuator and active inerter suspension.

With the further reform and development of the electricity retail market in China, the premium power value-added service (PPVS) product is becoming increasingly demanded by high-tech customers. However, the problem of PPVS demand-level matching has not been well studied. How to build an optimal matching and decision-making model which can improve both customers’ and electricity retail companies’ satisfaction degree is an urgent issue. Thus, this paper proposes a decision-making method for PPVS products with multi-index expectation based on two-sided matching. Firstly, a multi-index evaluation system is established from the perspective of customers and electricity retail companies. Secondly, the loss and gain matrices of customers and electricity retail companies are constructed, considering the difference between the expected level (EL) and the actual level (AL) of the evaluation indices. Thirdly, perceived utility (PU) of both customers and electricity retail companies are described with the introduction of elation function and disappointment function, due to different perceptions concerning the matching results under both sides’ evaluation indices. Fourthly, a multi-objective two-sided matching optimization model that aims to maximize the PU of both sides is developed. Finally, an empirical analysis is conducted on three large high-tech electronic-based customers in an industrial park in western Guangdong for demonstrating the effectiveness and rationality of the proposed method.

To achieve optimal performance of load frequency control (LFC), a data-driven scheme is proposed for renewable power systems in this paper. A multi-agent Actor-Double-Critic deep reinforcement learning approach is developed to ensure real-time scheduling that complies with system safety operation constraints within the multi-area LFC power system. For implementation, each individual controller only needs local information in its control area to deliver optimal control signals. A Self-Critic and Cons-Critic network is employed to improve the convergence speed during the multi-agent training process. Simulations on two-area and three-area LFC power systems are performed to verify and validate the analytical results. Comparisons with conventional PI and fuzzy PI controllers demonstrate that the presented approach effectively reduces training difficulties, guarantees the satisfaction of system safety constraints, and significantly improves the dynamic frequency regulation performance of the power system.

The dimensional accuracy of the bearing inner ring is critical for the operational performance and reliability of high-end equipment. However, nonlinear deformation of the measurement mechanism caused by temperature variations and temperature drift of the sensor significantly affect the measurement accuracy. In this study, a novel online measurement system for bearing inner diameter was designed, which integrates a two-degree-of-freedom motion mechanism and an adaptive elastic measurement probe. To compensate for the measurement errors caused by temperature effects in the proposed system, an intelligent compensation method based on a CNN-LSTM–Attention hybrid model was proposed. The raw sensor signals and ambient temperature were used as the model inputs, and an end-to-end nonlinear mapping relationship for the actual bearing inner diameter deviation was established without the need to construct complex explicit physical equations. The experimental results show that, within the investigated temperature interval of 11–21 °C, the proposed method controls the measurement error within 1.87 μm, thereby satisfying the dimensional measurement requirement for P4-grade bearings with a tolerance of 0 to −6 μm.

The continuous rotating valve plate piston pump (CRVPPP) can efficiently drive actuators such as hydraulic cylinders or hydraulic motors to generate excitation motion. This CRVPPP-driven excitation system can avoid the throttling losses associated with servo-valve-controlled excitation systems. However, this excitation system exhibits an asymmetric excitation phenomenon during actual operation. Through theoretical analysis and experimental research on the mechanical characteristics of the valve plate pair in the CRVPPP, it was found that the asymmetric excitation originates from the annular grooves of the fixed valve plate alternating between oil suction and discharge states. This alternation subjects the rotating valve plate to an overturning moment, which in turn causes a periodic variation in the end-face clearance of the valve plate. Targeting the asymmetric and nonlinear leakage characteristics of the CRVPPP, an adaptive neural network module was established based on the Amesim-Matlab/Simulink co-simulation framework. This module incorporates the mapping from the rotational speeds of the rotating valve plate and cylinder block to the equivalent leakage opening of the distribution grooves. By training with experimental data, the CRVPPP- driven excitation system model was formulated. Experimental results show that the established model achieves a correlation coefficient of 0.99786 on the training set, indicating its excellent fitting accuracy. Furthermore, the mean squared error on the test set is within 0.04 mm², demonstrating the model’s good generalization ability. It can reproduce the dynamic characteristics of the CRVPPP-driven excitation system with high precision, thereby laying a solid modeling foundation for the characteristic analysis, structural optimization, and high-precision control of such excitation systems.