The vehicle-mounted flywheel battery will inevitably be disturbed by the road conditions and lose stability while working. To make up for the deficiencies of existing studies, a robust sensorless control strategy of flywheel battery against continuous road disturbances is designed, which is relatively simple, accurate, and easy for engineering. First, the dynamic characteristics of the flywheel under various continuous road disturbances are analyzed. Second, a robust sensorless control strategy of flywheel battery is designed. Third, the rule of control parameter adjustment is explored by the analysis results. Finally, verification and comparison experiments are carried out based on the vehicle-mounted flywheel battery experimental platform. The experimental results show that the proposed robust sensorless control strategy has good control performance and better reliability and robustness than the conventional sensor control strategy.

Compared to traditional, static-based flywheel systems, vehicle-mounted magnetic suspension flywheels face more complex operating conditions, and existing control strategies usually regard disturbances in vehicles under different operating conditions to be the same problem. Therefore, it is necessary to determine the interference from complex operating conditions and reasonably distinguish among them under different operating conditions to provide flywheel systems with strong stability (the rotor offset was less than 0.025 mm). Thus, this paper proposes a high-stability control strategy for flywheels based on the classification of vehicle-driving conditions and designs its control strategy by taking the vehicle-mounted magnetic suspension flywheel with a virtual inertia spindle as an example. First, according to the different vehicle working conditions and the varying interference intensities affecting the flywheel system, the working mode is divided into four modes. Considering the obvious differences in each working mode, it is proposed to use BP neural network optimization based on the simulated annealing algorithm (SA-BPNN) to determine the flywheel’s working condition. A relatively simple neural network can improve the response speed of the whole system. It also has a good effect. Secondly, it is proposed to use deep learning models based on convolutional neural networks, long short-term memory networks and attention mechanisms (CNN+LSTM+ATTENTION) to train the corresponding control parameters under each working condition to judge and predict the control parameters under different working conditions. Three evaluation parameters are used to evaluate the training results, and all achieved good results. Finally, the classification of working conditions and performance tests are carried out. The experimental results show the effectiveness and superiority of the proposed control strategy.

Under the circumstances where the demands for energy transition and grid energy storage technology are constantly increasing, the magnetic suspension bearing, as the core component of the flywheel energy storage system, its control strategy directly determines the dynamic response, energy efficiency level and operational reliability of the system. This study focuses on the control strategy of magnetic suspension bearings used in flywheel energy storage. Firstly, the basic structure, working principle, composition of the experimental platform and performance indicators of the magnetic levitation bearing in the flywheel energy storage system are summarized. Based on this, the core technical requirements for the grid-connected application of flywheel energy storage systems have been clarified, and it has been distilled that magnetic suspension bearings in grid scenarios need to meet three core performance requirements: high dynamic response, low operating energy consumption, and strong robust stability. Then, the control strategy of magnetic bearings is analyzed from three aspects: Firstly, the technical paths of the classical and high dynamic response control methods under high power conditions are analyzed; Secondly, the low energy consumption control technology route based on energy consumption sources is proposed; Thirdly, the application logic research of the strong robustness strategy under the disturbance scenarios of power grid faults is conducted. This study systematically reviews the technical framework of the flywheel energy storage magnetic suspension bearing control strategy, providing theoretical support and technical references for its efficient and stable application in the grid energy storage. Finally, the development trend of control strategies and future research directions are prospected.

The bottleneck problem that the vehicle-mounted flywheel battery needs to solve is how to ensure that the system still has strong robustness under the interference of the complex traffic environment, so as to guarantee the safe and stable operation of the entire system. To this end, a robust robust intelligent control strategy is proposed, integrating a multidimensional environmental factor integration modeling method and a deep learning model that combines Bayesian optimization, transformer-encoder, Bidirectional long short-term memory, and fully connected layer. First, all kinds of crucial information are comprehensively collected and organized in a complex traffic environment. Second, the obtained data are processed and fed into the deep learning model. The dynamic data of the flywheel rotor are deeply mined, hyperparameters are intelligently explored, control parameters are output based on comprehensive analysis results, and a strong robust control system is constructed. Then, it is compared and evaluated with traditional models, and the results show that the proposed model is superior. Finally, performance experiments simulating the interference of the complex traffic environment are carried out on a mobile experimental platform and make a comparison. The good experimental results, obtained by comparing the proposed control strategy with traditional ones without considering the optimization of deep learning models, show that the proposed control strategy is superior to the traditional ones, and can ensure the robustness of the flywheel battery system in the complex traffic environment.

Against the backdrop of the global clean energy transition, this paper addresses the volatility of renewable energy like wind and PV power, focusing on magnetic suspended flywheel energy storage systems (FESS). It expounds FESS’s structure (flywheel body, magnetic suspension bearings, etc.) and working principles (charging, energy retention, discharging) and studies key technologies including rotor material selection, magnetic bearing classification/modeling, motor coordination, and heat dissipation. Challenges such as high material costs and magnetic bearing stability are pointed out, with prospects for developing FESS toward higher performance, lower cost, and multi-scenario integration to support the clean transformation of power systems.