In the heart of China’s coal mining belt, researchers are tackling a significant challenge that’s been plaguing the energy sector: vibration control in double-rotor permanent magnet drive systems. These systems, crucial for large belt conveyors, often face large vibrations under starting, braking, or non-uniform load conditions. The culprit? Periodic excitations, perturbations, and the non-sinusoidal distribution of the magnetic field, which introduces eddy current harmonics.
Enter Yongcun Guo, a researcher at the State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining at Anhui University of Science and Technology. Guo and his team have developed a novel solution to this persistent problem. Their research, published in *Meitan xuebao* (translated to *Coal Science and Technology*), introduces an innovative algorithm designed to suppress these vibrations and enhance the stability of these critical systems.
The team’s modified neural network iterative learning control algorithm (MNN−ILC) is a game-changer. By introducing an adaptive factor σ based on the error value and a regularized weight attenuation factor λ, the algorithm quickly responds to system changes and reduces error. “The neural network’s ability to fit the nonlinear features of the system allows it to continuously adjust parameters based on real-time vibration data,” Guo explains. This iterative learning process is key to achieving the goal of vibration suppression.
To validate their approach, the team conducted tests on a 55 kW double-rotor permanent magnet drive train. The results were impressive. Without any control, the maximum amplitude of the measurement point was about 18.7 μm. After applying the MNN−ILC algorithm, this value plummeted to just 3.1 μm—a reduction of approximately 83.4%. “The MNN−ILC algorithm not only suppresses vibration more effectively but also maintains stable control performance over time,” Guo notes.
The implications for the energy sector are substantial. Large belt conveyors are the backbone of many mining and material handling operations. By enhancing the stability and efficiency of these systems, the MNN−ILC algorithm can lead to significant cost savings and improved safety. “This study provides an important theoretical reference for the vibration suppression of double-rotor permanent magnet drive systems,” Guo states, highlighting the broader impact of their work.
The research also underscores the potential of advanced control algorithms in addressing complex engineering challenges. As the energy sector continues to evolve, the need for innovative solutions to enhance the performance and reliability of critical systems will only grow. Guo’s work is a testament to the power of interdisciplinary research, combining insights from control theory, neural networks, and mechanical engineering to drive progress in the field.
In the quest for more efficient and reliable energy systems, Guo’s research offers a promising path forward. By harnessing the power of advanced algorithms, we can overcome longstanding challenges and pave the way for a more stable and sustainable energy future.