Improving Maglev Performance with Machine Learning

For centuries, the transportation sector has been one of the largest contributors to global carbon emissions. To address this problem, many research groups are now actively exploring how technology can help transportation systems become more sustainable and environmentally friendly.

Among the most promising technologies currently being studied is magnetic levitation (Maglev), which uses powerful magnets to push trains as they hover just above their tracks. By virtually eliminating the friction caused by the track, Maglev trains can quickly accelerate to incredibly high speeds using very little energy.

Yet although Maglev systems have been widely studied for some time, it is still difficult for researchers to accurately measure the forces transmitted by their magnets. This lack of precision partly explains why Maglev has not yet replaced more conventional, carbon-intensive modes of transport.

Through research Published in Physica C: Superconductivity and its applications, a team led by Erkan Caner Ozkat of Recep Tayyip Erdogan University in Rize, Turkiye, shows how artificial intelligence can help improve the accuracy of these force measurements. Their findings could bring widespread deployment of Maglev systems closer to reality, helping the global transportation sector reduce its carbon emissions.

“As the human population and the amount of energy consumed are increasing rapidly, energy-efficient systems are of great importance,” explains Ozkat. “Superconducting Maglev systems fulfill this purpose due to their property of frictionless movement.”

In Maglev systems, the magnets are composed of high-temperature superconductors that can transmit electrical currents with zero resistance, even at outdoor ambient temperatures. Two different forces have a particularly strong influence on their performance: while levitation forces lift the trains vertically upward, reducing their friction with the track below, lateral forces act perpendicular to the tracks, causing the trains to sway. 'one side to the other.

To ensure sufficient load capacity and safe movement, it is crucial to improve both the levitation and lateral guiding force of Maglev systems. Previously, multi-surface interactions between superconductors and the permanent magnetic track have been shown to be effective. However, until now, mechanical constraints have made measurement of the system difficult.

Ozkat's team explored how to achieve this with the help of artificial intelligence. “We were motivated by the idea that some of the research challenges related to Maglev systems could be overcome through machine learning,” says Ozkat.

Machine learning is a branch of artificial intelligence that enables accurate predictions about the properties of systems based on prior experience with real data. Through their analysis, the researchers identified a machine learning model that was particularly effective at predicting both forces based on the properties of superconducting magnets, as well as the lateral and horizontal movements of Maglev trains.

Based on this model, the researchers then developed a step-by-step process to evaluate how Maglev systems could be adjusted to maximize levitation forces, while keeping lateral forces within a certain defined tolerance. “We believe that the generalizable methodology we have presented provides a guiding and problem-solving tool for researchers working in this area,” says Ozkat.

They now hope that their approach could help improve the efficiency and performance of real Maglev systems, making them more practical and economical. If so, it could help accelerate their deployment in transport systems around the world, perhaps bringing the goal of net zero carbon emissions closer to reality.