AI Optomises Inductive Motor Design for Higher Power Factor

Whether it is three phase for industry, or single phase ones for home use, induction motors are some of the most popular types of motor in use today. They are self-starting, reliable and don’t need much maintenance, so their popularity is no surprise. However, they do have one large drawback – their power factor is often low and when they start, there is a surge of current that can be up to 6x the rated full-load current. This extreme current draw can put a lot of stress on the power grid, leading to it becoming unstable in some cases, especially if there are multiple induction motors on the same grid. In developed countries with better power grids, there’s not too much risk, but in developing countries there is a much greater chance of the grid being stressed.

One person who is trying to find a solution to this problem is Dr Mbika Muteba from the University of Johannesburg, who has trained an AI to optimize the design of a squirrel cage motor. The AI was used to optimize the rotor design to cause as little disruption to the grid as possible while not losing any performance. The design was first modelled and then tested in a 5.5 kW motor design. The motors’ real-world performance matched the predicted performance closely. The new motor design had an auxiliary coil on the stator. The genetic algorithm optimized it for the highest performance across various loads on electrical current drawn (torque per ampere). Muteba verified the genetic algorithm’s results with finite element analysis.

The AI optimised 5.5kW motor shows excellent power factor in the laboratory setup, ranging from 0.93 measured at 0% loading, to 0.99 at 60% loading through to 120% loading. The efficiency at full load of the AI-optimised motor is 85.87%, which is within 1-2% of the unoptimized motor. Its efficiency for loads under 30% is also much improved compared to the unoptimized motors. The AI optimized design’s torque per ampere was a double-digit improvement on that of the motor without AI optimization.

Using AI to optimize the rotor and auxiliary capacitive coil design can save a lot of time, compared to entrenched design practices. The genetic algorithm took 27 minutes to optimize the rotor and auxiliary capacitive coil design, within 8 executions and 60 ‘generations’ of chromosomes processed.