see. think. act.
Virtual Sensor Virtual Sensor

AI Helps to Measure Temperature

Min Reading Time
When an electric motor rotates at high speed, it is difficult to determine the exact temperature inside. However, this information is important for function development. AI is now helping where humans and measuring struggle with a solution.
Andreas Neemann,
Andreas Neemann wrote his first ZF text in 2001 about 6HP transmissions. Since then, the automotive writer has filled many publications for internal and external readers, showcasing his passion for the Group's more complex subjects.
What exactly happens in a ZF electric motor when the stator is cooled by oil mist while the rotor rotates inside at varying speeds? There is no physically accurate answer to this question – the behavior of the millions of moving oil droplets that carry the heat away from the stator is too chaotic and completely different depending on the speed. "However, we depend on temperature data that is as exact as possible," explains Alexander Hoffmann, Senior Manager Electrified Powertrain Technology at ZF. "After all, when developing our software functions, we must ensure that the magnets in the rotor do not overheat in the various operating modes."

A Case for AI: Millions of Possible Combinations

AI helps ZF engineers to understand processes where cost or time constraints prevent them from developing a physically reliable model. The problem is that the temperature inside the rotor cannot be measured directly while the electric motor operates in the vehicle. Exact thermal measurements therefore require a very complex setup on the test bench. Furthermore, an FEM simulation cannot reliably determine the effect of the oil cooling. "The test bench showed that we have a too large deviation with our simulation models – this is not precise enough," says Hoffmann.

On the other hand, there is enough information and a lot of measurement data. Both are determined during complex functional tests on the test bench and later also in the test vehicles. Temperature measurements from the environment – such as the temperature of the oil in the oil pan – are available as well as the oil quantity used for cooling. The rotor speeds are also measured continuously.

At first glance, the figures might seem manageable – but, in fact, you are dealing with a flood of data resulting from a wide variety of possible operating points and their progression over time. These figures depend on whether and when drivers call up full power or cruise along at walking pace. This results in millions of possible combinations of the measured parameters. A human being cannot look at this data and find recurring patterns.

Development Time Slashed to One Third

This is precisely where AI algorithms come into their own. "Trained" accordingly, the computer filters out precisely those correlations that are particularly significant for the temperature changes on the rotor and stator. The ZF simulation models can then be fine-tuned with this information. "On the test bench, we determined that the results obtained in this way deviate by just few degrees from the real temperature," says Hoffmann.
"On the test bench, we determined that the results obtained in this way deviate by just few degrees from the real temperature."
Alexander Hoffmann

This support by artificial intelligence has enormous potential for ZF. On the one hand, it slashes development times for electric motors used in passenger cars. "Time-consuming special tests that we used with earlier procedures to ‘protect’ the physical properties of wide-ranging components and so check the simulation quality, can now be omitted," explains Hoffmann. Another aspect is that temperature measurement in inaccessible, dynamic areas is an important factor not only for electric motors for passenger car drives: "The AI model could be applied to many ZF products – whenever the operating temperature is essential for function development and exact measurement during operation is not possible," adds Dr Martina Flatscher, AI Strategist in Corporate R&D at ZF

However, AI support does not come for "free”. Tailoring the data to AI entails lots of work. "Data preparation takes up as much as 90 percent of the time; the actual training of the AI then only accounts for ten percent of the total time," according to Flatscher's rule of thumb. If the algorithm programmed by ZF is to compare the terabytes of measurement data, this data must be as uniform as possible – which is not usually the case. In addition to divisional differences at ZF, there are also customer-specific deviations – both in terms of signal standards and metadata. "The designation for motor speed, for example, changes depending on the brand of the test vehicle," Hoffmann says.

People Are More Important Than Ever

AI can only provide meaningful support where valid measurement data is available as a reference and where standardized amounts of data are available for evaluation. As such, "human" colleagues are also becoming increasingly important. Measuring technology expertise and good measurement data handling are crucial here. It is worth rethinking priorities. The question: "What does it take to optimally teach an AI algorithm?" could play a much more important role in future development work.