AI can make Good Engineers even Better

At the CTI Symposium 2025 in Novi, Luca Zampieri, Engineering Director US at Neural Concept, gave a presentation on “Engineering Intelligence Driving the Future of Powertrain Development”. We spoke with him about how engineers and the products they design can benefit from using AI engineering software.

Luca, what can Neural Concept do for the automotive industry? What is your product?

At Neural Concept, we develop AI software that accelerates the engineering process. Our idea is to connect and speed up the internal workflow, all the way from design to manufacturing. Our platform allows you to stay connected to today’s workflows – moving back and forth with your current tool stack – while also leveraging new technology and big data: state-of-the-art algorithms and computing infrastructure, all in a single environment. That’s what we offer the automotive industry: faster, better design and engineering processes.

So far, AI has remained a rather abstract topic for many engineers. To begin with, what are the milestones in AI history that led to today’s capabilities in powertrain development?

It goes back to the first AI revolution, which was about statistics and optimization – Gaussian processes, traditional machine learning. But today we focus more on what came after the advent of deep learning: convolutional networks – which scan and compress visual data into patterns a model can learn from – and transformers, which let a model weigh the relevance of different parts of an input against each other. A key milestone was the creation of surrogates predicting physics as well as displaying generative capabilities for 3D shapes. These technologies matter greatly for powertrain development. And now we also use large language models, also powered by transformers, for an agentic control and consumption of the platform.

How does your platform learn the patterns for engineering requirements – through integration with common engineering tools?

Exactly. Our platform includes such tools and interfaces. But the main idea is to access the whole workflow, from design and conception through to manufacturing, removing the bottlenecks along the way. One such bottleneck is generative modeling, or surrogacy – the idea of replacing a physical simulation with a learned model that approximates it much faster. For some applications, we provide pre-trained models that come with their own data. For most others, we provide an agentic framework to create your own surrogates as well as automations to collect and label data.

What does that mean – this is a huge amount of knowledge you need. How do you train this as a user, as an engineer?

For a physical surrogate, you don’t need much knowledge as a user, because everything is already set up. What you need is data and your engineering knowledge. We work with small amounts of data because it’s essential to focus only on what matters to you. By default, engineers tend to replicate the full simulation output simply because that’s what they are used to seeing. But most of the time, what matters is only part of that output – and capturing just that part is often much easier, and requires far less data, than reproducing the whole simulation.

Isn’t there a risk that engineers lose expertise and creativity by being assisted by an AI engineering assistant?

I don’t think it’s one versus the other. The question is how the product designer can leverage simulation to better judge when a design is a good one. The engineer still needs all of the expertise. Andrej Karpathy, founding member of OpenAI and former Tesla Autopilot AI director, once said that you can outsource your thinking to AI models, but not your understanding. The same applies here:

these tools can help the expert gain even more expertise, because quick feedback lets you better understand the physical phenomena behind your design. Today, engineers spend much of their time on repetitive, low-skilled tasks, leaving less time to focus on the depth of the problem. Our AI tools allow them to focus fully on the problem they’re actually trying to solve.

Let’s assume I’m a designer working with your tool. Do I use natural language to communicate with the agent?

That’s one option. A lot of knowledge lives in natural language, so you can interact a great deal through text. But you can also interact naturally – clicking, moving, manipulating the interface – so it’s not only text. Just as a picture is worth a thousand words, I’d say an interactive interface is worth a thousand pictures. If I needed to explain something to you, I’d probably sketch it. We encourage sketching because it conveys design intent far better. The goal is for you to convey your design intent to the machine, and natural language is just one way of doing that.

What benefits does your AI software offer in terms of time savings, accuracy, performance, or quality?

The accuracy of the AI matters less than you’d expect. What matters is how fast you can design something, and how much better a design you can find. We often say AI is a thousand times faster than simulation – but that figure alone is meaningless. What matters is how much faster you reach the final result, and that depends heavily on the workflow and the product. It’s usually a trade-off between speed and performance. We’ve seen products designed in three days instead of three months. We’ve seen performance double. And we’ve sometimes seen performance improve by just one percent – which can still be extremely impactful. In powertrain development specifically, we typically target performance gains of around 10 to 15 percent, and time savings of about a quarter of the original development time.

You also spoke about combining parametric and non-parametric development methods. What would be an example in the development of an electric powertrain?

It’s both parametric and non-parametric – think of parametric as a design defined by a fixed set of adjustable variables, like the dimensions of a known shape, and non-parametric as a free-form shape with no such constraints. It’s also a case of combining new technology with old. Manufacturing teams use CAD, while newer techniques let you explore a much richer, more organic design space. But hand manufacturing teams something too organic, and they’ll push back. So the idea is to use traditional parametric methods with CAD where that makes sense, and non-parametric freedom where it’s needed – and to keep both connected to the tools used today, adopting new ones only where they add value. If we think about an e-motor, for example, the aim is to increase performance while reducing noise and vibration. In this case, you might want the magnet shape to remain parametric, but the air pockets to be non-parametric and organic.

You also mentioned so-called world models. What’s their relevance to automotive powertrain development?

A world model is one trained on enough data that the usual distinction between “in-distribution” and “out-of-distribution” data – cases the model has and hasn’t effectively seen before – no longer applies; the whole domain you want to explore falls within what it can predict. That doesn’t mean it’s a fully generic physical model. Building a robust world model requires considerably more data, and its accuracy is typically lower than that of a specialized model built close to the specific design you’re examining. For heat exchangers, for instance, world models generalize well across many configurations. For e-motors, though, it makes more sense to combine a world model with a specialized model close to the design being explored to get better accuracy.

Generative AI, as many of us use it in daily life, tends to produce answers at all costs, even when it combines facts incorrectly. How do you avoid such reasoning errors in engineering?

It’s essential to validate whatever the AI model produces. In engineering, optimization happens under constraints – and if you’re good at optimizing, you’ll very likely produce a result that violates some rule you hadn’t specified, whether a manufacturing limit or a physical consideration from another department. That’s why validation is so important. When using AI for design and optimization, it doesn’t really matter if the model hallucinates, because in the end, you’ll have a set of optimal results to cross-reference and verify.

To put it bluntly, could one say that the role of developers is thus shifting more toward that of a highly qualified supervisor?

I think engineers already work this way; they’ll simply do more of it. Designers from other departments already bring designs that engineers need to check and adjust. Here, that process is streamlined, and validation itself can be automated – not as fast as AI, but AI helps automate it, so you don’t need to spend time on it manually. You can automatically trigger higher-fidelity tests instead.

How does working with your tools change the prospects of engineers?

It changes them considerably. Skills like tool use and repetitive work become less important. But creativity and a deep understanding of the product you’re working on – already the hallmark of a good designer or engineer – will matter even more tomorrow. The good designers and engineers will become even better; the weaker ones risk becoming obsolete.

Interview: Gernot Goppelt

Rethinking Power Conversion for Mobility

Kim App, VP Sales & Marketing, Marel Power

Electrification is redefining passenger vehicles and heavy-duty trucks, placing new demands on efficiency, power density, scalability, and supply resilience. At the center of this shift is the power conversion layer — the link between the power semiconductors and the systems that deliver motion. Marel’s architecture rethinks how electrical and thermal paths work together, allowing semiconductors to do more with less. The result is a platform that cuts size and weight by 50% and semiconductor count by a third, while staying flexible across applications and semiconductor suppliers. To be clear, Marel does not manufacture semiconductor die, nor does Marel build full inverter systems. Instead, Marel delivers ultracompact power stacks that sit between the two, enabling performance levels that conventional architectures cannot achieve.

Unlocking More from Every Die

Traditional power modules limit performance through high thermal resistance and parasitic inductance. Conventional designs place dielectric material close to the die, restricting heat removal, while inefficient electrical paths introduce overshoot, ringing, and switching losses. Our architecture addresses both by relocating the dielectric closer to the coolant, and double-sided cooling of the die and enabling a more direct thermal path., increasing thermal capacitance and thermal conductivity. The result is ~0.05 K/W thermal resistance junction to coolant (8 SiC per switch), and ~2 nH parasitic inductance. This enables each semiconductor die to operate closer to its true capability, increasing current per die and reducing the number of die required to achieve a given power level—lowering system cost.

Compact Scalable Power for Mobility

The architecture is inherently modular, easily scaling from hundreds of kilowatts to megawatt-class systems. For passenger vehicles, this enables smaller, lighter inverter systems. For heavy-duty trucks, it delivers high continuous power in a compact form while reducing cooling system size and complexity. Requiring fewer semiconductors and supporting both IGBT and SiC from multiple suppliers, the system also improves supply resilience and adaptability to support evolving technology roadmaps.

A New Foundation for Electrification

Marel operates between semiconductor suppliers and system integrators, providing the core power stack that enables next-generation inverters and converters. A simple visual—such as a 1 MW power stack next to a Coke can—makes the value clear: exceptional power density. By rethinking how power is packaged, cooled, and scaled, this approach delivers meaningful system-level advantages in size, weight, performance, and flexibility. The result is not just incremental improvement, but a structural shift in power conversion designed for the next generation of mobility.

High Performance, Magnet-Free Electric Motors

Rory Brogan, Founder & CEO, Torev Motors

Torev Motors develops wound rotor axial flux motors for automotive and defense vehicles.

Building on proven, scalable technologies

Torev’s architecture builds on technologies already proven in production vehicles, including wound rotor motors used by companies including BMW and Nissan, and axial flux used by companies including Mercedes and Ferrari. By integrating these approaches, Torev aims to deliver motors capable of up to 2x the torque density of radial flux motors, that use 0 kg of permanent magnetic material, and that saves up to an estimated 50% on active material costs.

1.1 How it Works & Performance

Wound rotor motors, also called externally excited motors, replace permanent magnets with electrically excited coils. These motors offer greater torque and almost constant power at high speeds [1], wide efficiency maps stemming from direct control over the rotor fields, and material cost efficiencies from using no permanent magnets. Historically, these systems introduced greater weight, rotor thermal cooling requirements, and additional control complexity and cost stemming from the rotor energizing current, which modern designs are increasingly addressed through improved cooling strategies and power electronics. While brushed operation is traditionally the most common, modern brushes can last a vehicle’s lifetime and wireless power transfer methods are gaining in popularity.

Axial flux motors, also called pancake motors, take advantage of a shorter magnetic flux path that runs parallel to the axis of rotation, a cubic relationship between torque and motor diameter, and a greater magnetic interaction surface area to increase power and torque density along with efficiency [2]. This makes axial flux motors strong contenders for hybrid vehicle range extender and in-wheel drive applications. However, these very high-performance machines generally come with an equally high price tag arising from a combination of air gap control complexity in manufacturing, the use of materials like carbon fiber for structural integrity and lightweighting, and use of rare earth permanent magnets.

These architectures, when combined, enable Torev to develop magnetfree oil-cooled motors anticipated to produce peak torque and power densities of 15 Nm/kg and 3.5 kW/kg, and peak efficiencies upwards of 96% for their 180 kW 800 V flagship motor unit. These motors have an expected envelope of 370 mm OD x 225 mm Length.

This product is TRL 4 and has been tested and validated by 3rd party motor testing firms, with a 15kW sub-scale prototype in operation and the 180 kW units expected to be ready for customer validation testing in the next 12 months.

1.2 Applications & Opportunities

Key advantages of this technology include direct control over the rotor field windings, the use of no permanent magnets, and the axial flux architecture. The rotor field is directly controlled, enabling an additional degree of system-level powertrain design freedom, the ability to fully demagnetize the rotor fields, and full motor programmability suitable for software defined vehicle architectures. No permanent magnets means both cost savings and no thermal demagnetization risk, the peak temperature of the motor is instead defined by the insulation class. The axial flux geometry fits naturally into a hybrid vehicle’s bell housing and also enables direct drive optionality as these motors generally perform strongly at speeds matched to that of an ICE crankshaft.

References
[1] Schaeffler. Magnet-free axle drive EESM. https://www.schaeffler.de/en/products-and-solutions/e-mobility/magnet-free-axle-drive-eesm
[2] E-Mobility Engineering. (2021, May 17). Power and torque density. https://www.emobility-engineering.com/challenge-of-power-torque-density.