How AI Redefines Automotive Engineering Workflows

Posted on 2nd September 2026

Théophile Allard, CTO and co-founder at Neural Concept

The automotive industry is undergoing a structural shift. Development cycles compress from years to months, regulatory requirements multiply and customer expectations rise. The automotive industry’s structural challenges feel more burning than ever: deliver better vehicles, faster, without sacrificing quality or cost.

For decades, the answer was adding more tools and specialists. But engineering organisations are fragmented, iteration loops are long, and system-level insights arrive too late. In perspective, AI looks like the perfect solution that will magically absorb workloads and shrink timelines. In reality, despite heavy investment, most initiatives stall at the pilot stage.

The issue is workflow fit, not AI capability. What is needed is a different engineering playbook, one built around how AI-native development actually works.

The fragmentation problem

Modern vehicle development involves hundreds of specialists across aerodynamics, thermal management, crashworthiness, NVH, and manufacturing, each operating with separate tools and timelines.

This workflow is deeply sequential: designers create geometry, analysts spend weeks on simulations, results return, changes are requested, the loop repeats. By the time conflicts surface, design freedom has evaporated. Today, AI can generate and evaluate thousands of design variants per day across multiple physics domains. The constraint is the old workflow, not ready to leverage these new technology capabilities.

From iteration to exploration

The shift happens when teams move from design iteration to design space exploration. Traditionally, engineers work on one design at a time, modifying CAD, running simulations, and interpreting results.

In AI-native workflows, engineers define a design space with rules, constraints, and performance targets. AI populates that space with thousands of variants. Engineers navigate possibilities, select promising designs, and refine constraints. This fundamentally changes how engineering knowledge is captured, shared and applied.

The intelligence layer

For this to scale, AI must embed in tools that engineers already use, not exist in isolated environments. In practice, AI functions as an intelligence layer connecting to CAD, CAE, and PLM systems through APIs. Engineers work in familiar interfaces but gain AI-powered features: automated geometry generation, real-time performance feedback and cross-discipline constraint propagation.

AI-based surrogate models trained on historical simulation data predict aerodynamic drag, thermal performance, or structural behavior with near-CFD/FEA accuracy at a fraction of computational cost. Engineers see design changes consequences in real time, early exploration happens where iteration is cheap and fast, and promising candidates get validated with high-fidelity tools only when needed.

At scale, this approach collapses development timelines, reduces late-stage redesigns, and shifts critical decisions to phases where design freedom remains high.

The path forward

For organizations ready to make this shift, the first step is identifying workflows where fragmentation causes the most friction and faster exploration would deliver clear value. Aerodynamics and thermal management are common entry points: physics are well understood, simulation data is abundant, and geometry changes have measurable impact.

But success requires more than deploying technology. Engineers need training, infrastructure must support AI workloads at scale, and organizations must accept that this transition will not happen overnight. Those who get it right will make designers more productive, decisions more informed, and better products.

We Need to Talk About the Grounding Ring

Posted on 26th August 2026

Goeff Lewis, Technical Director, Duvelco

OEMs love SiC and GaN [1]; higher switching speeds lead to more efficient motors, which in turn mean greater range or lighter, less expensive batteries for the same BEV range.

Higher switching speeds, dV/dt, can mean increased displacement current coupled onto the motor shaft [2].

For a given common-mode voltage (CMV) amplitude, this causes the floating shaft voltage to reach its limit more quickly. Oil films on the bearing races can break down at around 20 to 50 volts, which in turn can lead to bearing damage through electrical erosion (EDM) and related pitting. Higher-speed, higher-frequency multipole motors mean the number of possible EDM events increases broadly in proportion to the voltage excitation frequency, hastening possible bearing failure.

One widely adopted solution is to fit a shaft grounding ring, which effectively clamps the floating shaft voltage to near zero — typically within a few volts in practice.

Why don’t OEMs love this solution?

• An additional component with associated cost, complexity, and assembly considerations.
• Axial packaging space requirement, which can be challenging in highly integrated e-axle designs.
• Requirement for a dry operating environment (i.e. separation from the lubrication system), which may necessitate additional sealing and space.
• A wear component that may not reliably meet the ~15-year design life expected of BEV drivetrains.
• Potential source of NVH (Noise, Vibration and Harshness), particularly noticeable in inherently quiet electric vehicles.
• Most critically, a hidden degradation mechanism can be difficult to detect and may lead to non-graceful bearing failure, potentially immobilising the vehicle.

Engineers and product managers have therefore sought to design out the risk of EDM entirely – the ideal solution. However, despite the use of advanced filters and common-mode chokes, this has not yet been achieved without compromising the efficiency gains offered by SiC- and GaN-based inverters.

A commonly adopted mitigation strategy is the use of electrically insulated bearings. These may take the form of bearings with ceramic insulating coatings or hybrid bearings with ceramic rolling elements.

Such bearings can be relatively expensive and, to some extent, more fragile. In addition, thin ceramic coatings with a moderate dielectric constant can still support capacitive coupling, allowing displacement currents to flow and reducing the overall impedance at high frequencies.

A dimensionally stable, creep-resistant polymer insulator with a low dielectric constant (e.g. ~2.7 at 1 MHz and 150 °C) could enhance the robustness of such mitigation strategies.

Research from Leibniz Universität Hannover (IMKT) has shown that polyimide coatings can exhibit higher electrical impedance than conventional ceramic coatings, approaching that of hybrid bearings while providing improved robustness [3].

Building on this work, Ducoya — a highly crystalline, PFAS-free PMDA–ODA polyimide from Duvelco — offers excellent flow characteristics, enabling high-precision moulding of thinner-walled sections. Its relatively low dielectric constant also helps reduce parasitic capacitance and associated displacement currents. Together, these attributes enable reduced material usage and improved dimensional control, providing an economically attractive route to enhance the robustness of grounding strategies and mitigate EDM-related bearing damage.

Duvelco Ducoya also exhibits high compressive and tensile strength and toughness at elevated temperatures, which may be advantageous across a wider range of applications.

Duvelco Ducoya is available both as a moulding-grade polymer for use with suitable modern precision processing equipment and as finished components for integration by bearing manufacturers or OEMs.

The preliminary data in the graphs below, demonstrates how Ducoya also exhibits high compressive and tensile strength and toughness at elevated temperatures, which may be advantageous across a wider range of applications.

As electrified powertrains continue to evolve, the focus is increasingly shifting from mitigating EDM risk to addressing it at source. Advancedmaterials such as Ducoya may offer new possibilities for more robust, spaceefficient insulation strategies, helping engineers explore alternatives to traditional approaches. The question is: could a material-led solution play a greater role in future drivetrain design?

---

[1] Silicon Carbide and Gallium Nitride.
[2] I=C. dV/dt
[3] Pauchard, P., Berger, C., and Jackowiak, R., “Effective Solutions for bearing Insulation to prevent electrical corrosion in E-Drive Systems” CTI Magazine, December 2025, pp. 25.

Thermal Analysis of Axial-Flux In-Wheel Motors

Posted on 19th August 2026

* Simulation results visualizing free surface flow of the oil jet (injection nozzle indicated by the yellow arrow) on the left side and heat distribution in the rotor on the right side, resulting from one single MPX simulation. The green circle marks the location of an infrared sensor.

Investigating e-motor thermals as a result of free-surface flow cooling strategies has long been a complex, laborious effort. We demonstrate a novel simulation method – Mesh-Particle Multiphysics (MPX) – which can provide high-fidelity insights from a single simulation run.

Johannes Becker, Dive CAE
Liam Pek, Dive CAE

Automotive drivetrain electrification presents major challenges to engineering teams, as performance, thermal, weight, and packaging requirements drive the need for increasingly efficient and power-dense designs. At the same time, global supply chain volatility drives the need for high-performance motors that do not rely on rare-earth magnets to enable domestic manufacturing and strengthen industrial resilience.

The primary objectives of drivetrain prototyping are to validate performance, efficiency, durability, and system integration before moving to production. Prototypes for e-motors undergo thorough load testing on test rigs and in demonstrator vehicles to confirm structural and thermal stability under expected real-world and extreme conditions. Insufficient cooling and lubrication leading to prototype failure results in costly iterative rework or even changes to the underlying system architecture, significantly impacting time-to-market.

While virtual testing of lubrication and cooling performance via simulation has been industry standard for years, it is often done in isolated domains, as workflows to combine particle-based simulations used for oil flow analysis and structural thermal simulations often involving multiple solvers and laborious processing steps that require deep numerical expertise. A novel solution to this problem, Mesh-Particle Multiphysics (MPX), enables single-run analyses of free-surface flow lubrication and cooling strategies including full conjugate heat transfer (CHT) through structural elements with timescale coupling. Leveraging the strengths of Smoothed-Particle Hydrodynamics (SPH) for the fluid dynamics of jet, spray, or sump cooling, and the Finite Element Method (FEM) for heat propagation through structures in one unified solver architecture reduces complexity and can reduce time-to-result in e-motor studies from weeks to hours.

The ORBIS ELECTRIC HaloDrive is an axial-flux electric motor architecture with a wide range of applications across industries, including as an in-wheel motor for passenger EV or commercial vehicle propulsion. Depending on the intended application, it supports different cooling strategies optimized for the expected load cycles, operational environment, and TCO.

Using Dive’s MPX, we investigate thermal performance of rotor cooling, comparing a passively cooled rotor as a baseline case with multiple intensities of active jet cooling, axially applied to the rotor. Jet cooling is confirmed to reduce rotor temperature at the position of a radial infrared sensor (see green circle) by up to 22% after 100 seconds of runtime at 1,500 rpm. While the 5m/s jet configuration reaches steady-state temperatures after about 70 seconds of runtime, both 10 and 15m/s jet configurations stabilize around 30 seconds into the test, with diminishing returns of going beyond 10m/s.

Importantly, results for this study were obtained in a single afternoon – requiring less than one hour of simulation pre-processing and four to five hours (depending on flow rate) of simulation time. Executing thermal studies on complex free-surface flow phenomena enables simulation-driven design that produces advanced cooling strategies which are well-validated and understood before going into a physical prototype.

---

References
› HaloDrive model provided by ORBIS ELECTRIC. www.orbiselectric.com/halodrive
› Mesh-Particle Multiphysics (MPM). www.divecae.com/technology