A Tier 1 Supplier Reduces E-Motor Development Time with Surrogate Modeling and Structured Engineering Data

Why E-Motor Development Is Bottlenecked by Simulation Cost

As electrification accelerates, global automotive suppliers advancing next-generation e-motor technologies face a fundamental engineering constraint: designing efficient cooling systems requires evaluating complex interactions across electrical, thermal, and mechanical performance metrics simultaneously. Engineers must assess KPIs including winding temperature, oil coverage, and heat exchange performance across large design spaces - and with traditional simulation workflows, each evaluation requires a full simulation run consuming significant compute resources.

‍

For this Tier 1 supplier, the bottleneck was measurable: full simulation runs across large design spaces were time-intensive, each design iteration consumed costly compute, and the ability to explore alternative configurations was constrained by time and budget. RFQ turnaround had stretched to 1.5 months, reducing competitive responsiveness to OEM demands. Identifying optimal designs was taking far longer than the engineering complexity warranted.

‍

90% Cost Reduction Through Surrogate Modeling on Structured Engineering Data

The company implemented a surrogate modeling approach powered by structured engineering data within Key Ward. Simulation data across winding temperature, oil coverage, and heat transfer rates was organised into consistent, queryable datasets. Machine learning models trained on this structured data predicted performance metrics instantly, without full simulation runs. Engineers used the surrogate to rapidly screen design candidates and reserved full simulation only for the most promising configurations.

‍

The workflow became reusable across programmes - the same structured data foundation and surrogate model applied to new design variations without being rebuilt. Results: 90% reduction in simulation and compute costs, engineering loops shortened from 1.5 months to days, and 70% faster RFQ resolution versus traditional engineering workflows.

‍

What the Full Case Study Documents

The full case study documents the structured dataset architecture for e-motor KPIs, the surrogate model training and validation approach, the measured reduction in compute cost and development cycle time, and the RFQ turnaround improvement. If your team is evaluating surrogate modeling for faster e-motor design exploration and lower simulation costs, the methodology documented here is directly applicable.