Altair Case Studies Emulating Engineering Expertise with AI: Crashworthiness Optimization at BMW

	Emulating Engineering Expertise with AI: Crashworthiness Optimization at BMW Altair

Emulating Engineering Expertise with AI: Crashworthiness Optimization at BMW

Altair

Technology Category	Analytics & Modeling - Machine Learning
Applicable Industries	Automotive Education
Applicable Functions	Human Resources Product Research & Development
Use Cases	Predictive Maintenance Time Sensitive Networking
Services	Data Science Services
Challenge	BMW, a leading manufacturer of premium automobiles and motorcycles, faced a significant challenge in ensuring passenger safety during crash events. The complexity of orchestrating the chain of events during a crash, including the timing of discrete events such as bolts breaking or parts coming into contact, was a daunting task. The key performance indicators, including energy absorption, peak force level before failure, local displacements, and weight, were either too complex or resulted in over-constrained optimization problems. This made it difficult to confidently validate crashworthiness within the fast-paced product development process. The challenge was to find a solution that could simplify this process, reduce the number of design iterations required, and ensure the highest level of safety for passengers. Read More
About Customer	The BMW Group is the world’s leading manufacturer of premium automobiles and motorcycles, with 31 production and assembly facilities in 15 countries and a global sales network. The company is also a provider of premium financial and mobility services. As an innovation leader, BMW sets trends in production technology and sustainability with an intelligent material mix, a technological shift towards digitalization, and resource-efficient production. The company also ensures competitiveness through flexibility and continuous optimization of value chains. Read More
Solution	BMW turned to Altair’s integrated Machine Learning solutions within HyperWorks to generate optimization constraints that mimic engineering expertise. The solution involved the use of clustering, an unsupervised machine learning algorithm, to help engineers understand how crash kinematics affect key performance indicators. Favourable crash kinematics were then enforced during the optimization process through the use of a classifier that emulates engineering decision making. This approach simplified the formulation of the optimization problem and reduced the number of design iterations required to develop complex automotive crash structures. The machine learning-powered workflow augmented and extended BMW’s existing engineering expertise, allowing them to more efficiently allocate computing and human resources to high-value simulation, analysis, and validation efforts. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Applicable Industries

Automotive

Education

Applicable Functions

Human Resources

Product Research & Development

Use Cases

Predictive Maintenance

Time Sensitive Networking

Services

Data Science Services

Challenge

BMW, a leading manufacturer of premium automobiles and motorcycles, faced a significant challenge in ensuring passenger safety during crash events. The complexity of orchestrating the chain of events during a crash, including the timing of discrete events such as bolts breaking or parts coming into contact, was a daunting task. The key performance indicators, including energy absorption, peak force level before failure, local displacements, and weight, were either too complex or resulted in over-constrained optimization problems. This made it difficult to confidently validate crashworthiness within the fast-paced product development process. The challenge was to find a solution that could simplify this process, reduce the number of design iterations required, and ensure the highest level of safety for passengers.

About Customer

The BMW Group is the world’s leading manufacturer of premium automobiles and motorcycles, with 31 production and assembly facilities in 15 countries and a global sales network. The company is also a provider of premium financial and mobility services. As an innovation leader, BMW sets trends in production technology and sustainability with an intelligent material mix, a technological shift towards digitalization, and resource-efficient production. The company also ensures competitiveness through flexibility and continuous optimization of value chains.

Solution

BMW turned to Altair’s integrated Machine Learning solutions within HyperWorks to generate optimization constraints that mimic engineering expertise. The solution involved the use of clustering, an unsupervised machine learning algorithm, to help engineers understand how crash kinematics affect key performance indicators. Favourable crash kinematics were then enforced during the optimization process through the use of a classifier that emulates engineering decision making. This approach simplified the formulation of the optimization problem and reduced the number of design iterations required to develop complex automotive crash structures. The machine learning-powered workflow augmented and extended BMW’s existing engineering expertise, allowing them to more efficiently allocate computing and human resources to high-value simulation, analysis, and validation efforts.

Impact #1	The implementation of Altair’s Machine Learning solutions within BMW's crashworthiness optimization process has resulted in a more efficient allocation of computing and human resources. By emulating engineering expertise through machine learning, BMW has been able to simplify the formulation of the optimization problem and reduce the number of design iterations required to develop complex automotive crash structures. This has not only improved the efficiency of the product development process but also enhanced the company's ability to ensure passenger safety during crash events. In the future, BMW plans to explore further applications of Altair ML technologies across their design processes.

Impact #1

The implementation of Altair’s Machine Learning solutions within BMW's crashworthiness optimization process has resulted in a more efficient allocation of computing and human resources. By emulating engineering expertise through machine learning, BMW has been able to simplify the formulation of the optimization problem and reduce the number of design iterations required to develop complex automotive crash structures. This has not only improved the efficiency of the product development process but also enhanced the company's ability to ensure passenger safety during crash events. In the future, BMW plans to explore further applications of Altair ML technologies across their design processes.

Download PDF Version

Overview

Emulating Engineering Expertise with AI: Crashworthiness Optimization at BMW

Operational Impact