Emulating Engineering Expertise With AI
Crashworthiness optimization at BMW with AI-enhanced surrogate modeling.
BMW uses Altair’s integrated Machine Learning solutions within HyperWorks to generate optimization constraints that mimic engineering expertise. Clustering, an unsupervised machine learning algorithm, helps engineers to understand how crash kinematics affect key performance indicators (KPIs). Favorable crash kinematics are then enforced during the optimization process through the use of a classifier that, in effect, emulates engineering decision making throughout
Altair® Flux® Can Take the Heat - Optimizing The Energy Exchange of an Induction Hob System at Groupe SEB
As inductive heating becomes more popular, cookware manufacturers must develop efficient cooking pans that meet consumers’ expectations. Groupe SEB’s engineers aimed to create a new pan that fulfilled product requirements while minimizing material and development costs. Because testing physical prototypes is time-consuming, the engineers created a virtual prototype of an induction hob. The Groupe SEB’s team realized a parametric model of an induction hob heating system considered the entire system’s magnetic and thermal aspects. Parallel lab tests confirmed the numeric model’s accuracy, which gave the engineers a better understanding of the induction exchange, and helped them eliminate valid but inefficient solutions before building the first prototype.
Bringing the Future Faster Through Innovation and Analysis, by American Axle & Manufacturing (AAM)
AAM has been providing mechanical drivelines to automotive customers for more than 25 years. As the automobile transitions to electrification, so too must the driveline. AAM has developed a suite of innovative, lightweight, compact and cost-optimized electric drive units and electric beam axles to meet the growing global technology demand as electric vehicles continue to expand over the next decade. Engineering simulation, optimization and validation tools were significant enablers to increase the validation confidence and reduce the time to market for these new products.
The Future of Design Exploration with AI-powered Design
Gaining insights into a product’s performances has never been easier. With the HyperWorks Design Explorer, users can easily set up and execute the design of experiments (DOE) and optimization studies, learning which attributes contribute the most to the different performances, review, plot, and compare results from multiple runs, and ultimately identify optimal designs. The quick and easy setup process is solver independent, yet fully integrated with Altair’s structural analysis solutions.
On the other hand, many design specifications are quantifiable and can be confirmed by physics but optimizing a design for subjective design requirements such as the look and feel of a product requires a different approach. This is when expertAI can help. It uses machine learning to enable you to include criteria that have traditionally been considered purely subjective or expert-driven in design optimization. The AI algorithms cluster your designs with respect to their subjective behaviors allowing them to be labeled to train a model aligned with your preferences.
The Power of AI and ML in Product Design
Altair products are quickly evolving into AI-driven products. Starting from the modeling and visualization products, the latest release of Altair HyperWorks includes features like shapeAI, which quickly finds and classifies parts “by shape” inside geometry files or finite element meshes - when you want to locate all of the bolts, shafts, and gears in a complex assembly - by applying machine learning.
Altair® HyperStudy® - Automated design generation and data-driven optimization
In this workshop, you will get an insight into HyperStudy and learn about the key features and benefits of simulation- and data-driven optimization.
Development engineers, designers and component managers face a wide variety of challenges in their daily work: Shortened development times have to be met, complexity and the number of variants continue to increase, multidisciplinary requirements for products sometimes go beyond the development process and are constantly changing. At the same time, they must be able to operate various modular systems.
What is Simulation Doing for Machine Builders
A key development goal of any machine-building project is to produce perfectly running, reliable machines that make high-quality products. By leveraging accurate virtual prototypes, seamless production can be ensured earlier in the development process to help assess and improve product profitability.
Complex Radome Electromagnetics Simulation in Minutes
Radomes are used across multiple industries, including aerospace, defense, electronics, and
telecommunications. When properly designed, the radome can actually enhance the performance
of an antenna system. The proper selection of a radome for a given antenna can help improve the
overall electromagnetic system performance by eliminating wind loading, allowing for all-weather
operation, and providing shelter for installation and maintenance. Altair’s radome simulation
solution helps to streamline the design of these complex components, ensuring performance while
significantly reducing development time.
Data Discipline: Managing Engineering Data for AI-powered Design
The advancements in the fields of AI and ML, combined with the increased availability of robust simulation, testing, and field data sets has made engineering data science a critical component of the modern product development lifecycle, but in order to extract maximum value from these exciting tools, companies need a plan to store, manage, and utilize their data efficiently. They need data discipline
Applying Machine Learning Augmented Simulation to Heavy Equipment
Simulation-driven design changed heavy equipment product development forever, enabling engineers to reduce design iterations and prototype testing. Increasing scientific computing power expanded the opportunity to apply analysis, making large design studies possible within the timing constraints of a program. Now engineering data science is transforming product development again.
Augmented simulation features inside Altair® HyperWorks® are accelerating the design decision process with machine learning (ML). The power of ML-based AI-powered design combined with physics-based simulation-driven design leveraging the latest in high-performance computing is just being realized.
AI-Powered Product Design
What makes artificial intelligence a game changer is not what movies depict with the loud destructive powers of artificially intelligent robots. It’s the opposite, it is the silent creative destruction that it brings as apps in our phones or features in the tools that we use such as spam filters, fraud detectors, and recommendation engines. When combined, these tools make our lives more enjoyable, safe, and productive.
In a similar spirit, at Altair, we have been working on powering product design and development with AI to make your work lives more enjoyable, and productive. Our focus has been improving processes and outcomes by reducing repetitive, labor-intensive, non-value-added tasks as well as emulating experts and enriching performance predictions with real-time field predictions. What makes these offerings unique is their no-code integration to the tools that you are already familiar with and hence not requiring you to have to leave your own working environment. In this presentation, examples of such AI-Powered product design processes will be demonstrated.
The presentation by Dr. Fatma Kocer, VP of Engineering Data Science at Altair, aired at Future.AI in June 2021, and is almost 30 minutes long.
Ready to see how your company can drive innovation with AI-powered design? Contact our solutions experts today.
View all Future.AI 2021 Presentations
AI Powered Product Design
Dr. Fatma Kocer VP, Engineering Data Science at Altair showcases the impact of AI in development environments. In particular on how CAE tools will evolve and Design Exploration is taken to the next level.
ATCx Industrial Machinery 2021
Failing Fast is not an option! Develop world's first robotic car storage service with accurate virtual prototypes
Benoit Pelourdeau presents how Stanley Robotics SAS drives the design process with simulation, to develop the world's first robotic car storage service.
Learn from him how the interdisciplinary mechatronic product development team succeeds with accurate virtual prototypes.
ATCx Industrial Machinery 2021
Faster evaluation of real-world machines - Improve the Design with Studies and Design Exploration
Simon Zwingert, Technical Consultant, gives a Demo Sessions on Altair Simulation Solutions for faster evaluation of real-world machines, explaining how, to improve the design with studies and the design exploration on the complete assembly to perform weld line optimization.
ATCx Industrial Machinery 2021
From CNC Jobshop to the largest manufacturer of CNC Rotary tables
Indradev Babu, Managing Director, UCAM PVT LTD, explains how he developed a CNC Jobshop to the largest manufacturer of CNC Rotary tables—presenting different development examples, he explains how Simulation Driven Design helps him to differentiate and what simulation Strategies he implements in the customer-centric development for the following generation Machine Tools at UCAM.
ATCx Industrial Machinery 2021
Battery Part 1: Developing Predictive Electro Thermal Cell Models for Pack Level Deployment
Martin Kemp, Regional Manager at Altair, Dr. Denis Cumming, a Senior Lecturer at The University of Sheffield, John Milios, CEO at Sendyne, Dr. Gregory Offer, Reader at Imperial College London and finally Professor Jun Xu, Director of Vehicle Energy & Safety Laboratory at The University of North Carolina, present - Developing Predictive Electro Thermal Cell Models for Pack Level Deployment.
This presentation will focus on the simulation of the battery cell to represent its complex thermal and mechanical behaviour. The thermal behaviour requires the simulation of the electric behaviour within the cell which leads to the generation of heat. Managing the thermal behaviour is fundamental to the long term health of the battery. The talk provides an overview of the technologies used to simulate battery behaviour, commencing with the understanding of the battery structure including the simulation of electrode manufacture. Both electrochemical and equivalent circuit models will be discussed with the advantages and disadvantages of both methods presented. Finally, machine learning technology is used to create an intelligent cell model which retains accuracy whilst delivering computational efficiency which can be used in Part 2.
Battery Part 3: Simulation Technology Facilitating Battery Pack Range Optimization
Dr. Richard Boyd, Technical Specialist at Altair take us through his presentation, Simulation Technology Facilitating Battery Pack Range Optimization.
Richard will take the battery module presented in Part 2 and create a full 3D model of the module - the duty cycle, event and optimization is repeated in this environment. This is performed efficiently in a Finite Element environment. In addition, a link to a 3D Computational Fluid Dynamics solver is highlighted if additional verification is required.
Creating the World’s Most Power Dense Electric Motor
James Eves, Team Manager at Altair, Jonathan Stevens, Senior Development Engineer at Equipmake and Andy Jones, Innovation Program Manager at HiETA Technologies, discuss AMPERE, a joint project to produce an extremely lightweight, efficient but low-cost electric motor with an extremely high continuous power density. The consortium will present some of the engineering challenges that designing such a high performance motor has posed, and how these challenges have been overcome through advanced manufacturing technology and simulation driven design.
Streamline your e-Motor Design with Multiphysics Optimization at Early Concept Level
Altair FluxMotor™ is a software dedicated to the design of e-Motor concepts. It enables designers to build machines within minutes, quickly run multiphysics tests to assess machine performance, and select most promising concepts. Coupled with Altair HyperStudy™, more design exploration and optimization can be accomplished. Using these tools confidence can be established in meeting requirements, even at this early design stage.
Product Overview Videos
Rapid Modelling of Chopped Fibre and Recycled Composites
Matt Kedgley from Engenuity introduces us to FiRMA, an analysis method that tackles the difficult task of predicting the structural performance of randomly oriented fibre composite components. This method has been developed and made possible using a customisation of Hypermesh. The Finite Element (FE) models are pre-processed into the FiRMA format before being submitted for analysis solve through HyperStudy.
Optimizing Medical Stents with Machine Learning
Medical stents are a lifeline for patients with cardiovascular illness and disease. Altair's solutions can speed up development time by satisfying the testing of variables virtually, allowing engineers to truly optimize the design and performance of medical stents.
Altair for Fluids and Thermal Applications
From detailed component analysis to full systems performance, Altair provides a range of scalable solvers and robust pre- and post-processing software for CFD.
Altair HyperWorks - Design Explorer
Altair HyperWorks' Design Explorer is an end-to-end workflow for real time performance prediction and evaluation.
Training - Design of Experiments Using HyperStudy
Design of Experiments Using HyperStudy
CAD Based Hydraulic Pump Optimization
Many engineering projects start with CAD geometries. In order to perform design exploration studies and optimization on CAD-based FE models, an automated process is required including CAD, Preprocessor, Solver and Design exploration tools. This example presents a solution to implement CAD tools into an automated simulation-driven design exploration and optimization process.
Shear Wall Layout Optimization
Due to the large scale nature of Architectural, Engineering & Construction projects, frequent change orders, and on-time delivery pressure, more often than not the ability to use traditional simulation methods for design guidance and validation is simply time and resource prohibitive.
Simulation in the Field of Implantable Cardiovascular Devices
Steven Ford, Principal Engineer at Edwards Lifesciences does a high-level walk through on how simulation has evolved in the cardiovascular device space over the last two decades. An example of how Altair HyperStudy has been an exceptional tool for deeper learning with respect to device performance will also be highlighted as a step along this journey.
The recording is about 15 minutes long and was originally presented at the Altair Technology Conference 2020.
Global ATC 2020
Altair HyperStudy™ - General Working Process
Altair HyperStudy is a multi-disciplinary design exploration software helping engineers to improve their designs. This video presents the general working process.
Product Overview Videos
Improving Performance Using FEKO and HyperStudy at Northrop Grumman
Scott Burnside, Senior Antenna & RF Engineer at Northrop Grumman, explains how Altair Feko and HyperStudy can be combined to design and optimize antennas for land vehicles, helicopters, and aircrafts.
Improving Speed and Precision of a CNC Milling Machine with Holistic System Simulation
The presentation outlines a solution strategy for how a digital twin of a milling machine is solving mechatronic challenges. To improve cycle times, accuracy, and addressing vibration problems a holistic system simulation serves as the basis for optimization.
The efficient modeling of the real system behavior with flexibilities, contacts, gaps, friction, nonlinearities in the drives (incl. saturation effects of motors), power electronics in combination with the control system is the basis for efficient controller design and optimization of the control parameters.
The dynamic interaction of multiple system components combining 3D finite elements analysis
multi-body dynamics and control system helps avoiding Tracking-, drag-, positioning errors rebound, and accumulation effects.
Optimize Medical Stents with Machine Learning
Medical stents are a lifeline for patients with cardiovascular illness and disease. Device manufacturers are required to dedicate large amounts of time and expense to clinical tests to validate safety and performance claims. Simulation can speed up these trials by satisfying the testing of variables virtually.
This webinar presents Altair’s process for fast and intelligent stent optimization by coupling simulation, Design of Experiments (DOE) and machine learning algorithm to generate an analytical model.
Solving the Design Paradox
Full evaluation of a design concept requires the definition of many complex details. However, complex geometric details constrain design flexibility.
Optimization-enabled Structural and Multiphysics Analysis
Simulation-driven design powered by topology optimization was created by OptiStruct over two decades ago. Its success has changed the CAE/CAD industry as today all vendors have embraced this trend.
Multiphysics Simulation of Electrical Rotating Machines and Next Gen Design - Rotating Machinery
This workshop will showcase a process-oriented multidisciplinary simulation environment to accurately analyse the performance of complex rotating machines. The participants would learn about multiple physics analysis of motors; including electromagnetics, structural, thermal, and fluid dynamics using highly automated modelling tasks, helping to drastically reduce the time spent creating finite element models and interpreting results.
Unique solution by Altair for rotating machinery process takes setup to a solution, time from hours to minutes which allows engineer to try multiple design iterations in a short time and create a performance curve in the automated environment.
Altair for Multiphysics Applications
Altair provides an industry-leading portfolio of multiphysics-enabled software to simulate a wide range of interacting physical models including fluid-structure interaction (FSI), flexible bodies, aeroacoustics, and thermomechanical simulation.
SimLab St & HyperStudy - CAD Based Parametric Optimisation
CAD Based Parametric Optimisation Using SimLab St & HyperStudy
Using HyperStudy with a remote HPC infrastructure via Altair Access
Altair HyperStudy is a design exploration tool that manages simulation model variability, run submission and extracts simulation responses.
HyperStudy allows to seamlessly perform Design of experiments, generate metamodels and perform optimizations and reliability studies.
However, some simulations are computationally expensive to run in local machines. Altair Access can assist to submit the jobs to a remote HPC server seamlessly, with the reduced simulation time and increased compliance with IT policies.
Tips & Tricks
Infographic: The Impact of Multiphysics Optimization on e-Motor Development
Simulation helps you validate at the end of a product design cycle, but deployed early and throughout a development process, it can actually allow you to explore more potential solutions, collaborate more effectively and optimize the design for cost, performance, weight, and other important criteria. This infographic provides a framework for developing and implementing your own simulation-driven process to help you produce more efficient e-motors and shorten development times.
Electric Motors Multidisciplinary Optimization Platform
The design of a high-performance e-Motor is a complex undertaking. Engineers have conflicting constraints to consider including efficiency, temperature, weight, size and cost. To explore more ideas, better understand their designs and improve performance, Altair HyperWorks™ has a workflow to guide motor designers through an efficient process of Simulation-Driven Design. This analysis and optimization solution supports multi-disciplinary teamwork and reduces design times.
HyperStudy – New Definition Concept
Every approach now contains a unique definition of the models, variables, and responses for that approach. These “Definitions” streamline the process of making modifications between approaches. This new framework provides more freedom to explore diverse and multi-disciplinary studies in a single session.
Tips & Tricks
HyperStudy – Measure the Difference Between Curves
Area is a new data source tool that defines a metric to measure the difference between two curves. By minimizing this metric in an optimization, it is simple to tune simulation models to match targets.
Tips & Tricks
HyperStudy – Submit Simulations to Altair PBS Works
HyperStudy has new infrastructure to seamlessly interact with the Altair Access high performance computing platform. This connection handles the upload, submission, and download of the simulation files. Easy access to scalable computing enables design exploration for larger problems.
Tips & Tricks
HyperStudy – Compare Fit and Solver Results
Compare fit and solver results in HyperStudy. Verification - This approach compares two data sets in a side by side comparison.
Tips & Tricks
HyperStudy – Extract Responses from Spreadsheets
Spreadsheet is a new data source tool that can be used identify data in a spreadsheet (*xls or *xlsx) by specifying the sheet name and cell ranges. It is now simple to extract results from software that produces output spreadsheets.
Tips & Tricks
Altair HyperStudy Product Overview
HyperStudy is a multi-disciplinary design exploration software helping engineers to improve their designs. By using an automatic processes combining state-of-the-art mathematical methods, predictive modeling and datamining, HyperStudy explores the design space smartly and efficiently.
Product Overview Videos
Design Exploration and Optimization of an Aluminum Profile
Faraone Srl - a company leader in designing and manufacturing "transparent architectures" - as been working with Altair to develop an optimization and design exploration workflow for their aluminum profiles. Profiles initially designed with Altair Inspire, are then passed to the new Design Explorer tool - included in Altair HyperWorks X - to further evaluate and refine the design.
An Efficient and Automated Design Strategy for Multi-physics E-Motor Development
This presentation introduces an application of a unique, highly automatic, multi-physics design strategy for E-motors, based on a current program at Mercedes-AMG GmbH. The strategy considers essential development requirements including electromagnetics and thermal requirements, NVH, stress and durability. It accommodates for DOE, multi-objective optimization and design exploration methods to be used to explore and find feasible motor designs. The presentation will show how the strategy adds efficiency to the E-motor development process and how it impacts the total costs of development.
Using Machine Learning and Optimization to Develop e-Motor
The Altair Multiphysics platform provides a broad portfolio of solvers and tools to help engineers develop e-motor design requirements by using simulation and optimization methods. This presentation provides examples, using Altair Machine Learning and optimization solutions, of the e-motor requirements by leveraging in data available, which is key for e-motor designers to reduce time-to-market.