Machine Learning in Engineering

Renishaw uses Altair signalAI to deliver advanced digital gauging with real-time melt-pool analytics. This AI-driven quality assurance process helps Renishaw identify manufacturing anomalies earlier, develop parts quicker, and realizes a stable production.

Knowledge Studio delivers explainable artificial intelligence (AI) and automates machine learning tasks to enable people to make fully informed decisions based on massive amounts of data. The software displays all the details of a model’s configuration so it is easy to understand how it generates predictions. Analysts who may not be familiar with modeling or AI processes can quickly uncover insights to help solve complicated problems. Data scientists can fine tune model parameters and develop highly sophisticated models using a drag-and-drop interface with no coding required.

Altair’s Data Analytics Assessment Service helps answer the tough questions: • What data do I have? • Can it be leveraged for analytics? • What other data do I need and how do I get it? • What ML technology can be used with my available data? • How do I get started?

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.

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

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.

Information silos present a major challenge to Heavy Equipment OEMs. Poor integration of simulation models across the product life cycle, limited reuse of models between programs, and a variation of modeling maturity across various engineering disciplines result in lack of traceability and ultimately hampers development efficiency and product performance. Using system modeling and asset-centric data analytics solutions help develop and orchestrate coherent models to increase decision-making confidence and speed.

Learn how Altair AcuSolve™ performs with AMD EPYC™ 7003 series processors

Fluid mechanics simulation is a critical tool for late-stage failure risk mitigation, as well as a driver of design insights throughout the product development process. Used across all levels of product design and validation, from design engineers seeking to understand fluid and thermal effects on a design proposal to analysts performing advanced aerodynamic modeling, Computational Fluid Dynamics (CFD) serves a broad array of applications and a range of users with varied levels of expertise. The sometimes complex and computationally intensive nature of CFD necessitates careful consideration of the software and hardware investments required to produce accurate solutions and scale them at the speed of a company’s development process.

Two- and three-wheeler vehicle manufacturers, whether they are existing OEMs, new EV start-ups, or suppliers serving this segment, all have the goal of shortening product development time and getting product to market faster. With Altair HyperWorks™, ride, durability, and vehicle dynamics simulations for two- and three-wheeled vehicles can now be seamlessly performed using an intuitive and easy to use GUI with built-in libraries for vehicle models, analyses, and predicting and optimizing vehicle behavior.

Accurately predicting future consumer behavior allows credit risk analysts, financial marketing analysts, and fraud detection teams to better deploy strategies to capitalize on opportunities while deploying strategies that act as preventative measures against disruptive forces to their business models.

Today, most products are complex mechatronic combinations of advanced technologies, mixing electrical parts with controllers and embedded software. To efficiently manage innovative products, organizations are turning to a Model-Based Development approach for concept studies, control design, multi-domain system simulation and optimization. To meet this demand, Altair’s simulation and optimization suite aims to transform design and decision-making throughout product lifecycles with their multi-disciplinary software tools and consultancy services.

A company specializing in 3D printing relies on simulation to make tools for injection molding that are less expensive, lighter and better than those created with traditional methods.

To design and build an aerial ladder for a firetruck, the engineer needs to accurately determine the working loads the ladder will encounter. Some of these can be easy to interpret such as the weight of the firefighter in the basket at the end of the ladder, or the weight of the water being supplied to the nozzle. Other loads can be a little harder to quantify, such as how wind affects the ladder. There are several different ways to determine this effect, and two of those will be explored in this paper: the standard equation (ASCE 7-10), and CFD.

Optimal design methods involving the coupling of fluid and structural solutions are a topic of active research; particularly for aerospace applications. The paper presents a coupled fluid and structure approach to topology optimization using two commercial finite element solutions; AcuSolve and OptiStruct. A gradient based method is used to minimize the compliance of a structure subject to thermal loading. The optimal material distribution to minimize compliance is computed using the Solid-Isotropic Material with Penalty (SIMP) method available in OptiStruct. A volume fraction constraint is imposed in order to iteratively reduce the parts mass. Draw constraints are used to ensure manufacturability. The thermal loading is computed iteratively using a computational fluid dynamics (CFD) solution from AcuSolve. The optimization produces an innovative design which increases the heat rejection rate of the part while reducing the mass.

Nowadays, it is more and more difficult to design electro-technique devices without having a look at thermal stress. In more and more applications (more electric vehicles, more electric aircrafts, …) designers need to reduce weight, cost, increase efficiency, and keep the same security factor. One possibility is to increase current for the same device, needing to check how to draw away the heat. This is why the classical approximations need to be cross checked with complementary analysis. These new tools have to be rapid and accurate in order to run parametric and even optimization analysis. There is also a need for fast model in order to check robustness versus driving cycles. The goal in this article is to review rapidly the different methods available, depending on the accuracy required and the solving speed. The method includes equivalent thermal circuits, Finite elements methods and CFD analysis.

Development tools and methods, such as simulation, are increasingly important to face and address the pressure of innovation. As an example, for successful new design methods and to show how simulation tools are used, Altair developed a virtual demonstrator based on a cobot application. This complex machine interacts with a human operator as the ultimate smart manufacturing equipment - to show how challenges in modern product design can be overcome.