According to McKinsey, “over the next two decades, artificial intelligence (AI) will transform most aspects of the auto-manufacturing process. In particular, advances in AI will give machines the ability to learn from past experiences how to improve future performance." The main challenges Engineering organisations face with regards to the adoption of AI is that they are hampered by tools and processes that require repetitive desktop-based workflows, are unable to learn from previous experiences and knowledge, and lack the collaboration capabilities enabling agile R&D. Monolith is a no-code AI platform that any engineer can use. It empowers engineers to build AI models that learn from previous tests or simulations in order to predict the outcome of new ones, which dramatically accelerates design cycles. Maxion Wheels is an automotive supplier with a 100-year heritage in developing and manufacturing steel and aluminium wheels. It has 30 facilities across 15 different countries and counts over 10,000 employees. Over the last few months, engineers from Maxion Wheels have started to use Monolith, and have seen first-hand the benefits which it can have on suppliers in the automotive industry. Here is a summary of the 5 key benefits highlighted from this experience.
Reducing tests and simulations
Engineering organisations like Maxion Wheels, who are invested into digital transformation, are on a journey to increase agility, improve compliance/quality and reduce time to market by using data and AI. They realise that the repetitive nature of their product development workflows lends itself very well to an AI solution that learns from past experiences to predict the outcome of new ones. As an automotive supplier, Maxion Wheels carries out numerical simulations and physical tests to design and manufacture wheels according to customer requirements. Their areas of focus include structural mechanics, weight reduction, aerodynamics, Noise Vibration & Harshness (NVH), and manufacturability. When a customer approaches them with a new wheel design, they need to ensure it can be manufactured to specific performance/quality requirements, while maintaining a desired aesthetic.
Over its 100+ year history, engineers at Maxion Wheels have developed deep expertise in developing simulation tools and test rigs which are capable of assessing the quality or performance of a wheel design. This expertise and the data which gets produced from it represent a goldmine of historic knowledge which can be leveraged by AI.
Indeed, by integrating some of the methods detailed later in this article into their product development workflow, companies like Maxion Wheels can build machine learnings models which are capable of predicting the outcome of simulation or tests. This makes it possible for design and engineering teams to iterate much faster, reduce the total amount of simulations or tests which need to be carried out, and develop better products faster.
For automotive suppliers like Maxion Wheels, it is of particular concern to find methods to accelerate their product development processes as they often deal with the competitive nature of supplying products and services to OEMs. The Request for Quotation (RfQ) process is a particularly competitive segment of their process, in which they need to provide guarantees of manufacturability and performance in a highly timely manner. Of course, once a design has been assigned to them for manufacture, in-depth development begins, and it is critical to make efficient use of vast amounts of resource in order to remain competitive.
So, extracting value with AI from historic design, simulation, testing or manufacturing data can enable engineering organisations to drastically reduce the number of simulations or tests they’ll need to carry out to assess and/or optimise product performance. But who is best positioned in the company to do so?
Making engineers gain a digital edge
The emergence of AI is making companies increasingly eager to transform their business towards being able to derive insight from data for decision-making. However, for large traditional companies, this is a complex challenge: their data is often static, and their analytics tools can’t handle vast amounts of data and don’t have AI capabilities built in.
To address this challenge, many companies turn to data scientists as the people who can help make this change happen for them. However, relying exclusively on data scientists is a major risk, especially for Engineering organisations. As well as being scarce and expensive, they often lack the context and intuitions which are needed to understand and handle engineering data. Companies who realise this challenge look to engage engineers themselves to gain a digital edge. Engineers are deeply embedded in the business and understand better than anyone else the complex physical systems on which they work daily. They understand the kind of insights which are needed to drive positive change for their team and their organisation.
Monolith is a no-code AI platform that any engineer can use. It aims to democratise AI, by empowering engineers to self-serve in building AI solutions for their engineering problems. In our experience, their engineering expertise coupled with easy access to complex AI tools is a winning recipe which drives digital transformation for Engineering organisations.
But how exactly might an engineer build and deploy AI models, for complex engineering use cases such as the ones faced by Maxion Wheels?
Encoding highly complex 3D data
Machine learning algorithms are mathematical algorithms which train models using historic data in order to make predictions without being explicitly programmed to do so. The data used to train these models could be contained in a simple spreadsheet, with each column corresponding to an input or output variable and each row corresponding to an observation. In Engineering use cases, the input parameters might be geometric parameters, boundary conditions, operating conditions, or environmental conditions. Output parameters might be the results of a numerical simulation or of a physical test. Trained machine learning models understand the correlation between the inputs and the outputs and are therefore capable of predicting the performance or quality of a new design tested under new conditions.
However, in many cases, it is impossible to fully describe a design’s geometry with a straightforward set of known numerical parameters or measurements. For products like the ones developed by Maxion Wheels, the creative freedom in the design process means that there is an unlimited amount of variation which the geometry could adopt. Indeed, 3D wheel designs represent highly complex aesthetics and, up until now, it has been difficult to develop methods of deriving quantitative ways of comparing this kind of 3D data in order to feed it into a machine learning model.
Monolith AI has developed patent-pending 3D deep learning technology capable of automatically parameterising a dataset of 3D CAD designs. These algorithms can scan 3D CAD files to extract the distinct geometry feature which characterise each design.
This automatic parameterisation has two benefits:
- To encode new designs into a set of numerical parameters, in order to predict their performance.
- To generate new, performance-optimised designs which satisfy target goals and constraints.
To visualise this process, here are a few snippets of a workflow in the Monolith platform, in which raw 3D data is parameterised using Monolith’s AI deep learning algorithms in order to predict the performance of new designs. The data demonstrated here is open source (not from Maxion Wheels).
The starting point is a dataset of 3D CAD files. These designs have complex aesthetic differences between them which are impossible to quantify manually.
Deep learning algorithms enable these complex designs to be parameterised. A new 3D design created by a designer or engineer that has been parameterised can be quantitatively compared to other designs in the dataset of historic 3D data. These learned dependencies of the algorithm can then be used as inputs to more conventional machine learning models such as Neural Networks, which predict performance quantities of interest.
The ultimate aim is to enable users to make instant predictions for the outcome of simulations or physical tests, for of new 3D designs.
The ability to make predictions for the outcome of tests or simulations by presenting complex 3D CAD data in this way is a game changer for Engineering organisations. It allows design and engineering teams to iterate much faster by reducing the number of simulations or tests needed to be carried out to develop high-quality designs.
Predicting 3D fields of simulation data
Monolith is an AI platform tailored to solving Engineering problems. It is for this reason that it offers the ability to present 3D CAD designs directly to machine learning models, to obtain a prediction for the outcome of a simulation or test.
Another area for which Monolith offers solutions tailored to engineers handling 3D data is in its ability to predict entire 3D fields of simulation results. For example, for simulation engineers working on Computational Fluid Dynamics (CFD) or Finite Elements Analysis (FEA) applications, this means they can train AI models capable of producing a prediction of a stress field, a pressure field, or a temperature field, etc. for a new 3D design and new sets of boundary conditions.
Whilst machine learning models are usually restricted to predicting scalar values, users of Monolith can investigate the local effects of design changes on an entire 3D field of data, through visual analysis and through post-processing.
Combining learnings from different stages of the product development process
For an organisation such as Maxion Wheels, the development of a new product involves complex sets of performance/quality requirements, each indicated by their own simulation or physical test. The aim of Engineering teams is to find the right balance between weight and stiffness, between manufacturing cost and durability, or between aerodynamics and aesthetics, for example.
In our experience, engineering teams can see the full benefit when they use AI models capable of predicting multiple performance metrics to help in decision-making. Indeed, by gathering historic data from multiple engineering teams, users of Monolith can paint a holistic picture of the performance of new designs which helps them understand the trade-off which may exist and make better-informed decisions. In particular, the ability to forecast late-stage performance in the early stages of a product development process can help engineering teams prioritise design and engineering effort in areas of their product which may have otherwise required costly U-turns in the development.
To enable building this cross-functional AI solution, Monolith offers users the ability to collaborate by sharing data, models, data processing pipelines and dashboards on the cloud. For generally speaking, the ease of installation and ease of use of the product is a strong enabler for effective collaboration – a pre-requisite to being able to build a network of machine learning models which touch upon all aspects of the development of new designs.