Automotive industry

Monolith brings revolutionary artificial intelligence to the automotive industry, reducing product development time and costs by up to 50%

Monolith, a fast-growing artificial intelligence (AI) software company, is set to radically reshape the development time for new cars. Its breakthrough AI platform can significantly reduce the testing and associated costs automakers currently need to bring new vehicles to market.

Monolith software uses self-learning models to instantly predict the outcomes of complex vehicle dynamics systems, reducing the need for physical testing or simulations. This revolutionary approach will dramatically accelerate every step of the automotive development process, from initial concept, design iterations, validation and production, which currently require repetitive, time-consuming and costly testing and simulation. Using Monolith also results in fewer physical prototypes, trips to specialized test sites and on-road testing, making the final stages of validation safer and more sustainable.

– The current gap between virtual and physical testing

To this day, automakers use a combination of realistic virtual simulations and physical testing when developing vehicles. For each design iteration, a simulation solves the physics underlying the system modeling; a notoriously difficult and computationally intensive process. Virtual simulations reduce the number of physical tests required, but the accuracy and fidelity of the results may be limited. Many physical tests are therefore still necessary to calibrate and validate the virtual results, as well as to understand the performance under non-simulable operating conditions.

For example, aerodynamics optimize airflow over a vehicle to reduce drag and are notoriously difficult to solve mathematically, reducing the accuracy of simulated models. Due to the highly iterative nature of the automotive design process, engineers supplement virtual aerodynamic testing with hundreds of hours of wind tunnel testing in facilities that can cost thousands of dollars per hour.

– Monolith Transforms Automotive Product Development

Monolith offers an alternative and radical solution to reduce the time and cost of vehicle testing. Virtual and physical testing creates large volumes of valuable data that is currently underutilized. Now, with Monolith, this data can be leveraged to train highly accurate AI self-learning models to instantly predict system performance by understanding its behavior from the data, instead of solving complex system physics. or perform a physical test. Using this approach, engineers can quickly predict performance under more operating conditions and for areas of the car that were previously impossible to simulate, further reducing the number of tests required. Monolith is already used to reduce wind tunnel dynamics, tracks, wheels and tires, as well as vehicle dynamics, durability, crashes and powertrain testing.

Dr Richard Ahlfield, CEO and Founder of Monolith, “Monolith was founded to enable engineers with AI to instantly solve even their most intractable physics problems. We know this resonates especially with automotive engineers who struggle to optimize hundreds of often conflicting criteria with hundreds of complex simulations.Requiring hours or days to solve problems, engineers became frustrated with the sheer amount of physical testing still needed to compensate for the limitations of virtual testing. time, the data created during the process represents a huge opportunity when used with AI. By predicting outcomes with self-learning models, we can radically speed up the development process.

Today, automakers are spending billions developing electric architectures and software capabilities as they strive to win the race for electric, shared, and autonomous mobility. This squeezes R&D budgets and product timelines in other areas, creating enormous pressure on engineering teams working to develop higher quality vehicle hardware systems in less time and with fewer resources. As Toyota CEO Akio Toyoda said, “Data is the new gold” but the “[vehicle] will be the backbone of mobility as a service for autonomy, for car sharing, for all the services we want to make possible”. Data to build better vehicles while reducing costs and saving time – this is at the heart of how Monolith is uniquely transforming vehicle development.

The Monolith platform enables automotive R&D teams to use AI to derive the best possible insights from years of existing test data or instantly predict the results of a small sample of ongoing tests. Ultimately, this means OEMs can get new vehicles to market faster, which is not only vital to achieving EV ambitions, but allowing automotive engineers to do what they love. plus: design amazing new vehicles. »

– Mature and proven technology, ready to evolve

Monolith has spent the past six years developing its platform and working closely with some of the best engineering teams in the world to stress test it. Today, it has mature and proven technology that integrates seamlessly into customers’ daily activities. Engineering teams from leading automotive OEMs and Tier 1 suppliers around the world are already realizing substantial reductions in physical testing after working with Monolith:

1) Sensor and instrument company Kistler achieved a 72% reduction in sensor-based testing

2) Honda had an 83% faster design cycle

3) JOTA Sports Endurance Racing Team reduced the number of simulations and tests by 50% and the associated costs by 66%

Dr. Joel Henry, Principal Engineer at Monolith, said, “Optimizing a system or finding a new solution based on a decade of historical data is like giving an engineer an instant decade of experience. That’s the power of AI – it energizes an individual’s subject matter expertise by unleashing the expertise stored in a company’s data. Monolith is truly the engineer’s ideal partner.

Built from the ground up by engineers for engineers, the no-code platform delivers a seamless user experience with powerful interactive dashboards. The Monolith team is made up of industry and software experts who work with customers to identify their most effective use cases that can quickly realize the value of AI.

Use cases depend on business needs and data type. For example, an OEM can use its legacy data to find new information hidden in its decades of expertise and unique data. Alternatively, data captured from a handful of tests using a physical prototype can be used to teach self-learning Monolith models to predict behavior under more operating conditions; including in unstable states, when the variables of interest have not stabilized and continue to change over time. Monolith self-learning models predict behavior in these typically hard-to-capture unstable states in seconds, instead of weeks or months by capturing behavior under all driving and operating conditions. This allows engineers to explore even more parameters and requirements to create products that are even more fit for purpose while dramatically reducing development time.

– The $46 billion opportunity

The company is currently focused on automotive customers, but has ambitions and applications in countless industries. Monolith can be used for any system that requires data, repetitive testing, or digital twins for design development, validation, production, or data evaluation. Digital twins, which are real-time virtual representations of a physical object or process, are increasingly being used in a wide range of industries, including manufacturing, healthcare, supply chain and retail. The digital twin market is estimated to be worth $46.08 billion by 2026. Monolith is already working in this space with global brands such as L’Oreal and pharmaceutical company Nanopharm.

Monolith is set to scale rapidly with a team of experts, a network of industry partners, an extensive intellectual property portfolio and £10.6 million in funding.

Copyright © acrofan All rights reserved