Technology: impact of digital twins in optimised tire processes

London: Manufacturing industry is currently in a stage of transition, reacting to a rapidly changing consumer marketplace and employing more environmentally friendly methods of production to satisfy the demand for action on climate-change. 

For the tire manufacturing industry, this fast-evolving situation is creating  an unprecedented number of challenges and obstacles – many affecting productivity, efficiency and, of course, profitability. 

Firstly, the supply of materials used in the manufacturing process is under pressure because of an increase in demand for tires. Equally, the drive for sustainability and product lifecycle transparency is driving efforts to establish greener manufacturing methods. Also, changing transport and commuting trends are ushering in a demand for new smart, lightweight tires with higher resiliency. 

These, and several other factors, are leading tire makers to focus their efforts on increasing digitalisation in their production processes. This strategy offers the best solution to the challenges of the modern-day market – increasing product quality, as well as driving efficiency and increasing productivity, leading to much healthier profit and loss accounts.
 
At the forefront of this is the introduction of digital twin technology.

Breakthroughs in tire innovation are happening because of the use of digital twins – dynamic digital replicas of a tire and vehicle system across its lifecycle that use comprehensive data, analytics, simulations, and emulations.

Digital twins are used at the design stage of a tire, allowing the business to apply virtual validation and testing to a design before it is put into production. They can deliver uncommon innovations in faster times and at lower risk, compared to a costly physical prototype which is difficult to make. Market leaders utilising this technology have seen double-digit results across all areas of pre-production from concept to launch.

There are five interrelated types of models used in digital twins which effectively digitise the pre-production process. 
•    CAD – Geometric and polygonal models provide digital representations of a tire’s physical composition and geometry.
•    Physics – Digital models of a tire’s physical dynamics such as heat exchange, pressure, vibrations, and sound.
•    Automation – Models of production and automation processes, which are used to digitally emulate tire production processes so they can be studied and improved.
•    Extended reality – Digital representation of the human experience with tires and tire production including observation, maintenance, operations, and training procedures.
•    Analytics – Digital characterisation of the data, measurements, sensor readings and telematics of the tire, vehicle system and manufacturing assets used to produce the tire.

At every stage of the pre-production process, through concept and feasibility planning, to development, testing, and launch, digital twins are having a big impact on productivity and efficiency. 

In the concept phase, where companies assess the market opportunity for new tire concepts, digital twins accelerate the development of high-performance tires that could not be achieved via traditional physical experimentation. Using artificial intelligence (AI), real-world data on raw materials can be combined with advanced analytical data, allowing scientists to predict the properties of compounded rubber more accurately before use.

The technical approach to production for a new tire product is determined at the feasibility and planning stage. At a large tire manufacturer, digital twin emulation was used on various material compounds to find out which is the most ideal for a product. They were able to produce a special tire for hybrid vehicles that featured a 30 per cent drop in rolling resistance without compromising any safety-relevant properties.

Advanced analytical models and machine learning are utilised at the development phase to develop tires and verify their functionality and performance. At one manufacturer, optimising tire building with advanced machinery to increase productivity led to more than half a million more tires per year in production potential per plant.

Digital twins also enhance the testing process, an essential stage of pre-production which stabilises operational, service, and support processes. Streamlining the approach to designing, building and testing physical prototypes using a digital twin allows engineers to leverage complex simulations to reduce expenditures on pre-production building and testing by up to 25%.
The final phase of pre-production is the launch of the product to the market, where teams assess tire product performance to identify future improvements. AI can be implemented at this stage to monitor and learn from driver behaviour, tire pressure and performance. 

For example, one global tire leader was able to develop a connected tire sensor solution for a commercial fleet, which helped them achieve double-digit improvement on tire-related functional problems, including breakdowns and safety.

The overall results of digital twin and machine learning adoption speak for themselves, with a roughly 45% reduction in downtime, and thousands of additional tires produced per year. In component manufacturing too, it has allowed for a 30% increase in parts per hour, and a 60% reduction in non-certified workers at stations, increasing efficiency and reducing costs.

Whether you’re reallocating resources or shifting your tire operations to address these challenges, digital technologies should be central to your strategy.  Technology leaders who adopt this new approach to production stand a much better chance of overcoming the challenges this industry faces going forward.