0 of 0 for ""

AI in construction: why digital design will be essential to reducing waste and emissions

Sweco authors: Chris Neeves & Ricardo Farinha

Design decisions can have an enormous impact on the environmental performance of a building. Optimising projects’ lifetime environmental performance is hugely complex, and artificial intelligence could hold the key to unlock significant gains, as Ricardo Farinha, Director of Technology at Sweco and Chris Neeves, Buildings Performance Operations Manager explain.

BIM Services Consultants

As governments around the world increase their focus on reducing energy consumption, greenhouse gas emissions and waste, the construction industry is high on the hit-list for reforms.

Estimated to consume 40 per cent of the world’s energy, and produce between 25 and 40 per cent of all carbon emissions, it is a major generator of waste. So, if the construction industry can make a sizeable improvement in its performance in these areas, that would translate into large overall global gains.

But, to achieve these gains, evolution of design and construction practices will be required at a fundamental level.

A needle in a haystack

The list of constraints that any building must comply with is long and complex. In very broad strokes, it includes the physical geometry and conditions of the site, the client’s finances and business objectives, any planning and regulatory restrictions and the needs of the intended occupants – along with a host of less tangible considerations like aesthetics and marketing aims.

Finding workable solutions is the job of architects, engineers and specialist advisors. However, the complexity of the problem that building design presents means there are inevitably multiple potential solutions, all of which offer a different set of benefits and disadvantages. The design process involves making a huge number of significant decisions, all of which can have a profound impact on a project’s success and viability.

Working in the traditional way, exploring and understanding the outcomes of decisions at any given stage in the process is enormously time consuming, if not impossible. Often, decisions are based on intuition and the experience of the individual designer, with any alterations having to be processed manually before their impact can be fully understood.

This is why artificial intelligence can make a big difference, by modelling the potential outcomes and allowing a designer to understand the ramifications of any given decision in minutes, rather than days or weeks.

Additionally, whenever changes need to be made to a design that has already been detailed, they can often have knock-on effects for the whole project. AI systems can allow a designer to quickly check the feasibility of the changes and implement them, where traditional ways of working may have required the work to be started from scratch.

Using AI-supported tools also allows for greater standardisation of engineering approaches. Instead of the current situation where asking 10 different engineers the same question would deliver 10 different answers, with agreed models, repeatable solutions would begin to emerge. At this point, collaborative working brings even greater efficiencies, with all partners able to work and update from the same central source knowing that version control and accuracy is no longer an issue.

Smarter modelling

To give just one seemingly simple example, the positioning of windows can have a significant impact on energy performance. Designers will know that by placing more and larger windows in north-facing parts of the building that don’t receive direct sunlight, and by building in solutions to limit direct sunlight entering south-facing windows, the cost of controlling the climate in a building throughout its lifespan – and the associated energy consumption – can be significantly reduced.

However, doing this requires designers to use the building’s orientation and surroundings to inform the placement of windows differently for each building they design – a complex and time-consuming task. Where budgets are tight, this isn’t always possible with traditional ways of working, and poorly adapted standardised approaches that don’t respond to the site are common.

Using parametric design-assisted modelling techniques, better optimised solutions can be found much more quickly. Combining these parametric methodologies with AI technology would then allow us to ‘learn’ continuously, with these AI pulling data from previous projects to inform decision making in real time, meaning that building designs could naturally come to respond instantly to specific site conditions using past learnings and insights.

Towards data-driven design

The possible applications of this approach are endless and include every aspect of the way a building works, from the structural elements that support it to heating, ventilation and energy management systems.

Ultimately, data-driven workflows could well become the key tool in helping engineers to make practical decisions based purely on facts, rather than relying solely on intuition, while enabling them to push the boundaries of design with the means to instantly test new ideas and approaches.

The technology that will enable this is still in its infancy, but it is developing quickly. Placing parametric design and AI tools in the hands of designers and engineers will dramatically increase their ability to truly optimise buildings, potentially revolutionising building design as well as delivering major cost and energy savings. This innovation will play a key role in helping the industry plan and design the sustainable cities and communities of the future.

The global construction sector is under more pressure than ever to improve its environmental performance, and AI-based design automation could be a major part of the solution.

Parametric design modelling is already helping to deliver the designs that will drive down carbon emissions from the built environment – something that is critical if governments are to hit their climate change targets, and which can only be achieved through fundamental changes at the design stage.

The engineer of the future

With the fundamental changes to the way buildings and infrastructure are designed, the transition for designers to learn new skills to imagine and engineer the future is considerable. Whilst the fundamental laws of physics, mathematics and design does not change, the journey to the new end point is very different now to what it was only a few years ago, and will be in the near future.

Whilst the inevitable outcome of this change is that some roles may cease to exist in their current form, requiring upskilling of people and changes to roles, and a  seismic shift in the tools, processes and output. This means that successful leaders in design and innovation will need to employ new roles such as software engineers, data analysists, application developers and IT professional alongside and embedded within the architecture, engineering and construction teams. The current trend for open architecture and data transparency allows forward thinking organizations to develop there own tools, applications and digital processes for maximum advantage to the project.

With the right skills we can leverage AI in the design process and deploy new tools and applications to solve problems and provide solutions, but this can only be achieved by investing in those roles which historically have not been attracted to Architecture, Engineering and construction sectors. At SWECO we have a strong team of developers and innovators to lead in these exciting developments within our industry.