Enabling high performing production sites with digital asset engineering
Unplanned downtime and emergency maintenance can damage a company’s efforts to operate efficiently. Indeed, 90% of 232 companies surveyed, ranked these as the most significant problems they face. How can these issues be solved?
Digital asset engineering can offer a solution to these challenges. Designing and developing high-performance production sites where the assets and the supply chain are inextricably linked using digital technologies, creates multiple benefits. At a corporate level, a digital asset engineering approach can optimise large CAPEX (capital expenditure) investments using a parametric design approach. At a plant level, maintenance investments - small CAPEX and OPEX (operational expenditure) - are controlled using internet-of-things (IoT), artificial intelligence (AI) and digital twin.
What is digital asset engineering?
Digital asset engineering exploits emerging digital technologies to link the business rationale to big or small data collected. On the one hand, accurate data captured using IoT helps to build real-time models and develop algorithms to adapt maintenance schemes. On the other hand, dynamic digital twins of real world business processes can be developed to enhance maintenance and design solutions further.
Digital asset engineering works through the use of three core technologies: parametric design; artificial intelligence (AI); and digital twin. These three core technologies work interdependently for optimum results.
Parametric design employs relational building information models (BIM) to manipulate the design of processes and structures. Parametric design is a perfect way to quickly generate optimal designs that can be easily scaled up. It takes various constraints into consideration and generates the optimal design to minimise unexpected problems such as insufficient storage space for a warehouse in a given period or sub-optimal project spend considering the forecasted industrial activities. A parametric design approach allows you to measure all aspects of a project, instantly modify the data and reconfigure elements of a space, building, or any structure. Last-minute changes no longer require weeks of redesign. Instead the model is updated and the design is modified with new parameters immediately. Think of a data center design. By developing an application that captures specific knowledge of the data center building system and expert engineers in a parametric model, the data center provider can discuss with their clients the required specifications and instantly create multiple configurations that can be evaluated on cost, power and cooling requirements, and suitability for the proposed site. The resulting configuration can be used as input for the further detailed design, shortening the time-to-market and lowering the design cost for this stage. Since the repetitive parts of the design work are automated, engineers can focus on the areas where their expertise can make a real difference.
Using AI, meanwhile, large amounts of data collected from various projects can be gathered and processed by IoT - enabled infrastructure to help extend the lifetime of an asset, improve its reliability, performance and safety. Real-time condition monitoring, for example, can help determine correlations among the design, use of assets, and their conditions. This data can be exploited to improve the design of similar assets by feeding the parametric models with constraints, calibrated by the correlations obtained from similar existing assets.
Finally, a digital twin is a virtual representation of both physical assets and their behaviours, and is generated using data collected through sensors, cameras, predicted simulation results and additional data sources such as from enterprise resource planning (ERP) systems. When presented to plant managers (CEO, COO) and engineers, the digital twin can provide them with valuable insights for the whole lifecycle of assets that are not widely available using traditional design practices. This in turn can help in digital asset engineering processes by improving the algorithms applied in the parametric approach. Digital twin provides a continuous improvement loop for design, build and use of assets.
Main barriers for implementation
Despite the many advantages of digital asset engineering, it can be difficult for an organisation to know where to start implementing it. They need to begin with simple business cases and build from there. The time-series data collected by IoT devices and other unstructured data sources need to be parsed and interpreted for relevant insights, which can then be fed-back into design solutions. This way of working requires a good understanding of the possibilities and constraints of both worlds: engineering and data science.
The whole digital asset engineering system needs to be built from the ground up with numerous advanced technologies.
An expert in digital asset engineering
As an expert in digital asset engineering, Royal HaskoningDHV can help you with this fast-moving technology by implementing techniques such as parametric design and digital twins to monitor and evaluate different options for your physical assets cost-effectively. Our digital asset engineering service is highly customised, technology agnostic and enables the data-based design of future-proof, high-performance production sites that are classified as benchmark performers.
The key takeaways:
1. Designing high performance production sites where assets and supply chain are inextricably linked using digital technology creates stable, flexible and efficient operations.
2. An open mindset is required to fully exploit emerging digital technologies.
3. The three core technologies: parametric design, AI and digital twin are mutually dependent and can all be applied for maximum benefit.
4. Digital asset engineering process is a fundamental design and maintenance transformation for the industry.