Digital Twins — Delivering EBIT Improvements in months, not years

Sam Sur
4 min readDec 10, 2020

Start small, connect some, make those recommendations, drive some value, repeat. That’s the mantra.

Photo by Markus Spiske on Unsplash

Industrial downtime caused by equipment and process failure in just about every industry is still causing ever-increasing and a significant impact on manufacturing EBIT, production, and quality output.

Assets and equipment are not being replaced or maintained as they should be, which results in higher risks, larger costs, and adverse impact on balance sheets. Before the Covid crisis, it was recognized that many companies and asset operators are also not on top of how to optimize uptime and availability. As we emerge from this terrible Covid crisis, this trend of “sweating the asset” is significantly getting worse.

Asset & equipment intensive companies are always looking to reduce operating risk while improving efficiency and controlling cost.

Data has been critical to the success of many leading and well-known manufacturing brand supply chains, but the growing influence of the Industrial Internet of Things (IIoT) has brought the industry’s digital and physical worlds together like never before. Thanks to continuous ingestion, processing, and analysis of real-time data, it’s now possible to create a digital model of virtually any product or process, enabling manufacturers to detect issues sooner and predict outcomes more accurately.

Digital Twin is a digital model of the physical world generated from such data. A more textual definition of Digital Twin is a digital model of a physical asset, system, process, or place that enables monitoring and analysis throughout its lifecycle. The ability to keep the models constantly updated is what differentiates a digital twin from a static model.

While optimization concepts have been around for a long time in the manufacturing supply chain, the ability of twins to model assets more accurately by harnessing a combination of real-time data and learning from historical data radically changes the value proposition. As assets get complex, are deployed in multiple geographical locations and the workforce composition changes, the value proposition only gets stronger — towards faster, transparent, and quality decision making.

Even before an asset wears down its digital twin can provide recommendations on how and when to fix the problem and the most optimal time for the wider manufacturing process.

Digital Performance Twin:

Makoro™ is a Digital Performance Twin that continuously ingests, correlates, and analyzes asset data from enterprise, operations, and IoT sources and makes real-time recommendations on asset performance. The brain behind Makoro’s recommendations is Makoro Mind™ — the underlying AI and advanced analytics platform the delivers the foundational capabilities necessary for continuous performance and optimization of the twin. Interfacing with Mind™ is Makoro Edge™ and Makoro Bind™ — the two connectivity components that make the acquisition of real-time (or near real-time, depending on the use case) data possible from IIoT, enterprise, and operations sources in virtually any format.

Continuous Intelligence:

Devices capture data for a variety of parameters related to assets, process steps, and factory conditions. Data from these sensors are correlated and analyzed with information from systems such as manufacturing execution systems, inventory management systems, ERP systems, and CMMS systems. Continuous Intelligence in Makoro Mind™ finally transforms the results of the analysis into recommendations. Dynamic Learning in Makoro Mind™ provides the learning capabilities in Makoro™ which makes recommendations increasingly more relevant and accurate.

Recommendations:

The recommendation system in Makoro™ is what sets it apart from other twins. While twins deliver results in various forms of advanced visualizations — often as graphs and charts related to business KPIs, Makoro™ delivers advanced analytics as simple, natural language recommendations that the workforce understands and can act upon quickly. This drives frontline adoption of Makoro™ and lowers the barriers to adoption of digital twins by freeing businesses from having to augment their workforce with teams of data scientists and data analysts.

Transparency:

A digital thread of data flows continuously through Makoro™, starting with data from devices through processing, augmentation, and analysis all the way to recommendations and user interactions, leading to transparency through the decision-making process.

Lower Capital Investment:

With costs continuing to fall and deployment times shortening, companies are now able to start their digital twin journeys with lower capital investment and shorter time-to-value than ever before. The reward may be new business values that were previously inconceivable.

Best Practices:

The use of digital twins can unlock product quality improvements, efficient operations, lower maintenance costs, and higher workforce utilization. However, adopting a boil-the-ocean strategy — taking too fast and broad an approach, or taking a data-first approach (rather than an outcome-first approach) — guarantees getting lost in the complexity of data streams and model versions and losing sight of the business imperatives. The key is to start in one area, deliver value there, and continue to develop.

Published By

Originally published at https://www.linkedin.com.

--

--

Sam Sur
0 Followers

Data is not Enough. Builder. Explorer.