Digital Twins & Digital everything: bringing AI in our physical world

Can you build the digital twin of everything, every system, every living thing?

Many companies have realized or are realizing the potential of “Digital twins” to connect the physical and virtual worlds, with digital twins which constantly monitor and correlate both systems, allowing us to prevent critical issues, create new services, and investigate the future through simulations.

Already 75+ percent of global companies that use or are starting to use the Internet of Things (IoT) are also using digital twins, or plan to do so within the next 12 months (Source: Straits research). But it is not only in industry (with automotive leading the way) that Digital Twins are finding large applications: from energy to aerospace, from infrastructure to smart cities to retail, including social-health systems. Digital twins are powerful tools to optimize operations, predict performances, and gain a clearer view on any kind of physical/virtual entity.

A digital twin is designed to reflect with as much precision as possible the physical object of which it is a digital "twin". The object being studied, for example a wind turbine, a residential building, a factory, or a power grid, is equipped with various sensors relating to vital areas of functionality. These sensors produce data on various aspects of the physical object's performance, such as energy production, temperature, weather conditions, and more. These data are then transmitted to a processing system and applied to the digital copy.

Once informed with such data, the virtual model can be used to run simulations, study performance issues, and generate possible enhancements, all with the goal of generating valuable information-which can then be reapplied to the original physical object. Although simulations and Digital Twins both use digital models to replicate various processes in a system, a Digital twin is thus actually a "virtual environment", making it considerably richer and more widely used. The difference between the Digital Twin and a normal simulation is also a matter of scale: while a simulation typically studies a specific process, a Digital Twin can execute any number of useful simulations, studying multiple developments and scenarios at the same time.

The differences do not end there. For example, simulations do not usually take benefit from having real-time data. Digital twins, on the other hand, are designed around a two-way flow of information that first occurs when object sensors provide relevant data to the system processor and then happens again when insights created by the twinre shared with the original source object.

By having better and constantly updated data related to a wide range of areas, combined with the added computational power that accompanies a virtual environment, digital twins are then able to study more problems from far more advantageous vantage points than standard simulations can do, with greater ultimate potential for improving products and processes. It is effectively a matter of having a physical reality and a digital reality that are constantly in sync, aligning and sometimes influencing each other.

In the near future scenarios related to digital twins will become increasingly complex and evolved. The latter could, for example, be used to simulate the entire infrastructure of a city, including transportation systems, telecommunication networks, power grids, water networks, and public services. In addition, digital twins could be used to provide AI and process optimization solutions, to monitor system performance in real time, and to predict problems before they occur, not only as today on specific systems but at the macro-system level, or at any rate on complex, interconnected systems.

Managing digital twins is anyway not just a technical matter. Humanists, philosophers and ethicists are needed because people are always indispensable. While these simulation-based technologies disproportionately expand our possibilities and work life scenarios, what are the economic, social, and ethical consequences we should consider?

This short post is taken from an article I published this month on ?????? ?????????? ???????????????????? ????????????, on which you may find many more information on Digital Twins and their potential implications. Please refer to the original article for more insights, looking forward to any feedback, experience, perspective you may have.