Generally Digital Twin is a virtual presentation of some physical asset. The same one may be represented by a number of DTs serving different purposes. Purpose defines the DT life cycle. For example, a mechanical 3D model is used before the plant construction, but the plant operation does not need it.

What makes DT meaningful? The ability to predict the outcome that cannot be obtained by other means, future or present. This requirement drives the DT development. Can you identify it in the following description?

"By utilizing the digital twin (an exact digital copy of the Al-Khobar 1 seawater reverse osmosis plant [SWRO]), a team of specialists in Madrid was able to start the tests and start the plant up remotely, reducing the number of personnel on site to a minimum."

The plant remote data acquisition system is not DT unless it is equipped with algorithms predicting the remaining useful life (RUL) of the asset, or the equipment's abnormal conditions, or its failure times. These tasks are the essence of plant maintenance.

DT development is part of the business digitization. It makes or breaks DT. Both are endless in time, going deep into engineering fundamentals. Both require new know-how. It cannot be discovered by assembling DT from disparate IT tools available on the market (like BIM, or SCADA, or Siemens SIMIT).

New business paradigm

The smart customer questions are the same whether she buys a family car or a multi-million dollar desalination plant.

1. What maintenance shall be done and how often?
2. How is it reliable?
3. How economical is it?

The DT in question shows in real time (accelerated or not)

1. the plant equipment state and performance parameters
2. the plant maintenance tasks (like intake pigging, CIP cleaning, etc.)
3. the equipment preventive maintenance tasks and tests to be executed
4. the equipment failures
5. total power consumption, production, and energy cost

This DT is not built solely for a customer; it is a vehicle for the next-generation desalination mega-plants as it removes the following challenges plagued the plant design evolution.

Plant systems mismatch due to over- or under-design. The capacity variation between systems is mostly within 20%. It is a substantial reserve for decreasing the production costs as both capex and opex are subject to optimization..

Plant annual production prediction. Its rigid procedure is computationally intensive as it requires an hourly tracking of local conditions’ variation over the time of the year. Trying to implement it manually adds substantial risk to the PPP projects of missing the contract product price.

Plant control algorithms validation and tuning. Today, it is executed during the plant operation. As this practice is inherently not safe, it negatively affects the plant operation and economics.

Plant alarms rationalization. It deals with the alarm settings re-validation and fine-tuning, and alarms prioritization and suppression. It is needed to stabilize the plant operation and make it safe. This process takes 2-3 years to accomplish, and a lot of trial and error.

Plant maintenance costs prediction. Maintenance cost is the biggest after the energy cost and capital cost. Despite its criticality for the PPP project's success, its rigorous prediction is beyond the engineering companies' expertise and computational capabilities.

Plant operator training. Today, operators are trained on a live plant, which is not acceptable at all. Equipment damage as a result of the operator's wrong action is not rare.

AI model training. The AI progress in desalination hinges on the availability of contextualized structured data covering all aspects of the plant design and operation. Building a perfect data source is a task beyond engineering companies' expertise. Under the circumstances, a digital twin may be successfully used to engineer, train, and tune AI models.