The Digital Twin: Are You Prepared?

Posted on September 7th, 2021
Posted in Uncategorized   

Digital twins have been garnering a lot of attention lately, but talk to ten people and you’ll probably get ten different answers as to what a digital twin is, so let’s start with some basics. What is a digital twin?

A digital twin is a virtual representation of an object or system that spans its lifecycle, is updated from real-time data, and uses
simulation, machine learning and reasoning to help decision making.

The digital twin marketplace is poised to explode in growth, with a projected market size of $16.4B by 2024. Early movers who have taken advantage of this technology are healthcare and pharma industries, manufacturing asset excellence, and commercial building optimization. In the oil and gas and petrochemical industries the use has been primarily limited to plant turnarounds and large scale engineering projects. Specifically, the upstream oil and gas community has been slow to adopt, with understandable technical hurdles, namely desperate and aging OT systems, poor communication infrastructure, and lack of scalable products on the marketplace. That paradigm is shifting. Industrial IoT devices are dramatically decreasing in cost, and it is now easier than ever to acquire high frequency data, and either run advanced computations at the edge (i.e. onsite with field deployed hardware) or in a cloud instance.

When it comes to digital twins, the natural place to start is with Advanced Fault Detection. SCADA systems are great at alerting operators when telemetry readings fall above or below a threshold. They can even handle more advanced computations such as rates of change or duration, but there is nothing to guarantee that the previously established alerts are “correct” or “accurate” for the current state of the system. As wells mature, fields develop and infrastructure changes so does the operating envelope of the equipment. This is where digital twins come into play. By creating a digital copy of the system using physics and statistical based equations, the digital twin is able to constantly compare real world values with that of the model. This produces a continually updating system that can alert operators when the system is not operating efficiently.

The next logical step is to look into the future and predict the Remaining Useful Life of a piece of equipment or system. By labeling and identifying previous failures, a digital twin is able to detect how current conditions affect the remaining life of equipment. Finally, the “holy grail” of digital twinning is Supervisory Process Control. Essentially, this is an advanced operating layer above the traditional SCADA system focused on optimizing pad or full field operations in a closed loop control system.

All of this sounds great, but how do you actually implement a digital twin, and “train” this software? This requires two key elements to seamlessly come together. First, is a powerful piece of software that can ingest OT data, and contains a development environment where all the necessary code can be developed, tested, deployed, and maintained. Second, are subject matter experts that can identify key problems, label data sets and develop interfaces that allow other subject matter experts to interact with the software and continue training it. This is where a strong implementation partner, such as Halker Smart Solutions, that can leverage both years of process and mechanical knowledge, and industrial automation, can offer an advanced level of insight and control to upstream oil and gas operators.