(130b) Enabling Alive and Aware Digital Twins in Process Industries

The digital ecosystems of chemical and process industries are expanding with the rapid pace of digitalization. Several models are being developed using various digital twin technologies (first-principal models, machine learning models, simulation models, etc.) and native development software. Many Industry 4.0 technologies employ soft sensors and/or digital twins under the hood, which in turn depend on the (simulation) models. These models (digital assets) are typically developed by the domain experts using various software but utilized by plant personnel with diverse backgrounds and levels of training. Understanding and utilizing such models is not straightforward and demands significant time and attention from the user. Due to this, these models exist in silos and are shelved when not in use, rendering them stale or dormant (i.e., out of tuning) for dynamic operations. However, it is a time and resource consuming task to tune such dormant models before re-deploying them for plant data analysis. Moreover, due to the specialized nature of these models, their accessibility is limited to the expert users, creating a long turn-around time for operations analyses. A very real concern in the minds of industry operators is how to make sure that their huge investment in sophisticated digitalization technologies does not go to waste due to changes that their process and/or operations may experience. It would be desirable to overcome or ameliorate at least one of the above-described problems, or at least to provide a useful alternative.

Aleph Digital Technologies is developing a low-code software platform for managing generation and updating of digital twins of physical assets. A new paradigm for sustaining the digital twins developed using different technologies, birthed by different native software, and deployed at different scales is presented. The proposed approach facilitates central hosting and evolution of various digital twins through continuous assessment, identification of performance issues, and smart decision making for model calibration, training, and versioning. With this, the digital twins are kept alive and aware, in turn maintaining their accuracy and reliability. We have been actively working with various chemical and pharmaceutical plants to facilitate their sustainable digital ecosystems. One such example is a chemical process plant (CPP) based in India, let us call them CPP due to confidentiality reasons. CPP has embarked on a digitalization journey and wanted to adopt a low-code digital twin solution to accelerate and streamline their troubleshooting activities. In this work, we present a case study for one key problem that our proposed platform solved for CPP.

CPP was experiencing a lower-than-expected throughput for one of their distillation columns. Their in-house team of engineers tried to do manual troubleshooting analysis for months that temporarily helped them to increase throughput slightly. Due to this persistent issue, they decided to adopt our low-code, automated digital twin management platform. We began by building a high-fidelity first principles process digital twin for their system, followed by calibrating it to operational data. Next, we used the process twin to analyze the factors that could be responsible for low throughput. With this, our ML-based optimization engine utilized the process twin to determine the optimal process variables that can help achieve the desired throughput without affecting the product quality at the least cost. Our optimization suggested that there is a need to control reflux flow rate by installing a reflux drum that would reduce the reboiler duty by 5-7%, thus reducing energy and cost. It also highlighted the need to preheat the feed to higher temperatures by installing a preheater so that the column can give 15-20% higher throughput as the reboiler reaches its heat transfer limits. It also enabled operators to determine the optimal operating conditions under different feed conditions. Additionally, our software platform enabled continuous monitoring of product quality through process twins, thereby reducing the need to do frequent lab analyses. Overall, the deployed software platform and digital twin enables both domain experts and non-domain personnel to perform simulations, assess the impact of various operational decisions on product quality, energy cost, and emissions.