gPROMS – Deploying deep process knowledge to generate sustainable value

Digital Process Twin technology for the entire process lifecycle

Process organisations need to make complex design and operating decisions daily. Siemens gPROMS models capture deep process knowledge in the form of high-fidelity predictive process models that can then be used to explore the process and product decision space rapidly and effectively, to provide essential information to support process design, product design and operating decisions. The result: accelerated innovation, optimized plant designs, optimized product formulations, high-performance plants and reduced emissions and energy costs.

Find out more

Contact our experts

Digital Process Twin

What is a Digital Process Twin and how does it create value?

gPROMS Digital Process Twins capture fundamental knowledge about a process – physics, chemistry, control philosophy, operating policy, feedstock and energy costs, product prices – in the form of mathematical models and their associated data. The model is then used in conjunction with state-of-the-art mathematical techniques to analyze and optimize the process design or operation – rapidly, accurately and effectively.

Optimizing a process or product design can lock in value over the lifetime of production – amounting to billions of dollars in some cases. Optimizing plant operation can generate new value on a daily basis.


Process lifecycle approach

Laboratory to operating plant: application across the process lifecycle

Siemens PSE pioneered the ‘process lifecycle’ approach now being adopted across the process industries. From early-stage R&D, through engineering design and commissioning to automation and plant operations, the same integrated modelling framework is used to capture corporate information and leverage knowledge across the organisation, maximizing consistency and efficiency while minimizing total cost of ownership.

DIGITAL R&D & DESIGN – creating value over the process lifetime

While much of the process industry still uses trial-and-error simulation for process design, the leading innovators are deploying state-of-the-art digital design techniques that allow systematic analysis and MINLP optimization. These use high-fidelity predictive models of process physics and chemistry, validated against experimental or pilot data where necessary, systematically to accelerate innovation and arrive at economically optimal process designs, based on quantified, managed technology risk. Siemens’ Construct-calibrate-analyze-optimize cycle provides an industry-leading digital design workflow and the tools to support it.


Use drag & drop flowsheeting to create models from the process industry’s most sophisticated and widest-ranging set of model libraries: pharmaceutical APIs, catalytic reaction, polymerization, adsorption electrochemical reactors and all the standard process operations, such as heat exchange and distillation. Or build your own model libraries using gPROMS’ industry-leading custom modelling capabilities.


Use established, state-of-the-art validation techniques to calibrate models against laboratory, pilot and operating data- using advanced parameter estimation techniques to ensure models are predictive over a wide range of conditions – allowing you to explore a wide decision space with confidence.


Analyze the system using steady-state and dynamic simulation, or deploy global system analysis to explore the process decision space rapidly and effectively by systematically assessing the effect of variations and uncertainty on key process indicators (KPIs). 


Determine the optimal values of multiple decision variables – including integer decisions – simultaneously, to arrive at a truly optimal process design that will lock in value over the lifetime of the plant.

Digital Applications for Operations

Using Digital Process Twins online to generate value every day

A key advance of the digital revolution for the process industries is the ability to bring deep process knowledge into process operations and control using high-fidelity digital process twins. A new generation of Digital Applications can generate value daily by combining real-time or historic plant data with the deep process knowledge contained within the process models. The wealth of new information generated is used to create additional daily value from the plant via equipment and process health monitoring, soft-sensing, real-time optimization and “what-if” operations decision support. Applications execute in athe robust, fail-safe applications platformgPROMS Digital Applications Platform within or connected to the plant automation system (PAS), exchanging data with the historian or distributed control system (DCS) directly.

Equipment and process health monitoring

Use the plant digital twin combined with real-time and historic run data to determine the values of key parameters subject to drift over the operation of the plant – for example, catalyst activation state in a catalytic reactor, or amount of coking in a furnace coil. This provides essential information for optimization of operations and maintenance planning, as well as early warnings of potential problems.

Real-time soft sensing

Use the plant digital twin combined with real-time plant data to provide reliable current values of KPIs such as yields, conversion/severity, coking rate, as well as equipment internal variables that cannot normally be measured. This provides valuable information for real-time monitoring of operation, or use in enhanced process control.

Real-time Optimization (RTO) 

Use the plant digital twin to determine set points for economically optimal operation taking account current plant state, feedstock availability, product demands and equipment and processing plant constraints. This makes it possible to maximize the economic performance of the plant from hour to hour, and react rapidly to disturbances and upsets.


“What-if” decision support

Use the up-to-date plant digital twin for what-if analysis of steady-state and dynamic operating scenarios. This allows operators to visualise and understand the consequences of their decisions


Run length prediction

Use the up-to-date plant digital twin to determine the expected end-of-run date under different operational scenarios. This can be used to improve maintenance scheduling, or to determine the most profitable operation mode for the remainder of the run.

Nonlinear MPC (NLMPC)

Use the up-to-date plant digital twin combined with plant data to soft-sense key product quality variables and apply nonlinear advanced process control (APC) using Siemens’ state-of-the-art nonlinear model-predictive control (NLMPC).

Key applications

Helping the process industries address their most pressing challenges

Product Portfolio

Next Generation Modelling Tools Across the Process Lifecycle

Siemens provides a set of advanced process modelling tools and environments that cover the entire digital process lifecycle, from R&D through Engineering Design to Operations and Manufacturing.

Modelling environments

Digital Applications

Online applications for monitoring, soft-sensing, optimizing and general operations support of process plants, based on high-fidelity process models.

Platform technologies

Siemens’ model-based technologies are built on a set of advanced software platforms that are under constant development. 

Use cases

From oil & gas to pharmaceuticals and food …

From optimization of daily oilfield production, through maximizing yield of ethylene in olefins plants, to production of pharmaceutical APIs or operation of spray dryers to produce milk powder … gPROMS Digital Process Twins are enhancing process performance and design at every stage.

Events & webinars

Siemens PSE hosts and partakes in many events every year.

You can also choose from a variety of online webinars to learn more about how gPROMS enables organisations to accelerate innovation, optimize plant designs, operate high-performance plants, and reduce emissions and energy costs. See the Events & Webinars page for our current events list.

Go to the Events & Webinars


Accelerate innovation, improve process efficiency and reduce emissions using model-based approaches

We can help you accelerate process development, optimize design, and enhance the efficiency of operating plant to reduce emissions and save energy using model-based technologies that deploy deep process knowledge.