Advanced Process Control and Analytics: new tools revolutionize data analysis, reduce modeling effort

Advanced controllers and analytic models used for monitoring, predictive analytics and closed-loop control optimize operations in real-time and make predictions and estimations even in absence of reliable measurements. The new technology has the potential to take software-as-service business model to an entirely new level.

When advanced modeling algorithms meet artificial intelligence and visualization at the device, edge and cloud

Share this page

Traditionally, APC relies on model predictive control and moving horizon estimation strategies that use either a linear or non-linear mathematical model of the industrial plant and smart algorithms to estimate unmeasured states and control process variables. APC helps industries attain operational and financial targets by increasing throughput and reducing energy use.

Typically, process industries and energy companies integrate APC in distributed control systems such as ABB Ability™ 800xA and ABB Ability™ Symphony Plus, which allows industry users to benefit from distributed resource allocation, redundancy, and communication as well as the intrinsic cybersecurity infrastructure of these modern DCSs.

As APC technology continues to evolve with new components and features, ABB scientists and engineers are exploring the potential of artificial intelligence (AI) with the use of reinforcement learning neural networks as well as edge and cloud technologies for digital analytics and optimization for operational services in the process and power industries.

ABB Ability™ Platform is the digitally enabling technology that can reside at the device, edge and cloud levels. Currently, it allows the implementation of APC solutions.
A recent innovation in digital solutions is the ABB Ability™ Advanced Process Control & Analytics (APCA) Suite, which offers analytics & optimization (A&O) services for monitoring, predictive analytics and closed-loop control

Examples of industrial applications powered by APCA

OPT800
Paper mill efficiency

Optimize pulp & paper process even when measurements are not adequate or available. The use of analytic models in conjunction with advanced controllers not only strengthens production and yield from 1 to 5% but also reduces Kappa value and residual alkali variation between 25 and 50% in digesters. Similar reductions in waste and improved variation of KPIs are achieved during other stages.
ABB Ability™ Expert Optimizer
Digital twin with APC in mining

Improved throughput – Ranged from 1% to 3%
Improved maximization of torque – Ranged from 1% to 7%
Improved disturbance rejection – Ranged from 0.5% to 3.5%
Improved response time and circuit stability – Reduced STD > 5%
ABB Ability™ Ventilation Optimizer
Underground mine ventilation

Maintain optimal airflow levels and provide rapid expulsion of blast gases while ensuring minimum power consumption. The newest APCA capability can identify complex multiple-input multiple-output (MIMO) systems using gain delay models. This technology has been crucial in the creation of smart ventilation solution that improves air quality and provides mines with energy savings up to 50% annually.
ABB Ability™ Marine Advisory System OCTOPUS
Vessel fuel consumption

Determine the optimal load for each generator and adjust it in real time. Predictive power plant optimization solution uses the predicted power demand of a ship during its entire voyage as input data. By taking advantage of ABB’s APCA technology, ship operators can reduce fuel costs and consumption by at least 4 %, and lower emissions; this reduces the carbon footprint and overall cost of operation.

More industrial APC applications

How it works: new powerful optimization and prediction tools

The ABB Ability APCA Suite comprises a set of tools that make the deployment of advanced controllers and analytic models a fully streamlined process:

  • APCA Model builder (offline),
  • APCA Diagnostics (offline),
  • APCA Configuration manager (online),
  • APCA Run-time engine (online) and
  • APCA Manager web service (online).

Security is one of the greatest challenges for industries reliant on data analytics and control and APCA Model builder provides a solution. Ability APCA issues certificates to authorized users to control the authenticity and integrity of the analytic models and advanced controllers developed in APCA Model builder. Thus, only models and controllers with valid certificates originating from authorized users will be digitally signed in APCA Model builder and can then be exported to the APCA Configuration manager.

Furthermore, with APCA Diagnostics, users can analyze the performance of deployed controllers by visualizing the controller actions history from log files. Estimated values of the process variables and the quality of predictions can be compared with the data received from the plant, thus allowing control engineers to easily troubleshoot abnormal situations.

A key feature of the online system is the ability to include industrial communication standards (eg, OPC) that allow users to connect to a plant, create or configure tags and map them to imported controller variables. Security is established with authentication and encryption techniques; usually the secure web socket communications (HTTPS), certificate-based security (SSL) and transport layer security (TLS) are used.

When control engineers face the need to infer data from missing measurements or infer backup data for unreliable measurements, analytic models can be deduced from either first principles or process data and deployed in the APCA Run-time system.

Analytic models that can be used in the APCA Model builder are:

  • graphical (first principles),
  • linear regressions,
  • nonlinear regression,
  • principal component analysis (PCA),
  • artificial neural networks (ANN) and
  • support vector machines (SVM).

Users can test various models and choose the one with either the best fit or performance statistic, thereby leveraging state-of-the-art advanced analytics.

The advantage of developing advanced controllers and analytics offline in APCA Model builder is that the client’s applications data can be readily leveraged by carrying out modeling and controller design tasks and analysis before deploying the solutions. Users can import large data sets and perform advanced data processing tasks like resampling, interpolation, and filtering in addition to open and closed-loop simulations.

The newly designed and updated ABB Ability Advanced Process Control and Analytics Suite revolutionizes data analysis and reduces modeling effort. The result is improved commissioning and online monitoring of advanced controllers.

The new technology has the potential to take software-as-service, as a business model, to an entirely new level making strategic predictions easy and collaborative operations optimal.


Learn more

Download original article
Model predictive control technology demystified
More process and production optimization strategies and software
  • Contact us

    Submit your inquiry and we will contact you

    Contact us
Select region / language