Top
Logo Dr. Rafał Noga · Virtual-Sensor

Virtual sensors that know your process

Virtual sensors — also called soft-sensors — combine system knowledge with available measurements to deliver reliable estimates of variables that are expensive, inaccessible, or impossible to measure directly.

What Are Virtual Sensors?

A virtual sensor — also called a soft-sensor — uses a mathematical model of the process together with existing measurement data to compute an estimate of a variable of interest. Unlike a physical instrument, a virtual sensor or soft-sensor requires no additional hardware: it runs as software on existing control systems, exploiting the instrumentation already in place.

Virtual sensor architecture: system knowledge + measurements → estimation algorithm → virtual sensor output
Virtual sensor / soft-sensor architecture — adding system knowledge to available measurements.

Industry Problems Solved

Measurement is too expensive

Problem

Analytical instruments for quality, viscosity or composition cost €50k–€500k and are shared across streams — giving only periodic samples, not continuous data.

Solution

A virtual sensor delivers continuous estimates between analyzer samples, enabling tighter real-time control.

Instrumentation cannot be installed

Problem

Flow meters at valve locations, heat loads in cryogenic circuits, or torque in sealed drives cannot be instrumented due to cost, space, or harsh conditions.

Solution

A virtual sensor computes the variable from correlated upstream/downstream measurements already present in the system.

No direct measurement exists

Problem

Variables such as polymer melt index, cell concentration, or catalyst activity have no real-time in-line sensor technology.

Solution

A virtual sensor infers these variables from measurable proxies — temperature, pressure, flow, spectroscopy — using first-principles or data-driven models.

Sensor failure and redundancy

Problem

Critical measurements fail during startup, upset, or fouling. A single point of failure in a safety-critical loop cannot be tolerated.

Solution

A virtual sensor merges redundant measurements from multiple instruments to provide a fault-tolerant estimate that remains valid when individual sensors fail.

Measurement accuracy

Problem

Two instruments measuring the same variable may have complementary accuracy profiles — one fast but noisy, one slow but precise.

Solution

A virtual sensor fuses both signals using optimal estimation theory to produce an estimate that is simultaneously fast, precise, and drift-free.

Technology

Measurements

The exact sensor requirements are determined case by case. In most cases, existing instrumentation is sufficient — no new hardware is needed.

Models

Models encode the system knowledge exploited by the virtual sensor. Complexity ranges from simple empirical correlations to full thermo-hydraulic or kinetic dynamic models. We specialise in first-principles modelling for process industry and aeronautical applications.

Estimation Algorithms

From linear observers (Luenberger, Kalman Filter) to nonlinear algorithms (Extended Kalman Filter, Unscented Kalman Filter, Moving Horizon Estimation). The choice depends on the degree of nonlinearity, available compute, and required accuracy.

Measured Results

Virtual Sensor / Soft Sensor vs Physical Instrument

A direct comparison for procurement and feasibility decisions.

AspectPhysical InstrumentVirtual Sensor / Soft Sensor
Upfront cost€50k–€500k per instrumentSoftware only — runs on existing DCS/PLC
InstallationWeeks to months (civil works, cabling)Days to weeks (model integration)
MaintenanceCalibration shutdowns, fouling, replacementModel update — no process downtime
CoverageOne physical location per deviceAny variable reachable by the model
Data ratePeriodic (analyzer: 1–2 h) or single pointContinuous, synchronous with control cycle
Failure modeHard failure — loop goes openGraceful degradation — model-only fallback

Products

Advanced Virtual Flow Meter

Software-based flow calculation at valve locations using valve position, pressure and temperature measurements — no physical flow meter required.

Learn more

Digital Variometer SSDV12

High-precision climb/descent rate sensor for paraglider pilots using virtual sensor data fusion of pressure, inertial and GPS measurements.

Learn more

References

Selected Publications

Peer-reviewed research on virtual sensor and soft-sensor methods applied in industrial and scientific projects.

Full publication list on noga.es →

Frequently Asked Questions

What is a virtual sensor?

A virtual sensor (also called a soft-sensor) computes estimates of hard-to-measure process variables using a mathematical model and existing instrumentation. No new hardware is required.

Is a virtual sensor as reliable as a physical instrument?

For well-modeled processes with good instrumentation, a virtual sensor can match or exceed analyzer accuracy — and provides continuous data rather than periodic samples. The CERN LHC application estimated 5 thermodynamic states in real time from 3 pressure sensors.

What hardware do I need?

No additional hardware. Virtual sensors run as software on your existing DCS, PLC, or edge computer, using signals already available in your control system.

How long does implementation take?

Typically 4–12 weeks from project start to commissioning, depending on model complexity and data availability. A 30-minute feasibility call is enough to scope the work.

Stay informed

Occasional updates on virtual sensor methods, products, and case studies. No spam.

Discuss Your Measurement Challenge

Every virtual sensor project starts with understanding your process, instrumentation, and what you need to measure. A 30-minute call is enough to assess feasibility.

📅 Book a 30-min call Contact MPC closes the loop on virtual sensor estimates →

About

Virtual-Sensor is a specialised engineering practice led by Dr. Rafał Noga — APC/MPC consultant with experience in virtual sensor and soft-sensor development for process industry, cryogenics, and aeronautics since 2007.

→ Main site: noga.es