Top posts:

Building Virtual Sensors using Machine Learning

Virtual Sensing logo

Virtual sensing techniques are helpful to provide economic and feasible alternatives to impractical or costly physical measurements.

We can implement a virtual sensor by creating a machine learning model. This model extracts information from other measurements and estimates the quantity of interest.

This approach promises cost savings because the company virtually performs physical, costly tasks.

Contents:

  1. Objectives.
  2. Benefits.
  3. Approach.
  4. Conclusions.

Objectives

Virtual sensing tries to model our target variable, so there is no need to measure it physically.

The challenge is to get the correct variables for our model to predict the quantity of interest.

Benefits

It allows obtaining measures by using a machine learning model, reducing costs and work hours, as these measures must usually be obtained in a laboratory.

REDUCE COSTS

SAVE TIME

Approach

Virtual sensing is to create an approximation model that takes in some input variables related to our target and estimates the latter.

Neural networks can model the correct values of the target variable so we don't need to take physical meassures.

That allows to save costs and time on meassure's obtention.

Conclusions

Virtual sensing makes companies save money and time since measure taking becomes a software issue, improving planning and decision making.

Neural Designer uses machine learning to build predictive models that represent a broad range of variables associated with virtual sensing.

Related posts: