Ebook

Chapter 4

Creating a Digital Twin: Modeling Methods

Now that you know what a digital twin is and why you would use one, consider what type of model you would create. The decision on what to model, and subsequently how to model it, rests on system knowledge and application need.

This section focuses on:

  • Modeling methods
  • How many models are needed
Gradient Arrow

Data-Driven Modeling

Data Driven Modeling

Physics-Based Modeling

Physics Based Modeling
section

Modeling Methods: Data-Driven

Let’s say you want to optimize maintenance schedules by estimating remaining useful life (RUL).

You use a data-driven model. Your knowledge on the type of the data from the pump will determine which model you’ll be using.

If you have complete histories from similar machines, then you can use similarity models. If you have data only from time of failure, then you can use survival models. If failure data is not available but you know of a safety threshold, you can use degradation models to estimate RUL.

RUL Estimator Models

RUL Estimator Models

Assume that you’re using a degradation model to create a digital twin to estimate the remaining useful life of the pump.

This degradation model is constantly updated using the data from the pump measured by different sensors such as pressure, flow, and vibration.

section

Modeling Methods: Physics-Based

Modeling Methods: Physics-Based

Now let’s say you want to simulate future scenarios and monitor how the fleet will behave under those scenarios. Then you can use a physics-based model.

An example would be a physical model like this one, which is created by connecting mechanical and hydraulic components. This model is fed with data from the pump, and its parameters are estimated and tuned with this incoming data to keep the model up to date.

Using this model, you can inject different types of faults and simulate the pump’s behavior under different fault conditions.

section

Modeling Methods: Data and Physics Combined - Kalman Filters

Similarly, a Kalman filter can be also used as a digital twin, which can model the degradation of the pump as a state and periodically update this state to represent the current condition of the pump.

Modeling Methods: Data and Physics Combined -  Kalman Filters
section

Review of Modeling Methods

These are some examples of the types of digital twin models you can create using MATLAB® and Simulink® products. Based on the intended use, the digital twin can also be a combination of these models.

Reviewing Modeling Methods

Data-driven

Degradation model
Predictive Maintenance Toolbox

Data and physics combined

Kalman filter
System Identification Toolbox

Physics-based

Physical model
Simulink and Simscape

section

How Many Digital Twin Models Do You Need to Create?

Now that you have an idea of how you can create a digital twin, you may be wondering how many digital twins you need to create for the fleet.

For every individual asset, you need to create a unique digital twin. This means that for each of the pumps at different well sites, you need to create a unique digital twin that has been initialized with the specific pump’s parameters.

The total number of unique twins you need will depend on your application. If you are modeling a system of systems, you may or may not need a twin for each system of components depending on your required level of precision.

Digital Twin Predictive Maintenance How many Models do you need?

Based on the intended use, a pump may have multiple digital twins.

For example, if you want to do failure prediction and fault classification, then you need to create different models that serve these different purposes.