Ebook

# Digital Twins for Predictive Maintenance

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

### 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

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.

### 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.

### 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.

### 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.

Data-driven

Predictive Maintenance Toolbox

Data and physics combined

Kalman filter
System Identification Toolbox

Physics-based

Physical model