====Virtual Sensor Modelling====

===Our Goal===

We'd like to create a **Virtual Sensor** for a measurement we're currently taking by hand.

===Plan===

To do this, we will need a few steps.

----

1) Record the manual measurements, along with the precise time they were taken, \\
2) For each of those times, look up the machine state \\

===Step 1a: Get Data===

Collect your data and record it in a spreadsheet.

When you've collected a number of samples in various conditions, you can then export that information as a CSV file. 

Ensure that your CSV file has a header row and one column is called either 'Time' or 'Date'.

<code javascript>
Time, Vibration
2025-02-01 10:00:00, 21.4
2025-02-03 02:34:33, 0.5</code>

===Step 1b: Add an Upload Layer===

To accept this CSV file for use in Capture, we add a [[get_upload|get_upload]] layer.

<code javascript>
{
	"type": "get_upload",
        "columns": ["Vibration"]
}
</code>

===Step 2a: Capture the Machine State===

Next, we get all of the context information we can about our machine.

<code javascript>
{
	"type": "get_query",
	"query": "'Machine' ASSET AIPOINTS",
        "samples": 30,
	"comment": "Get Activity Details"
}
</code>

===Step 2b: Capture the Middle Value===

Finally, we'll get the 'middle' value out of the samples we picked up.

<code javascript>
{
	"type": "flatten",
	"method": "middle",
        "comment": "Getting Sample Data"
}
</code>

===Results===

If you have a reasonable amount of context data, you'll have a huge amount of insight available to build an AI around your vibration.

Not only will this include the current state of your **machine** (ie. speed, current, voltage etc.), but also information about the entire production line, ambient conditions etc.