Predicting Turbine Yield Energy using MindsDB

Want to Predict Turbine Yield Energy but don’t know enough Machine Learning Algorithms? Worry not, MindsDB has automated predictors which can make this job easy.

In this tutorial we will see how to predict the Turbine Yield Energy based on various other factors using predictor in MindsDB Cloud with gt_2015.csv data file which can be downloaded from here.

Step 1: Uploading Data to MindsDB

Make sure you have a MindsDB account. Get it from here .

Uploading File

Now, Click on the Upload Data tab and Go to Files and Click Upload and upload the .csv file from your PC.

Step 2: Viewing the table and Visualising the Data

I have saved the data table as energy. So, to view the Table, use the following syntax. Replace the number in LIMIT with required number of rows to be displayed.

SHOW TABLES FROM files;
SELECT * FROM files.energy LIMIT 10;

Energy Table

The explanations of sensor measurements and their brief statistics are given below.

Variable (Abbr.) Unit Min Max Mean
Ambient temperature (AT) C –6.23 37.10 17.71
Ambient pressure (AP) mbar 985.85 1036.56 1013.07
Ambient humidity (AH) (%) 24.08 100.20 77.87
Air filter difference pressure (AFDP) mbar 2.09 7.61 3.93
Gas turbine exhaust pressure (GTEP) mbar 17.70 40.72 25.56
Turbine inlet temperature (TIT) C 1000.85 1100.89 1081.43
Turbine after temperature (TAT) C 511.04 550.61 546.16
Compressor discharge pressure (CDP) mbar 9.85 15.16 12.06
Turbine energy yield (TEY) MWH 100.02 179.50 133.51
Carbon monoxide (CO) mg/m3 0.00 44.10 2.37
Nitrogen oxides (NOx) mg/m3 25.90 119.91 65.29

Click the Data Insights tab to view Detailed Data analysis of the table.

Data Insights

AFDP being Analysed

Step 3: Train the model

This is where MindsDB makes life easy. With the Automatic Predictor, we can easily Train the model and get best results which would require lot of work to do with traditional ML based approach.

CREATE PREDICTOR mindsdb.energy_predictor
FROM files
(SELECT * FROM energy)
PREDICT TEY;

We can give any name to our predictor after mindsdb[dot]. Enter the column that you want to predict after PREDICT. In this case it is TEY(Turbine Energy Yield).

Run this and wait for the model to train. And Viola, the ML model is built!

You can see the status of the training of model using this:

SELECT status FROM mindsdb.predictors WHERE name='energy_predictor';

Step 4: Getting Predictions for this Regression model

SELECT TEY,TEY_Confidence,TEY_Explain FROM
mindsdb.energy_predictor
WHERE AT=1.567
AND AH=69.876
AND TIT=1234.67;

This is the syntax for Predictions. The TEY_Confidence determines the confidence with which the prediction is made. The more data we give, the more confident the prediction becomes. The TEY_Explain explains the various confidences, bounds etc.

Prediction of TEY

Thus using MindsDb, even a layman can make predictions easily. Hence it is a powerful tool.

For more information:

https://docs.mindsdb.com/sql/tutorials/