Machine Learning applied to manufacturing processing

Name: Machine Learning applied to manufacturing processing
Rating: 3.9 (84 reviews)

Learn to develop a machine learning project to real world problems in manufacturing processes

Created byLeo Bravo

Last updated 3/2020

English

English [Auto],

What you'll learn

How to apply machine learning techniques to real world problems in the area of manufacturing
Learn to implement useful and popular machine learning algorithms
Learn what manufacturing processing is
Learn about supervised and unsupervised machine learning approaches
Learn to train a machine learning model
Learn how to apply machine learning to a power plant
Learn how a real data analysis project is developed
Learn how to work with data files and load for data analysis
Learn how to use free python libraries for machine learning
Learn how to use jupyter notebook as a tool to develop a machine learning project
Get valuable insights from data analysis and build a report

Course content

6 sections • 17 lectures • 1h 58m total length

Introduction to Unit operations4:48
If you want to get the course's slides file in PDF (for free) to support your learning process, you can subscribe here and I will send you the material:
https://forms.gle/ZeNuNPBTxbqXX3VXA
Control and monitoring systems of processes4:47
Explore how machine learning applied to manufacturing processing enables automated control and monitoring systems that manage unit operations, valves, pipelines, and sensors using plant data.
Production measurements in production plants1:31

Introduction to Machine Learning4:34
Basic supervised learning algorithms (linear regression)14:31
Basic unsupervised learning algorithms3:50
Learn basic unsupervised learning algorithms like clustering and dimensionality reduction, enabling grouping of data and lowering dimensionality for manufacturing processing.
PCA for dimensionality reduction3:39
Learn how principal component analysis reduces high-dimensional manufacturing data by transforming multiple sensors into a few essential principal components, preserving core information while removing redundancy.
Workflow to train a model1:55

Defining objective of data analysis1:09
Loading the dataset5:37
The data set link:

https://archive.ics.uci.edu/ml/datasets/Combined+Cycle+Power+Plant

If you do not have "Jupyter notebook", you can download "Conda" (it's a software that contains all the required libraries in the course (included Jupyter notebook)):

https://docs.conda.io/projects/conda/en/latest/user-guide/install/

If you do not want to use it, you are going to need a text editor. I recommend you:

- Sublime ( https://www.sublimetext.com/ )
- Visual Studio ( https://visualstudio.microsoft.com/ )

And then install all the libraries we are going to use. So you should install:

- python
- numpy
- pandas
- matplotlib
- sklearn

All these resources are for free!
Analyze data distributions and correlations6:15

Univariate Linear regression to predict production23:18
Learn to build a univariate linear regression to predict production from temperature, including data preparation and plotting. Train the model with scikit-learn, evaluate with r-squared, and predict future output.
Multivariate Linear regression to predict production13:06
Dimensionality Reduction (to more than 1 Dimension) using PCA and then, apply a15:05

Requirements

Basic knowledge of Python is required in order to understand the analysis (but I explained you all the code we are developing)
No previous knowledge in Machine Learning is required
No previous knowledge in manufacturing is required

Description

In this course, you are going to learn how to develop a machine learning project to solve real-world problems that you can find in the manufacturing area.

You will learn the more practical and useful algorithms that can help you to do predictions and work with big data.

If you are not familiar with machine learning and manufacturing, don't worry, because, in this course, you will learn the necessary to understand these manufacturing areas and machine learning thinking, so easily you will apply these techniques to this field.

And as we know, the best way to learn is making, so we will develop a project using python, in which we are going to analyze a real production power plant and we are going to develop different machine learning in order to predict the production of electricity based on various variables.

So, get started in machine learning with this amazing course and start to learn a bit about how machine learning can improve the manufacturing world.

Who this course is for:

Anyone who wants to learn about Machine Learning and its applications to manufacturing area
Anyone who wants to learn how to build a real world machine learning project

Machine Learning applied to manufacturing processing

What you'll learn

Explore related topics

Course content

Introduction to Manufacturing processes3 lectures • 11min

Introduction to Machine Learning5 lectures • 28min

Explanation of the study case2 lectures • 11min

Data exploration of the study case3 lectures • 13min

Machine learning models applied to study case3 lectures • 51min

Building a report with the insights of data analysis1 lecture • 4min

Requirements

Description

Who this course is for: