Transforming Data into Information

Loading...

来自 University at Buffalo 的课程

Intelligent Machining

92 个评分

University at Buffalo

Intelligent Machining

92 个评分

课程 5（共 9 门，Specialization Digital Manufacturing & Design Technology ）

Manufacturers are increasingly utilizing machine tools that are self-aware – they perceive their own states and the state of the surrounding environment – and are able to make decisions related to machine activity processes. This is called intelligent machining, and through this course students will receive a primer on its background, tools and related terminology. Learn how the integration of smart sensors and controls are helping to improve productivity. You’ll be exposed to various sensors and sensing techniques, process control strategies, and open architecture systems that can be leveraged to enable intelligent machining. This course will prepare you to contribute to the implementation of intelligent machining projects. Main concepts of this course will be delivered through lectures, readings, discussions and various videos. This is the fifth course in the Digital Manufacturing & Design Technology specialization that explores the many facets of manufacturing’s “Fourth Revolution,” aka Industry 4.0, and features a culminating project involving creation of a roadmap to achieve a self-established DMD-related professional goal. To learn more about the Digital Manufacturing and Design Technology specialization, please watch the overview video by copying and pasting the following link into your web browser: https://youtu.be/wETK1O9c-CA

从本节课中

Sensors and Sensing Techniques

The purpose of this module is to introduce spectrum of sensors used to implement intelligent machining. The module will also discuss the basics of signal processing and analysis techniques that has brought intelligent machining paradigm closer to industrial realization. Following issues pertaining to sensors and sensing techniques will be elaborated up: (1) Which sensors are to be used in each application? (2) How to acquire and process sensor signals?

Transforming Data into Information4:49

与讲师见面

Rahul Rai
Associate Professor
Mechanical and Aerospace Engineering

[MUSIC]

Welcome to lesson three.

This lesson is a preface to the following lesson on machine learning and

artificial intelligence in sensing.

In this current lesson, we will be introduced to factors driving the need for

machine learning to transform large sets of data into information that

can be used to make smarter decisions.

In this lesson, we will learn the meaning of terms, features,

and how features can help convert raw data into prediction using machine learning.

Using a few day-to-day examples, students will learn how all our lives are being

touched by fusing of several exciting and emerging fields of technologies.

Such as machine learning, artificial intelligence and big data.

Let's consider the question why machine learning.

As we discussed in the previous module, that is module one, we need

three main components to enable intelligent manufacturing framework.

First, sensors to collect data.

Second, a data acquisition and management system to process and store data.

And third, machine learning and

knowledge discovery component to process the stored data.

We spoke about components number one and component number two,

which is sensor collecting data and signal processing, in the previous lessons.

Now, let's discuss how the output of signal processing can be used

by the machine learning and knowledge discovery component to make decisions.

In this context, we will introduce the concept of machine learning.

To understand the concept of machine learning, let's consider an example.

You may have used Netflix to watch your favorite movie.

You log in, search for a movie title, then select a movie,

and you watch it halfway or in full.

Then you sign out and go about your daily life.

Once you log back, again,

into Netflix system, have you noticed that the system gives you a list of recommended

movies in a similar genre to the one you have watched previously?

How does that occur?

The system uses data from our previous system users and

learns about our likes and dislikes,

and makes prediction based on our past users of Netflix.

This is an example of machine learning working in our daily lives.

In the Netflix example, some features used to make predictions

are the age of the user, genre of the movie and movie actors.

Features are salient way to abstract and

represent data that are useful to make predictions.

There are several other examples of machine learning in action in

our daily lives.

For example, social networking profile recommendation features of LinkedIn and

Facebook uses machine learning.

The online shopping recommendations in Amazon and

Ebay are enabled by machine learning.

The machine learning is also pivotal in implementation of automated

office assistants such as Apple's Siri and Microsoft Cortana.

In general terms,

we can explain the conceptual working model of machine learning, as follows.

Machine learning focuses on the development of computational models

that can teach themselves to learn patterns or models from existing data.

And utilize the learned model when exposed to new data.

In the advanced analysis course, we spoke about big data,

high-volume of data of wide variety being generated at high velocity.

The three Vs of big data.

Machine learning systems search through big data to learn patterns in the data.

And use these patterns to make predictions or recommendation in light of new data.

For example, recommending movie genres a user may like based on pattern

learned from the past users is the use of machine learning.

探索我们的目录

免费加入并获得个性化推荐、更新和优惠。

Coursera 致力于普及全世界最好的教育，它与全球一流大学和机构合作提供在线课程。

© 2018 Coursera Inc. 保留所有权利。

通过 App Store 下载

通过 Google Play 获取