Machine learning For Smarter Manufacturing & its Fundamentals
- 1. Click to edit Master title style 1 Machine Learning F o r S m a r t e r M a n u f a c t u r i n g a n d i t s F u n d a m e n t a l s S u c h i t G a i k w a d M . S c S t a t i s t i c s
- 2. Click to edit Master title style 2 Introduction : What is Machine Learning ? Machine learning (ML) is the study of computer algorithms that improve automatically through experience. It is seen as a subset of AI (Artificial Intelligence). Machine learning algorithms build a Statistical model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision 2
- 3. Click to edit Master title style 3 Lets Understand with Example 3 • After First Attempt You realized that you are applying too much force • After Second Attempt Your are closer to target but you need to increase the throw angel • This way you are learning something at every attempt and improving the end result
- 4. Click to edit Master title style 4 You can Do Something Similar with machine Too 4 • You can Program a machine from Every attempt or Experience or Data Point and there by improve the outcome • Machine Learning Provides Computer with the ability to learn without being explicitly programmed
- 5. Click to edit Master title style 5 Evolution of Machine Learning . 5 1950s 1960s 1970s 1980s 1990s 2000s 2010s Pioneering machine learning research is conducted using simple algorithms Bayesian methods are introduced for probabilistic inference in machine learning ‘AI Winter’ Caused by pessimism about machine learning effectiveness Neural network became popular Work on machine learning shifts from a knowledge-driven approach to a data- driven approach Support Vector Clustering and other Kernel methods and Unsupervised machine learning method become widespread Deep Learning Becomes Feasible, which leads to machine learning becoming integral to many widely used software and applications.
- 6. Click to edit Master title style 6 1950’s 6 • In 1952 AI Pioneer Arthur Samuel he was working for IBM & He Created First Learning Machine In Fact he was the First Person to popularized the term machine learning and his System could learn to play checkers or Draft with help of Simple Algorithm.
- 7. Click to edit Master title style 7 1960’s 7 • With the Help Of Bayesian methods to solve the probabilistic inference in ML • For Ex: Given the test is positive, what is the probability that person has cancer
- 8. Click to edit Master title style 8 1970’s 8 • In the history of Machine Learning, an AI winter is a period of reduced funding and interest in Machine Learning research. • Which Caused by pessimism about machine learning effectiveness
- 9. Click to edit Master title style 9 1980’s 9 • A neural network can be trained to produce outputs that are expected, given a particular input. • For Ex: Stock Market Prediction.
- 10. Click to edit Master title style 10 1990’s 10 • Scientists begin creating programs for computers to analyze large amounts of data and draw conclusions – or "learn" – from the results. • Deep Blue was a chess - playing computer developed by IBM in 1997. It is known for being the first computer chess-playing system to win both a chess game and a chess match against a reigning world champion under regular time controls
- 11. Click to edit Master title style 11 2000’s 11 • With help of Kernel Methods and Unsupervised Machine Learning methods in 2006 Geoffrey Hinton Publish are research recognizing Handwritten digits with an Accuracy grater than 98% that when Machine Learning Explosion Starts.
- 12. Click to edit Master title style 12 2010’s 12 • Deep Learning Helps which Film You Want to watch Showing in BookmyShow Applications. • Recommendation Of product on Amazon and Flipkart Based on your Requirements • Now at this Moment Machine learning is now part of life its is every were.
- 13. Click to edit Master title style 13 Role of Machine Learning in Manufacturing Industry • Machine Learning plays an important role in enhancing the quality of the manufacturing process. • Deep-learning neural networks can help in the availability, performance, quality of assembly equipment, and weaknesses of the machine. • Data has become a valuable resource, and it’s cheaper than ever to capture and store. Through the use of artificial intelligence, specifically Process-Based Machine Learning, manufacturers can use data to significantly impact their bottom line by greatly improving production efficiency, product quality, and employee safety. 13
- 14. Click to edit Master title style 14 Enabling Predictive Quality Analytics with Machine Learning 14 • Preventing downtime is not the only goal that industrial AI can assist us with. The quality of output is crucial and product quality deterioration can also be predicted using Machine Learning. Knowing beforehand that the quality of products being manufactured is destined to drop prevents the wastage of raw materials and valuable production time. • Machine Learning can be split into two main techniques – Supervised and Unsupervised machine learning.
- 15. Click to edit Master title style 15 Lets Understand How Machine Learning is Classified 15
- 16. Click to edit Master title style 16 Supervised Machine Learning 16 • In manufacturing use cases, supervised machine learning is the most commonly used technique since it leads to a predefined target: we have the input data; we have the output data; and we’re looking to map the function that connects the two variables . • Supervised machine learning demands a high level of involvement – data input, data training, defining and choosing algorithms, data visualizations, and so on. The goal is to construct a mapping function with a level of accuracy that allows us to predict outputs when new input data is entered into the system .
- 17. Click to edit Master title style 17 Supervised Machine Learning Flow Diagram 17
- 18. Click to edit Master title style 18 Supervised Machine Learning 18 • Initially, the algorithm is fed from a training dataset, and by working through iterations, continues to improve its performance as it aims to reach the defined output. The learning process is completed when the algorithm reaches an acceptable level of accuracy. • In manufacturing, one of the most powerful use cases for Machine Learning is Predictive Maintenance, which can be performed using two Supervised Learning approaches: Classification and Regression . • These 2 approaches share the same goal: to map a relationship between the input data (from the manufacturing process) and the output data (known possible results such as part failure, overheating etc .)
- 19. Click to edit Master title style 19 Classification 19 • When data exists in w ell -defined categories, C lassif ication can be used. A n example of C lassif ication t hat w e’re all f amiliar w ith is t he email f ilt er algorit hm t hat decides w hether an email should be sent t o our spam f older, or not . C lassif ication is limit ed t o a Boolean value response, but can be very usef ul since only a small amount of dat a is needed t o achieve a high level of accuracy. • Predict ive Maint enance makes use of mult i - class classif icat ion since t here are mult iple possible causes for the failure of a machine or component . These are possible out comes t hat are classif ied as pot ent ial equipment issues, calculat ed using a number of variables including machine healt h, risk levels and possible reasons f or malf unct ion.
- 20. Click to edit Master title style 20 Classification 20 • In machine learning, common Classification algorithms include Decision Trees, k -Nearest Neighbour (kNN) & Support Vector Machine (SVM)
- 21. Click to edit Master title style 21 Regression 21 • R e g r e s s i o n i s u s e d w h e n d a t a e x i s t s w i t h i n a r a n g e ( e g . t e m p e r a t u r e , w e i g h t ) , w h i c h i s o f t e n t h e c a s e w h e n d e a l i n g w i t h d a t a c o l l e c t e d f r o m s e n s o r s . • I n m a n u f a c t u r i n g , r e g r e s s i o n c a n b e u s e d t o c a l c u l a t e a n e s t i m a t e f o r t h e R e m a i n i n g U s e f u l L i f e ( R U L ) o f a n a s s e t . T h i s i s a p r e d i c t i o n o f h o w m a n y d a y s o r c y c l e s w e h a v e b e f o r e t h e n e x t c o m p o n e n t / m a c h i n e / s y s t e m f a i l u r e . • F o r r e g r e s s i o n , t h e m o s t c o m m o n l y u s e d m a c h i n e l e a r n i n g a l g o r i t h m i s L i n e a r R e g r e s s i o n , b e i n g f a i r l y q u i c k a n d s i m p l e t o i m p l e m e n t , w i t h o u t p u t t h a t i s e a s y t o i n t e r p r e t . A n e x a m p l e o f l i n e a r r e g r e s s i o n w o u l d b e a s y s t e m t h a t p r e d i c t s t e m p e r a t u r e , s i n c e t e m p e r a t u r e i s a c o n t i n u o u s v a l u e w i t h a n e s t i m a t e t h a t w o u l d b e s i m p l e t o t r a i n .
- 22. Click to edit Master title style 22 Linear Regression 22 • Linear Regression – A modeling function that assumes a linear relationship between the input variables x and the single output variable y and creates a trend-line (prediction model) using the formula y=ax+b • For Example regression model for variables like fabric Gauge and Square meter weight • But with machine Learning we can make this algorithm and use to analyze every single day. y = 1.2802x - 0.2669 R² = 0.9707 1.18 1.19 1.2 1.21 1.22 1.23 1.24 1.25 1.26 1.27 1.28 1.13 1.14 1.15 1.16 1.17 1.18 1.19 1.2 1.21 SquaremeterWeight Fabric Gauge LINEAR REGRESSION
- 23. Click to edit Master title style 23 Logistic Regression 23 • Logistic Regression – Also known as exponential (x2, x3, …, xn) or polynomial (y=ax2+bx+c) regression, is similar to linear regression but the trend- line (y=1/(1+ex)) is assumed to be of a higher order
- 24. Click to edit Master title style 24 Unsupervised Machine Learning 24 • With Supervised machine learning we start off by working from an expected outcome and train the algorithm accordingly. Unsupervised learning is suitable for cases where the outcome is not yet known.
- 25. Click to edit Master title style 25 Clustering 25 • In some cases, not only will the outcome be unknown to us, but information describing the data will also be lacking (data labels). By creating clusters of input data points that share certain attributes, a Machine Learning algorithm can discover underlying patterns. • Clustering can also be used to reduce noise (irrelevant parameters within the data) when dealing with extremely large numbers of variables.
- 26. Click to edit Master title style 26 Classification Vs. Clustering 26
- 27. Click to edit Master title style 27 Artificial Neural Networks 27 • In the manufacturing sector, Artificial Neural Networks are proving to be an extremely effective Unsupervised learning tool for a variety of applications including production process simulation and Predictive Quality Analytics. • The basic structure of the Artificial Neural Network is loosely based upon how the human brain processes information using its network of around 100 billion neurons, allowing for extremely complex and versatile problem solving. • This ability to process a large number of parameters through multiple layers makes Artificial Neural Networks very suitable for the variable -rich and constantly changing processes common to manufacturing. Moreover, once properly trained, an Artificial Neural Network can demonstrate a high level of accuracy when creating predictions regarding the mechanical properties of processed products, enabling cuts in the cost of raw materials.
- 28. Click to edit Master title style 28 Artificial Neural Networks 28 • This ability to process a large number of parameters through multiple layers makes Artificial Neural Networks very suitable for the variable -rich and constantly changing processes common to manufacturing. Moreover, once properly trained, an Artificial Neural Network can demonstrate a high level of accuracy when creating predictions regarding the mechanical properties of processed products, enabling cuts in the cost of raw materials.
- 29. Click to edit Master title style 29 Programming Languages used in Machine Learning 29 • Machine learning is writing code that lets machines make decisions based on pre - defined algorithms on provided datasets . • So, what is the most popular programming language for machine learning? Almost any programming language can be used to write ML based applications. However, writing every algorithm from scratch is a time - consuming process. The best suited programming language is the one that comes with pre -built libraries and have advanced support of data science and data models.
- 30. Click to edit Master title style 30 Most popular programming languages for machine learning. 30 • Python • C++ • Java • JavaScript • C# • R • Julia • GO • TypeScript • Scala
- 31. Click to edit Master title style 31 Python 31 • P yt h o n i s o n e o f t h e m o s t p o p u l a r p r o g r a m m i n g l a n g u a g e s o f r e c e n t t i m e s . P yt h o n , c r e a t e d b y G u i d o va n R o s s u m i n 1 9 9 1 , i s a n o p e n - s o u r c e , h i g h - l e ve l , g e n e r a l p u r p o s e p r o g r a m m i n g l a n g u a g e . P yt h o n i s a d yn a m i c p r o g r a m m i n g l a n g u a g e w h i c h s u p p o r t s o b j e c t - o r i e n t e d , i m p e r a t i ve , f u n c t i o n a l a n d p r o c e d u r a l d e ve l o p m e n t p a r a d i g m s . P yt h o n i s ve r y p o p u l a r i n m a c h i n e l e a r n i n g p r o g r a m m i n g . • P yt h o n i s o n e o f t h e f i r s t p r o g r a m m i n g l a n g u a g e s t h a t g o t t h e s u p p o r t o f m a c h i n e l e a r n i n g vi a a va r i e t y o f l i b r a r i e s a n d t o o l s . • S c i k i t a n d Te n s o r F l o w a r e t w o p o p u l a r m a c h i n e l e a r n i n g l i b r a r i e s a va i l a b l e t o P yt h o n d e ve l o p e r s .
- 32. Click to edit Master title style 32 Benefits of using Python 32 • Python is widely considered as the preferred language for teaching and learning Ml (Machine Learning). Few simple reasons are: • It’s simple to learn. As compared to c, c++ and Java the syntax is simpler and Python also consists of a lot of code libraries for ease of use. • Though it is slower than some of the other languages, the data handling capacity is great. • Open Source! – Python along with R is gaining momentum and popularity in the Analytics domain since both of these languages are open source. • Capability of interacting with almost all the third party languages and platforms.
- 33. Click to edit Master title style 33 Benefits of Machine Learning for Manufacturing 33 • The introduction of AI and Machine Learning to industry represents a sea change with many benefits that can result in advantages well beyond efficiency improvements, opening doors to new business opportunities . • Some of the direct benefits of Machine Learning in manufacturing include…
- 34. Click to edit Master title style 34 Benefits of Machine Learning for Manufacturing 34 • Cost reduction through Predictive Maintenance. PdM leads to less maintenance activity, which means lower labor costs and reduced inventory and materials wastage. • Predicting Remaining Useful Life (RUL). Knowing more about the behavior of machines and equipment leads to creating conditions that improve performance while maintaining machine health. Predicting RUL does away with “unpleasant surprises” that cause unplanned downtime. • Improved supply chain management through efficient inventory management and a well monitored and synchronized production flow.
- 35. Click to edit Master title style 35 Benefits of Machine Learning for Manufacturing 35 • Improved Quality Control with actionable insights to constantly raise product quality. • Improved Human- Robot collaboration improving employee safety conditions and boosting overall efficiency. • Consumer-focused manufacturing – being able to respond quickly to changes in the market demand.
- 36. Click to edit Master title style 36 Thank You