Unit No: 2

Technological Foundations of
Digital Manufacturing

Dr. Ganesh B. Narkhede

Asst. Professor (Mechanical)
VIIT, Pune

BRACT’S, Vishwakarma Institute of Information Technology, Pune-48

(An Autonomous Institute affiliated to Savitribai Phule Pune University)
(NBA and NAAC accredited, ISO 9001:2015 certified)
Points to be discussed…
Syllabus

In-depth study of IoT (Internet of Things) and its significance in manufacturing industries.

Introduction to Artificial Intelligence and Machine Learning, Big data analytics

Robotics and automation technologies for enhanced productivity

Additive manufacturing (3D printing) and its impact on sustainable production

 Introduction
• In recent years, technological advancements
have propelled us into an era of unprecedented
connectivity, automation, and innovation.
• Several key technological foundations are at the
forefront of this transformation.
• We will explore the foundations of IoT (Internet
of Things), AI and ML(Artificial Intelligence and
Machine learning), BDA (Big Data Analytics),
Robots and Automation, AR and VR, CPS
(Cyber-Physical Systems), and 3D printing.
Technological foundations of Digital Manufacturing
Introduction to IoT (Internet of Things) in Manufacturing:
• The Internet of Things (IoT) refers to the network of
interconnected physical devices, sensors, actuators,
and other objects embedded with software and
connectivity capabilities.
• These devices collect and exchange data, enabling
them to communicate and interact with each other
over the internet.

In the context of manufacturing, IoT plays a crucial role in transforming traditional industrial processes,
giving rise to what is often termed as the "Industrial Internet of Things" (IIoT).
Applications: Continuous monitoring, Data collection, Quality control, process optimization
Significance of IoT in Manufacturing Industries:
• Increased Operational Efficiency: IoT devices in manufacturing enable real-time monitoring of
equipment, processes, and production lines. This facilitates data-driven decision-making, leading to
improved efficiency in production processes.
• Predictive Maintenance: IoT sensors on machinery and equipment collect data on performance and
condition. This data is then analyzed to predict when maintenance is required, reducing downtime
and preventing costly equipment failures.
• Quality Control: IoT facilitates continuous monitoring of product quality by collecting data throughout
the manufacturing process. This ensures that any deviations from quality standards are identified
early, reducing defects and waste.
Continue…
• Supply Chain Optimization: IoT enables better visibility and traceability in the supply chain.
Manufacturers can track the movement of raw materials, components, and finished goods in real-
time, allowing for more efficient inventory management and timely response to disruptions.
• Energy Efficiency: IoT devices help monitor energy consumption in manufacturing facilities. By
analyzing data on energy usage, manufacturers can identify opportunities for optimization and
implement energy-saving measures, leading to cost reductions and sustainability benefits.
• Enhanced Safety: IoT devices can be employed to monitor workplace conditions and detect potential
safety hazards. This contributes to creating a safer working environment for employees by providing
real-time alerts and insights into potential risks.
Continue…
• Smart Factories: IoT is a key enabler of smart factories, where interconnected devices and systems
communicate seamlessly. This allows for adaptive and responsive manufacturing processes that can
be adjusted in real-time based on changing conditions.
• Data Analytics and Business Intelligence: The massive amount of data generated by IoT devices in
manufacturing can be analyzed to extract valuable insights. Predictive analytics and business
intelligence tools can provide manufacturers with a competitive edge by optimizing processes and
identifying new business opportunities.
• Cost Reduction: IoT-driven improvements in efficiency, maintenance, and resource management can
lead to significant cost reductions for manufacturing industries, contributing to increased profitability.
Summary…

• In summary, IoT is revolutionizing the manufacturing sector by providing new ways to monitor,
control, and optimize processes. The adoption of IoT in manufacturing is driven by the desire for
increased efficiency, reduced costs, improved product quality, and the overall competitiveness of
businesses in the rapidly evolving industrial landscape.
Key components of IoT in manufacturing:
• Sensors and Actuators: Sensors capture data from the physical environment, such as temperature,
humidity, pressure, vibration, and more. In manufacturing, sensors are crucial for collecting real-
time data from machinery and processes. Actuators respond to signals from the IoT system by
performing physical actions. For example, actuators may adjust the speed of a conveyor belt or
control the temperature of a furnace.
• Connectivity: Communication Protocols such as MQTT (Message Queuing Telemetry Transport),
CoAP (Constrained Application Protocol), and others, are used to enable data exchange between
devices and the IoT platform. Networking Infrastructure:** Reliable and scalable networking
infrastructure, including Wi-Fi, Ethernet, and sometimes specialized industrial protocols like
Modbus or OPC UA, ensures seamless communication among IoT devices.
Continue…
• IoT Gateways: These devices act as intermediaries between sensors and the cloud or edge computing
systems. Gateways preprocess and filter data, reducing latency and bandwidth requirements while
providing a secure link to the broader network.
• Cloud Computing and Edge Computing: Cloud Computing: IoT platforms leverage cloud services to store,
process, and analyze vast amounts of data. Cloud-based solutions offer scalability and accessibility for
manufacturers to manage and extract insights from their data. Edge Computing: In some cases, processing
data at the edge of the network, closer to where it is generated, can reduce latency and improve real-time
decision-making. Edge computing is particularly useful for applications that require quick response times.
• IoT Platforms: These software frameworks facilitate the management, storage, and analysis of IoT data.
IoT platforms often include features for device management, data analytics, security, and integration with
other enterprise systems.
Continue…
• Security Measures: Device Security: Implementing security measures on individual devices, including encryption, secure
boot, and access controls, helps protect against unauthorized access and data breaches. Network Security: Ensuring
secure communication channels, firewalls, and intrusion detection systems are essential for safeguarding data during
transmission. Data Security: Encryption, authentication, and secure storage practices protect sensitive information at
rest and in transit.
• Data Analytics and Artificial Intelligence (AI): Leveraging analytics tools and AI algorithms helps manufacturers derive
actionable insights from the massive amounts of data generated by IoT devices. Predictive maintenance, quality
control, and process optimization are common applications.
• Human-Machine Interface (HMI) and Visualization Tools: Intuitive interfaces and visualization tools enable operators
and decision-makers to interpret complex data easily. HMIs may include dashboards, alerts, and other features to
monitor and control manufacturing processes.
Continue…
• Application Programming Interfaces (APIs): APIs facilitate the integration of IoT systems with existing enterprise
applications, such as Enterprise Resource Planning (ERP) or Customer Relationship Management (CRM) systems.
• Blockchain Technology (Optional): In some cases, blockchain technology is employed for secure and transparent
transactions within the IoT network, providing an immutable and decentralized ledger for data integrity.

The successful implementation of IoT in manufacturing involves the seamless integration of these components to create a
robust and efficient system that enhances operational processes and decision-making.
IoT case studies
Case Study 1: Voice Assisted Forging System Case Study 2: IoT Enabled Assembly Line

 The average rejection count is reduced by 90.3%. Parameters Before IoT After IoT
Rejection Rate 25%. 10%
 The operational productivity is increased by 71.2%. Non-value added activity
33.33%. 11.06%.
 The labour productivity is increased by 83.7%. time (NVA)
Production Rate / day 49%. 67%.
 The average process accuracy is increased from 92.75% Percentage Utilization of
Tools and Fixtures in 85% 95%.
to 99.30%.
Assembly
 Number of accidents are reduced to zero. Scrap 5%. zero.
Case Study 1: Voice Assisted Forging System

Case Study 2: IoT Enabled Assembly Line

Detail case study: Voice assisted forging machine
Case Study 3: Industry 4.0 Enabled System for Identifying Defected
Work-Piece
Artificial Intelligence & Machine Learning (AIML)
• AIML in manufacturing refer to the application of
advanced computational technologies to optimize
and automate various aspects of the
manufacturing process.
• These technologies leverage data, algorithms, and
computational power to make machines, systems,
and processes smarter, more efficient, and
adaptable.

Artificial Intelligence (AI): AI refers to the development of computer systems that can perform tasks that typically
require human intelligence. These tasks include problem-solving, learning, perception, language understanding, and
decision-making.
Machine Learning (ML): ML is a subset of AI that focuses on the development of algorithms that enable computers to
learn patterns and make predictions or decisions without being explicitly programmed.

Applications: Predictive maintenance, Quality control, process optimization

1.Types of AI:
• Narrow AI (Weak AI): Systems designed and trained for a particular task, such as virtual personal
assistants or image recognition software.
• General AI (Strong AI): Hypothetical machines with the ability to understand, learn, and apply
knowledge across different domains, similar to human intelligence.
2.Key Components of AI:
• Machine Learning: A subset of AI that focuses on the development of algorithms enabling systems to
learn from data.
• Natural Language Processing (NLP): Enables machines to understand, interpret, and generate
human-like text.
• Computer Vision: Allows machines to interpret and make decisions based on visual data.
1. Types of Machine Learning:
• Supervised Learning: The algorithm is trained on a labeled dataset, where the input data is paired with
corresponding output labels.
• Unsupervised Learning: The algorithm is given unlabeled data and must find patterns or relationships
within the data.
• Reinforcement Learning: Agents learn to make decisions by receiving feedback in the form of rewards or
penalties.
2. Key Concepts in Machine Learning:
• Feature Extraction: Identifying relevant features or variables from raw data for model training.
• Model Training: The process of adjusting model parameters to improve its performance.
• Prediction and Inference: Applying trained models to make predictions or decisions on new, unseen
data.
1.Applications of AI and ML:
• Healthcare: Diagnosis, drug discovery, personalized medicine.
• Finance: Fraud detection, risk assessment, algorithmic trading.
• Retail: Customer recommendations, demand forecasting, supply chain optimization.
• Automotive: Autonomous vehicles, predictive maintenance.
• Natural Language Processing (NLP): Chatbots, language translation, sentiment analysis.
2.Challenges and Considerations:
• Bias and Fairness: Ensuring algorithms are fair and unbiased.
• Interpretability: Understanding and explaining the decisions made by AI models.
• Data Privacy and Security: Safeguarding sensitive information used in training AI models.
3.Future Trends:
• Explainable AI (XAI): Efforts to make AI systems more transparent and interpretable.
• AI in Edge Computing: Bringing AI capabilities closer to the data source for faster processing.
• AI Ethics: Addressing ethical considerations in AI development and deployment.
Big Data Analytics (BDA)
• Big Data Analytics (BDA) in manufacturing refers
to the process of collecting, processing, and
analyzing large volumes of data generated
within the manufacturing ecosystem.
• This data includes information from various
sources such as sensors, machines, production
processes, supply chains, and customer
interactions.
The goal of applying BDA in manufacturing is to extract valuable insights, identify patterns, and make data-
driven decisions to improve efficiency, productivity, and overall business performance..

Applications: Demand forecasting, Root Cause Analysis, Risk Management.

Industrial Robots

• Industrial robots are automated, reprogrammable machines designed to perform tasks traditionally
carried out by humans in industrial settings.
• These robots are a crucial component of modern manufacturing, helping to increase efficiency, improve
precision, and enhance overall productivity.
Applications: Welding, Assembly, Material Handling, Painting and Coating, Inspection and Testing.
3D Printing
• 3D printing, also known as Additive Manufacturing, is a
process of creating three-dimensional objects layer by
layer from a digital model.
• Unlike traditional manufacturing methods that involve
processes such as machining or cutting, 3D printing
builds objects layer by layer, offering design flexibility
and the ability to create complex geometries.

• The process involves melting or binding materials, such as plastic, metal, or powder, layer upon layer to
create the desired object.
Applications: Prototyping, Customized Products, Aerospace Components, Automotive Parts, Medical Models
and Prosthetics
Some complex shape geometries by 3D printing
Virtual Reality (VR)
• Virtual Reality (VR) is a computer-generated
simulation of a three-dimensional environment
or experience that can be interacted with and
explored by a user.
• VR typically involves the use of headsets or other
immersive devices that provide a visual and often
auditory experience, creating a sense of presence
within the virtual environment.

Applications: Product Visualization, Safety Training and Simulation

Examples of VR

Design Visualization
Training & Simulation
Visualizing and optimizing product
Immersive training experiences
product designs in a virtual
for complex tasks and scenarios.
environment.
 Any Question?
BRACT’S, Vishwakarma Institute of Information Technology, Pune-48

(An Autonomous Institute affiliated to Savitribai Phule Pune University)

(NBA and NAAC accredited, ISO 9001:2015 certified)
 Email ID: [email protected]
Mob: +91 9767895083

BRACT’S, Vishwakarma Institute of Information Technology, Pune-48

(An Autonomous Institute affiliated to Savitribai Phule Pune University)

(NBA and NAAC accredited, ISO 9001:2015 certified)