What Is Ann?

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 16

WHAT IS ANN?

Artificial Neural Networks contain artificial neurons which are called units. These
units are arranged in a series of layers that together constitute the whole Artificial
Neural Network in a system. A layer can have only a dozen units or millions of units
as this depends on how the complex neural networks will be required to learn the
hidden patterns in the dataset. Commonly, Artificial Neural Network has an input
layer, an output layer as well as hidden layers. The input layer receives data from
the outside world which the neural network needs to analyse or learn about. Then
this data passes through one or multiple hidden layers that transform the input
into data that is valuable for the output layer. Finally, the output layer provides an
output in the form of a response of the Artificial Neural Networks to input data
provided. In the majority of neural networks, units are interconnected from one
layer to another. Each of these connections has weights that determine the
influence of one unit on another unit. As the data transfers from one unit to
another, the neural network learns more and more about the data which
eventually results in an output from the output layer.

The structures and operations of human neurons serve as the basis for artificial
neural networks. It is also known as neural networks or neural nets. The input layer
of an artificial neural network is the first layer, and it receives input from external
sources and releases it to the hidden layer, which is the second layer. In the hidden
layer, each neuron receives input from the previous layer neurons, computes the
weighted sum, and sends it to the neurons in the next layer. These connections are
weighted means effects of the inputs from the previous layer are optimized more
or less by assigning different-different weights to each input and it is adjusted
during the training process by optimizing these weights for improved model
performance.

Feature Artificial Neural Network Biological Neural Network (BNN)


(ANN)
Composition Silicon chips, software Complex organic molecules, cell
algorithms membranes
Structure Simple, often single- Highly complex, interconnected
layered networks with trillions of neurons and
synapses
Information Discrete, binary signals Analog, graded electrical signals
Processing
Learning Supervised or Plasticity, adaptability through
Mechanism unsupervised algorithms neurotransmitters and synaptic
changes
Signal Faster, in the nanosecond Slower, in the millisecond range
Transmission range
Speed
Fault Tolerance Limited, network failure High, individual neuron death
disrupts processing doesn't significantly impact
overall function
Energy High, requires significant Low, utilizes electrochemical
Consumption electrical power processes efficiently
Scalability Easily scaled up with Limited by physical constraints of
additional hardware the brain
Learning Scope Narrow, focused on Broad, capable of general
specific tasks learning and adaptation
Creativity and Not yet demonstrated Arguably present in the brain's
Reasoning convincingly complex functions
Applications Image recognition, Sensory processing, learning,
machine translation, memory, consciousness,
autonomous vehicles emotions

Biological Artificial
Neuron Neuron
Dendrite Inputs

Cell Nodes
nucleus or
Soma
Synapses Weights

Axon Output

Example of Artificial Neural Networks


Consider an example of an ANN applied to quality control in manufacturing.
Suppose you have a manufacturing process that produces products with certain
quality characteristics. You can train an ANN to analyse data from sensors and
cameras on the production line to predict whether a product meets quality
standards or not. The network learns to associate patterns in the input data with
the quality outcomes, enabling it to make predictions on new, unseen data.

Application in Description
Advanced
manufacturing and
CIM
Quality Control Using ANNs to analyse sensor data, images, etc., for
identifying defects and ensuring products meet quality
standards.
Predictive Maintenance Employing ANNs to predict equipment failures based
on historical data, allowing proactive maintenance
scheduling and minimizing downtime.
Process Optimization Applying neural networks to optimize manufacturing
processes by learning complex relationships among
various parameters, such as toolpath planning for CNC
machining.
Supply Chain Utilizing ANNs for demand forecasting, optimizing
Management inventory levels, and improving overall supply chain
efficiency in integrated CIM environments.
Energy Efficiency Implementing ANNs to analyse energy consumption
patterns and suggest real-time adjustments to optimize
energy usage in manufacturing processes.
Fault Detection & Using ANNs for detecting and diagnosing faults in
Diagnosis integrated manufacturing systems by analysing data
from different sensors and components.

Example One industry where Artificial Neural Networks (ANNs) are extensively
used is the healthcare industry. In healthcare, ANNs are applied in various domains
to enhance diagnosis, treatment, and overall patient care. Here are a few examples
of how ANNs are employed in healthcare:
• Medical Imaging
• Disease Prediction and Diagnosis
• Drug Discovery
• Personalized Medicine
• Clinical Decision Support Systems
• Patient Monitoring
• Natural Language Processing in Healthcare

Importance in Description
Advanced
Manufacturing and
CIM
Efficiency Improvement ANNs optimize processes, leading to increased
efficiency, reduced waste, and improved overall
productivity in advanced manufacturing setups.
Cost Reduction Predictive maintenance and quality control provided
by ANNs help reduce downtime, maintenance costs,
and material wastage, contributing to overall cost
savings.
Adaptability to ANNs are well-suited to adapt to and optimize
Complex Systems intricate systems and processes found in advanced
manufacturing and CIM environments.
Real-time Decision Neural networks enable real-time decision-making
Making based on incoming data, allowing for agile responses
to changes in the manufacturing process or external
factors.
Enhanced Product ANNs contribute to the production of high-quality
Quality products by ensuring better quality control and
process optimization, meeting or exceeding industry
standards.

WHAT IS REVERSE ENGINEERING?

Reverse engineering is the process of deconstructing and analysing a product or


system to understand its components, functions, and design principles. This
practice involves dismantling, examining, and sometimes even replicating an
existing product or system without access to its original design documentation.

The process of reverse engineering involves several key steps, and it can be
adapted based on the specific goals and the nature of the product or system being

reverse engineered. A generalized overview of the typical process is given below:

1. Define Objectives: Clearly define the goals and objectives of the reverse
engineering project. Understand what specific information or improvements
are sought through the process.
2. Initial Analysis: Gather available information about the product or system.
This may include any existing documentation, patents, or technical
specifications.

3. Physical Disassembly: If applicable, physically disassemble the product or


system to access its internal components. Document the arrangement and
connections of each part.

4. Functional Analysis: Identify the functions performed by each component.


Understand how these components work together to achieve the overall
functionality of the product or system.

5. Data Collection: Use various techniques to collect data about the product's
geometry, structure, and material properties. This may involve
measurements, 3D scanning, or other data capture methods.

6. Data Representation: Create digital representations of the physical


components using tools like Computer-Aided Design (CAD) software. This
step involves translating the collected data into usable digital models.

7. Analysis of Data: Analyse the digital models to understand the relationships


between components, identify design principles, and gain insights into
manufacturing processes.

8. Reverse Engineering Tools: Utilize specialized software tools for reverse


engineering, such as point cloud processing software, surface modelling
tools, and other applications that aid in reconstructing digital models from
collected data.

9. Documentation: Generate detailed documentation, including CAD models,


assembly drawings, and functional specifications. This documentation is
crucial for understanding the product's design and functionality.

10.Analysis and Improvement: Evaluate the collected data and digital models to
identify areas for improvement or optimization. This step may involve
making design enhancements, incorporating new materials, or addressing
any shortcomings discovered during the analysis.

11.Prototyping or Reconstruction: Develop a prototype or a modified version of


the product based on the reverse-engineered data. This step may include
manufacturing new components using the improved design.

12.Verification and Validation: Validate the reconstructed or modified product


to ensure that it meets the desired specifications and functions as intended.
Testing and validation are critical to guarantee the success of the reverse
engineering efforts.

13.Documentation Update: Update the documentation with any changes made


during the reverse engineering process. This ensures that accurate records
are maintained for future reference.

Reverse engineering process can vary significantly depending on the industry, the
complexity of the product or system, and the specific goals of the project. Legal
and ethical considerations should be taken into account to ensure compliance with
intellectual property rights and regulations.

Reverse engineering in the automotive industry is instrumental for innovation,


quality improvement, and staying competitive in the market.

Application Key Aspects


Design Optimization - Understand existing products for optimization.
- Improve performance, efficiency, or cost-effectiveness.
Quality Control - Identify best practices from competitor products.
- Implement quality control measures to meet industry
standards.
Interoperability - Ensure seamless integration of systems and processes.
- Understand interfaces and connections between
components.
Rapid Prototyping - Facilitate quick and efficient reproduction of existing
designs.
- Support the development of prototypes.
Lifecycle - Manage the entire lifecycle of products.
Management
- Facilitate upgrades, repairs, and improvements.

Importance Key Aspects


Innovation and - Stay competitive by adopting innovative designs
Competitiveness and processes.
Cost Reduction - Identify cost-effective alternatives or
improvements.
Legacy System Integration - Integrate new technologies without a complete
overhaul.
- Adapt to the use of legacy systems.
Efficiency Improvement - Enhance the efficiency of production processes.
Customization and - Support customization in manufacturing
Flexibility processes.
- Tailor processes to specific needs.

WHAT ID 5G?

• 5G is the 5th generation mobile network. It is a new global wireless standard


after 1G, 2G, 3G, and 4G networks.
• 5G works in 3 bands (Low, Mid and High frequency spectrum) - all of which
have their own uses as well as limitations.
• It enables a new kind of network that is designed to connect virtually
everyone and everything together including machines, objects, and devices

Why Optical Fiber is backbone of 5G technology?

▪ High Speed: Fiber provides more bandwidth and has standardized performance
up to 10 Gbps and beyond, something that it is impossible to achieve when using
copper.
More bandwidth means that fiber can carry more information with far greater
efficiency than copper wire.
▪ Range of Transmission: Since data travels in the form of light in fiber-optic cables,
very little signal loss occurs during transmission and data can move at higher
speeds and greater distances.
▪ Not susceptible to interference: Fiber-optic cable is also much less susceptible to
noise and electromagnetic interference than copper wire.
It is so efficient, in fact, that roughly 99.7% of the signal reaches the router in most
cases.

▪ Durability: Fiber-optic cable is completely immune to many environmental


factors that affect copper cable.
The core is made of glass, which is an insulator, so no electric current can flow
through.

What Do We Mean by Optical Fiber?

• Optical fiber is the backbone of the digital infrastructure — the data is


transmitted by light pulses travelling through long strands of thin fiber.
• Metal wires are preferred for transmission in optical fiber communication as
signals travel with fewer damages.
• The optical fiber works on the principle of total internal reflection (TIR).
• Light rays can be used to transmit a huge amount of data (In case of long
straight wire without any bend).
• In case of a bend, the optical cables are designed such that they bend all the
light rays’ inwards (using TIR).
Example
India can be considered as one of the biggest examples of how 5G transformed
manufacturing.

5G technology is still in its early stages of deployment in India, with wide-scale


rollout beginning in 2020, there are promising developments and potential
applications across various sectors:
Enhanced Automation and Robotics:
• Real-time data transfer and low latency: 5G enables robots to receive
instructions and send feedback almost instantaneously, improving precision
and efficiency in tasks like welding, assembly, and quality control.
• Remote operation and collaboration: 5G facilitates remote control of robots
from distant locations, allowing for safer operation in hazardous
environments or streamlining operations across geographically dispersed
facilities.
Smart Manufacturing and Predictive Maintenance:
• Sensor data collection and analysis: 5G can connect a vast network of
sensors on machines and throughout production lines, generating real-time
data on performance, energy consumption, and potential equipment issues.
• Predictive maintenance: Advanced analytics powered by AI can use this data
to anticipate equipment failures and schedule preventive maintenance,
reducing downtime and production losses.
Supply Chain Optimization and Logistics:
• Improved visibility and tracking: 5G-enabled smart tags and connected
vehicles can track raw materials, components, and finished products in real-
time, optimizing inventory management, logistics, and delivery schedules.
• Autonomous vehicles and drones: 5G's high bandwidth supports the
development and deployment of autonomous vehicles and drones for on-
site transportation and delivery, streamlining logistics within manufacturing
facilities.
Other notable areas of progress:
• Augmented Reality (AR) and Virtual Reality (VR): 5G's capabilities can
enhance AR/VR applications in manufacturing, such as providing technicians
with remote assistance or overlaying digital instructions onto real-world
workspaces.
• Digital Twins and simulations: Creating digital twins of factories and
production processes using 5G data can enable virtual testing and
optimization of operations, leading to improved efficiency and reduced
waste.

Application of 5G in advanced Description


manufacturing and CIM
Smart Factories Real-time communication for increased
automation and efficiency.
Industrial IoT (IIoT) Massive device connectivity for
comprehensive Industrial IoT.
Augmented Reality (AR) and Virtual Enhanced worker training, remote
Reality (VR) assistance, and maintenance.
Remote Monitoring and Control Remote oversight and control of
manufacturing processes.
Network Slicing for Customized Customized 5G slices for specific
Services manufacturing applications.

Importance of 5G in advanced Description


manufacturing and CIM
Increased Efficiency Real-time data and automation contribute
to enhanced efficiency.
Flexibility and Customization Network slicing allows customized
connectivity for different processes.
Improved Safety and Security Low latency and secure data exchange
enhance safety in manufacturing.
Global Connectivity Consistent connectivity across global
manufacturing facilities.
Innovation in Product High data speeds and low latency facilitate
Development innovative development.

WHAT IS INDUSTRY 4.0?


Industry 4.0, also known as the fourth industrial revolution, represents a paradigm
shift in manufacturing and production processes.

The term “Industry 4.0” (or the Fourth Industrial Revolution) was popularized
around a decade ago and refers to the deployment of a wide range of technologies
with the potential to transform industry through new cognitive tools, connectivity,
virtual modeling (including digital twins), collaboration tools, and new techniques
for manufacturing and supply chain, including advanced robotics and blockchain.
Industry 4.0 technologies already provide significant benefits to those companies
that have successfully deployed them to help transform their businesses. For
example, according to data from case examples in Arthur D. Little’s (ADL’s)
Operational Excellence Database, these benefits are often double-digit in scale:
• 15%-30% reductions in operational capital deployed
• 10%-30% reductions in supply chain costs
• 30% increased utilization of production capacity
• 10%-40% reductions in maintenance costs

Key Features of Industry 4.0:

• Interconnectivity: Machines, devices, sensors, and people are connected and


communicate with each other through the Internet of Things (IoT).

• Information Transparency: Real-time data and information are available


throughout the entire production process, enabling better decision-making.

• Technical Assistance: Cyber-physical systems assist humans in decision-


making and problem-solving, utilizing advanced technologies like artificial
intelligence.

• Decentralized Decision-Making: Smart systems have the ability to make


decisions autonomously, reducing the need for centralized control.

Examples Siemens' Digital


Factory
Siemens has implemented
Industry 4.0 principles in
its own factories, creating
a digital twin of the entire
production process.
Sensors collect data on
every machine, allowing
for real-time monitoring,
predictive maintenance,
and optimization of
resource usage. This has resulted in significant improvements in productivity,
efficiency, and quality.

Applications of Industry Importance in Advanced Manufacturing and CIM


4.0
IoT Sensors Enables real-time data collection for monitoring and
optimizing processes. Improves efficiency and
reduces downtime.
Big Data Analytics Analyses large datasets to identify patterns, optimize
processes, and predict maintenance needs. Facilitates
data-driven decision-making.
Artificial Intelligence (AI) Enhances predictive maintenance, quality control,
and production scheduling. Enables autonomous
decision-making for greater efficiency.
Robotics and Automation Improves precision and efficiency in manufacturing
processes. Collaborative robots work alongside
human workers.
3D Printing/Additive Rapid prototyping and production of complex
Manufacturing components. Enhances flexibility in manufacturing
and reduces time-to-market.
Augmented Reality (AR) Used for training, maintenance, and improving
and Virtual Reality (VR) worker efficiency by providing real-time information
and instructions.
Cloud Computing Provides a platform for storing and accessing vast
amounts of data. Enables remote monitoring and
control of manufacturing processes.
Smart Factories Optimizes production schedules, reduces downtime
through predictive maintenance, and enhances
overall efficiency in manufacturing.
Digital Twin A digital representation of physical systems, allowing
simulation and analysis before implementation.
Reduces the risk of errors in manufacturing.
Flexible Manufacturing Rapid reconfiguration of production lines to
Systems accommodate different products and respond to
changes in demand. Enhances overall flexibility.
Supply Chain Improves visibility into the supply chain, enabling
Optimization better inventory management, demand forecasting,
and coordination among stakeholders.
Quality Control Real-time monitoring and analysis of production
processes contribute to improved quality control,
reducing defects and waste.
Enhanced Connectivity Extends the integration of computer systems,
creating a comprehensive and interconnected
manufacturing ecosystem.
Data-Driven Decision The abundance of data enables informed decision-
Making making at every stage of the manufacturing process,
enhancing overall efficiency.
Improved Automation Goes beyond traditional automation by incorporating
autonomous decision-making systems, self-
optimizing processes, and smart machines.
Agility and Flexibility Allows for more agile and flexible manufacturing
processes, accommodating changes in production
requirements and responding to market dynamics.

You might also like