Advanced Robotics

While robotics have been used in manufacturing for decades, Industry 4.0 has given
new life to this technology. With recent advancements in technology, a new
generation of advanced robotics is emerging, capable of performing difficult and
delicate tasks. Powered by cutting-edge software and sensors, they can recognise,
analyse and act upon the information they receive from the environment, and even
collaborate and learn from humans. One area of robotics gaining significant traction
is collaborative robots (“cobots”), designed to work safely around people, freeing
workers from repetitive and dangerous tasks.
Example :
California-based Fetch Robotics has developed collaborative Autonomous Mobile
Robots (AMRs) for locating, tracking, and moving inventory in warehouse and
logistics facilities. A DHL distribution centre in the Netherlands is using Fetch AMRs
to perform pick and place operations. At DHL, AMRs autonomously move across the
facility alongside the workers, automatically learning and sharing the most efficient
travel routes. Using self-driving robots in this way can help reduce order cycle time
by up to 50% and provide up to twice the picking productivity gain, according to the
company.As robots become more autonomous, flexible and cooperative, they will be
able to tackle even more complex assignments, relieving the workers from
monotonous tasks and increasing productivity on the factory floor.

Big Data & Analytics

Big Data refers to the large and complex data sets generated by IoT devices. This
data comes from a wide range of cloud and enterprise applications, websites,
computers, sensors, cameras and much more, all coming in different formats and
protocols. In the manufacturing industry, there are many different types of data to
take into consideration, including the data coming from production equipment fitted
with sensors and databases from ERP, CRM and MES systems. With data analysis.
When it comes to data, the use of data analytics is essential to convert data to
information that can deliver actionable insights. Ultimately, by taking previously
isolated data sets, collecting and analysing them, companies are now able to
find new ways to optimise the processes that have the greatest effect on yield.

INDUSTRY EXAMPLE:
UPS is a real-world example of big data logistics leading to big savings. After
examining their data, UPS found that trucks turning left was costing them a lot of
money. In other words, UPS found that turning into oncoming traffic was causing a
lot of delays, wasted fuel, and safety risk.

UPS analysed routes, delivery times and other statistics and found out that drivers should
not turn left. As a result,

● Their vehicles had to travel nearly 33 million kilometres less,

● 350,000 more packages were shipped and
● 20,000 tonnes less carbon dioxide has been emitted into the atmosphere.

It is clear from the data that turning left reduces the chances of an accident and cuts delays
caused by waiting for a gap in the traffic, which would also waste fuel. This is possible
because of the data collected by sensors and other IoT (Internet of Things) devices,
processed with data mining tools to show how processes can be made faster, simpler and
more cost-effective.

Cyber Physical Systems

In manufacturing plants, there can be potential loss in productivity when there is a

repair on the machine. Gone are those days where the production is stopped for
those unplanned failures.

Cyber-Physical Systems (CPS) are integrations of computation, networking, and

physical processes. Embedded computers and networks monitor and control the
physical processes, with feedback loops where physical processes affect
computations and vice versa.

These Cyber systems acts as a hub where deep learning algorithms are run in which
the machine detects its failure based on the pre-defined dataset and automates the
solutions by itself. This maintenance information can serve as feedback to business
management systems. Operators and factory managers, in turn, can use it to make
informed decisions. At the same time, the machine itself can adjust its working load
or manufacturing schedule to reduce down time caused by machine malfunctions.

Example : Big Data decision-making at Bosch Automotive factory in China. Once

data is collected, advanced data analytics tools process the data in real time and alert
workers when any bottlenecks in the production operations have been identified.

Taking this approach helps to predict equipment failures, enabling the factory to schedule
maintenance operations well before any failures occur.

Additive Manufacturing
The demand for the goods is not always forecasted thus resulting in customer
dissatisfaction. To overcome this,3D printing is one of the most recent trends in the digital
manufacturing which produces goods on-demand.

3D printing, or additive manufacturing, is the construction of a three-dimensional object from

a CAD model or a digital 3D model. The term "3D printing" can refer to a variety of
processes in which material is deposited, joined or solidified under computer control to
create a three-dimensional object, with the material being added together.

AM offers a huge scope of possibilities for manufacturing from tooling to mass customisation
across virtually all industries. It enables parts to be stored as design files in virtual
inventories, so that they can be produced on-demand and closer to the point of need — a
model known as distributed manufacturing.

Such a decentralised approach to manufacturing can reduce transportation distances, and

hence costs, as well as simplify inventory management by storing digital files instead of
physical parts. It can further improve OTIF KPI in Supply chain management.

Example : Fast Radius created a virtual parts warehouse consisting of 3,000 items for a
heavy equipment manufacturer. With the high costs involved in storing rarely ordered parts,
this approach is an innovative solution for supply chain management.

REFERENCES:

https://www.irjet.net/archives/V7/i8/IRJET-V7I8337.pdf

https://www.emerald.com/insight/content/doi/10.1108/JMTM-08-2018-0280/full/pdf

https://www.econstor.eu/bitstream/10419/209250/1/hicl-2015-20-031.pdf