THE USE OF ARTIFICIAL INTELLIGENCE IN REFRACTORY MAINTENANCE By Prakash Bharati, Senior Manager at Calderys, iron and steel specialist
failure with self-awareness, self-prediction
and self-comparison and go deeper into self- configuration and self-optimization to improve intelligence and performance.
With these capabilities, a blast furnace and its system can be transformed to be smarter and resilient to dynamic changing environments. What if a blast furnace refractory system can learn from its own history? If its peers have the same design, volume and process, the maintenance generated.
requirement can be quickly
What if Stack gunning and shotcrete (which are common installation processes) pods were equipped with a laser that can measure the residual lining thickness of the blast furnace refractory? Based on laser
In the 18th century, the introduction of water and steam powered mechanical manufacturing triggered the First Industrial Revolution. The Second Industrial Revolution was mainly driven by ideas and division of labour, whereas the Third Revolution was driven by the introduction of programmable logic
designed for automation in the manufacturing industry.
The world is rapidly moving toward Industry 4.0, or the Fourth Industrial Revolution. Artificial intelligence (AI) and machine-learning based systems are not only changing the way we interact with information & systems but also revolutionizing the manufacturing sector.
In the field of refractories (including equipment/ furnace, process, operating
maintenance) the product selection is usually designed and supplied
experience. In other terms, you have to be on the field to know exactly what you need.
This may change in the future. The decision process will be increasingly assisted by self- optimising and knowledgeable manufacturing systems. The “smart factory” will be equipped with
cyber-physical systems which
enable the communication between humans, machines and products alike. As they are able to acquire and process the data, they can self- control certain parts and interact with humans via an interface. Let’s go further into details.
In the Iron making industry, the blast furnace (BF) is the major equipment that requires significant refractory maintenance on a daily basis. Although blast furnaces have existed for centuries, it is still a grey area for the operations
September 2018 Issue
& maintenance teams when it comes to inner refractory lining systems. It is nearly impossible to predict the wear & tear of inner refractory lining without shutting down the furnace.
Over the last decade, the BF lifetime has increased successively thanks to modern stave coolers, improved lining concepts & innovative refractory lining maintenance such as Stack gunning or shotcrete (where a pod is inserted inside the blast furnace through the hatch door & is controlled remotely, the temperature remaining very high inside the blast furnace). Combining these repair
an automation process makes it one of the quickest & most effective methods for prolonging the life of a blast furnace, because the repair refractory mixes can be applied very precisely on worn areas.
A smart maintenance concept can help to improve refractory efficiency. This results in higher service life, higher hot metal production and more flexibility for plant maintenance at reasonable refractory costs.
Cyber Physical System (CPS) will
The term CPS refers to the new generation of systems with integrated computational and physical capabilities that can interact with humans through new modalities. In the future, CPS will completely transform the interaction of a blast furnace system, just like the birth of Internet disrupted the way people interact with information.
CPS will improve blast furnace productivity by reducing downtime through smart prognostic and diagnostic using big data from different networked sensors, machines and systems. Each machine can predict and prevent potential
ENGINEER THE REFRACTORIES
evaluation, the gunning map could be defined on the user interface and then the shotcrete pod could apply the correct repair material automatically, at the right place with the ideal amount. The shotcrete machine can be equipped with an advanced water mixing system, allowing it to decide on the amount of water required to prepare a homogeneous mix for effective repair.
Integrating Thermal Imaging with CPS: If a thermal imaging system continuously scans the blast furnace shell, it could detect the rise in temperature that triggers the grouting pump to push grouting material through the nipples surrounding the reported area. Losing heat through the blast furnace shell may affect the overall thermal load, disturb the skull formation & increase the fuel rate. A quick action taken by CPS will not only prevent loss of heat energy but also save coke or fuel.
In a nutshell, AI and machine learning are the backbones of Industry 4.0. The deployment of cutting-edge AI and machine learning technology will lead to massive disruption in
refractory lining maintenance. systems, in
technological advances in the manufacturing industry paved the way for a systematical deployment of cyber-physical
which information from connected equipment will be closely monitored and synchronized between the physical blast furnace and cyber computational space. Cyber-physical systems are expected to play a major role in the design and development of future
systems with new capabilities that far exceed today’s level of automation, functionality and reliability.
| Page 2
| Page 3
| Page 4
| Page 5
| Page 6
| Page 7
| Page 8
| Page 9
| Page 10
| Page 11
| Page 12
| Page 13
| Page 14
| Page 15
| Page 16
| Page 17
| Page 18
| Page 19
| Page 20
| Page 21
| Page 22
| Page 23
| Page 24
| Page 25
| Page 26
| Page 27
| Page 28
| Page 29
| Page 30
| Page 31
| Page 32