Beyond Mining pitch deck presentation (EN)

Pitch deck of Beyond Mining startup.

1. AI for miners made by miners

2. Summary
We are a Brazilian
Mining tech. We
were born on
November 2019.
Mining tech
The mining
operation is well
monitored, this
generates a lot of
data that is not used
to the full.
Underutilized data
We use AI to address
this geodata.
Artificial
Intelligence

3. 450%
2050
There will be an increase
of production of critical
minerals
fonte: World Bank Group
green future+
mining
+

4. big data
The mining industry has a lot of
specific processes and they are
well monitored, this generates a
big data.
Mining sector

5. Problem
The geodata is mostly used to
look at the past of the
operation generating
data
underutilization

6. Consequences
productivity
loss
accidents
and death
waste of
time
unnecessary
cost increase
and expenses

8. Merging 10 years of R&D
and mine experience, in
2019 Beyond Mining and
GAIA were born.

9. GAIA is a single machine
learning algorithm, with
industrial property registered. It
is capable of adapting to the
many different processes along
the production chain,
generating a specific trained
model for the focused geodata.

10. GAIA’s unique algorithm
brings high scalability in an
extremely diverse
production chain but with a
common point: a set of
intricate geodata.

11. end-to-end production chain
Drilling and
blasting
Vibration, noise
and dust
geotechnics
Blending,
processing and
metallurgy

12. GAIA, the mining industry artificial
intelligence, uses it as an input to
obtain hidden insights, patterns,
simulations, optimizations and
predictions to the mining operation.
The operational geodata is
our source

13. GAIA’s “gold” are the
mathematical abstractions
combined with specific
knowledge of geodata
and its intrinsic statistical
uncertainty and nuances.

14. prediction of sound level

15. prediction of sound level
Based on climate monitoring and fleet movement geodata, GAIA
predicts the noise level produced by the operation, and also
separates the background noise.

16. optimization of calcination

17. optimization of calcination
Based on ore quality data, fuels and process setup parameters,
GAIA combines the optimization of the raw material blend with the
prediction of emissions.

18. grinding mill modelling and simulation

19. grinding mill modelling and simulation
Based on geodata on ore quality, slurry and process parameters,
GAIA predicts the degree of filling and wear of the inner coat of
ball mills.

20. sinter FeO performance prediction

21. sinter FeO performance prediction
Based on ore quality data, fluxes and process setup parameters,
GAIA predicts the metallurgical performance of the sinter feed.

22. fragmentation modelling

23. fragmentation modelling
Based on rock blasting design and rock mass properties, GAIA
predicts the fragmentation and optimizes the blast pattern design.

24. multi-blending optimization

25. multi-blending optimization
Based on the chemical properties of the different types of
available ores, combined with granulometric parameters, handling
and product quality target, GAIA optimizes the blend and predicts
the propagation of variability and estimation error along the
process.

26. flotation optimization

27. flotation optimization
Based on geodata on ore quality, slurry, process setup and reagent
dosage, GAIA predicts the final under and overflow levels, in
addition to mass and metallurgical recovery in the froth flotation
process.

28. TML modelling and prediction

29. TML modelling and prediction
Based on ore chemical properties, granulometry, handling and
process setup geodata, GAIA predicts the TML of the final blend,
with the ability to optimize the blend in order to meet TML
restrictions.

30. ore weight modelling and prediction

31. ore weight modelling and prediction
Based on the chemical properties of the different types of
available ores, combined with granulometric and handling
parameters, GAIA predicts the final weight of ore shipments on rail
cars for each product type and specification.

32. sintering process optimization

33. sintering process optimization
Based on the chemical properties of the different types of
available ores, combined with granulometric parameters, and
sintering process setup, GAIA optimizes the blend and improves
the performance of sintering process.

34. grind mill operations
increase of 2 million tons of ore per year
Economy of 100 hours of
maintenance
some
results
comminution circuits
increase of productivity in transport
Reduction of 3% of energy
consumption
compared to 2-3 days laboratory tests
improved iron ore metallurgical
performance
instant predictive analysis

35. GAIA is the AI for
miners.

36. Main Clients

37. Partners

38. Artificial Intelligence.
For miners. By miners.

39. Useful links
Proof of concepts presentations
DemoDay - M-Start Ciclo 3 - Anglo American
DemoDay - M-Start Ciclo 4 - Anglo American
DemoDay - M-Start Ciclo 5 - AngloGold Ashanti
DemoDay - M-Start Ciclo 7 - Samarco
DemoDay - M-Spot Ciclo 1 - Vale
DemoDay - M-Spot Ciclo 2 - Vale

40. 12° Workshop OPEX 2021 - Magazine “Minérios & Minerales” - Prediction of
Sound Level Pressure
IMXP2020 - Innovation and Data Science in Rock Blasting
Website “Notícias de mineração” AI in Rock Blasting
Pitch e-mineração IBRAM
LinkedIn Post UK Consulate BM and Imperial College partnership
LinkedIn Post Magazine “Minérios e Minerales”

Third party content about Beyond Mining

41. thank you!
[email protected]
[phone]
More about us!
??????