STEEL GRADES INCLUDED IN THE BENCHMARKING
214Cr-1Mo
(Energy)
C
Mn
Si
Cr
Ni
Mo
V
Co
Al
W
0,069
0,86
0,24
1,46
0
1,29
0
0
0
0
Cu
Nb
Ti
N
B
P
S
Sn
Zr
As
0
0
0
0
0
0,02
0
0
0
0
Carbide free bainitic steel
(Rails)
C
Mn
Si
Cr
Ni
Mo
V
Co
Al
W
0,18
0,36
1,2
1,4
0
0,49
0
0
0
0
Cu
Nb
Ti
N
B
P
S
Sn
Zr
As
0
0
0
0
0
0,027
0,011
0
0
0
Carbide free bainitic steel
(Rails)
C
Mn
Si
Cr
Ni
Mo
V
Co
Al
W
0,23
1,52
1,48
1,2
0,85
0,35
0
0
0
0
Cu
Nb
Ti
N
B
P
S
Sn
Zr
As
0
0
0
0
0
0,024
0,01
0
0
0
22MnB5
(Machinery)
C
Mn
Si
Cr
Ni
Mo
V
Co
Al
W
0,25
1,5
0,4
0,3
0
0
0
0
0
0
Cu
Nb
Ti
N
B
P
S
Sn
Zr
As
0
0
0,05
0,01
0,005
0,024
0,01
0
0
0
32CrB4
C
Mn
Si
Cr
Ni
Mo
V
Co
Al
W
0,34
0,9
0,3
1,2
0
0
0
0
0
0
Cu
Nb
Ti
N
B
P
S
Sn
Zr
As
0
0
0
0
0
0,025
0,025
0
0
0
DP 1000
C
Mn
Si
Cr
Ni
Mo
V
Co
Al
W
0,15
1,5
0,5
0
0
0
0
0
0
0
Cu
Nb
Ti
N
B
P
S
Sn
Zr
As
0
0
0
0
0
0,015
0,002
0
0
0
Low C high strength
C
Mn
Si
Cr
Ni
Mo
V
Co
Al
W
0,15
1,58
0,55
0,02
0,01
0
0
0
0
0
Cu
Nb
Ti
N
B
P
S
Sn
Zr
As
0
0,033
0
0
0
0,03
0,007
0
0
0
CCT SIMULATION
Machine learning based prediction of continuous cooling transformations in steels.
We are happy to provide the market with improved CCT simulation capabilities and to support additional CCT data use cases as the simulation accuracy has significantly improved compared to conventional tools.
The Ferritico CCT module is consumed as a SaaS where the CCT data is presented in a CCT diagram or in a aggregated data file.
Input:
-
Alloy composition
-
Austenitization temperature and time or grain size
-
Cooling rates
Output:
-
What phases are formed and their corresponding on- and offset temperatures
-
Phase fraction at room temperature
BENCHMARKING REPORT
The Ferritico CCT module simulation accuracy has been benchmarked through comparisons to empirical CCT measurements based on either Jominy or Dilatometer. The benchmark includes comparisons on phase formations and on- and offset temperatures but not phase fractions since the benchmarked diagrams did not include the fraction information. The benchmarking report below also compares the Ferritico simulation accuracy with market leading simulation software built on physical models.
Phase formation
The aggregated average percentage error for simulation of whether the phases Ferrite, Pearlite, Bainite and Martensite are formed. The benchmark is based on empirically measured CCT diagrams for 14 steel grades (some chemical compositions listed below) that are not included in the machine learning database and where benchmarking CCT data is available for 8-12 cooling rates.
Ferritico %-error
Ferrite
Pearlite
Bainite
Martensite
8.1 %
18.9 %
23.4 %
22.5 %
Competitor %-error
20.7 %
27.0 %
27.9 %
27.0 %
Phase transformation temperatures
The aggregated average error for simulation of the temperatures on which transformation of the phases Ferrite, Pearlite, Bainite and Martensite are starting and finishing respectively. The benchmark is based on empirically measured CCT diagrams for 14 steel grades (some chemical compositions listed below) that are not included in the machine learning database and where benchmarking CCT data is available for 8-12 cooling rates. In the table, _s and _f refer to the start and finish temperature of the transformation of a phase, e.g. Fe_s being Ferrite start temperature.
Ferritico error
Fe_s
Fe_f
P_s
P_f
B_s
B_f
M_s
34.9 °C
45.7 °C
28.4 °C
55.2 °C
53.6 °C
40.1 °C
39.6 °C
Competitor error
49.0 °C
77.5 °C
68.0 °C
117.1 °C
74.3 °C
93.4 °C
47.8 °C