Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods

Farshid Farrokhi; Sepideh Rahimi

Open Access

Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods

Farshid Farrokhi

and

Sepideh Rahimi

| Sep 30, 2020

Studia Geotechnica et Mechanica

Volume 42 (2020): Issue 3 (September 2020)

About this article

Cite

Published Online: Sep 30, 2020

Page range: 179 - 190

Received: May 28, 2019

Accepted: Jan 21, 2020

DOI: https://doi.org/10.2478/sgem-2019-0043

Keywords
Failure analysis, supervised machine learning, feature selection, tuned mass damper

© 2020 Farshid Farrokhi et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

IDA analysis of the (a,b) first, (c,d) fifth, (e,f) tenth, (g,h) fifteenth, and (i,j) twentieth story of the 20-story structure (a,c,e,g,i) not equipped with TMD, and (b,d,f,h,j) equipped with TMD

Characteristics of the structure.

Feature	Value
Height of structure (m)	60
Period of structure (s)	1.7247
Coefficient of reflection	0.9023
Coefficient of importance	1
Coefficient of behavior	7.5
Acceleration scheme	0.35
Coefficient of earthquake	0.0421

Performance evaluation of different models in prediction of the story drifts (parameters of each model are demonstrated in the text).

Regression model	Parameters	Normalized MSE		R²

		Train	Test	Train	Test
k-NN	k = 1	0.036	0.049	0.932	0.855
	k = 2	0.036	0.050	0.932	0.849
	k = 3	0.040	0.053	0.912	0.830
	k = 4	0.049	0.068	0.863	0.725
	k = 5	0.045	0.066	0.886	0.740
DT	type = ID3	0.022	0.038	0.988	0.918
	type = C4.5	0.020	0.033	0.994	0.942
	type = CART	0.025	0.042	0.978	0.896
	type = CHAID	0.043	0.060	0.897	0.783
	type = MARS	0.049	0.056	0.863	0.810
RF	-	0.033	0.048	0.946	0.862
ANN	hidden layer size = 2	0.050	0.066	0.857	0.740
	hidden layer size = 4	0.040	0.059	0.912	0.790
	hidden layer size = 6	0.039	0.054	0.917	0.824
	hidden layer size = 8	0.046	0.070	0.880	0.710
	hidden layer size = 10	0.039	0.052	0.917	0.837
	hidden layer size = 12	0.030	0.049	0.959	0.855
	hidden layer size = 14	0.037	0.058	0.927	0.797
	hidden layer size = 16	0.042	0.061	0.902	0.776
	hidden layer size = 18	0.051	0.067	0.851	0.732
	hidden layer size = 20	0.050	0.058	0.857	0.797
SVM	kernel type = linear, C = 10	0.019	0.029	0.998	0.960
	kernel type = linear, C = 20	0.022	0.031	0.988	0.951
	kernel type = linear, C = 30	0.021	0.035	0.991	0.933
	kernel type = Gaussian, C = 10	0.018	0.026	0.995	0.972
	kernel type = Gaussian, C = 20	0.017	0.025	0.995	0.976
	kernel type = Gaussian, C = 30	0.008	0.010	0.999	0.993
	kernel type = RBF, C = 10	0.030	0.038	0.959	0.918
	kernel type = RBF, C = 20	0.028	0.046	0.966	0.873
	kernel type = RBF, C = 30	0.029	0.046	0.962	0.873
NB	-	0.041	0.063	0.907	0.762

Results of feature selection for sensitivity analysis of seismic and structural uncertainties.

Story	Seismic uncertainty				Structural uncertainty

	Relieff	t-test	SFS	CSC	Relieff	t-test	SFS	CSC
1	0.44	0.51	0.50	0.68	0.23	0.30	0.29	0.11
5	0.53	0.60	0.52	0.69	0.44	0.35	0.45	0.32
10	0.85	1.00	0.76	0.82	0.70	0.59	0.71	0.77
15	1.00	0.95	1.00	1.00	0.73	0.86	0.80	0.83
20	0.84	0.81	0.79	0.78	0.70	0.79	0.74	0.79

Studied earthquake records and their characteristics.

Event	Year	Magnitude	Radius (km)	Station
Cape Mendocino	1992	7.1	23.6	Fortuna – Fortuna Blvd
Cape Mendocino	1992	7.1	18.5	Rio Dell Overpass – FF
Duzce	1999	7.1	15.6	Lamont
Northridge	1994	6.7	23.9	N Faring Rd
Northridge	1994	6.7	29.5	N Fletcher Dr
Loma Prieta	1989	6.9	19.9	Gilory Array #6
Loma Prieta	1989	6.9	21.4	Anderson Dam (Downst)
Loma Prieta	1989	6.9	21.4	Anderson Dam (Abut)
Loma Prieta	1989	6.9	22.3	Coyote Lake Dam
Northridge	1994	6.7	22.6	Castaic – Old Ridge Route
Northridge	1994	6.7	31.3	LA – Baldwin Hills
Northridge	1994	6.7	20.8	Beverly Hills – 12520 Mulhol
Northridge	1994	6.7	24.0	Big Tujunga, Angeles Nat F
Northridge	1994	6.7	25.7	LA – Century City C C North
Northridge	1994	6.7	23.7	LA – Chalon Rd
Northridge	1994	6.7	17.7	Sunland – Mt Gleason Ave
Northridge	1994	6.7	20.0	Burbank – Howard Rd
Northridge	1994	6.7	25.7	Hollywood – Willoughby A
Northridge	1994	6.7	24.5	Vasquez Rocks Park
San Fernando	1971	6.6	24.9	Castaic – Old Ridge Route

Dead and dynamic loads of stories and roofs.

	Dead load (kg.m⁻²)	Dynamic load (kg.m⁻²)
Stories	1250	500
Roof	1125	375

eISSN:: 2083-831X
Language:: English

Publication timeframe:: 4 times per year
Journal Subjects:: Geosciences, other, Materials Sciences, Composites, Porous Materials, Physics, Mechanics and Fluid Dynamics

Journal RSS Feed

Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods

Article Category: Research Article

Published Online: Sep 30, 2020

Page range: 179 - 190

Received: May 28, 2019

Accepted: Jan 21, 2020

DOI: https://doi.org/10.2478/sgem-2019-0043

Keywords
Failure analysis, supervised machine learning, feature selection, tuned mass damper

© 2020 Farshid Farrokhi et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1

Figure 2

Figure 3

Characteristics of the structure.

Performance evaluation of different models in prediction of the story drifts (parameters of each model are demonstrated in the text).

Results of feature selection for sensitivity analysis of seismic and structural uncertainties.

Studied earthquake records and their characteristics.

Dead and dynamic loads of stories and roofs.

Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods

Article Category: Research Article

Published Online: Sep 30, 2020

Page range: 179 - 190

Received: May 28, 2019

Accepted: Jan 21, 2020

DOI: https://doi.org/10.2478/sgem-2019-0043

KeywordsFailure analysis, supervised machine learning, feature selection, tuned mass damper

© 2020 Farshid Farrokhi et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1

Figure 2

Figure 3

Characteristics of the structure.

Performance evaluation of different models in prediction of the story drifts (parameters of each model are demonstrated in the text).

Results of feature selection for sensitivity analysis of seismic and structural uncertainties.

Studied earthquake records and their characteristics.

Dead and dynamic loads of stories and roofs.

Keywords
Failure analysis, supervised machine learning, feature selection, tuned mass damper