Machine learning-based failure mode identification of RCSPSW

2021 ◽  
Author(s):  
Dongqi Jiang ◽  
Shanquan Liu ◽  
Tao Chen ◽  
Gang Bi
Keyword(s):  
Machine Learning ◽  
Failure Mode ◽  
Failure Modes ◽  
Shear Failure ◽  
Tall Buildings ◽  
Shear Walls ◽  
Superior Performance ◽  
Ann Model ◽  
Mode Recognition ◽  
Wide Range

<p>Reinforced concrete – steel plate composite shear walls (RCSPSW) have attracted great interests in the construction of tall buildings. From the perspective of life-cycle maintenance, the failure mode recognition is critical in determining the post-earthquake recovery strategies. This paper presents a comprehensive study on a wide range of existing experimental tests and develops a unique library of 17 parameters that affects RCSPSW’s failure modes. A total of 127 specimens are compiled and three types of failure modes are considered: flexure, shear and flexure-shear failure modes. Various machine learning (ML) techniques such as decision trees, random forests (RF), <i>K</i>-nearest neighbours and artificial neural network (ANN) are adopted to identify the failure mode of RCSPSW. RF and ANN algorithm show superior performance as compared to other ML approaches. In Particular, ANN model with one hidden layer and 10 neurons is sufficient for failure mode recognition of RCSPSW.</p>

scholarly journals Experimental Study on the Cyclic Performance of Reinforced Concrete Shear Walls Exposed to Fire

2020 ◽  
Vol 14 (1) ◽  
Author(s):  
Eunmi Ryu ◽  
Heesun Kim ◽  
Yeongsoo Shin
Keyword(s):  
Temperature Distribution ◽  
Aspect Ratio ◽  
Failure Mode ◽  
Failure Modes ◽  
Shear Walls ◽  
Lateral Loads ◽  
Cyclic Performance ◽  
Concrete Wall ◽  
Aspect Ratios ◽  
Heated Area

AbstractThe purpose of this study was to investigate the thermal and cyclic behaviors of fire-damaged walls designed with different failure modes, aspect ratios and heated areas. These cyclic behaviors include temperature distribution, maximum lateral load, stiffness, ductility, and energy dissipations, etc. Toward this goal, the concrete wall specimens were exposed to heat following an ISO 834 standard time–temperature curve and the cyclic loading was applied to the fire-damaged walls. The test results showed that exposure to fire significantly reduced the cyclic performance of the RC walls. Especially, it was observed that heated area, designed failure mode, and aspect ratio have influences on maximum lateral loads, stiffness, and ductility of the fire-damaged walls, while almost no effects of the heated area, designed failure mode, and aspect ratio on temperature distribution and energy dissipation were found.

Combustion Tuning for a Gas Turbine Power Plant Using Data-Driven and Machine Learning Approach

2021 ◽  
Vol 143 (3) ◽  
Author(s):  
Suhui Li ◽  
Huaxin Zhu ◽  
Min Zhu ◽  
Gang Zhao ◽  
Xiaofeng Wei
Keyword(s):  
Machine Learning ◽  
Power Plant ◽  
Gas Turbine ◽  
Operating Conditions ◽  
Data Driven ◽  
Ann Model ◽  
Promising Alternative ◽  
Combustion Performance ◽  
Wide Range ◽  
Gas Turbine Power Plant

Abstract Conventional physics-based or experimental-based approaches for gas turbine combustion tuning are time consuming and cost intensive. Recent advances in data analytics provide an alternative method. In this paper, we present a cross-disciplinary study on the combustion tuning of an F-class gas turbine that combines machine learning with physics understanding. An artificial-neural-network-based (ANN) model is developed to predict the combustion performance (outputs), including NOx emissions, combustion dynamics, combustor vibrational acceleration, and turbine exhaust temperature. The inputs of the ANN model are identified by analyzing the key operating variables that impact the combustion performance, such as the pilot and the premixed fuel flow, and the inlet guide vane angle. The ANN model is trained by field data from an F-class gas turbine power plant. The trained model is able to describe the combustion performance at an acceptable accuracy in a wide range of operating conditions. In combination with the genetic algorithm, the model is applied to optimize the combustion performance of the gas turbine. Results demonstrate that the data-driven method offers a promising alternative for combustion tuning at a low cost and fast turn-around.

Experimental investigation and modeling of dynamic thermomechanical behavior of 4-harness satin weave carbon/epoxy composites

2017 ◽  
Vol 31 (9) ◽  
pp. 1181-1203 ◽  
Author(s):  
Xueyao Hu ◽  
Hui Guo ◽  
Weiguo Guo ◽  
Feng Xu ◽  
Longyang Chen ◽  
...  
Keyword(s):  
Mechanical Properties ◽  
Strain Rate ◽  
Composite Laminates ◽  
Failure Modes ◽  
Shear Failure ◽  
Experimental Studies ◽  
Temperature Shift ◽  
Thermomechanical Coupling ◽  
Longitudinal Splitting ◽  
Wide Range

Theoretical and experimental studies on the compressive mechanical behavior of 4-harness satin weave carbon/epoxy composite laminates under in-plane loading are conducted over the temperature range of 298–473 K and the strain rate range of 0.001–1700/s in this article. The stress–strain curves of 4-harness satin weave composites are obtained at different strain rates and temperatures, and key mechanical properties of the material are determined. The deformation mechanism and failure morphology of the samples are observed and analyzed by scanning electron microscope (SEM) micrographs. The results show that the uniaxial compressive mechanical properties of 4-harness satin weave composites are strongly dependent on the temperature but are weakly sensitive to strain rate. The peak stress and elastic modulus of the material have the trend of decrease with the increasing of temperature, and the decreasing trend can be expressed as the functional relationship of temperature shift factor. In addition, SEM observations show that the quasi-static failure mode of 4-harness satin weave composites is shear failure along the diagonal lines of the specimens, while the dynamic failure modes of the material are multiple delaminations and longitudinal splitting, and with the increasing of temperature, its longitudinal splitting is more serious, but the delamination is relatively reduced. A constitutive model with thermomechanical coupling effects is proposed based on the experimental results and the increment theory of elastic–plastic mechanics. The experimental verification and numerical analysis show that the model is shown to be able to predict the finite deformation behavior of 4-harness satin weave composites over a wide range of temperatures.

Analysis of seismic performance and research of load capacity of steel reinforced high strength concrete columns with rectangular helical hoops

2020 ◽  
pp. 136943322098165
Author(s):  
Jianyang Xue ◽  
Xin Zhang ◽  
Xiaojun Ke
Keyword(s):  
Failure Mode ◽  
Seismic Performance ◽  
Calculation Method ◽  
High Strength Concrete ◽  
Failure Modes ◽  
Shear Failure ◽  
High Strength ◽  
Shear Capacity ◽  
Strength Concrete ◽  
Shear Span

This paper mainly focused on the seismic performance and shear calculation method of steel reinforced high-strength concrete (SRHC) columns with rectangular helical hoops. An experimental investigation was performed in this paper. Eleven SRHC columns with rectangular helical hoops and one with ordinary hoops were constructed at the laboratory of Guangxi university. The failure modes, hysteresis loops, envelope curves, characteristic loads and displacements and cumulative damage analysis are presented and investigated. It can be seen from the test results that the failure modes of SRHC columns can be divided into three types with the shear span ratio increased, namely, shear baroclinic failure mode, flexure-shear failure mode and flexure failure mode. In addition, the specimens with rectangular helical hoops have plumper hysteretic loops. Shear span ratio is the main influencing factor of characteristic load; the axial compression ratio and concrete strength have less influence on characteristic load, while stirrup ratio has little effect on the characteristic load. Finally, a calculation method for shear capacity of SRHC columns under shear baroclinic failure and flexure-shear failure mode is proposed.

Dynamic Response and Failure Mode Analysis on Light-Weight Steel Columns under Blast Loads

2012 ◽  
Vol 166-169 ◽  
pp. 1489-1497 ◽  
Author(s):  
Shi Yan ◽  
Lei Liu ◽  
Peng Li ◽  
Zhi Qiang Xin ◽  
Bao Xin Qi
Keyword(s):  
Dynamic Response ◽  
Failure Mode ◽  
Failure Modes ◽  
Shear Failure ◽  
Mode Analysis ◽  
Material Strength ◽  
Light Weight ◽  
Blast Loads ◽  
Element Analysis ◽  
Steel Columns

The dynamic response and failure mode of light-weight steel columns under blast loads were studied in this paper by using nonlinear finite element analysis (FEA) software ANSYS/ LS-DYNA, aiming to develop the degree and modes of the excessive plastic deformation during failures of the columns under diverse parameters. The damaged columns with initial blast-induced deformation may evidently influence vertical stability of light-weight steel frame structures. During the numerical simulation, the element of three dimensional solid SOLID164 was used, and the strain rate effect on material strength was included in the material model with Plastic-Kinematic (MAT-03). The main parameters included in the analysis were boundary conditions, scaled distances of explosions, and the vertical compressive load ratios applied on tops of the columns. The results showed that the column with both two fixed ends was the most beneficial to resist blast shock wave, the horizontal displacement at the middle span of the columns were obviously decreasing as increasing of the scaled distances of the explosion, and the axial compression ratio only significantly influenced the column with a sliding end. The failure modes of the developed columns may be summarized as bending failure, direct shear failure, and bending shear combination failure.

scholarly journals Experimental Study of the Mechanical Characteristics of a Rock-Like Material Containing a Preexisting Fissure under Loading and Unloading Triaxial Compression

2020 ◽  
Vol 2020 ◽  
pp. 1-12 ◽  
Author(s):  
Taoli Xiao ◽  
Mei Huang ◽  
Min Gao
Keyword(s):  
Experimental Study ◽  
Failure Mode ◽  
Mechanical Characteristics ◽  
Failure Modes ◽  
Shear Failure ◽  
Triaxial Compression ◽  
Tensile Failure ◽  
Underground Engineering ◽  
Inclination Angles ◽  
Loading And Unloading

An experimental study of a rock-like material containing a preexisting fissure subjected to loading and unloading triaxial compression is carried out, and the results show that the mechanical characteristics of the rock-like specimen depend heavily on the loading paths and the inclination of the fissure. The triaxial loading experiment results show that the failure strength linearly increases, while the residual strength linearly decreases with increasing inclination. Furthermore, specimens subjected to triaxial compression show an “X”-type shear failure mode. The triaxial unloading compression experimental results show that specimens with different inclination angles have various failure modes. Specimens with gentle inclinations show a tensile-shear mix failure mode, specimens with middle inclinations show a shear-sliding failure mode, and specimens with steep inclinations show a tensile failure mode. These findings can be used to forecast excavation-induced instabilities in deep underground engineering rock structures.

Combustion Tuning for a Gas Turbine Power Plant Using Data-Driven and Machine Learning Approach

2020 ◽  
Author(s):  
Suhui Li ◽  
Huaxin Zhu ◽  
Min Zhu ◽  
Gang Zhao ◽  
Xiaofeng Wei
Keyword(s):  
Machine Learning ◽  
Power Plant ◽  
Gas Turbine ◽  
Operating Conditions ◽  
Data Driven ◽  
Ann Model ◽  
Promising Alternative ◽  
Combustion Performance ◽  
Wide Range ◽  
Gas Turbine Power Plant

Abstract In this paper, we present a cross-disciplinary study on the combustion tuning of an F-class gas turbine that combines machine learning with physics understanding. An artificial-neural-network-based (ANN) model is developed to predict the combustion performance (outputs), including NOx emissions, combustion dynamics, combustor acceleration, and turbine exhaust temperature. The inputs of the ANN model are identified by analyzing the key operating variables that impact the combustion performance, such as the pilot and the premixed fuel flow, and the inlet guide vane angle. The ANN model is trained by field data from an F-class gas turbine power plant. The trained model is able to describe the combustion performance at an acceptable accuracy in a wide range of operating conditions. In combination with the genetic algorithm, the model is applied to optimize the combustion performance of the gas turbine. Results demonstrate that the data-driven method offers a promising alternative for combustion tuning at a low cost and fast turn-around.

Load and Geometry Effect on Failure Mode Initiation of Composite Sandwich Beams

2006 ◽  
Vol 3-4 ◽  
pp. 173-178
Author(s):  
E.E. Gdoutos ◽  
M.S. Konsta-Gdoutos
Keyword(s):  
Failure Mode ◽  
Failure Modes ◽  
Shear Failure ◽  
Sandwich Beams ◽  
Compressive Failure ◽  
Honeycomb Core ◽  
Composite Sandwich ◽  
Failure Mode Transition ◽  
Aluminum Honeycomb ◽  
Geometrical Dimensions

Facing compressive failure, facing wrinkling and core shear failure are the most commonly encountered failure modes in sandwich beams with facings made of composite materials. The occurrence and sequence of these failure modes depends on the geometrical dimensions, the form of loading and type of support of the beam. In this paper the above three failure modes in sandwich beams with facings made of carbon/epoxy composites and cores made of aluminum honeycomb and two types of foam have been investigated. Two types of beams, the simply supported and the cantilever have been considered. Loading included concentrated and uniform. It was found that in beams with foam core facing wrinkling and core shear failure occur, whereas in beams with honeycomb core facing compressive failure and core shear crimping take place. Results were obtained for the dependence of failure mode on the geometry of the beam and the type of loading. The critical beam spans for failure mode transition from core shear to wrinkling failure were established. It was found that initiation of a particular failure mode depends on the properties of the facing and core materials, the geometrical configuration and loading of composite sandwich beams.

Experimental Investigation on Compressive Properties for 3D Four-Directional Braided Composites

2010 ◽  
Vol 160-162 ◽  
pp. 1744-1748 ◽  
Author(s):  
Bao Lai Wang ◽  
Zhen Qing Wang ◽  
Guo Dong Fang ◽  
Jun Liang ◽  
Li Min Zhou
Keyword(s):  
Experimental Investigation ◽  
Compressive Stress ◽  
Failure Mode ◽  
Epoxy Matrix ◽  
Failure Modes ◽  
Shear Failure ◽  
Shear Direction ◽  
Compressive Properties ◽  
Braided Composites ◽  
Stress Strain

Based on changing the braid angle and geometrical sizes, the compressive experiment of 3D braided four-directional Carbon/Epoxy braided composites is researched. It is found that failure of the braided composites exhibits compressive and shear failure mode. The failure crack propagates mainly in one or two 45º shear direction. Epoxy matrix among braid yarns of the braided composites is squeezed out to form epoxy band. The stress-strain relations of the braided composites with 45º and 30º braid angles all appear nonlinear apparently. Meanwhile the correlation of failure modes and constitutive relation with geometrical sizes of the braided composites is obtained. The compressive stress-strain relations of the braided composites are not great affected by the geometrical sizes. The compressive strengths with great discrete behaviors do not have obvious rules with height of the braided composites.

Sign in / Sign up

Export Citation Format

Share Document