scholarly journals Evaluation of Tensile Performance of Steel Members by Analysis of Corroded Steel Surface Using Deep Learning

Metals ◽  
2019 ◽  
Vol 9 (12) ◽  
pp. 1259 ◽  
Author(s):  
Pang-jo Chun ◽  
Tatsuro Yamane ◽  
Shota Izumi ◽  
Toshihiro Kameda
Keyword(s):  
Deep Learning ◽  
Domain Knowledge ◽  
Steel Structures ◽  
Shell Element ◽  
Effective Thickness ◽  
Steel Plates ◽  
Structural Members ◽  
Steel Members ◽  
High Level ◽  
The Cost

To conduct safety checks of corroded steel structures and formulate appropriate maintenance strategies, the residual strength of steel structural members must be assessed with high accuracy. Finite element method (FEM) analyses that precisely recreate the morphology of corroded surfaces using solid elements are expected to accurately assess the strength; however, the cost of conducting these calculations is extremely high. Therefore, a model that uses mean thickness as the thickness of the shell element is widely used but this method has precision issues, particularly regarding overestimation of risk. Thus, this study proposes a method of structural analysis in which the effective thickness of a shell element is assessed using the convolutional neural network (CNN), a type of deep learning performed on tensile structural members. An FEM model is then built based on the shell element that uses this effective thickness. We cross-validated this method by adding a feature extraction layer that reflects the domain knowledge, together with convolutional and pooling layers that are commonly used for CNN and found that a high level of accuracy could be achieved. Furthermore, regarding corroded steel plates and H-section steel, our method demonstrated results that were extremely close to those of models that used solid elements.

scholarly journals Experimental Study on the Behavior of Tension Member Under Rupture

2021 ◽  
Keyword(s):  
Experimental Study ◽  
Tensile Force ◽  
Steel Structure ◽  
Steel Structures ◽  
Structural Members ◽  
Steel Members ◽  
Tension Member ◽  
Strong Relation ◽  
Almost All ◽  
Tension Members

Abstract. A steel structure is naturally lighter than a comparable concrete construction because of the higher strength and firmness of steel. Nowadays, the growth of steel structures in India is enormous. There are so many advantages in adopting the steel as structural members. Almost all high-rise buildings, warehouses & go-downs are steel structures and even some of the commercial buildings are made of steel. Tension members are the elements that are subjected to direct axial load which tends in the elongation of the structural members. Even today bolted connections play a major role in the connection of hot rolled structural steel members. In this experimental study the behavior of tension members (TM) such as plates, angles & channels have been studied under axial tensile force. There is strong relation between pitch and gauge (with in the specified limit as per IS 800:2007) in determining the rupture failure plane. In this study we intensively tested the behaviour of TM for different fasteners pattern by changing the pitch, gauge, end & edge distance and by adopting the different patterns or arrangements of bolted connection in it.

scholarly journals Deep Learning to Detect Skin Cancer using Google Colab

2019 ◽  
Vol 8 (6) ◽  
pp. 2176-2183 ◽  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Skin Cancer ◽  
Domain Knowledge ◽  
Error Rates ◽  
Data Set ◽  
Training Models ◽  
Learning Machine ◽  
High Level

Different mathematical models, Artificial Intelligence approach and Past recorded data set is combined to formulate Machine Learning. Machine Learning uses different learning algorithms for different types of data and has been classified into three types. The advantage of this learning is that it uses Artificial Neural Network and based on the error rates, it adjusts the weights to improve itself in further epochs. But, Machine Learning works well only when the features are defined accurately. Deciding which feature to select needs good domain knowledge which makes Machine Learning developer dependable. The lack of domain knowledge affects the performance. This dependency inspired the invention of Deep Learning. Deep Learning can detect features through self-training models and is able to give better results compared to using Artificial Intelligence or Machine Learning. It uses different functions like ReLU, Gradient Descend and Optimizers, which makes it the best thing available so far. To efficiently apply such optimizers, one should have the knowledge of mathematical computations and convolutions running behind the layers. It also uses different pooling layers to get the features. But these Modern Approaches need high level of computation which requires CPU and GPUs. In case, if, such high computational power, if hardware is not available then one can use Google Colaboratory framework. The Deep Learning Approach is proven to improve the skin cancer detection as demonstrated in this paper. The paper also aims to provide the circumstantial knowledge to the reader of various practices mentioned above.

Fatigue Behavior of Corroded Structural Steel Members in Boundary with Concrete

2007 ◽  
Vol 348-349 ◽  
pp. 245-248
Author(s):  
Shigenobu Kainuma ◽  
Naofumi Hosomi ◽  
In Tae Kim
Keyword(s):  
Fatigue Life ◽  
Stress Concentration ◽  
Structural Steel ◽  
Fatigue Behavior ◽  
Fatigue Tests ◽  
Steel Plates ◽  
Structural Members ◽  
Analytical Results ◽  
Steel Members ◽  
Corrosion Pit

In this research, fatigue tests were carried out to investigate the fatigue behavior of corroded structural members in boundary with concrete. Specimens were corroded by accelerated exposure tests and then used in the fatigue tests. FEM analyses were also performed on the models of the corroded surfaces of the specimens and the simulated corrosion surfaces to investigate the stress concentration at the corrosion pit in the boundary. The experimental and analytical results clarified the fatigue behaviors of corroded steel plates in boundary with concrete. The method for evaluating and predicting the fatigue life of corroded steel members were also proposed.

scholarly journals Surface Rust Detection Using Ultrasonic Waves in a Cylindrical Geometry by Finite Element Simulation

2018 ◽  
Vol 3 (3) ◽  
pp. 29 ◽  
Author(s):  
Qixiang Tang ◽  
Cong Du ◽  
Jie Hu ◽  
Xingwei Wang ◽  
Tzuyang Yu
Keyword(s):  
Finite Element ◽  
Early Stage ◽  
Steel Corrosion ◽  
Steel Structures ◽  
Potential Method ◽  
Ultrasonic Waves ◽  
Steel Plates ◽  
Fiber Optic Sensor ◽  
Surface Corrosion ◽  
Steel Members

Detection of early-stage corrosion on slender steel members is crucial for preventing buckling failures of steel structures. An active photoacoustic fiber optic sensor (FOS) system is reported herein for the early-stage steel corrosion detection of steel plates and rebars using surface ultrasonic waves. The objective of this study is to investigate a potential method for detecting surface corrosion/rust of steel rods using numerically simulated surface ultrasonic waves. The finite element method (FEM) was applied in the simulation of propagating ultrasonic waves on steel rod models. The pitch-catch mode of damage detection was adopted, in which one source (transmitter) and one sensor (receiver) were considered. In this research, radial displacements at the receiver were simulated and analyzed by short-time Fourier transform (STFT) for detecting, locating, and quantifying surface rust located between the transmitter and the receiver. From our time domain and frequency domain analyses, it was found that the presence, location, and dimensions (length, width, and depth) of surface rust can be estimated by ultrasonic wave propagation.

Reuse System of Building Steel Structures - Structural Performance of Reusable Members and Practical Examples

2012 ◽  
Vol 517 ◽  
pp. 513-521 ◽  
Author(s):  
Masanori Fujita
Keyword(s):  
Life Cycle ◽  
Steel Structures ◽  
Structural Member ◽  
Structural Performance ◽  
Structural Members ◽  
Crucial Element ◽  
Environmental Burden ◽  
The Past ◽  
Steel Members ◽  
Reuse System

Longevity, reuse and recycle can be effective in reducing environmental burden in the life cycle of building steel structures. Longevity is the most crucial element in reducing the environmental burden of building steel structures. Nevertheless, there are always a number of buildings that need to be demolished for physical, architectural, economic, and social reasons. When such building steel structures have been demolished in the past, their structural members have been scrapped for recycling. Steel, by nature, is the only type of structural member that can be fabricated. Even without special joints that facilitate demolition work, steel members can be reused after minor fabrication procedures such as cutting, drilling, and welding. In this paper we discuss structural performance of reusable members and practical examples using reusable members.

scholarly journals Surface Rust Detection Using Ultrasonic Waves in a Cylindrical Geometry by Finite Element Simulation

2018 ◽  
Author(s):  
Qixiang Tang ◽  
Cong Du ◽  
Jie Hu ◽  
Xingwei Wang ◽  
Tzuyang Yu
Keyword(s):  
Finite Element ◽  
Early Stage ◽  
Steel Corrosion ◽  
Steel Structures ◽  
Ultrasonic Waves ◽  
Steel Plates ◽  
Surface Corrosion ◽  
Steel Members ◽  
Length Width ◽  
Simulated Surface

Detection of early stage corrosion on slender steel members is crucial for preventing buckling failures of steel structures. An active photoacoustic fiber optic sensors (FOS) system has been reported for early stage steel corrosion detection of steel plates and rebars using surface ultrasonic waves. The objective of this paper is to investigate the surface corrosion/rust detection problem on steel rods using numerically simulated surface ultrasonic waves. The finite element method (FEM) is applied in simulating the propagation of ultrasonic waves on steel rod models. Transmission mode of damage detection is adopted, in which one source (transmitter) and one sensor (receiver) are considered. In this research, radial displacements at the receiver were simulated and analyzed by short-time Fourier transform (STFT) for detecting, locating, and quantifying a surface rust located between the transmitter and the receiver. From our time domain and frequency domain analyses, it is found that the presence, location, and dimensions (length, width, and depth) of surface rust can be estimated by ultrasonic waves propagating through the surface rust.

Reduction of Manufacturing Distortion in Arc Welded Ship Panels Using Thermal Tensioning

2008 ◽  
Vol 24 (04) ◽  
pp. 177-179
Author(s):  
Ruth Sanderson ◽  
Bill Lucas ◽  
Roy Pocock
Keyword(s):  
Arc Welding ◽  
Thermal Stresses ◽  
Welding Process ◽  
Steel Structures ◽  
Steel Plates ◽  
Welded Steel ◽  
Large Structures ◽  
Arc Welding Process ◽  
Thermal Tensioning ◽  
The Cost

Large sheet or thin plate steel structures invariably suffer from distortion especially when fabricated using an arc welding process. The cost of reworking in shipbuilding is high. Low-stress no-distortion (LSND) welding has been demonstrated to effectively prevent distortion. The technique has been show to work well by rapidly cooling the weld with atomized water or liquid CO2 immediately after solidification. However, this can be expensive and difficult to apply in the fabrication of large structures. In this work, only a thermal tensioning technique is presented. The technique controls distortion by applying thermal stresses in front of the weld pool to counteract the stresses induced in the structure by welding. A combination of finite element modeling and experimentation has been used to find a thermal tensioning arrangement that reduces distortion by 50% in 4 mm butt welded steel plates using arc welding.

BEAM-COLUMN RESISTANCE OF STEEL MEMBERS: A COMPARATIVE STUDY OF AISC LRFD AND EC3 APPROACHES

2011 ◽  
Vol 11 (02) ◽  
pp. 345-361 ◽  
Author(s):  
DANNY J. YONG ◽  
AITZIBER LÓPEZ ◽  
MIGUEL A. SERNA
Keyword(s):  
Comparative Study ◽  
Axial Compression ◽  
Steel Structures ◽  
Building Structures ◽  
Structural Members ◽  
Beam Columns ◽  
Steel Members ◽  
Moment Distribution ◽  
European Code ◽  
The Comparative Study

The paper presents a comparative study of a well-established steelwork design standard, the American AISC LRFD, and the new European code for the design of steel structures, Eurocode 3. The study is focused on the resistance capacity of steel members subjected to one of the following load cases: axial compression, bending, and combined axial compression and bending. First, the paper compares the formulation of both codes in order to identify similarities and differences. Particular attention is given to the resistance of beam columns since many steel structural members in building structures fall into this category. In the case of pure bending and combined axial compression and bending, the paper considers two extreme cases of linear moment distribution: equal end moments and opposite end moments. The results are presented graphically in order to make possible their interpretation and to detect significant differences in resistance. The comparative study shows that the resistance capacities given by LRFD and EC3 can differ appreciably for some of the cases considered. Moreover, there are also significant differences between the two methods proposed by the Eurocode when slenderness is high and the beam is subjected to linear moment distribution with opposite end moments. Finally, the paper stresses those points where each standard offers a simpler approach.

Influence of Size and Proximity of Paint Coating Defects on Corrosion Behavior of Carbon Steel Plates

2015 ◽  
Vol 665 ◽  
pp. 125-128 ◽  
Author(s):  
Shigenobu Kainuma ◽  
Young Soo Jeong ◽  
Junji Kobayashi
Keyword(s):  
Corrosion Behavior ◽  
Salt Water ◽  
Steel Structures ◽  
Steel Plates ◽  
Coated Steel ◽  
Wetting And Drying ◽  
Single Defect ◽  
Steel Members ◽  
Water Wetting ◽  
Circular Defect

To ensure the safety of painted steel structures, it is important to evaluate the influence of the size and proximity of coating defects on corrosion behavior. In this research, accelerated exposure tests were carried out using combined corrosion cycles, which consisted of exposure to atomizing salt water, wetting, and drying with hot and warm wind. The test specimens were paint-coated steel plates with individual circular machined coating defects 1, 3, 10, and 15 mm in diameter. Multi-circular defects 1 mm in diameter were also created in the specimens. The test results indicate that the mean and maximum corrosion depths increased with increasing diameter of the single defect of the coated steel plate. When actual coated steel members are exposed to corrosive chloride environments such as those represented by the corrosion cycle testing conducted in this research, the corrosion depth for multi-circular defects 1 mm in diameter appears to be 1.5 to 2.5 times greater than that for a single-circular defect.

Sign in / Sign up

Export Citation Format

Share Document