scholarly journals Artificial Neural Networks in Classification of Steel Grades Based on Non-Destructive Tests

Materials ◽  
2020 ◽  
Vol 13 (11) ◽  
pp. 2445 ◽  
Author(s):  
Alexey Beskopylny ◽  
Alexandr Lyapin ◽  
Hubert Anysz ◽  
Besarion Meskhi ◽  
Andrey Veremeenko ◽  
...  

Assessment of the mechanical properties of structural steels characterizing their strength and deformation parameters is an essential problem in the monitoring of structures that have been in operation for quite a long time. The properties of steel can change under the influence of loads, deformations, or temperatures. There is a problem of express determination of the steel grade used in structures—often met in the practice of civil engineering or machinery manufacturing. The article proposes the use of artificial neural networks for the classification and clustering of steel according to strength characteristics. The experimental studies of the mechanical characteristics of various steel grades were carried out, and a special device was developed for conducting tests by shock indentation of a conical indenter. A technique based on a neural network was built. The developed algorithm allows with average accuracy—over 95%—to attribute the results to the corresponding steel grade.

2022 ◽  
pp. 648-667
Author(s):  
Tuğba Özge Onur ◽  
Yusuf Aytaç Onur

Steel wire ropes are frequently subjected to dynamic reciprocal bending movement over sheaves or drums in cranes, elevators, mine hoists, and aerial ropeways. This kind of movement initiates fatigue damage on the ropes. It is a quite significant case to know bending cycles to failure of rope in service, which is also known as bending over sheave fatigue lifetime. It helps to take precautions in the plant in advance and eliminate catastrophic accidents due to the usage of rope when allowable bending cycles are exceeded. To determine the bending fatigue lifetime of ropes, experimental studies are conducted. However, bending over sheave fatigue testing in laboratory environments require high initial preparation cost and a long time to finalize the experiments. Due to those reasons, this chapter focuses on a novel prediction perspective to the bending over sheave fatigue lifetime of steel wire ropes by means of artificial neural networks.


2018 ◽  
Vol 2018 ◽  
pp. 1-16 ◽  
Author(s):  
Aref M. al-Swaidani ◽  
Waed T. Khwies

Numerous volcanic scoria (VS) cones are found in many places worldwide. Many of them have not yet been investigated, although few of which have been used as a supplementary cementitious material (SCM) for a long time. The use of natural pozzolans as cement replacement could be considered as a common practice in the construction industry due to the related economic, ecologic, and performance benefits. In the current paper, the effect of VS on the properties of concrete was investigated. Twenty-one concrete mixes with three w/b ratios (0.5, 0.6, and 0.7) and seven replacement levels of VS (0%, 10%, 15%, 20%, 25%, 30%, and 35%) were produced. The investigated concrete properties were the compressive strength, the water permeability, and the concrete porosity. Artificial neural networks (ANNs) were used for prediction of the investigated properties. Feed-forward backpropagation neural networks have been used. The ANN models have been established by incorporation of the laboratory experimental data and by properly choosing the network architecture and training processes. This study shows that the use of ANN models provided a more accurate tool to capture the effects of five parameters (cement content, volcanic scoria content, water content, superplasticizer content, and curing time) on the investigated properties. This prediction makes it possible to design VS-based concretes for a desired strength, water impermeability, and porosity at any given age and replacement level. Some correlations between the investigated properties were derived from the analysed data. Furthermore, the sensitivity analysis showed that all studied parameters have a strong effect on the investigated properties. The modification of the microstructure of VS-based cement paste has been observed, as well.


Author(s):  
Fred Kitchens

For hundreds of years, actuaries used pencil and paper to perform their statistical analysis It was a long time before they had the help of a mechanical adding machine. Only recently have they had the benefit of computers. As recently as 1981, computers were not considered important to the process of insurance underwriting. Leading experts in insurance underwriting believed that the judgment factor involved in the underwriting process was too complex for any computer to handle as effectively as a human underwriter (Holtom, 1981). Recent research in the application of technology to the underwriting process has shown that Holtom’s statement may no longer hold true (Gaunt, 1972; Kitchens, 2000; Rose, 1986). The time for computers to take on an important role in the insurance underwriting process may be upon us. The author intends to illustrate the applicability of artificial neural networks to the insurance underwriting process.


Author(s):  
Tuğba Özge Onur ◽  
Yusuf Aytaç Onur

Steel wire ropes are frequently subjected to dynamic reciprocal bending movement over sheaves or drums in cranes, elevators, mine hoists, and aerial ropeways. This kind of movement initiates fatigue damage on the ropes. It is a quite significant case to know bending cycles to failure of rope in service which is also known as bending over sheave fatigue lifetime. It helps to take precaution in the plant in advance and eliminate catastrophic accidents due to usage of rope when allowable bending cycles are exceeded. To determine bending fatigue lifetime of ropes, experimental studies are conducted. However, bending over sheave fatigue testing in laboratory environments require high initial preparation cost and longer time to finalize the experiments. Due to those reasons, this chapter focuses on a novel prediction perspective to the bending over sheave fatigue lifetime of steel wire ropes by means of artificial neural networks.


2021 ◽  
Vol 45 (2) ◽  
pp. 277-285
Author(s):  
A.V. Astafiev ◽  
D.V. Titov ◽  
A.L. Zhiznyakov ◽  
A.A. Demidov

The paper considers the development of a method for positioning a mobile device using a sensor network of BLE-beacons, the approximation of RSSI values and artificial neural networks. The aim of the work is to develop a method for positioning small-scale industrial mechanization equipment for building unmanned systems for product movement tracking. The work is divided into four main parts: data synthesis, signal filtering, selection of BLE beacons, translation of the RSSI values into a distance, and multilateration. A simplified Kalman filter is proposed for filtering the input signal to suppress Gaussian noise. A description of two approaches to translating the RSSI value into a distance is given: an exponential approximation function with a coefficient of determination of 0.6994 and an artificial feedforward neural network. A comparison of the results of these approaches is carried out on several test samples: a training one, a test sample at a known distance (0–50 meters) and a test sample at an unknown distance (60–100 meters). The artificial neural network is shown to perform better in all experiments, except for the test sample at a known distance (0–50 meters), for which the r.m.s. error is higher by 0.02 m 2 than that for the approximation function, which can be neglected. An algorithm for positioning a mobile device based on the multilateration method is proposed. Experimental studies of the developed method have shown that the positioning error does not exceed 0.9 meters in a 5×5.5 m room under monitoring. The positioning accuracy of a mobile device using the proposed method in the experiment is 40.9 % higher. Experimental studies are also conducted in a 58.4×4.5 m room, showing more accurate results compared to similar studies.


2021 ◽  
Vol 63 (6) ◽  
pp. 565-570
Author(s):  
Serkan Balli ◽  
Faruk Sen

Abstract The aim of this work is to identify failure modes of double pinned sandwich composite plates by using artificial neural networks learning algorithms and then analyze their accuracies for identification. Mechanically pinned specimens with two serial pins/bolts for sandwich composite plates were used for recognition of failure modes which were obtained in previous experimental studies. In addition, the empirical data of the preceding work was determined with various geometric parameters for various applied preload moments. In this study, these geometric parameters and fastened/bolted joint forms were used for training by artificial neural networks. Consequently, ten different backpropagation training algorithms of artificial neural network were applied for classification by using one hundred data values containing three geometrical parameters. According to obtained results, it was seen that the Levenberg-Marquardt backpropagation training algorithm was the most successful algorithm with 93 % accuracy rate and it was appropriate for modeling of this problem. Additionally, performances of all backpropagation training algorithms were discussed taking into account accuracy and error ratios.


2010 ◽  
Vol 452-453 ◽  
pp. 733-736
Author(s):  
Su Tae Kang ◽  
Hyun Jin Kang ◽  
Gum Sung Ryu ◽  
Gyung Taek Koh ◽  
Jang Hwa Lee

Bottom ash based alkali-activated mortar is prepared by incorporating sodium hydroxide and sodium silicate with some additional water if needed, and is activated with temperature curing. This research was conducted to derive an optimum mixture design of the bottom ash based alkali-activated mortar. The experimental studies were first performed to estimate the effect of the added water content, alkali activator to bottom ash ratio, sodium silicate to sodium hydroxide ratio as well as curing temperature on workability and strength. In order to optimize the mix proportion, based on the experimental results, artificial neural networks were introduced.


2020 ◽  
Vol 9 (1) ◽  
pp. 41-49
Author(s):  
Johanes Roisa Prabowo ◽  
Rukun Santoso ◽  
Hasbi Yasin

House is one aspect of the welfare of society that must be met, because house is the main need for human life besides clothing and food. The condition of the house as a good shelter can be known from the structure and facilities of buildings. This research aims to analyze the classification of house conditions is livable or not livable. The method used is artificial neural networks (ANN). ANN is a system information processing that has characteristics similar to biological neural networks. In this research the optimization method used is the conjugate gradient algorithm. The data used are data of Survei Sosial Ekonomi Nasional (Susenas) March 2018 Kor Keterangan Perumahan for Cilacap Regency. The data is divided into training data and testing data with the proportion that gives the highest average accuracy is 90% for training data and 10% for testing data. The best architecture obtained a model consisting of 8 neurons in input layer, 10 neurons in hidden layer and 1 neuron in output layer. The activation function used are bipolar sigmoid in the hidden layer and binary sigmoid in the output layer. The results of the analysis showed that ANN works very well for classification on house conditions in Cilacap Regency with an average accuracy of 98.96% at the training stage and 97.58% at the testing stage.Keywords: House, Classification, Artificial Neural Networks, Conjugate Gradient


2019 ◽  
pp. 69-72

Pronóstico de caudales medios mensuales del rio caplina, aplicando redes neuronales artificiales (rna) y modelo autorregresivo periódico de primer orden par (1) Forecast for mean monthly discharge of the caplina river, by applying artificial neural network (rna) and periodic Autoregressive model par (1) Pino Vargas Edwin, Siña Espinoza Luis, Román Arce Carmen Programa de Doctorado en Recursos Hídricos / U.N.Agraria La Molina, Lima Perú, [email protected] Universidad Nacional Jorge Basadre G. Tacna, [email protected] Universidad Nacional Jorge Basadre G. Tacna, [email protected] DOI: https://doi.org/10.33017/RevECIPeru2011.0025/ RESUMEN El rio Caplina es el principal tributario de la cuenca hidrográfica del mismo nombre; tiene una extensión de 4 239,09 km2, esto hace que sea una de las principales fuentes de abastecimiento de agua para distintos usos en la ciudad de Tacna. Por esta razón diversas entidades se han interesado en conocer la disponibilidad hídrica actual y futura del rio Caplina, ya que conocer dichos valores es de fundamental importancia para el planeamiento y manejo de los sistemas de recursos hídricos. Los modelos estocásticos han sido durante largo tiempo, la alternativa más común en la predicción de caudales. Actualmente, las herramientas de computación inteligente como las redes neuronales artificiales, especialmente las redes multi-capas con algoritmo de retro-propagación. En este contexto, la actual investigación centro sus esfuerzos en la aplicación de las redes neuronales a la predicción de los caudales medios mensuales del río Caplina-Estación Bocatoma Calientes, desarrollo de modelos de redes neuronales a partir de datos de caudales, precipitación y evaporación, así como la evaluación de la capacidad de desempeño frente a modelos estocásticos. De esta manera, se desarrollaron 10 modelos de redes neuronales artificiales con distintas arquitecturas, cuyo entrenamiento se realizo con un primer subconjunto de datos correspondientes al periodo 1939 – 1999, y su validación con un segundo subconjunto de datos del periodo 2000 – 2006. Los modelos de redes neuronales artificiales mostraron comparativamente mejor desempeño en materia de predicción frente a un modelo autorregresivo periódico de primer orden PAR (1). Descriptores: Cuenca Caplina, Redes Neuronales Artificiales, Series de Tiempo. ABSTRACT Caplina river is the main tributary of the hydrographic basin of the same name, It has an extension of 4 239,09 km2, because of this reason it is one of the principal sources of water supply for different uses in Tacna's city. For this reason diverse entities have been interested in knowing the water current and future availability of the river Caplina, because know the above mentioned values performs is the fundamental importance for the planning and managing of the systems of water resources. The stochastic models have been during long time, the most common alternative in the prediction of flows. Nowadays, the tools of intelligent computation like the artificial neural networks, specially the networks you multi-geld with algorithm of retro-spread. In this context, the current investigation center his efforts on the application of the neural networks to the prediction of the average monthly flows of the river Caplina-station Bocatoma Calientes, model development of neural networks from information of flows, rainfall and evaporation, as well as the evaluation of the capacity of performance opposite to stochastic models. So, 10 models of artificial neural networks were developed with different architectures, which training was realize with the first subset of information corresponding to the period 1939 - 1999, and his validation with the second subset of information of the period 2000 - 2006. The models of artificial neural networks showed comparatively better performance as for prediction opposite to a periodic autoregressive model of the first order PAR (1). Keywords: Caplina Basin, artificial neural networks, Series of Time.


SINERGI ◽  
2021 ◽  
Vol 25 (3) ◽  
pp. 237
Author(s):  
Zendi Iklima ◽  
Muhammad Imam Muthahhar ◽  
Asif Khan ◽  
Arifiansyah Zody

As known as Parallel-Link Robot, Delta Robot is a kind of Manipulator Robot that consists of three arms mounted in parallel. Delta Robot has a central joint constructed as an end-effector represented as a gripper. An Analysis of Inverse Kinematic (IK) used to convert the end-effector trajectory (X, Y) into rotations of stepper motors (ZA, ZB and ZC). The proposed method used Artificial Neural Networks (ANNs) to simplify the process of IK solver. The IK solver generated the datasets contain motion data of the Delta robot. There are 11 KB Datasets consist of 200 motion data used to be trained. The proposed method was trained in 58.78 seconds in 5000 iterations. Using a learning rate (α) 0.05 and produced the average accuracy was 97.48%, and the average loss was 0.43%. The proposed method was also tested to transfer motion data over Socket.IO with 115.58B in 6.68ms.


Sign in / Sign up

Export Citation Format

Share Document