Prediction of Salt Spray Test results of Micro Arc Oxidation coatings on AA2024 alloys by combination of Accelerated Electrochemical Test and Artificial Neural Network

2021 ◽  
pp. 127370
Author(s):  
Alexandre Finke ◽  
Julien Escobar ◽  
Julien Munoz ◽  
Mikael Petit
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Salt Spray ◽  
Salt Spray Test ◽  
Test Results ◽  
Electrochemical Test ◽  
Micro Arc Oxidation ◽  
Artificial Neural

scholarly journals Prediction of the Dynamic Stiffness of Resilient Materials using Artificial Neural Network (ANN) Technique

2019 ◽  
Vol 9 (6) ◽  
pp. 1088 ◽  
Author(s):  
Changhyuk Kim ◽  
Jung-Yoon Lee ◽  
Moonhyun Kim
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Residential Buildings ◽  
Dynamic Stiffness ◽  
Test Results ◽  
High Rise ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Sound Reduction ◽  
Reduction Capacity

High-rise residential buildings are constructed in countries with high population density in response to the need to utilize small development areas. As many high-rise buildings are being constructed, issues of floor impact sound tend to occur in buildings. In general, resilient materials are implemented between the slab and the finishing mortar to control the floor impact sound. Various mechanical properties of resilient materials can affect the floor impact sound. To investigate the impact sound reduction capacity, various experimental tests were conducted. The test results show that the floor impact sound reduction capacity has a close relationship with the dynamic stiffness of resilient materials. A total of six different kinds of resilient materials were loaded under four loading conditions. The test results show that loading time, loading, and material properties influence the change in dynamic stiffness. Artificial neural network (ANN) technique was implemented to obtain the responses between the deflection and dynamic stiffness. Three different algorithms were considered in the ANN models and the trained results were analyzed based on the root mean square error. The feasibility of using the ANN technique was verified with a high and consistent level of accuracy.

Soft Computing Tools to Predict Progression of Percent Embedment of Aggregates in Chip Seals

2018 ◽  
Vol 2672 (12) ◽  
pp. 32-39 ◽  
Author(s):  
Aksel Seitllari ◽  
M. Emin Kutay
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Soft Computing ◽  
Embedment Depth ◽  
Test Results ◽  
Multilinear Regression ◽  
Neuro Fuzzy ◽  
Chip Seal ◽  
Regression Techniques ◽  
Artificial Neural

In this study, soft computing and multilinear regression techniques were employed to develop models for prediction of progression of chip seal percent embedment depth ( Pe). The model uses inputs such as cumulative equivalent traffic volume, Vialit test results, dust content of aggregates, and initial embedment depth. Multilinear regression, adaptive neuro-fuzzy system, and artificial neural network techniques were used to estimate the Pe. The contribution of the variables affecting Pe was evaluated through a sensitivity analysis. The results indicate that while most of the proposed models were able to predict the Pe reasonably, the artificial neural network model performed the best.

Research on Heavy-Duty Coating Protection System of Magnesium Alloy

2015 ◽  
Vol 1119 ◽  
pp. 525-528
Author(s):  
Ru Tang Yan ◽  
Yuan Yuan Li ◽  
Chun Wei She ◽  
Hua Geng Li ◽  
Hua Pan Li
Keyword(s):  
Corrosion Resistance ◽  
Magnesium Alloy ◽  
Salt Spray ◽  
Salt Spray Test ◽  
Protection System ◽  
Test Time ◽  
Test Results ◽  
Ageing Test ◽  
Micro Arc Oxidation ◽  
Resistance Performance

The poor corrosion resistance of magnesium alloys become the bottleneck restricting its development. Based on micro-arc oxidation (MAO) technology and the characteristics of fluorocarbon coating the surface of magnesium alloy build a high corrosion protection system, namely: Based on micro-arc oxidation coating fluorocarbon coatings. The formation of the composite coating through the resistance to ageing test through the resistance to ageing test, acid and alkali experiment and salt spray test results show the excellent corrosion resistance performance. Among them, the resistance to salt spray test time can reach 1500 h, which breaks the bottleneck of magnesium alloy corrosion resistance of 1000 h.

scholarly journals Prediction of Waste Heat Energy Recovery Performance in a Naturally Aspirated Engine Using Artificial Neural Network

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Safarudin Gazali Herawan ◽  
Abdul Hakim Rohhaizan ◽  
Azma Putra ◽  
Ahmad Faris Ismail
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Waste Heat ◽  
Simulation Method ◽  
Spark Ignition Engine ◽  
Test Results ◽  
Simulation Test ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Heat Energy Recovery

The waste heat from exhaust gases represents a significant amount of thermal energy, which has conventionally been used for combined heating and power applications. This paper explores the performance of a naturally aspirated spark ignition engine equipped with waste heat recovery mechanism (WHRM). The experimental and simulation test results suggest that the concept is thermodynamically feasible and could significantly enhance the system performance depending on the load applied to the engine. The simulation method is created using an artificial neural network (ANN) which predicts the power produced from the WHRM.

A New Chromate-Free Insulating Coating on Silicon Steel

2014 ◽  
Vol 1004-1005 ◽  
pp. 757-762 ◽  
Author(s):  
Shuang Hong Wang ◽  
Yong Feng Long ◽  
Shi Lu Zhao ◽  
Cheng Qiang An ◽  
Ke Ding
Keyword(s):  
High Temperature ◽  
Salt Spray ◽  
Silicon Steel ◽  
Salt Spray Test ◽  
Neutral Salt ◽  
Test Results ◽  
High Temperature Annealing ◽  
Electrochemical Test ◽  
Comprehensive Performance ◽  
Resistance Value

The water-based paint had been examined to prepare a new chromate-free insulating coating on silicon steels. The structure of the insulating coating was characterized by scanning electron microscopy, energy dispersive spectroscopy and infrared spectroscopy. Adhesion, high temperature annealing, and surface insulating resistance were measured. Corrosion resistance was investigated by neutral salt spray test and electrochemical test. Results exhibited that the insulating coating had excellent comprehensive performance. The adhesive level was 5B degree; the high temperature annealing test showed no coating degradation after heat treatment of 2 h at 450 °C in air or at 750 °C in nitrogen; the salt spray test showed the corrosion area was less than 2 % after the 12 h salt spray; when the coating thickness was 1.0-1.2 μm, the surface insulating resistance value was 380-420 Ω/mm2.

scholarly journals Assessing the risk of dengue severity using demographic information and laboratory test results with machine learning

2020 ◽  
Vol 14 (12) ◽  
pp. e0008960
Author(s):  
Sheng-Wen Huang ◽  
Huey-Pin Tsai ◽  
Su-Jhen Hung ◽  
Wen-Chien Ko ◽  
Jen-Ren Wang
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Laboratory Test ◽  
Prognostic Models ◽  
Severe Dengue ◽  
Test Results ◽  
Demographic Information ◽  
Laboratory Test Results ◽  
Artificial Neural

Background Dengue virus causes a wide spectrum of disease, which ranges from subclinical disease to severe dengue shock syndrome. However, estimating the risk of severe outcomes using clinical presentation or laboratory test results for rapid patient triage remains a challenge. Here, we aimed to develop prognostic models for severe dengue using machine learning, according to demographic information and clinical laboratory data of patients with dengue. Methodology/Principal findings Out of 1,581 patients in the National Cheng Kung University Hospital with suspected dengue infections and subjected to NS1 antigen, IgM and IgG, and qRT-PCR tests, 798 patients including 138 severe cases were enrolled in the study. The primary target outcome was severe dengue. Machine learning models were trained and tested using the patient dataset that included demographic information and qualitative laboratory test results collected on day 1 when they sought medical advice. To develop prognostic models, we applied various machine learning methods, including logistic regression, random forest, gradient boosting machine, support vector classifier, and artificial neural network, and compared the performance of the methods. The artificial neural network showed the highest average discrimination area under the receiver operating characteristic curve (0.8324 ± 0.0268) and balance accuracy (0.7523 ± 0.0273). According to the model explainer that analyzed the contributions/co-contributions of the different factors, patient age and dengue NS1 antigenemia were the two most important risk factors associated with severe dengue. Additionally, co-existence of anti-dengue IgM and IgG in patients with dengue increased the probability of severe dengue. Conclusions/Significance We developed prognostic models for the prediction of dengue severity in patients, using machine learning. The discriminative ability of the artificial neural network exhibited good performance for severe dengue prognosis. This model could help clinicians obtain a rapid prognosis during dengue outbreaks. However, the model requires further validation using external cohorts in future studies.

scholarly journals Pemanfaatan Data Mining dalam Penentuan Rekomendasi Mustahik (Penerima Zakat)

2020 ◽  
Vol 12 (2) ◽  
pp. 67-73
Author(s):  
Andi Abdul malik Ahmad ◽  
Zawiyah Saharuna ◽  
Muhammad Fajri Raharjo
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Artificial Neural Network ◽  
Learning Rate ◽  
Test Results ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Artificial Neural ◽  
Hidden Layer ◽  
Artificial Neural Network Algorithm

This study applies data mining in determining recommendations for mustahik. The application is carried out using a classification method with an artificial neural network algorithm where the attributes used are age and type of work of the head of the family, the condition and ownership of the residence, the place of sewage, family monthly income, number of dependents, and diet. Tests are carried out using a combination of values ​​between learning rate, epoch, k-fold, and hidden layer neurons. Based on the test results from the classification process, it is found that the artificial neural network algorithm has the highest accuracy when the number of hidden layer neurons is six, the learning rate is one, the fold is seven, and the number of epochs is 200, which is 92.09%. The test results are then displayed on the Mustahik information system page.

QUALITY MANAGEMENT OF THE EDUCATIONAL PROCESS ON THE BASIS OF THE ANALYSIS OF TEST TASKS BY USING ARTIFICIAL INTELLIGENCE

2019 ◽  
Vol 22 (6) ◽  
pp. 175-182
Author(s):  
V. P. Dobritsa ◽  
E. I. Goryushkin
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Information And Communication Technologies ◽  
Communication Technologies ◽  
Educational Process ◽  
Test Results ◽  
Information And Communication ◽  
Artificial Neural

Introduction. The use of information and communication technologies allows the teacher to update the content of training. The success of the educational process is largely determined by the ICT competence and ICT literacy of the teacher. Data mining based on artificial neural networks can be used as one of the elements of information and communication technologies. The main direction of application of tests is to measure the level of knowledge of students. A large amount of accumulated test results with proper processing can provide the teacher with additional (hidden) data. The use of an artificial neural network for the analysis of test results makes it possible to expand the direction of the tests. Methods. The theoretical basis of the study is based on a complex of scientific statements of domestic and foreign scientists in the field of education and artificial intelligence. Practical research methods are based on an experiment in creating a test in computer science, testing students and accumulating data, as well as their processing simulated artificial neural network. Results. The article describes the process of analyzing the results of research using the SPSS STATISTICA 20 programs. The search for hidden patterns of the test was carried out, the reliability of the results obtained was verified. Discussion. There was suggested the possibility of further application of the results obtained in the educational process. The results obtained can be used to search for and correct difficult or easy test items, and to replace failed test tasks. The teacher has the opportunity to redistribute the time resource for the study of difficult digestible topics, due to easily digestible. The idea of an integrated approach to the use of artificial neural networks in education is proposed.

Sign in / Sign up

Export Citation Format

Share Document