Research of Artificial Neural Networks in the Al2O3 Ceramic Laser Milling Application

2014 ◽  
Vol 528 ◽  
pp. 101-106 ◽  
Author(s):  
Zhao Mei Xu ◽  
Zong Hai Hong ◽  
Gang Yang ◽  
Qin Gan Wang
Keyword(s):  
Laser Power ◽  
Scanning Speed ◽  
Milling Quality ◽  
Laser Process ◽  
Laser Milling ◽  
The Mean ◽  
Ceramic Laser ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Based on the artificial neural network (ANN), a model is established to describe the relation of the laser milling quality of the Al2O3ceramics with the ceramics parameters. The milling quality of Al2O3ceramics are predicted with the model in which the input parameters consist of laser power, scanning speed and defocus amount and the output parameters include the milling depth and width. The results show that the mean error is small, and the model has good verifying precision and excellent ability of predicting. The laser process parameters can be chosen easily and accurately to improve the processing quality of laser milling.

Best Architecture of an Artificial Neural Network to Model Prefilming Airblast Atomization: Not So Deep Learning

2021 ◽  
Author(s):  
Geoffroy Chaussonnet ◽  
Sebastian Gepperth ◽  
Simon Holz ◽  
Rainer Koch ◽  
Hans-Jörg Bauer
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Space ◽  
Middle Layer ◽  
Ann Model ◽  
Deformation Velocity ◽  
The Mean ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Domain Of Parameters

Abstract A fully connected Artificial Neural Network (ANN) is used to predict the mean spray characteristics of prefilming airblast atomization. The model is trained from the planar prefilmer experiment from the PhD thesis of Gepperth (2020). The output of the ANN model are the Sauter Mean Diameter, the mean droplet axial velocity, the mean ligament length and the mean ligament deformation velocity. The training database contains 322 different operating points. Two types of model input quantities are investigated and compared. First, nine dimensional parameters are used as inputs for the model. Second, nine non-dimensional groups commonly used for liquid atomization are derived from the first set of inputs. The best architecture is determined after testing over 10000 randomly drawn ANN architectures, with up to 10 layers and up to 128 neurons per layer. The striking results is that for both types of model, the best architectures consist of only 3 hidden layer in the shape of a diabolo. This shape recalls the shape of an autoencoder, where the middle layer would be the feature space of reduced dimensionality. It was found that the model with dimensional input quantities always shows a lower test and validation errors than the one with non-dimensional input quantities. In general, the two types of models provide comparable accuracy, better than typical correlations of SMD and droplet velocity. Finally the extrapolation capability of the models was assessed by a training them on a confined domain of parameters and testing them outside this domain.

Adaptive Power-Saving Mechanism for VoIP Over WiMAX Based on Artificial Neural Network

2019 ◽  
pp. 158-177
Author(s):  
Tamer Emara
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Power Saving ◽  
Ieee 802.16 ◽  
Feed Forward Neural Network ◽  
Artificial Neural ◽  
Adaptive Power ◽  
Artificial Neural Network Ann ◽  
Hidden Layer

The IEEE 802.16 system offers power-saving class type II as a power-saving algorithm for real-time services such as voice over internet protocol (VoIP) service. However, it doesn't take into account the silent periods of VoIP conversation. This chapter proposes a power conservation algorithm based on artificial neural network (ANN-VPSM) that can be applied to VoIP service over WiMAX systems. Artificial intelligent model using feed forward neural network with a single hidden layer has been developed to predict the mutual silent period that used to determine the sleep period for power saving class mode in IEEE 802.16. From the implication of the findings, ANN-VPSM reduces the power consumption during VoIP calls with respect to the quality of services (QoS). Experimental results depict the significant advantages of ANN-VPSM in terms of power saving and quality-of-service (QoS). It shows the power consumed in the mobile station can be reduced up to 3.7% with respect to VoIP quality.

Effect of Laser Processing Parameters on Microhole Quality of Aluminium Nitride Ceramics

2021 ◽  
Vol 871 ◽  
pp. 277-283
Author(s):  
Chun Yan Yang ◽  
Yun Hao ◽  
Bozhe Wang ◽  
Hai Yuan ◽  
Liu Hui Li
Keyword(s):  
Laser Processing ◽  
Laser Power ◽  
Picosecond Laser ◽  
Scanning Speed ◽  
Processing Parameters ◽  
Recast Layer ◽  
Aluminium Nitride ◽  
Obvious Effect ◽  
Nitride Ceramics

A picosecond laser in spin-cutting mode was used to drill 500μm diameter microholes on 150μm thick aluminium nitride ceramic. The effects of laser processing parameters such as the laser power, scanning speed, and defocus amount on the microhole quality were studied. The results show that as the laser power increases, the inlet and outlet diameters of the holes increase, the taper decreases slightly, and the thickness of the recast layer decreases evidently. The scanning speed has no obvious effect on the diameter and taper of the hole; however, the hole can not be drilled through when the speed is too large. Positive defocus can effectively reduce the taper of the hole. Under 28.5W laser power, 400Hz frequency, 200mm/s scanning speed, and zero defocus amount conditions, high-quality microholes with a taper of 0.85° were obtained.

Influence of the Temperature in the Direct Forming Laser Process of 316L Stainless Steel with CO2 Laser

2014 ◽  
Vol 802 ◽  
pp. 334-337
Author(s):  
C.L. Santos ◽  
G. Vasconcelos ◽  
H.S. Oliveira ◽  
L.G. Oliveira ◽  
J.F. Azevedo ◽  
...  
Keyword(s):  
Surface Roughness ◽  
Stainless Steel ◽  
Melting Point ◽  
Laser Beam ◽  
316L Stainless Steel ◽  
Turbine Blades ◽  
Scanning Speed ◽  
Sample Surface ◽  
Laser Process

This study shows the influence of the temperature in the Direct Forming Laser process (DFL) of 316L stainless steel metal powder. Results shows that an increasing in the sample surface temperature can improve the laser beam absorption in the DFL process. A pre-heating in the substrate and in the powder contributed to decrease the time to reach the melting point and to improve the surface roughness. This effect was investigated with constant lasers parameters (scanning speed and intensity) and a heating in the samples in the temperature range of 20oto 200oC. It was possible to evaluate the DFL process and to optimize the quality of the sample surface roughness. These results will benefit the knowledge of the DFL technology that can be applied in the development of turbine blades.

scholarly journals Length of Hospital Stay Prediction at the Admission Stage for Cardiology Patients Using Artificial Neural Network

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Pei-Fang (Jennifer) Tsai ◽  
Po-Chia Chen ◽  
Yen-You Chen ◽  
Hao-Yuan Song ◽  
Hsiu-Mei Lin ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Coronary Atherosclerosis ◽  
Inpatient Care ◽  
Length Of Hospital Stay ◽  
Ann Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Christian Hospital

For hospitals’ admission management, the ability to predict length of stay (LOS) as early as in the preadmission stage might be helpful to monitor the quality of inpatient care. This study is to develop artificial neural network (ANN) models to predict LOS for inpatients with one of the three primary diagnoses: coronary atherosclerosis (CAS), heart failure (HF), and acute myocardial infarction (AMI) in a cardiovascular unit in a Christian hospital in Taipei, Taiwan. A total of 2,377 cardiology patients discharged between October 1, 2010, and December 31, 2011, were analyzed. Using ANN or linear regression model was able to predict correctly for 88.07% to 89.95% CAS patients at the predischarge stage and for 88.31% to 91.53% at the preadmission stage. For AMI or HF patients, the accuracy ranged from 64.12% to 66.78% at the predischarge stage and 63.69% to 67.47% at the preadmission stage when a tolerance of 2 days was allowed.

scholarly journals Modeling the Producibility of 3D Printing in Polylactic Acid Using Artificial Neural Networks and Fused Filament Fabrication

Polymers ◽  
2021 ◽  
Vol 13 (19) ◽  
pp. 3219
Author(s):  
Mohammad Saleh Meiabadi ◽  
Mahmoud Moradi ◽  
Mojtaba Karamimoghadam ◽  
Sina Ardabili ◽  
Mahdi Bodaghi ◽  
...  
Keyword(s):  
Polylactic Acid ◽  
Production Cost ◽  
Cost Effective ◽  
Fused Filament Fabrication ◽  
3D Printers ◽  
Artificial Neural ◽  
End Use ◽  
Artificial Neural Network Ann ◽  
Part Thickness

Polylactic acid (PLA) is a highly applicable material that is used in 3D printers due to some significant features such as its deformation property and affordable cost. For improvement of the end-use quality, it is of significant importance to enhance the quality of fused filament fabrication (FFF)-printed objects in PLA. The purpose of this investigation was to boost toughness and to reduce the production cost of the FFF-printed tensile test samples with the desired part thickness. To remove the need for numerous and idle printing samples, the response surface method (RSM) was used. Statistical analysis was performed to deal with this concern by considering extruder temperature (ET), infill percentage (IP), and layer thickness (LT) as controlled factors. The artificial intelligence method of artificial neural network (ANN) and ANN-genetic algorithm (ANN-GA) were further developed to estimate the toughness, part thickness, and production-cost-dependent variables. Results were evaluated by correlation coefficient and RMSE values. According to the modeling results, ANN-GA as a hybrid machine learning (ML) technique could enhance the accuracy of modeling by about 7.5, 11.5, and 4.5% for toughness, part thickness, and production cost, respectively, in comparison with those for the single ANN method. On the other hand, the optimization results confirm that the optimized specimen is cost-effective and able to comparatively undergo deformation, which enables the usability of printed PLA objects.

scholarly journals ARTIFICIAL NEURAL NETWORKS FOR PREDICTING THE GENERATION OF ACETALDEHYDE IN PET RESIN IN THE PROCESS OF INJECTION OF PLASTIC PACKAGES

2021 ◽  
Vol 9 (6) ◽  
pp. 97-119
Author(s):  
Mauro Reis Nascimento ◽  
David Barbosa de Alencar ◽  
Manoel Henrique Reis Nascimento ◽  
Carlos Alberto Monteiro
Keyword(s):  
Decision Making ◽  
Strategic Decision ◽  
Drying Temperature ◽  
Pet Bottles ◽  
Injection Process ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Method Analysis ◽  
Plastic Injection

The industrial production of preforms for the manufacture of PET bottles, during the plastic injection process, is essential to regulate the drying temperature of the PET resin, to control the generation of Acetaldehyde (ACH), which alters the flavor of carbonated or non-carbonated drinks, giving the drink a citrus flavor and putting in doubt the quality of packaged products. In this work, an Artificial Neural Network (ANN) of the Backpropagation type (Cascadeforwardnet) is specified to support the decision-making process in controlling the ideal drying temperature of the PET resin, allowing specialists to make the necessary temperature regulation decisions  for the best performance by decreasing ACH levels. The materials and methods were applied according to the manufacturer's characteristics on the moisture in the PET resin grain, which may contain between 50 ppm and 100 ppm of ACH. Data were collected for the method analysis, according to temperatures and residence times used in the blow injection process in the manufacture of the bottle preform, the generation of ACH from the PET bottle after solid post-condensation stage reached residual ACH levels below (3-4) ppm, according to the desired specification, reaching levels below 1 ppm. The results found through the Computational Intelligence (IC) techniques applied by the ANNs, where they allowed the prediction of the ACH levels generated in the plastic injection process of the bottle packaging preform, allowing an effective management of the parameters of production, assisting in strategic decision making regarding the use of temperature control during the drying process of PET resin.

scholarly journals Assessing the Impact of Expert Labelling of Training Data on the Quality of Automatic Classification of Lithological Groups Using Artificial Neural Networks

2020 ◽  
Vol 25 (2) ◽  
pp. 145-152
Author(s):  
Yan Kuchin ◽  
Ravil Mukhamediev ◽  
Kirill Yakunin ◽  
Janis Grundspenkis ◽  
Adilkhan Symagulov
Keyword(s):  
Neural Network ◽  
Automatic Classification ◽  
Training Data ◽  
Classification Problems ◽  
Expert Opinions ◽  
Input Parameters ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
The Impact

AbstractMachine learning (ML) methods are nowadays widely used to automate geophysical study. Some of ML algorithms are used to solve lithological classification problems during uranium mining process. One of the key aspects of using classical ML methods is causing data features and estimating their influence on the classification. This paper presents a quantitative assessment of the impact of expert opinions on the classification process. In other words, we have prepared the data, identified the experts and performed a series of experiments with and without taking into account the fact that the expert identifier is supplied to the input of the automatic classifier during training and testing. Feedforward artificial neural network (ANN) has been used as a classifier. The results of the experiments show that the “knowledge” of the ANN of which expert interpreted the data improves the quality of the automatic classification in terms of accuracy (by 5 %) and recall (by 20 %). However, due to the fact that the input parameters of the model may depend on each other, the SHapley Additive exPlanations (SHAP) method has been used to further assess the impact of expert identifier. SHAP has allowed assessing the degree of parameter influence. It has revealed that the expert ID is at least two times more influential than any of the other input parameters of the neural network. This circumstance imposes significant restrictions on the application of ANNs to solve the task of lithological classification at the uranium deposits.

Influence of laser parameters and Ti content on the surface morphology of L-PBF fabricated Titania

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Abid Ullah ◽  
HengAn Wu ◽  
Asif Ur Rehman ◽  
YinBo Zhu ◽  
Tingting Liu ◽  
...  
Keyword(s):  
Surface Morphology ◽  
Laser Beam ◽  
Surface Quality ◽  
Selective Oxidation ◽  
Laser Power ◽  
Scanning Speed ◽  
Content Type ◽  
Powder Bed ◽  
Laser Parameters

Purpose The purpose of this paper is to eliminate Part defects and enrich additive manufacturing of ceramics. Laser powder bed fusion (L-PBF) experiments were carried to investigate the effects of laser parameters and selective oxidation of Titanium (mixed with TiO2) on the microstructure, surface quality and melting state of Titania. The causes of several L-PBF parts defects were thoroughly analyzed. Design/methodology/approach Laser power and scanning speed were varied within a specific range (50–125 W and 170–200 mm/s, respectively). Furthermore, varying loads of Ti (1%, 3%, 5% and 15%) were mixed with TiO2, which was selectively oxidized with laser beam in the presence of oxygen environment. Findings Part defects such as cracks, pores and uneven grains growth were widely reduced in TiO2 L-PBF specimens. Increasing the laser power and decreasing the scanning speed shown significant improvements in the surface morphology of TiO2 ceramics. The amount of Ti material was fully melted and simultaneously changed into TiO2 by the application of the laser beam. The selective oxidation of Ti material also improved the melting condition, microstructure and surface quality of the specimens. Originality/value TiO2 ceramic specimens were produced through L-PBF process. Increasing the laser power and decreasing the scanning speed is an effective way to sufficiently melt the powders and reduce parts defects. Selective oxidation of Ti by a high power laser beam approach was used to improve the manufacturability of TiO2 specimens.

scholarly journals Multi-objective numerical simulation of geometrical characteristics of laser cladding of cobalt-based alloy based on response surface methodology

2020 ◽  
pp. 002029402094495
Author(s):  
Lu-jun Cui ◽  
Meng Zhang ◽  
Shi-Rui Guo ◽  
Yan-Long Cao ◽  
Wen-Han Zeng ◽  
...  
Keyword(s):  
Prediction Model ◽  
Response Surface ◽  
Laser Cladding ◽  
Process Parameters ◽  
Laser Power ◽  
Influence Factors ◽  
Scanning Speed ◽  
Laser Cladding Remanufacturing ◽  
Main Influence

The objectives of this study are to optimize the key process parameters of laser cladding remanufacturing parts, improve the sealing quality of the hemispherical valve and prolong and improve its service life and reliability. A high-power fiber-coupled semiconductor laser was used to fabricate a single Co-based alloy cladding layer on the pump valve material ZG45 plate. The key process parameters of laser power, scanning speed and powder feeding rate in the process of laser remanufacturing are taken as optimization variables, and the coating width, coating height, coating depth, aspect ratio and dilution rate are taken as response indexes. Based on the response surface analysis method, the central compound experiment is designed using Design-Expert software. The variance analysis of the experimental results is performed, and the regression prediction model of the process parameters relative to the corresponding index is established. Through analysis of the established perturbation diagram and three-dimensional response surface, it is concluded that the main influence factors of melting width and penetration depth are laser power and positive effect, and the main influence factors of melting height are scanning speed and negative effect. The average error of each regression prediction model is lower than 10%. The above research work has important guiding significance for optimizing the process parameters and improving the cladding quality of cobalt-based alloy on ZG45.

Sign in / Sign up

Export Citation Format

Share Document