ABC and GA Optimized NN to Model Resin Bonded Mould/Core Sand System: A Soft Computing-based Approach

2014 ◽  
Vol 14 (4) ◽  
pp. 257-267 ◽  
Author(s):  
Pandu R. Vundavilli ◽  
B. Surekha ◽  
Mahesh B. Parappagoudar
Keyword(s):  
Transfer Functions ◽  
Population Based ◽  
Experimental Investigations ◽  
Good Surface ◽  
Bee Colony ◽  
Good Surface Finish ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
Population Based Search ◽  
Core Sand

AbstractResin bonded sand system is an emerging area, and it can be used to produce dimensionally accurate castings with good surface finish. In the present paper, experimental investigations are carried out on the resin bonded cores, to develop a non-linear mathematical model, using the concept of design of experiments. Subsequently, an artificial neural network (ANN) with four neurons each on input and output layers has been used to model the resin bonded sand system. It is important to note that the process parameters, such as percentage of resin, percentage of hardener, number of strokes and curing time are considered as inputs and the mechanical properties of the core, namely compression strength, tensile strength, shear strength and permeability are treated as the outputs of the network. It is to be noted that the performance of developed ANN depends on several factors of the network, such as type of transfer functions, coefficients of transfer functions, number of neurons in the hidden layer and connecting weights between different layers. In the present study, two population based search and optimization algorithms, namely genetic algorithm (GA) and artificial bee colony (ABC) are used for optimizing the parameters of ANN. It has been observed that both GA and ABC trained neural networks (that is, GA-NN and ABC-NN) are found to have good agreement with the experimental data and can be used effectively to model the resin bonded core sand system.

scholarly journals Tribological Behavior and Analysis on Surface Roughness of CNC Milled Dual Heat Treated Al6061 Composites

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
A. Bovas Herbert Bejaxhin ◽  
G.M. Balamurugan ◽  
S.M. Sivagami ◽  
K. Ramkumar ◽  
V. Vijayan ◽  
...  
Keyword(s):  
Heat Treatment ◽  
Surface Roughness ◽  
Lower Surface ◽  
Cnc Machining ◽  
Depth Of Cut ◽  
Good Surface ◽  
Heat Treated ◽  
Good Surface Finish ◽  
Artificial Neural Network Ann ◽  
Machining Properties

Dual heat treatment (DHT) effect is analyzed using the machining of Al6061-T6 alloy, a readily available material for quickly finding the machining properties. The heat treatments are conducted twice over the specimen by the furnace heating before processing through CNC machining. The HSS and WC milling cutters are preferred for the diameter of 10 mm for the reviewed rotational speeds of 2000 rpm and 4000 rpm, and the constant depth of cut of 0.5 mm is chosen based on various reviews. Worthy roughness could be provided mostly by the influence of feed rates preferred here as 0.05 mm/rev and 0.1 mm/rev. The influencing factors are identified by the Taguchi, genetic algorithm (GA), and Artificial Neural Network (ANN) techniques and compared within it. The simulation finding also helps to clarify the relationship between influenced machining constraints and roughness outcomes of this project. The average values of heat treated and nonheat treated Al6061-T6 are compared and it is to be evaluated that 41% improvement is obtained with the lower surface roughness of 1.78975 µm and it shows good surface finish with the help of dual heat treatment process.

Experimental Investigations on Machining Micro Alloy Steel (MAS 38MnSiVS5) Using K 20 Multi Coated Carbide Insert

2014 ◽  
Vol 591 ◽  
pp. 15-18
Author(s):  
Subramani Muniraj ◽  
Nambi Muthukrishnan
Keyword(s):  
Alloy Steel ◽  
Surface Finish ◽  
Cutting Speed ◽  
Cutting Parameters ◽  
Experimental Investigations ◽  
Good Surface ◽  
Good Surface Finish ◽  
Coated Carbide ◽  
Carbide Insert ◽  
Spindle Power

An experimental investigation is carried out on machining Micro Alloy Steel (MAS). The cylindrical rods of diameter 60 mm and length 250 mm is machined using the medium duty lathe of 2 kW spindle power to study the machinability issues of MAS using K20 multi coated (TiN-TiCN-Al203-ZrCN) Carbide insert. The optimum cutting parameters have been identified by power consumed by main spindle, and average surface roughness of machined component. Results show at higher cutting speeds; good surface finish is obtained. It is concluded that, surface finish is directly proportionate to the cutting speed. Results provide some useful information.

Development of a Neural Statistical Model for the Relative Humidity Levels Prediction in the Region of Rabat-Kenitra (Morocco)

2021 ◽  
Author(s):  
Kaoutar Elazhari ◽  
Badreddine ABDALLAOUI ◽  
Ali DEHBI ◽  
Abdelaziz ABDALLAOUI ◽  
Hamid ZINEDDINE
Keyword(s):  
Relative Humidity ◽  
Meteorological Parameters ◽  
Transfer Functions ◽  
Mean Squared Error ◽  
Neural Model ◽  
Ann Model ◽  
History Of ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
Mlp Model

Abstract This work provides the development of a powerful artificial neural network (ANN) model, for the prediction of relative humidity levels, using other meteorological parameters of the Rabat-Kenitra region. The treatment was applied to a database containing a daily history of five meteorological parameters of 9 stations covering this region for a period from 1979 to mid-2014. We have shown that for the prediction of relative humidity in this region, the best performing three-layer ANN (input, hidden and output) mathematical model is the multi-layer perceptron (MLP) model. This neural model using the Levenberg-Marquard algorithm, having an architecture [5-11-1] and the transfer functions Tansig in the hidden layer and Purelin in the output layer was able to estimate values for relative humidity very close to those observed. Indeed, this was affirmed by a low mean squared error (MSE) and a fairly high correlation coefficient (R), compared to the statistical indicators relating to the other models developed as part of this study.

scholarly journals Identification the appearance quality of rice kernels by vision technology and neural network classifier

2020 ◽  
Vol 9 (1) ◽  
pp. 118
Author(s):  
Ali Dabaghi ◽  
Mohammad Hadi Khoshtaghaza ◽  
Mohamad Reza Alizadeh ◽  
Hemad Zareiforoush
Keyword(s):  
Neural Network ◽  
Transfer Functions ◽  
Selection Process ◽  
Low Cost ◽  
Appearance Quality ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
Sorting System ◽  
Ann Classifier

In this study, the appearance quality of Hashemi variety of rice grains was evaluated using image processing and artificial neural network (ANN) classifier. Non-touching kernel images of different classes in a Hashemi rice sample were acquired using a flatbed scanner. Then preprocessing, segmentation, feature extraction and effective feature selection process were done on each objects of image. To categorized grains, various structures of ANN consisting network with one and two hidden layer with different hidden nodes, different training and transfer functions were considered. Results of validation stage showed ANN with 13-18-18-5 topology and LM training and tansig transfer functions had highest mean of classification accuracy (97.33%) and the lowest value of RMSE (0.08361). It’s concluded that the suggested method uses low cost equipment to identify quality of rice with acceptable accuracy. Results of this research can be used for fast and accurate grading and developing an efficient rice sorting system.  

Comparison of Meta-heuristic Algorithms on Benchmark Functions

2019 ◽  
Vol 2 (3) ◽  
pp. 508-517
Author(s):  
FerdaNur Arıcı ◽  
Ersin Kaya
Keyword(s):  
Heuristic Algorithms ◽  
Optimization Problems ◽  
Search Algorithm ◽  
Optimization Algorithms ◽  
Gravitational Search Algorithm ◽  
Differential Evolution Algorithm ◽  
Population Based ◽  
Time Interval ◽  
Bee Colony ◽  
Different Characteristics

Optimization is a process to search the most suitable solution for a problem within an acceptable time interval. The algorithms that solve the optimization problems are called as optimization algorithms. In the literature, there are many optimization algorithms with different characteristics. The optimization algorithms can exhibit different behaviors depending on the size, characteristics and complexity of the optimization problem. In this study, six well-known population based optimization algorithms (artificial algae algorithm - AAA, artificial bee colony algorithm - ABC, differential evolution algorithm - DE, genetic algorithm - GA, gravitational search algorithm - GSA and particle swarm optimization - PSO) were used. These six algorithms were performed on the CEC’17 test functions. According to the experimental results, the algorithms were compared and performances of the algorithms were evaluated.

CONTINUOUS-CAST 45-12 DUCTILE IRON

Alloy Digest ◽  
1989 ◽  
Vol 38 (4) ◽  
Keyword(s):  
Continuous Casting ◽  
Ductile Iron ◽  
Heat Treating ◽  
Grain Structure ◽  
Continuous Cast ◽  
Good Surface ◽  
Fine Grain ◽  
High Speeds ◽  
Good Surface Finish ◽  
Iron Grade

Abstract Ductile Iron grade 45-12 produced by continuous casting has consistent density and fine grain structure. It is the softest of the regular grades of ductile iron and it machines at high speeds with good surface finish. This datasheet provides information on composition, physical properties, microstructure, hardness, elasticity, and tensile properties. It also includes information on heat treating, machining, and joining. Filing Code: CI-58. Producer or source: Federal Bronze Products Inc..

scholarly journals Mapping and Estimation of Monthly Global Solar Irradiation in Different Zones in Souss-Massa Area, Morocco, Using Artificial Neural Networks

2017 ◽  
Vol 2017 ◽  
pp. 1-19 ◽  
Author(s):  
O. Nait Mensour ◽  
S. Bouaddi ◽  
B. Abnay ◽  
B. Hlimi ◽  
A. Ihlal
Keyword(s):  
Solar Energy ◽  
Solar Irradiation ◽  
Kriging Interpolation ◽  
Solar Pv ◽  
Energy Potential ◽  
Global Solar Irradiation ◽  
Interpolation Technique ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer

Solar radiation data play an important role in solar energy research. However, in regions where the meteorological stations providing these data are unavailable, strong mapping and estimation models are needed. For this reason, we have developed a model based on artificial neural network (ANN) with a multilayer perceptron (MLP) technique to estimate the monthly average global solar irradiation of the Souss-Massa area (located in the southwest of Morocco). In this study, we have used a large database provided by NASA geosatellite database during the period from 1996 to 2005. After testing several models, we concluded that the best model has 25 nodes in the hidden layer and results in a minimum root mean square error (RMSE) equal to 0.234. Furthermore, almost a perfect correlation coefficient R=0.988 was found between measured and estimated values. This developed model was used to map the monthly solar energy potential of the Souss-Massa area during a year as estimated by the ANN and designed with the Kriging interpolation technique. By comparing the annual average solar irradiation between three selected sites in Souss-Massa, as estimated by our model, and six European locations where large solar PV plants are deployed, it is apparent that the Souss-Massa area is blessed with higher solar potential.

The “Lost Wax” Process of Precision Casting

1950 ◽  
Vol 162 (1) ◽  
pp. 66-74 ◽  
Author(s):  
J. S. Turnbull
Keyword(s):  
Gas Turbine ◽  
Turbine Blades ◽  
Casting Process ◽  
Alternative Methods ◽  
Casting Technique ◽  
Gas Turbine Blades ◽  
Precision Casting ◽  
Good Surface ◽  
Wax Pattern ◽  
Good Surface Finish

The paper describes a casting process which differs from standard foundry practice in that it uses a wax pattern in a high refractory one-piece mould to produce metal castings with a good surface finish to an accuracy of ±0·002 inch. The process involves making a master pattern in either hard wood or metal, relating it to a soft metal die by precision casting technique, and then the production of wax patterns from the die on an injection machine. Finally, the wax patterns are invested in refractory moulds, the wax is melted out, the mould baked, and the metal component is cast. The “lost wax” process is advantageous in cases where ( a) the metal is unmachinable, or ( b) where the component is of an unmachinable shape, or ( c) where production by other methods takes too long. One of the most common applications is in the manufacture of gas-turbine blades. The tool costs are relatively low compared to the costs involved in alternative methods of manufacture, the die cost being a function of the number of castings required. The production of cheap castings is necessarily dependent on the scrap percentage being kept to a minimum; at present the scrap from the manufacture of gas-turbine blades is less than 30 per cent, and the author surmises that it would not be unreasonable to expect it to be less than 10 per cent in two years' time.

Manufacturability of Aircraft Winglet for Wind Tunnel Testing

2015 ◽  
Vol 830-831 ◽  
pp. 100-103
Author(s):  
L. Gopinath ◽  
S. Ravishankar
Keyword(s):  
Wind Tunnel ◽  
Metal Cutting ◽  
Tool Path ◽  
Cutting Parameters ◽  
Cnc Machining ◽  
Depth Of Cut ◽  
Manufacturing Strategy ◽  
Thin Sections ◽  
Good Surface ◽  
Good Surface Finish

The form, shape and dimensions of the scaled down winglet model become small and thin bringing complexity to manufacturing. The trailing edge tapers to a thickness varying from 0.065mm to 0.099mm along its length. The mounting portion of the winglet is provided with a close tolerance having a slot gap of 5mm and a depth of 35 mm with an angle. Additionally, wind tunnel models require good surface finish on the aerodynamic surfaces and this involves adopting a manufacturing strategy with a control over on the metal cutting parameters to be implemented on a three axes CNC machining centre. The winglet surface is divided into segments in order to handle the cutting forces on the varying aerodynamic cross section. Various metal cutting parameters such as tool path, cutter diameter, feed rate, depth of cut, spindle speed, etc., are evaluated by monitoring segments where the metal cutting is carried out [1] and flow of chips observed. Fixtures and lugs are planned effectively to accommodate the machining of the angular slot in a three axes machining centre itself. Routing of operations to handle the varying thin sections and realisation of the close tolerance slot has enabled a reliable manufacturing approach in an economical way.

Sign in / Sign up

Export Citation Format

Share Document