Multiple regression and neural networks analyses in composites machining

Lin, J.T.; Bhattacharyya, Debes; Kecman, Vojislav

doi:10.1016/s0266-3538(02)00232-4

Cited by 100 publications

(69 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lina et al [13] established the relationship between machining forces and wear of a tool wear made of an aluminium metal matrix composite by using a multiple regression analysis (MRA) and a generalized radial basis function (GRBF) neural network. Liao and Chin [12] used a generalized back-propagation (BP) neural network with two-hidden layers to establish a model for the grinding process.…”

Section: Modelling Of An Artificial Neural Network For Electrical Dismentioning

confidence: 99%

See 1 more Smart Citation

Modelling of an Artificial Neural Network for Electrical Discharge Machining of Hot Pressed Zirconium Diboride-Silicon Carbide Composites

Sivasankar¹,

Jeyapaul

2016

T FAMENA

View full text Add to dashboard Cite

SummaryModelling is carried out to map the relationship between the input process parameters and the output response, considered in the machining process. To represent real-world systems of considerable complexity, an artificial neural network (ANN) model is often utilized to replace the mathematical approximation of the relationship. This paper explains the methodological procedure and the outcome of the ANN modelling process. The percentage of SiC in the workpiece material, the product of thermal conductivity and the melting point of the tool material, the pulse on time, and the pulse off time are considered as input parameters, while the material removal rate (MRR), the tool wear rate (TWR), roughness, roundness, taper angle and overcut are considered as output responses. The network is trained initially with one neuron in the hidden layer, i.e.,-a 4-4-6 topology is considered for training. In the subsequent phases, the number of hidden neurons in the hidden layer is increased gradually and then the network is tested with two hidden layers with the same number of hidden neurons in the second hidden layer. A feed forward back propagation neural network model with one hidden layer having 35 neurons is found to be the optimum network model (4-35-35-6). The model has the mean correlation coefficient of 0.92408. IntroductionThe present manufacturing environment is characterized by complexity, interdisciplinary manufacturing functions and an ever growing demand for new tools and techniques to solve difficult problems. A neural network is used to capture the general relationship between variables of a system that are difficult to relate analytically. Neural network described as a brain metaphor of information processing or as a biologically inspired statistical too1 [22]. It has the capability to learn or to be trained for particular task, its own computational capabilities and the ability to formulate abstractions and generalizations. Neural network has an organization similar to that of a human brain and it is a network made up of processing elements called neurons. Neurons get data from the surrounding neurons, perform some computations and pass the results to other neurons. Connections between the TRANSACTIONS OF FAMENA XL-3 (2016) 67 S. Sivasankar, R. Jeyapaul Modelling of an Artificial Neural Network for Electrical Discharge Machining of Hot PressedZirconium Diboride-Silicon Carbide Composites neurons have weight associated with them. In the neural network, the knowledge is stored in its interconnection weights in an implicit manner; learning takes place within the system and plays the most important role in the construction of a neural network system. The neural network system learns by determining the interconnection weights from a set of given data [23]. A mathematical model was proposed to analyse the impacts of combustion parameters on pollutant production and combustion process efficiency. The influence of the air excess factor, fuel droplet size, fuel spray angle, and intensity of the swirl of combusti...

show abstract

Section: Modelling Of An Artificial Neural Network For Electrical Dismentioning

confidence: 99%

“…All the responses are given equal weightage of 0.16666. Global desirability (D) values of all the experiments are calculated by substituting 'w' values in the equation (13). The tools are ranked based on the global desirability values with equal weights.…”

Section: Influences Of Parameters On the Machinability Behaviour Of Tmentioning

confidence: 99%

Modelling of an Artificial Neural Network for Electrical Discharge Machining of Hot Pressed Zirconium Diboride-Silicon Carbide Composites

Sivasankar¹,

Jeyapaul

2016

T FAMENA

View full text Add to dashboard Cite

show abstract

“…For temperature, the best linear fit function is calculated as being: A=0.933T+30.9, while the correlation Tables 7 and 8 compare the second order regression models with neural networks, for forces and temperatures. It is often argued in the relevant literature that for complicated problems, neural networks perform better than regression models [17][18][19][20]. It can be concluded from the analysis that both methods can provide reliable results.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Application of Statistical and Soft Computing techniques for the Prediction of Grinding Performance

Dossis¹

2015

J Robot Mech Eng Resr

View full text Add to dashboard Cite

Thermal load in manufacturing processes is of special interest as it is closely connected with the surface integrity and life-cycle of the finished product. Especially in grinding, heat affected zones are created due to excessive heat dissipated within the workpiece during the process. In these zones, defects are created that undermine the quality of the workpiece and as grinding is a precision finishing operation, may render it unsuccessful. Grinding forces and temperatures are usually studied in relation to the heat affected zones. However, their experimental estimation or analytical evaluation may prove laborious and costly. Thus, simulation and modeling techniques are commonly employed for the prediction of these parameters and through them the performance evaluation of the process is performed. In this paper, statistical methods and soft computing techniques, namely regression models completed with analysis of variance, and artificial neural networks respectively, are presented for the estimation of grinding forces and temperature. A brief description of the models and a comparative study is performed, based on experimental results. Both modeling tools prove to be quite successful, predicting with high accuracy forces and temperatures.

show abstract

“…Predicted results are found to be more accurate compared to regression analysis. Lin et al [4] used radial basis function neural network and multiple regression analysis to predict machining forces and tool wear relationship. Alajmi and Alfares [5] presented a model used for prediction of cutting forces which were modeled using back propagation neural network with an enhancement by differential evolution algorithm.…”

Section: Introductionmentioning

confidence: 99%

Modeling of the Cutting Forces in Turning Process Using Various Methods of Cooling and Lubricating: An Artificial Intelligence Approach

Cica

Sredanović

Lakic-Globocki

et al. 2013

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Cutting forces are one of the inherent phenomena and a very significant indicator of the metal cutting process. The work presented in this paper is an investigation of the prediction of these parameters in turning using soft computing techniques. During the experimental research focus is placed on the application of various methods of cooling and lubricating of the cutting zone. On this occasion were used the conventional method of cooling and lubricating, high pressure jet assisted machining, and minimal quantity lubrication technique. The data obtained by experiment are used to create two different models, namely, artificial neural network and adaptive networks based fuzzy inference systems for prediction of cutting forces. Furthermore, both models are compared with the experimental data and results are indicated.

show abstract

Multiple regression and neural networks analyses in composites machining

Cited by 100 publications

References 14 publications

Modelling of an Artificial Neural Network for Electrical Discharge Machining of Hot Pressed Zirconium Diboride-Silicon Carbide Composites

Modelling of an Artificial Neural Network for Electrical Discharge Machining of Hot Pressed Zirconium Diboride-Silicon Carbide Composites

Application of Statistical and Soft Computing techniques for the Prediction of Grinding Performance

Modeling of the Cutting Forces in Turning Process Using Various Methods of Cooling and Lubricating: An Artificial Intelligence Approach

Contact Info

Product

Resources

About