In the current study, the effect of applied load, sliding speed, and type and weight percentages of reinforcements on the wear properties of ultrahigh molecular weight polyethylene (UHMWPE) was theoretically studied. The extensive experimental results were taken from literature and modeled with artificial neural network (ANN). The feed forward (FF) back-propagation (BP) neural network (NN) was used to predict the dry sliding wear behavior of UHMWPE composites. Eleven input vectors were used in the construction of the proposed NN. The carbon nanotube (CNT), carbon fiber (CF), graphene oxide (GO), and wollastonite additives are the main input parameters and the volume loss is the output parameter for the developed NN. It was observed that the sliding speed and applied load have a stronger effect on the volume loss of UHMWPE composites in comparison to other input parameters. The proper condition for achieving the desired wear behaviors of UHMWPE by tailoring the weight percentage and reinforcement particle size and composition was presented. The proposed NN model and the derived explicit form of mathematical formulation show good agreement with test results and can be used to predict the volume loss of UHMWPE composites.
1. Introduction
Polymers have high elasticity, good process ability, and reasonable strength, so they can be called multifunctional materials. Polymer-based composites are widely used in various applications and many fields, including microelectronics, biomedical engineering, electrical devices, and filtration [1–5]. Polymer-based nanocomposites formed by adding a small amount of micro- and nanoparticles to the matrix have created great interest in engineering and science. Composites with nanoparticles display superior thermal, electrical, and mechanical properties [6–8]. The properties of the materials have been improved by adding fillers such as graphite nanosheets, CNTs, and boron nitride (BN) to polymer matrices [9–11].
UHMWPE is widely used as the matrix material in the production of polymer matrix nanocomposites. UHMWPE has so many excellent properties such as being light in weight, corrosion resistant, biocompatible, and self-lubricant. Due to these special properties and several advantages, it has gained worldwide acceptance and is widely used in military, industrial, medical, and consumer applications involving wear and friction [12, 13]. UHMWPE is a complicated material, meaning that several factors can be responsible for wear. One method of increasing the wear resistance of UHMWPE is the adding of fiber fillers and nano- and microparticles in the composition and they are called UHMWPE composites. Theoretically, polymers can be strengthened by molecular alignment of the material. When sliding loads are applied to a specimen of UHMWPE, the molecular chains begin to straighten, be untangled, and align in load direction, and the strength tends to increase in this direction. UHMWPE composites can also be further engineered at a micro- or nanometer length scale by blending polymer powder resin with micro- or nanoparticles and fibers before consolidation. UHMWPE composites were reinforced by TiO2, CNT, kaolin, CF, hydroxyapatite, Al2O3, zirconium particles [14–18], and so forth. The works have demonstrated that the addition of optimum amount of nano- and microfibers and ceramic particles into UHMWPE would significantly affect the wear rate under sliding wear conditions.
Recently, the material properties with their own characteristics, applications, advantages, and limitations are important factors for designers and materials engineers. Due to UHMWPE’s complex behaviors, finding an appropriate model for determining the wear properties of UHMWPE can be challenging. The effect of type and weight percentage of fibers and particles in composition and one of the operation parameters such as applied load and sliding speed on wear behavior of UHMWPE was investigated separately. In selecting additive materials, type and percentage for an application are important. The experimental determination of additives for desired wear behavior of UHMWPE composites is cost- and time-consuming. ANN modeling has been used to minimize the experimental study and predict the wear characteristics to establish a correlation between the wear properties and operation parameters of UHMWPE composites. Therefore, the main aim is to determine and understand the effect of type, size, and weight percentage of different reinforcement and variables in operation condition on dry sliding wear properties of UHMWPE composites.
2. Neural Network
The ANNs are a methodology in different applications of materials including prediction of tribological and mechanical properties and were used by many researchers [19–24]. Venkata Rao et al. [25] used ANN to predict surface roughness, tool wear, and amplitude of work piece vibration. They reported that the neural network can help in the selection of proper cutting parameters to reduce tool vibration and tool wear and reduce surface roughness. Gyurova and Friedrich [26] for the prediction of sliding friction and wear properties of polymer composites used ANN and stated that the prediction profiles for the characteristic tribological properties of the ANN exhibited very good agreement with the measured results. Li et al. [27] modeled the sliding wear resistance of the Ni–TiN coatings by using ANN. They explained that the proposed ANN model shows an error of approximately 4.2% and can effectively predict sliding wear resistance of Ni–TiN nanocomposite coatings.
An ANN can be defined as a massively parallel distributed processor storing experiential knowledge and making it available for use [28]. NN is a computational framework that is inspired by biological neural systems. Figure 1 shows the input layer, hidden layer, and the output layer in NN system [29]. It consists of a number of interconnected simple processing units called artificial neurons. The basic structure of an artificial neuron was shown in Figure 2. In ANN modeling, the networks include artificial neurons that consist of three main components, namely, weights, bias, and transfer function.
A typical neural network image.
The basic structure of an artificial neuron [43].
Each neuron receives inputs, attached with a weight wi, which shows the connection strength for that input for each connection. Each input is multiplied by the corresponding weight of the neuron connection. Next, a bias (bi) value is added to the summation of inputs and corresponding weights (u) according to the following equation:(1)ui=∑j=1Hwijxj+bi.
The summation ui is converted as output with an activation (transfer) function, F(ui), yielding a value called the unit’s “activation,” as in the following formula:(2)O=fui.
3. Results and Discussion
NNs are commonly classified according to training algorithms (supervised and unsupervised) and network topology (feedback and feed forward) [30]. BP learning algorithm (Levenberg-Marquardt (Trainlm)) is the most popular and effective supervised learning method used in this study [31, 32]. Sigmoid function, which joins curvilinear, linear, and constant behavior depending on the values of the input, is commonly used as transfer function in NNs [33, 34]. The weight loss of the composites was converted to volume loss, V, by dividing it with the specific composite density by the following formula [35]:(3)V=W1-W2d,where W1,2 is the weight loss before and after wear test, respectively, and d is the density of the composites. In an ANN model, each of the input and output variables was scaled to fall into a range of 0 to 1, using the following scaling formula:(4)xN=x-xminxmax-xmin,where xN is the normalized value of the parameter x and xmax and xmin are the maximum and minimum values of this parameter, respectively. Output values resulted from ANN also in the range [0,1] and transformed to its equivalent values based on reverse method of normalization technique [36]. The unnormalized method is as(5)x=xNxmax-xmin+xmin.
An extensive literature survey has been performed for collecting the experimental data. Two main processing phases of NN include training and testing. The training process is the adjustment of weights and biases in order to obtain the output through applying a proper method. Hence, the experimental results were divided in two sets, training and testing sets. The training and testing data were randomly selected among experimental results as shown in the Appendix. The input (independent) variables are UHMWPE (wt.%), ZnO (wt.%), zeolite (wt.%), CNT (wt.%), CF (wt.%), GO (wt.%), wollastonite (wt.%), size of ZnO (μm) and zeolite (μm), load (N), and sliding speed (m/s), respectively. The output or dependent variable is volume loss (mm3).
The network architecture and parameters affect the performance of NN. One of the most important duties in NN works is the determination of the numbers of layers and neurons in the hidden layers. In other words, the ANN parameters, such as the number of neurons in the input, network architecture, hidden layer, output layer, learning algorithm, and transfer function, are to be selected for developing an ANN model. There is no well-defined procedure to find the optimal parameter settings and network architecture. The trial and error approach with various numbers of neurons in one hidden layer was used to determine the number of neurons. It was observed that the optimal NN architecture with logistic sigmoid transfer function was 11–12–1 NN architecture. Figure 3 shows the optimal architecture of NN. In the present study, the NN model consists of three layers, which comprises an input layer, a hidden layer, and an output layer.
Optimal NN selection process.
The performance of NN was evaluated by the correlation coefficient (R) as in the following expression:(6)R=covyt,yt′varyt·varyt′.
Mean absolute error (MAE) and mean square error (MSE) were used as error evaluation criteria in order to facilitate the comparisons between predicted values and desired values according to the following equations:(7)MAE=1N∑i=1Nti-t^i,MSE=1N∑i=1Nti-t^i2,where N is the total number of the datasets and ti and t^i are the experimental value and predicted output value from the neural network model for a given input, respectively.
The statistical data for the training and testing sets were shown in Table 1. The correlation of NN model with the experimental data for these sets was also shown in Figures 4 and 5.
Statistical parameters of training and testing sets.
Datasets
R
MAE
MSE
Training set
0.9400
3.63
0.389
Testing set
0.9176
4.07
0.412
Correlation of NN and experimental data for training set.
Correlation of NN and experimental data for testing set.
The correlation of coefficients in training and testing sets is 0.9400 and 0.9176 which means that the performance of network model is acceptable. MAE and MSE values of volume loss are 3.63 and 0.389 for training set and 4.07 and 0.412 for testing set. If the MSE reaches zero, the performance of model is regarded as being excellent [37]. Comparison between the test and predicted values shows that the prediction of the proposed NN model is in good agreement with the experimental data and all the errors are within acceptable ranges.
R2 values of training and testing sets are 0.8837 and 0.842, respectively. R2 value compares the accuracy of the model to the accuracy of a trivial assessment model. A high R2 value (R2=1) tells that all points lie exactly on the curve with no scatter and the results have the perfect correlation. It is clear that all the values are higher than 0.84.
The wear rate of the composites is strongly influenced by many factors, such as the shape and content of reinforcement, operating conditions, the morphologies of surfaces, physical morphology between the matrix material and reinforcement, the bond strength at the matrix/reinforcement interface, and homogeneous distribution of reinforcement [38, 39]. It is difficult to find the effect of each factor on the wear volume loss of the composites and it needs extensive studies. In the current work, the operating parameters and weight percentages and sizes of reinforcement were quantified. Nevertheless, R and R2 values of training set indicate that the learning ability of NN is well enough (Table 1 and Figure 4). The effects of the other parameters can be investigated in order to increase the prediction rate of the proposed NN model. It was concluded that the proposed NN model can predict the volume loss of UHMWPE composites containing different particles with size and weight percentages with high accuracy and reliability.
The sensitivity of wear volume loss of UHMWPE composites of each input variable from the minimum to the maximum was given in Figure 6. The sliding speed is an example of factors that can contribute to wear. Our theoretical results demonstrated that the sliding speed has the greatest effect on volume loss of UHMWPE among all input parameters. The different sliding speeds can result in different wear properties. The higher the loading speed is, the more the time UHMWPE will spend in the elastic deformation stage. It is clear that any change in sliding speed, load, UHMWPE (wt.%), ZnO (wt.%), and zeolite (wt.%) will be affected by the volume loss of UHMWPE in comparison to all the other input parameters.
Sensitivity of input vectors.
4. Formulation of NN Model
The main focus is to obtain the explicit formulation of the volume loss as a function of input variables under limited conditions. The ANN models emerged as good candidates for mathematical wear models due to their capabilities in nonlinear behavior, learning from experimental data, and generalization [40]. Hutching’s group [41] and Basavarajappa et al. [42] presented pioneering investigations of ANN techniques for predicting tribological parameters.
As a result, the wear behavior under various parameters was investigated to predict and analyze the relationship between the reinforcements and volume loss of UHMWPE composites. The volume loss (X) was determined by using the formula (8)X=84.185617∗11+e-v+0.212915,where the parameters are(9)v=-2.1888∗11+e-u1+1.5322∗11+e-u2+5.8748∗11+e-u3+4.2619∗11+e-u4+-0.6620∗11+e-u5+-2.9341∗11+e-u6+-0.6885∗11+e-u7+-0.6696∗11+e-u8+0.9414∗11+e-u9+-5.8760∗11+e-u10+-6.0830∗11+e-u11+-2.7599∗11+e-u12+-0.7807,u1=-0.7182∗A1+-0.5842∗A2+-0.7211∗A3+0.5435∗A4+0.7793∗A5+-0.1909∗A6+0.4002∗A7+0.8474∗A8+-0.7288∗A9+-0.2069∗A10+-1.9995∗A11+-0.0394,u2=0.7896∗A1+-0.2539∗A2+0.1801∗A3+-0.1505∗A4+0.0765∗A5+-0.2878∗A6+0.1697∗A7+0.5636∗A8+-0.0203∗A9+-0.8914∗A10+1.9869∗A11+-0.1818,u3=-2.3087∗A1+0.4084∗A2+0.4903∗A3+-0.8781∗A4+-1.3043∗A5+-0.9548∗A6+-0.6670∗A7+2.7410∗A8+-2.1091∗A9+3.2012∗A10+1.8193∗A11+-3.4212,u4=2.0533∗A1+-3.2323∗A2+0.7227∗A3+0.0295∗A4+-0.5151∗A5+0.0588∗A6+-0.7574∗A7+-0.2123∗A8+-0.6447∗A9+4.5743∗A10+0.5803∗A11+-0.8036,u5=0.3405∗A1+-0.2333∗A2+0.2794∗A3+0.3565∗A4+0.4379∗A5+-0.0345∗A6+-0.0986∗A7+0.0275∗A8+0.6663∗A9+-0.3537∗A10+-0.4749∗A11+-0.2079,u6=0.5510∗A1+-2.2037∗A2+0.1234∗A3+0.3718∗A4+0.3239∗A5+0.5667∗A6+-0.2435∗A7+-0.7447∗A8+1.1467∗A9+-2.4374∗A10+0.0093∗A11+0.0879,u7=0.1883∗A1+-0.4882∗A2+0.0982∗A3+0.1593∗A4+-0.0599∗A5+0.5295∗A6+0.3879∗A7+-0.2778∗A8+0.6221∗A9+-0.2125∗A10+-0.3791∗A11+0.1155,u8=0.7380∗A1+0.0758∗A2+0.4082∗A3+-0.0235∗A4+0.2302∗A5+-0.1718∗A6+0.0265∗A7+1.2521∗A8+-0.4670∗A9+1.0054∗A10+0.8061∗A11+0.5412,u9=0.2707∗A1+0.7648∗A2+0.2012∗A3+-0.4448∗A4+-0.5107∗A5+-0.2796∗A6+-0.1827∗A7+0.1138∗A8+-0.6849∗A9+0.4180∗A10+0.2120∗A11+-0.4322,u10=-1.8196∗A1+0.3943∗A2+-0.3793∗A3+-0.1015∗A4+-0.6886∗A5+-0.0171∗A6+-0.0900∗A7+2.7289∗A8+-0.3999∗A9+-6.8627∗A10+1.5364∗A11+-1.7102,u11=-0.0124∗A1+-2.2261∗A2+-0.5712∗A3+0.1810∗A4+0.7198∗A5+-0.3316∗A6+0.4865∗A7+-0.8473∗A8+-1.0742∗A9+4.8908∗A10+-1.9057∗A11+-0.4736,u12=-0.1888∗A1+-2.3874∗A2+-0.1633∗A3+0.2577∗A4+0.4452∗A5+0.0305∗A6+0.0384∗A7+-0.9836∗A8+0.0058∗A9+-2.1195∗A10+2.0152∗A11+-0.8806,where A1, A2, A3, A4, A5, A6, A7, A8, A9, A10, and A11 are normalized values of UHMWPE, ZnO (wt.%), zeolite (wt.%), CNT (wt.%), CF (wt.%), GO (wt.%), wollastonite (wt.%), size of ZnO and zeolite (μm),load (N), and sliding speed (m/s), respectively.
Using derived formulation, the wear volume loss of UHMWPE composite with the size of 1 μm and 5 wt.% ZnO under 10 N load at a sliding speed of 0.033 m/s was determined as 3.093 mm3. In the same experimental conditions, to decrease the wear volume loss to 1.992±0.165 mm3, the 1 wt.% of zeolite with the size of 45 μm was added according to the NN model theoretically. As a result, the wear volume loss formulation of UHMWPE was evaluated and the two volume loss values were calculated by using this formulation. Additionally, the correlation coefficients of the proposed equations were also evaluated. The correlations of NN, formulation, and experimental data were given in Figure 7.
Correlation of (a) NN and formulation and (b) NN and testing set.
It is clear that R2 values of formulation and NN model and formulation and experimental results are 0.9778 and 0.8097, respectively. This means that the proposed NN model (formulation) can predict the volume loss of the composites with 80.97% accuracy.
5. Conclusion
This study proposes an approach of artificial neural network modeling for the wear volume loss in the prediction of UHMWPE composites with different fibers and particles and in various operating parameters. The proposed NN model shows good agreement with the experimental results. Therefore, the explicit mathematical function was derived from ANN models. In the accuracy of the well-trained ANN model, all R2 values for training, testing, and formulation are bigger than 0.80 and the predicted model is of a high reliability rate. The mean absolute error for predicted values does not exceed 4.1%. The sensitivity analysis of the developed NN model demonstrated that sliding speed and applied load are the significant variables in affecting the volume loss. Hence, it was concluded that ANN is a successful and advantageous analytical tool for determining the properties of UHMWPE composites with considerable saving in cost and time.
Appendix
See Table 2.
Dataset used NN model.
Reference
UHMWPE
ZnO (wt.%)
Zeolite(wt.%)
CNT (wt.%)
CF (wt.%)
GO (wt.%)
Wollastonite(wt.%)
Load(N)
Sliding speed (m/s)
Volume loss (mm3)
Chang et al. [44]
100
—
—
—
—
—
—
10
0,033
5,699
95
5
—
—
—
—
—
10
0,033
3,093
90
10
—
—
—
—
—
10
0,033
2,075
85
15
—
—
—
—
—
10
0,033
2,329
80
20
—
—
—
—
—
10
0,033
2,413
95
5
—
—
—
—
—
10
0,033
3,781
90
10
—
—
—
—
—
10
0,033
2,218
85
15
—
—
—
—
—
10
0,033
1,962
80
20
—
—
—
—
—
10
0,033
2,091
100
—
—
—
—
—
—
20
0,033
13,333
95
5
—
—
—
—
—
20
0,033
6,101
90
10
—
—
—
—
—
20
0,033
6,440
85
15
—
—
—
—
—
20
0,033
6,927
80
20
—
—
—
—
—
20
0,033
6,541
95
5
—
—
—
—
—
20
0,033
6,358
90
10
—
—
—
—
—
20
0,033
4,150
85
15
—
—
—
—
—
20
0,033
4,965
80
20
—
—
—
—
—
20
0,033
4,611
100
—
—
—
—
—
—
30
0,033
15,914
95
5
—
—
—
—
—
30
0,033
10,225
90
10
—
—
—
—
—
30
0,033
9,159
85
15
—
—
—
—
—
30
0,033
8,582
80
20
—
—
—
—
—
30
0,033
7,613
95
5
—
—
—
—
—
30
0,033
7,905
90
10
—
—
—
—
—
30
0,033
4,722
85
15
—
—
—
—
—
30
0,033
7,172
80
20
—
—
—
—
—
30
0,033
4,986
100
—
—
—
—
—
—
10
0,368
22,151
95
5
—
—
—
—
—
10
0,368
14,435
90
10
—
—
—
—
—
10
0,368
13,094
85
15
—
—
—
—
—
10
0,368
12,566
80
20
—
—
—
—
—
10
0,368
10,723
95
5
—
—
—
—
—
10
0,368
14,092
90
10
—
—
—
—
—
10
0,368
9,874
85
15
—
—
—
—
—
10
0,368
12,382
80
20
—
—
—
—
—
10
0,368
8,096
100
—
—
—
—
—
—
20
0,368
27,742
95
5
—
—
—
—
—
20
0,368
18,818
90
10
—
—
—
—
—
20
0,368
17,029
85
15
—
—
—
—
—
20
0,368
15,631
80
20
—
—
—
—
—
20
0,368
13,993
95
5
—
—
—
—
—
20
0,368
16,326
90
10
—
—
—
—
—
20
0,368
12,665
85
15
—
—
—
—
—
20
0,368
13,669
80
20
—
—
—
—
—
20
0,368
11,312
100
—
—
—
—
—
—
30
0,368
29,032
95
5
—
—
—
—
—
30
0,368
22,255
90
10
—
—
—
—
—
30
0,368
17,816
85
15
—
—
—
—
—
30
0,368
17,347
80
20
—
—
—
—
—
30
0,368
15,923
95
5
—
—
—
—
—
30
0,368
17,271
90
10
—
—
—
—
—
30
0,368
13,309
85
15
—
—
—
—
—
30
0,368
15,324
80
20
—
—
—
—
—
30
0,368
12,867
100
—
—
—
—
—
—
10
1,022
23,226
95
5
—
—
—
—
—
10
1,022
14,435
90
10
—
—
—
—
—
10
1,022
13,952
85
15
—
—
—
—
—
10
1,022
10,482
80
20
—
—
—
—
—
10
1,022
9,543
95
5
—
—
—
—
—
10
1,022
14,350
90
10
—
—
—
—
—
10
1,022
13,666
85
15
—
—
—
—
—
10
1,022
15,018
80
20
—
—
—
—
—
10
1,022
9,704
100
—
—
—
—
—
—
20
1,022
27,527
95
5
—
—
—
—
—
20
1,022
31,277
90
10
—
—
—
—
—
20
1,022
22,682
85
15
—
—
—
—
—
20
1,022
20,657
80
20
—
—
—
—
—
20
1,022
18,818
95
5
—
—
—
—
—
20
1,022
26,895
90
10
—
—
—
—
—
20
1,022
22,825
85
15
—
—
—
—
—
20
1,022
24,458
80
20
—
—
—
—
—
20
1,022
16,942
100
—
—
—
—
—
—
30
1,022
53,333
95
5
—
—
—
—
—
30
1,022
84,207
90
10
—
—
—
—
—
30
1,022
58,958
85
15
—
—
—
—
—
30
1,022
60,500
80
20
—
—
—
—
—
30
1,022
58,171
95
5
—
—
—
—
—
30
1,022
42,361
90
10
—
—
—
—
—
30
1,022
39,067
85
15
—
—
—
—
—
30
1,022
30,465
80
20
—
—
—
—
—
30
1,022
33,348
Chang et al. [45]
100
—
—
—
—
—
—
10
0,209
2,800
90
—
10
—
—
—
—
10
0,209
2,200
80
—
20
—
—
—
—
10
0,209
2,200
100
—
—
—
—
—
—
20
0,209
5,000
90
—
10
—
—
—
—
20
0,209
3,600
80
—
20
—
—
—
—
20
0,209
3,500
100
—
—
—
—
—
—
30
0,209
5,900
90
—
10
—
—
—
—
30
0,209
4,700
80
—
20
—
—
—
—
30
0,209
4,700
100
—
—
—
—
—
—
10
0,419
4,700
90
—
10
—
—
—
—
10
0,419
3,900
80
—
20
—
—
—
—
10
0,419
3,100
100
—
—
—
—
—
—
20
0,419
6,500
90
—
10
—
—
—
—
20
0,419
6,000
80
—
20
—
—
—
—
20
0,419
5,200
100
—
—
—
—
—
—
30
0,419
8,100
90
—
10
—
—
—
—
30
0,419
7,900
80
—
20
—
—
—
—
30
0,419
6,200
100
—
—
—
—
—
—
10
0,838
8,000
90
—
10
—
—
—
—
10
0,838
5,900
80
—
20
—
—
—
—
10
0,838
5,000
100
—
—
—
—
—
—
20
0,838
9,800
90
—
10
—
—
—
—
20
0,838
9,000
80
—
20
—
—
—
—
20
0,838
7,000
100
—
—
—
—
—
—
30
0,838
11,000
90
—
10
—
—
—
—
30
0,838
10,500
80
—
20
—
—
—
—
30
0,838
8,900
Zoo et al. [18]
100
—
—
—
—
—
—
5
0,300
0,376
99,9
—
—
0,1
—
—
—
5
0,300
0,268
99,8
—
—
0,2
—
—
—
5
0,300
0,134
99,5
—
—
0,5
—
—
—
5
0,300
0,021
Dangsheng [14]
100
—
—
—
—
—
—
196
0,420
1,820
95
—
—
—
5
—
—
196
0,420
1,400
90
—
—
—
10
—
—
196
0,420
1,350
85
—
—
—
15
—
—
196
0,420
1,110
80
—
—
—
20
—
—
196
0,420
0,730
70
—
—
—
30
—
—
196
0,420
0,590
Tai et al. [46]
100
—
—
—
—
—
—
5
0,090
0,043
99,9
—
—
—
—
0,1
—
5
0,090
0,038
99,7
—
—
—
—
0,3
—
5
0,090
0,033
99,3
—
—
—
—
0,7
—
5
0,090
0,028
99
—
—
—
—
1
—
5
0,090
0,028
98
—
—
—
—
2
—
5
0,090
0,026
97
—
—
—
—
3
—
5
0,090
0,025
Tong et al. [47]
100
—
—
—
—
—
—
120
0,530
1,73
95
—
—
—
—
—
5
120
0,530
1,31
90
—
—
—
—
—
10
120
0,530
1,2
85
—
—
—
—
—
15
120
0,530
1,58
80
—
—
—
—
—
20
120
0,530
1,8
90
—
—
—
—
—
10
40
0,530
0,25
90
—
—
—
—
—
10
80
0,530
0,7
90
—
—
—
—
—
10
160
0,530
2,28
Conflict of Interests
The authors declare that there is no conflict of interests regarding the publication of this paper.
HuangZ.-M.ZhangY.-Z.KotakiM.RamakrishnaS.A review on polymer nanofibers by electrospinning and their applications in nanocomposites200363152223225310.1016/s0266-3538(03)00178-72-s2.0-0141683910KimY.LeeH.ParkS.ZhangX.Stress relaxation test of molding compound for MEMS packagingProceedings of the 13th InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm '12)June 2012San Diego, Calif, USAIEEE29029610.1109/itherm.2012.62314422-s2.0-84866150356LuytA. S.MolefiJ. A.KrumpH.Thermal, mechanical and electrical properties of copper powder filled low-density and linear low-density polyethylene composites20069171629163610.1016/j.polymdegradstab.2005.09.0142-s2.0-33645150837WooL.LingM. T. K.DingS. Y.WestphalS. P.Effect of ionizing radiation on the thermal oxidative stability of medical polymers19983241-217918510.1016/s0040-6031(98)00534-62-s2.0-0012989815DevasahayamS.YarlagaddaP.Mechanics of polyropylene-seed-coat-fibres composites andpolyropylene-wood fibres composites—a comparative study2014971915192810.1016/j.proeng.2014.12.345ShimB. S.StarkovichJ.KotovN.Multilayer composites from vapor-grown carbon nano-fibers20066691171117810.1016/j.compscitech.2005.11.0042-s2.0-33646194642LeeW. S.YuJ.Comparative study of thermally conductive fillers in underfill for the electronic components200514101647165310.1016/j.diamond.2005.05.0082-s2.0-24144499437ChoudharyV.GuptaA.Polymer/carbon nanotube nanocomposites2011chapter 4Rijeka, CroatiaInTech659010.5772/18423ZhaoW.WangH.TangH.ChenG.Facile preparation of epoxy-based composite with oriented graphite nanosheets200647268401840510.1016/j.polymer.2006.09.0252-s2.0-33751423618KemalogluS.OzkocG.AytacA.Properties of thermally conductive micro and nano size boron nitride reinforced silicon rubber composites20104991-2404710.1016/j.tca.2009.10.0202-s2.0-75149142776XieX.-L.MaiY.-W.ZhouX.-P.Dispersion and alignment of carbon nanotubes in polymer matrix: a review20054948911210.1016/j.mser.2005.04.0022-s2.0-22344447856KurtzS. M.2009Elsevier ScienceBarbourP. S. M.StoneM. H.FisherJ.A study of the wear resistance of three types of clinically applied UHMWPE for total replacement hip prostheses199920222101210610.1016/s0142-9612(99)00096-42-s2.0-0032879782DangshengX.Friction and wear properties of UHMWPE composites reinforced with carbon fiber2005592-317517910.1016/j.matlet.2004.09.0112-s2.0-9744273195PlumleeK.SchwartzC. J.Improved wear resistance of orthopaedic UHMWPE by reinforcement with zirconium particles20092675–871071710.1016/j.wear.2008.11.0282-s2.0-65749104667GuofangG.HuayongY.XinF.Tribological properties of kaolin filled UHMWPE composites in unlubricated sliding20042561-2889410.1016/S0043-1648(03)00394-62-s2.0-1642546250XiongD.LinJ.FoanD.JinZ.Wear of nano-TiO2/UHMWPE composites radiated by gamma ray under physiological saline water lubrication200718112131213510.1007/s10856-007-3199-y2-s2.0-36448938194ZooY.-S.AnJ.-W.LimD.-P.LimD.-S.Effect of carbon nanotube addition on tribological behavior of UHMWPE200416430531010.1023/B:TRIL.0000015206.21688.872-s2.0-2142650179DurmuşH. K.ÖzkayaE.MeriçC.The use of neural networks for the prediction of wear loss and surface roughness of AA 6351 aluminium alloy200627215615910.1016/j.matdes.2004.09.0112-s2.0-23944514874ÇetinelH.ÖztürkH.ÇelikE.KarlikB.Artificial neural network-based prediction technique for wear loss quantities in Mo coatings2006261101064106810.1016/j.wear.2006.01.0402-s2.0-33751062861ZhangZ.FriedrichK.VeltenK.Prediction on tribological properties of short fibre composites using artificial neural networks20022527-866867510.1016/s0043-1648(02)00023-62-s2.0-0036530936VassilopoulosA. P.GeorgopoulosE. F.DionysopoulosV.Artificial neural networks in spectrum fatigue life prediction of composite materials2007291202910.1016/j.ijfatigue.2006.03.0042-s2.0-33748957932KurtH. I.OduncuogluM.Formulation of the effect of different alloying elements on the tensile strength of the in situ Al-Mg2Si composites20155137138210.3390/met5010371KurtH. I.OduncuogluM.Effects of temperature, time, magnesium, and copper on the wettability of Al/TiC systemMathematical Problems in Engineering. In pressVenkata RaoK.MurthyB. S. N.Mohan RaoN.Prediction of cutting tool wear, surface roughness and vibration of work piece in boring of AISI 316 steel with artificial neural network2014511637010.1016/j.measurement.2014.01.0242-s2.0-84894247940GyurovaL. A.FriedrichK.Artificial neural networks for predicting sliding friction and wear properties of polyphenylene sulfide composites201144560360910.1016/j.triboint.2010.12.0112-s2.0-79952484326LiX.ZhuY.XiaoG.Application of artificial neural networks to predict sliding wear resistance of Ni-TiN nanocomposite coatings deposited by pulse electrodeposition2014408, part A117671177210.1016/j.ceramint.2014.04.0052-s2.0-84899158159HaykinS. S.1999Prentice HallYurdakulM.AkdasH.Modeling uniaxial compressive strength of building stones using non-destructive test results as neural networks input parameters2013471010101910.1016/j.conbuildmat.2013.05.1092-s2.0-84879478523Hecht-NielsenR.1990Addison-WesleyRumelhartD. E.HintonG. E.WilliamsR. J.DavidE. R.JamesL. M.GroupC. P. R.Learning internal representations by error propagation19861MIT Press318362CevikA.KutukM. A.ErkligA.GuzelbeyI. H.Neural network modeling of arc spot welding20082021–313714410.1016/j.jmatprotec.2007.09.0252-s2.0-42949130573RoigerR.GeatzM.2003Addison-WesleyLaroseD. T.Neural Networks2005John Wiley & Sons128146ChangB. P.AkilH. M.AffendyM. G.KhanA.NasirR. B. M.Comparative study of wear performance of particulate and fiber-reinforced nano-ZnO/ultra-high molecular weight polyethylene hybrid composites using response surface methodology20146380581910.1016/j.matdes.2014.06.031HassanA. M.AlrashdanA.HayajnehM. T.MayyasA. T.Prediction of density, porosity and hardness in aluminum-copper-based composite materials using artificial neural network2009209289489910.1016/j.jmatprotec.2008.02.0662-s2.0-58149145882SunY.ZengW. D.ZhangX. M.ZhaoY. Q.MaX.HanY. F.Prediction of tensile property of hydrogenated Ti600 titanium alloy using artificial neural network201120333534010.1007/s11665-010-9695-02-s2.0-79958284867SudheerM.PrabhuR.RajuK.BhatT.Effect of filler content on the performance of epoxy/PTW composites201420141197046810.1155/2014/9704682-s2.0-84901281338GuptaA.KumarA.PatnaikA.BiswasS.Effect of different parameters on mechanical and erosion wear behavior of bamboo fiber reinforced epoxy composites201120111059290610.1155/2011/5929062-s2.0-84861614592Dolata-GroszA.WieczorekJ.Tribological properties of hybrid composites containing two carbide phases2007283149155MahendraK. V.RadhakrishnaK.Characterization of stir cast Al-Cu-(fly ash + SiC) hybrid metal matrix composites2010448989100510.1177/00219983093463862-s2.0-77951106293BasavarajappaS.ChandramohanG.MukundK.AshwinM.PrabuM.Dry sliding wear behavior of Al 2219/SiCp-Gr hybrid metal matrix composites200615666867410.1361/105994906X1508032-s2.0-33845546131CevikA.GuzelbeyI. H.Neural network modeling of strength enhancement for CFRP confined concrete cylinders200843575176310.1016/j.buildenv.2007.01.0362-s2.0-37549035095ChangB.-P.AkilH. M.NasirR. B. M.Comparative study of micro- and nano-ZnO reinforced UHMWPE composites under dry sliding wear20132971-21120112710.1016/j.wear.2012.11.0832-s2.0-84872412380ChangB. P.AkilH. M.NasirR. M.Mechanical and tribological properties of Zeolite-reinforced UHMWPE composite for implant application201368889410.1016/j.proeng.2013.12.152TaiZ.ChenY.AnY.YanX.XueQ.Tribological behavior of UHMWPE reinforced with graphene oxide nanosheets2012461556310.1007/s11249-012-9919-62-s2.0-84862822282TongJ.MaY.JiangM.Effects of the wollastonite fiber modification on the sliding wear behavior of the UHMWPE composites20032551–673474110.1016/s0043-1648(03)00221-72-s2.0-0041627754