• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.4
• /
• pp.862-870
• /
• 2011

In this paper, we introduce a new topology of Radial Basis Function-based Polynomial Neural Networks (RPNN) that is based on a genetically optimized multi-layer perceptron with Radial Polynomial Neurons (RPNs). This study offers a comprehensive design methodology involving mechanisms of optimization algorithms, especially Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization (PSO) algorithms. In contrast to the typical architectures encountered in Polynomial Neural Networks (PNNs), our main objective is to develop a design strategy of RPNNs as follows : (a) The architecture of the proposed network consists of Radial Polynomial Neurons (RPNs). In here, the RPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Fuzzy C-Means (FCM) clustering method. The RPN dwells on the concepts of a collection of radial basis function and the function-based nonlinear (polynomial) processing. (b) The PSO-based design procedure being applied at each layer of RPNN leads to the selection of preferred nodes of the network (RPNs) whose local characteristics (such as the number of input variables, a collection of the specific subset of input variables, the order of the polynomial, and the number of clusters as well as a fuzzification coefficient in the FCM clustering) can be easily adjusted. The performance of the RPNN is quantified through the experimentation where we use a number of modeling benchmarks - NOx emission process data of gas turbine power plant and learning machine data(Automobile Miles Per Gallon Data) already experimented with in fuzzy or neurofuzzy modeling. A comparative analysis reveals that the proposed RPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• Structural Engineering and Mechanics
• /
• v.84 no.3
• /
• pp.337-344
• /
• 2022

Due to corrosion defects on the surface of the oil pipe, the sealing performance of the annular blowout preventer (BOP) decreases, and the leakage of toxic and harmful gases such as H₂S and SO₂ will threaten the safety of operators on the well. Therefore, this paper establishes the FE model for evaluating the sealing performance of BOP-oil pipe corrosion defects, which is based on the rubber large deformation theory and rubber core sealing mechanism, and designs the experiment of BOP sealing performance to verify the accuracy of the FE model. The sealing performance of BOP sealing oil pipe with corrosion defects is studied. The research results show that the sealing performance of BOP is more sensitive to the axial size of corrosion defects. With the increase of oil pipe outer diameter, the critical size of defects increases continuously. The sensitivity of radial and depth dimensions is low, When for 88.9 mm outer diameter oil pipe, the axial critical size of corrosion defect is 20 mm, the radial critical size is 16 mm and the critical depth is 2 mm. Fit the formula between the outer diameter of oil pipe and the piston increment. According to the formula, the operator can calculate the piston stroke increment required by the BOP to complete the sealing when the oil pipe is corroded.

• 유체기계공업학회:학술대회논문집
• /
• 1998.02a
• /
• pp.159-163
• /
• 1998

• The KSFM Journal of Fluid Machinery
• /
• v.9 no.1 s.34
• /
• pp.40-46
• /
• 2006

Efficiency of a centrifugal pump is known to drop rapidly with a decrease of specific speed $n_s$. However, below $n_s=60\;[min^{-1},\;m^3/min,\;m]$, the pump characteristics are not yet clear. Therefore, present study is aimed to investigate the influence of large change of specific speed on the performance of a very low specific speed centrifugal pump. Moreover, influence of impeller configuration on the performance of very low specific speed pump is investigated. The results show that very low specific speed can be accomplished by reducing volute throat sectional area using circular spacer. Influence of the spacer's location and configuration in the discharge passage on the pump performance is very small. Best efficiency of very low specific speed centrifugal pump decreases proportionally to the specific speed but the best efficiency decreases on a large scale in the range of $n_s<40$. Influence of impeller configuration on the pump performance and radial thrust of centrifugal pump are considerably small in the range of extremely low specific speed $(n_s=25)$.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.21 no.10
• /
• pp.1339-1349
• /
• 1997

A numerical method of calculating the performance of a scroll compressor for refrigerant R-22 and R-134a is presented in this paper. A series of involute curves are employed for the scroll wrap design and the compression volume is investigated geometrically. The radial leakage flow rate through tip clearance is calculated by the two-dimensional compressible flow. On the basis of the results, quasi one-dimensional leakage modeling can be applied to the performance analysis of a scroll compressor, more effectively. Furthermore, the heat transfer effect between scroll wrap and working fluid in compression chamber is considered for the performance analysis. As the results of this study, the effects of the radial and tangential leakage flow rate and heat transfer on the scroll compressor performance are derived precisely. These results may provide the guideline for the design and development of a real scroll compressor.

• Tribology and Lubricants
• /
• v.9 no.1
• /
• pp.45-54
• /
• 1993

The lubrication characteristics of line contacts between the vane and cam ring in an oil hydraulic vane pump with intravanes have been investigated. Variations of the radial acting force of a vane were calculated from previously measured results of dynamic internal pressures in four chambers surrounding a vane, and variations of the film thickness were estimated in both the rotational speed range from 500 to 1500 rpm and in the delivery pressure range from 1 to 14 MPa. The results indicate the variations of the radial acting force and film thickness. It is found that the regimes of lubrication in the vane tip contacts lover rigid-isoviscous to rigidvariable viscosities.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.315-315
• /
• 2000

In this paper, we perform the time series prediction using the SVM(Support Vector Machine). We make use of two different loss functions and two different kernel functions; i) Quadratic and $\varepsilon$-insensitive loss function are used; ii) GRBF(Gaussian Radial Basis Function) and ERBF(Exponential Radial Basis Function) are used. Mackey-Glass time series are used for prediction. For both cases, we compare the results by the SVM to those by ANN(Artificial Neural Network) and show the better performance by SVM than that by ANN.

• 연구논문집
• /
• s.33
• /
• pp.53-65
• /
• 2003

Electrostatic micro-motors can be divided into three classes: (i) salient type side drive motor, (ii) radial gap type wobble motor, (iii) axial gap type wobble motor. The working mechanism, torque evaluation, fabrication, and operational characteristics of each micro motors are compared. It is proved that axial gap type wobble motor has the bigger generating torque than that of the other type. The gear ratio of wobble motors increases the driving torque at the cost of a decreasing angular speed and decreases the friction because of the rolling motion instead of sliding at the bearing. Techniques for characterizing micro-motors performance are presented.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2203-2205
• /
• 1998

This paper describes fuzzy radial basis function networks(FRBFN) extracting fuzzy rules through the learning from training data set. The proposed FRBFN is derived from the functional equivalence between RBF networks and fuzzy inference systems. The FRBFN learn by assigning new fuzzy rules and updating the parameters of existing fuzzy rules. The parameters of the FRBFN are adjusted using the standard LMS algorithm. The performance of the FRBFN is illustrated with function approximation and system identification.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.5
• /
• pp.526-531
• /
• 1997

To control nonlinear chemical processes, a new neural linearizing control scheme is proposed. This is a hybrid of a radial basis function(RBF) network and a linear controller, thus the control action applied to the process is the sum of both control actions. Firstly, to train the RBF newtork a linear reference model is determined by analyzing the past operating data of the process. Then, the training of the RBF newtork is iteratively performed to minimize the difference between outputs of the process and the linear reference model. As a result, the apparent dynamics of the process added by the RBF newtork becomes similar to that of the linear reference model. After training, the original nonlinear control problem changes to a linear one, and the closed-loop control performance is improved by using the optimum tuning parameters of the linear controller for the linear dynamics. The proposed control scheme performs control and training simultaneously, and shows a good control performance for nonlinear chemical processes.