Wyniki wyszukiwania - BazTech

1

Design optimization of compliant mechanisms for vibration assisted machining applications using a hybrid Six Sigma, RSM-FEM, and NSGA-II approach

Pham Huy-Tuan, Nguyen Van-Khien, Dang Quang-Khoa, Duong Thi Van Anh, Nguyen Duc-Thong, Phan Thanh-Vu

Journal of Machine Engineering

|

2023

|

Vol. 23, No. 2

135--158

EN

Vibration-assisted machining, a hybrid processing method, has been gaining considerable interest recently due to its advantages, such as increasing material removal rate, enhancing surface quality, reducing cutting forces and tool wear, improving tool life, or minimizing burr formation. Special equipment must be designed to integrate the additional vibration energy into the traditional system to exploit those spectacular characteristics. This paper proposes the design of a new 2-DOF high-precision compliant positioning mechanism using an optimization process combining the response surface method, finite element method, and Six Sigma analysis into a multi-objective genetic algorithm. The TOPSIS method is also used to select the best solution from the Pareto solution set. The optimum design was fabricated to assess its performance in a vibration-assisted milling experiment concerning surface roughness criteria. The results demonstrate significant enhancement in both the manufacturing criteria of surface quality and the design approach criteria since it eliminates modelling errors associated with analytical approaches during the synthesis and analysis of compliant mechanisms.

2

A hybridization of machine learning and NSGA-II for multi-objective optimization of surface roughness and cutting force in AISI 4340 alloy steel turning

Nguyen Anh-Tu, Nguyen Van-Hai, Le Tien-Thinh, Nguyen Nhu-Tung

Journal of Machine Engineering

|

2023

|

Vol. 23, No. 1

133--153

EN

This work focuses on optimizing process parameters in turning AISI 4340 alloy steel. A hybridization of Machine Learning (ML) algorithms and a Non-Dominated Sorting Genetic Algorithm (NSGA-II) is applied to find the Pareto solution. The objective functions are a simultaneous minimum of average surface roughness (Ra) and cutting force under the cutting parameter constraints of cutting speed, feed rate, depth of cut, and tool nose radius in a range of 50–375 m/min, 0.02–0.25 mm/rev, 0.1–1.5 mm, and 0.4–0.8 mm, respectively. The present study uses five ML models – namely SVR, CAT, RFR, GBR, and ANN – to predict Ra and cutting force. Results indicate that ANN offers the best predictive performance in respect of all accuracy metrics: root-mean-squared-error (RMSE), mean-absolute-error (MAE), and coefficient of determination (R2). In addition, a hybridization of NSGA-II and ANN is implemented to find the optimal solutions for machining parameters, which lie on the Pareto front. The results of this multi-objective optimization indicate that Ra lies in a range between 1.032 and 1.048 μm, and cutting force was found to range between 7.981 and 8.277 kgf for the five selected Pareto solutions. In the set of non-dominated keys, none of the individual solutions is superior to any of the others, so it is the manufacturer's decision which dataset to select. Results summarize the value range in the Pareto solutions generated by NSGA-II: cutting speeds between 72.92 and 75.11 m/min, a feed rate of 0.02 mm/rev, a depth of cut between 0.62 and 0.79 mm, and a tool nose radius of 0.4 mm, are recommended. Following that, experimental validations were finally conducted to verify the optimization procedure.

3

The vertical screw conveying characteristics of cohesive particle and optimization of design parameters

Chen Suifan, Zhang Xiaomeng, Li Qipeng, Shen Ce, Shi Yongchang

Eksploatacja i Niezawodność

|

2023

|

Vol. 25, no. 1

art. no. 13

EN

The purpose of this paper is to solve the problem of low conveying efficiency and serious blade wear during vertical screw conveying of cohesive particles. Firstly, the reliability of DEM simulation was verified by comparing the simulated and theoretical values and the influence regularity of different design parameters (rotational speed, pitch, and clearance) on screw conveying characteristics were analyzed based on DEM. In addition, the effect of design parameters on the screw conveying characteristics is identified by ANOVA. Then, the multi-objective optimization model with the both of maximizing the average mass flow rate and minimizing the maximum wear depth of the blade was established using the polynomial fitting regression, which was solved by the non-dominated sorting genetic algorithm (NSGA-II). Finally, the comprehensive evaluation was used to determine the best design parameters. The above research results provide a certain reference for the study of cohesive particle’s vertical screw conveying characteristics and equipment optimization design.

4

Research on path optimization for multimodal transportation of hazardous materials under uncertain demand

Han Wei, Chai Huo, Zhang Jianpeng, Li Yuanping

Archives of Transport

|

2023

|

Vol. 67, iss. 3

91--104

EN

In the process of long-distance and large-volume transportation of hazardous materials (HAZMAT), multimodal transportation plays a crucial role with its unique advantages. In order to effectively reduce the transportation risk and improve the reliability of transportation, it is particularly important to choose a suitable transportation plan for multimodal transport of HAZMAT. In this paper, we study the transportation of HAZMAT in multimodal transport networks. Considering the fluctuation in demand for HAZMAT during the actual transportation process, it is difficult for decision makers to obtain the accurate demand for HAZMAT orders in advance, leading to uncertainty in the final transportation plan. Therefore, in this paper, the uncertain demand of HAZMAT is set as a triangular fuzzy random number, and a multi-objective mixed integer linear programming model is established with the objective of minimizing the total risk exposure population and the total cost in the transportation process of HAZMAT. In order to facilitate the solution of the model, we combined the fuzzy random expected value method with the fuzzy random chance constraint method based on credibility measures to reconstruct the uncertain model clearly and equivalently, and designed a non-dominated sorting genetic algorithm (NSGA-Ⅱ) to obtain the Pareto boundary of the multi-objective optimization problem. Finally, we conducted a numerical example experiment to verify the rationality of the model proposed in this paper. The experimental results indicate that uncertain demand can affect the path decision-making of multimodal transportation of HAZMAT. In addition, the confidence level of fuzzy random opportunity constraints will have an impact on the risk and economic objectives of optimizing the multimodal transportation path of HAZMAT. When the confidence level is higher than 0.7, it will lead to a significant increase in transportation risks and costs. Through sensitivity analysis, it can provide useful decision-making references for relevant departments to formulate HAZMAT transportation plans.

5

Multiobjective optimization of fluphenazine nanocomposite formulation using NSGA-II method

Abu Sharar Ahmed Adnan, Ramadan Saleem Z., Hussein-Al-Ali Samer Hasan

Materials Science Poland

|

2021

|

Vol. 39, No. 4

517--544

EN

The World Health Organization (WHO, 2019) reports that schizophrenia affects approximately 20 million people worldwide, and the annual number of new cases is estimated at 1.5%/10,000 people. As a result, there is a demand for making the relevant medicines work better. Using a fluphenazine (FZN) drug delivery system that has been optimized using nanoparticles (NPs) technology is an important alternative treatment option for noncompliant patients with schizophrenia. Compared to the conventional delivery system, the NPs delivery system provides a controlled-release treatment, minimizes drug levels reaching the blood, and has fewer side effects as well. As a result of using the NPs delivery system, patients can obtain the benefits of reduced daily dosing and improved compliance. In this context, this study was performed to develop a mathematical model for FZN to optimize its nanocomposite delivery system using a mixture-process DoE and multiobjective optimization (MOO) approaches. The influences of NPs input fabrication parameters [i.e., FZN percentage, chitosan (CS) percentage, sodium tripolyphosphate (TPP) percentage, and pH] were investigated by mixture-designed experiments and analyzed by analysis of variance (ANOVA); subsequently, based on the results of the analysis, three regression models were built for size, zeta potential (ZP), and drug loading efficiency (LE%); and thereafter, these models were validated using 26 experiments with three replicates. The MOO approach was employed using a non-dominated sorting genetic algorithm (NSGA-II) to provide the optimal fitness value of each objective function by minimizing NPs size, maximizing ZP, and maximizing LE%. Test of hypotheses showed no statistical differences between the average observed values and the corresponding predicted values calculated by the regression models (126.6 nm, 18.7 mV, and 91.6%, respectively). As there is no benchmark available for the optimal NPs input fabrication parameters in the literature, the optimized formulation was further characterized using X-ray diffraction (XRD), Fourier-transform infrared spectroscopy (FTIR), polydispersity index (PdI), and differential scanning calorimetry (DSC). Those tests indicated that FZN was successfully encapsulated into the final nanocomposite. Furthermore, an in-vitro drug release study was carried out and showed that at least 5 days would be needed for FZN to be fully released from its nanocomposite in a sustained-release pattern. The nanocomposite could serve as a model for the controlled and extended delivery of many drugs.

6

Optimal transmission expansion planning considering distributed generations by using non-dominated sorting genetic algorithm-II (NSGAII)

Kamarposhti Mehrdad Ahmadi, Kabalci Ersan

Journal of Power Technologies

|

2021

|

Vol. 101, nr 1

70--77

EN

Reconstructing power systems has changed the traditional planning of power systems and has raised new challenges in Transmission Expansion Planning (TEP). Because of these reason, new methods and criteria have been formed for planning transmission in reconstructed environments. Thus, a dynamic programming was used for transmission efficiency based on multi-objective optimization in this research. In this model, investment cost, cost of density and dependability have been considered three objectives of optimization. In this paper, NSGAII multi-objective genetic algorithm was used to solve this non-convex and mixed integer problem. A fuzzy decision method has been used to choose the final optimal answer from the Pareto solutions obtained from NSGAII. Moreover, to confirm the efficiency of NSGAII multi-objective genetic algorithm in solving TEP problem, this algorithm was implemented in an IEEE 24 bus system and the gained results were compared with previous works in this field.

7

An application of the NSGA-II algorithm in Pareto joint inversion of 2D magnetic and gravity data

Miernik Katarzyna, Węglińska Elżbieta, Danek Tomasz, Leśniak Andrzej

Geology, Geophysics and Environment

|

2021

|

Vol. 47, no. 2

59--70

EN

Joint inversion is a widely used geophysical method that allows model parameters to be obtained from the observed data. Pareto inversion results are a set of solutions that include the Pareto front, which consists of non-dominated solutions. All solutions from the Pareto front are considered the most feasible models from which a particular one can be chosen as the final solution. In this paper, it is shown that models represented by points on the Pareto front do not reflect the shape of the real model. In this contribution, a collective approach is proposed to interpret the geometry of models retrieved in inversion. Instead of choosing single solutions from the Pareto front, all obtained solutions were combined in one “heat map”, which is a plot representing the frequency of points belonging to all returned objects from the solution set. The conducted experiment showed that this approach limits the problem of equivalence and is a promising way of representing the geometry of the model that was retrieved in the inversion process.

8

Optimal planning and management of photovoltaic sources and battery storage systems in the electricity distribution networks

Zedak Chaimae, Belfqih Abdelaziz, Lekbich Anass, Boukherouaa Jamal, El Mariami Faissal

Przegląd Elektrotechniczny

|

2020

|

R. 96, nr 8

95--101

EN

In this paper, the Non-dominated Sorting Genetic Algorithm NSGA-II, accompanied by the Newton Raphson method for power flow calculation, has been applied to an IEEE 33 bus test network to plan locations of photovoltaic power plants and Battery Energy Storage Systems. In addition to the minimization of costs, total losses and the maintain of voltage within acceptable limits (minimize voltage drops), the determination of these optimal locations will make it possible to converge towards a decentralized network with optimized, local energy and close to the consumer.

PL

Przedstawiono wykorzystanie algorytmów genetycznych wspomaganych przez metodę Newton-Raphson do obliczania przepływów mocy. Analizowano szynę zgodną z IEEE 33 w planowanej sieci ze źródłami fotowoltaicznymi i bateryjnym zasobnikiem energii.

9

A practical pretreatment planning method of multiple puncturing for thermal ablation surgery

Li Jing, Xu Yuanqi, Shen Nanyan, Feng Lanyun, Ran Zhuang, Deng Zongqian

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 4

1469--1485

EN

Thermal ablation surgery serves as one of the main approaches to treat liver tumors. The pretreatment planning, which highly demands the experience and ability of the physician, plays a vital role in thermal ablation surgery. The planning of multiple puncturing is necessary for avoiding the possible interference, destroying the tumor thoroughly and minimizing the damage to healthy tissue. A GPU-independent pretreatment planning method is proposed based on multi-objective optimization, which takes the most comprehensive constraints into consideration. An adaptive decision method of closing kernel size based on Jenks Natural Breaks is utilized to describe the final feasible region more accurately. It should be noted that the reasonable procedure of solving the feasible region and the use of KD tree based high dimensional search approach are used to enhance the computational efficiency. Seven constraints are handled within 7 s without GPU acceleration. The Pareto front points of nine puncturing tests are obtained in 5 s by using the NSGA-II algorithm. To evaluate the maximum difference and similarity between the planning results and the puncturing points recommended by the physician, Hausdorff distance and overlap rate are respectively developed, the Hausdorff distances are within 30 mm in seven out of nine tests and the average value of overlap rate is 73.0% for all the tests. The puncturing paths of high safety and clinical-practice compliance can be provided by the proposed method, based on which the pretreatment planning software developed can apply to the interns' training and ability evaluating for thermal ablation surgery.

10

Prestack AVO inversion for brittleness index of shale based on BI_Zoeppritz equation and NSGA II

Bi Chenchen, Wang Yanchun, Xie Wei, Sun Wei, Liu Wei

Acta Geophysica

|

2020

|

Vol. 68, no. 4

1067--1082

EN

As one of the evaluation characteristics of shale sweet spots, the brittleness index (BI) of shale formations is of great sig nifcance in predicting the range of sweet spots, and guiding hydraulic fracturing. Based on the three elastic parameters of P-wave velocity (VP), S-wave velocity (VS) and density obtained by conventional prestack AVO inversion, BI can be calcu lated indirectly using the Rickman formula. However, the conventional AVO inversion based on Zoeppritz approximation assumes that incident angle is small and elastic parameters change slowly, which afects the inversion accuracy of the three elastic parameters. Additionally, using these three elastic parameters to obtain BI indirectly also leads to cumulative errors of the inversion results. Therefore, we propose an inversion method based on BI_Zoeppritz equation to directly estimate VP, VS and BI. The BI_Zoeppritz equation is an exact Zoeppritz equation for BI, which is used as the forward operator for the proposed method. The multi-objective function of the inversion method is optimized by a fast nondominated sorting genetic algorithm (NSGA II). An initial model and an optimized search window are used to improve the inversion accuracy. The test results of model data and actual data reveal that this method can directly obtain the BI with high precision. In addition, the stability and noise immunity of the proposed method are verifed by the seismic data with random noise.

11

Very Fast Non-Dominated Sorting

Smutnicki C., Rudy J., Żelazny D.

Decision Making in Manufacturing and Services

|

2014

|

Vol. 8, no. 1-2

13--23

EN

A new and very efficient parallel algorithm for the Fast Non-dominated Sorting of Pareto fronts is proposed. By decreasing its computational complexity, the application of the proposed method allows us to increase the speedup of the best up to now Fast and Elitist Multi-Objective Genetic Algorithm (NSGA-II) more than two orders of magnitude. Formal proofs of time complexities of basic as well as improved versions of the procedure are presented. The provided experimental results fully confirm theoretical findings.

12

Multi-Objective Optimization Based Approaches for Active Power Filter Design- A Comparison

Imani H. R., Mohamed A., Shareef H., Eslami M.

Przegląd Elektrotechniczny

|

2013

|

R. 89, nr 6

98--103

EN

This paper introduces an optimal active power filter design method to compensate simultaneously current harmonics and reactive power of a nonlinear load. The power filter consists of a passive RL low-pass filter placed in series with the load and a pure active filter which has RL elements connected in series with insulated gate bipolar transistors (IGBT) based voltage source converter. The filter is supposed to inject a current into the connection node of the load and grid in order to eliminate current harmonics and its imaginary current. The voltage source converter is placed in a hysteresis feedback control loop to generate the reference current. The band width and output amplitude of the hysteresis controller are optimized with inductance of RL filters. In solving the optimization problem, three objective functions are considered which include minimizing current total harmonic distortion (THD), maximizing power factor and minimizing the IGBT bridge current. The four optimization methods applied are the goal attainment, max ordering, non-dominated sorting genetic algorithm-II and strength Pareto evolutionary algorithm 2 (SPEA2) methods. The results of the four optimization methods are compared and it is shown that the SPEA2 method gives the best performance in terms of minimizing current THD and maximizing the power factor.

PL

Przedstawiono metody optymalizacji projektowania aktywnych filtrów mocy umożliwiające kompensację prądów harmonicznych i mocy biernej przy obciążeniu nieliniowym. Analizowany filtr składa się z pasywnego filtru dolnoprzepustowego RL połączonego szeregowo z obciążeniem i filtrem aktywnym. Filtr aktywny mam elementy R:L dołączane z wykorzystaniem tranzystora IGBT.

13

NSGA II algorithm application within the dynamic programming approach to business process optimisation

Wibig M.

Journal of Applied Computer Science

|

2013

|

Vol. 21, nr 2

195--207

EN

Processes are defined as sets of tasks which transform inputs into outputs. Based on such a definition, processes are graphically modelled as tasks and the connections (dependencies) between them. Another popular modelling practice is not to model the whole process as one enormous diagram, but to split it into high level diagram, presenting whole value chain, and detailed diagrams of sub-processes’. Rather than joining these subprocesses back into one huge process, an optimisation algorithm can use this modelling approach as an advantage. This paper describes the NSGA II algorithm and its implementation which can be used within the scheduler to use a process model with sub-processes as an input and output.

14

A multivariable multiobjective predictive controller

Ben Aicha F., Bouani F., Ksouri M.

International Journal of Applied Mathematics and Computer Science

|

2013

|

Vol. 23, no. 1

35--45

EN

Predictive control of MIMO processes is a challenging problem which requires the specification of a large number of tuning parameters (the prediction horizon, the control horizon and the cost weighting factor). In this context, the present paper compares two strategies to design a supervisor of the Multivariable Generalized Predictive Controller (MGPC), based on multiobjective optimization. Thus, the purpose of this work is the automatic adjustment of the MGPC synthesis by simultaneously minimizing a set of closed loop performances (the overshoot and the settling time for each output of the MIMO system). First, we adopt the Weighted Sum Method (WSM), which is an aggregative method combined with a Genetic Algorithm (GA) used to minimize a single criterion generated by the WSM. Second, we use the Non- Dominated Sorting Genetic Algorithm II (NSGA-II) as a Pareto method and we compare the results of both the methods. The performance of the two strategies in the adjustment of multivariable predictive control is illustrated by a simulation example. The simulation results confirm that a multiobjective, Pareto-based GA search yields a better performance than a single objective GA.

15

Multi-objective Optimization of the Allocation of DG Units considering technical, economical and environmental attributes

Chen M.-Y., Cheng S.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 12a

233-237

EN

A multi-objective optimization model which effectively replicates different perspectives is presented to address the optimal allocation of DG units. To offer diverse solutions, NSGA-II is applied to the nonlinear, combinatorial three-objective optimization problem. The encouraging simulation results suggest that the proposed approach not only optimally allocate DG units with benefits of reducing power loss, improving system’s reliability and decreasing pollutant emissions simultaneously but also provide alternative options and facilitate to make more rational evaluations.

PL

W artykule zaproponowano model optymalizacji wielozadaniowej na potrzeby rozmieszczenia rozproszonych generatorów energii. Dla zapewnienia różnorodności aplikacji, zastosowano algorytm NSGA-II do nieliniowej, kombinacyjnej optymalizacji trzyzadaniowej. Przedstawiono wyniki badań symulacyjnych potwierdzających skuteczność działania, ograniczenie strat mocy i redukcję emisji zanieczyszczeń.

16

FACTS location and size for reactive power system compensation through the multi-objective optimization

Belazzoug M., Boudour M., Sebaa K.

Archives of Control Sciences

|

2010

|

Vol. 20, no. 4

473-489

EN

The problem of the FACTS (Flexible Alternative Current Transmission System Devices) location and size for reactive power system compensation through the multi-objective optimization is presented in this paper. A new technique is proposed for the optimal setting, dimension and design of two kinds of FACTS namely: Static Volt Ampere reactive (VAR) Compensator (SVC) and Thyristor Controlled Series Compensator (TCSC) handling the minimization of transmission losses in electrical network. Using the proposed scheme, the type, the location and the rating of FACTS devices are optimized simultaneously. The problem to solve is multi criteria under constraints related to the load flow equations, the voltages, the transformer turn ratios, the active and reactive productions and the compensation devices. Its solution requires the the advanced algorithms to be applied. Thus, we propose an approach based on the evolutionary algorithms (EA) to solve multi-criterion problem. It is similar to the NSGA-II method (Ellitist Non Dominated Sorting Genetic Algorithm). The Pareto front is obtained for continuous, discrete and multiple of five MVArs (Mega Volt Ampere reactive) of compensator devices for the IEEE 57-bus test system (IEEE bus test is a standard network).