scholarly journals Artificial Intelligence Mechanisms on Interactive Modified Simplex Method with Desirability Function for Optimising Surface Lapping Process

2014 ◽  
Vol 2014 ◽  
pp. 1-16
Author(s):  
Pongchanun Luangpaiboon ◽  
Sitthikorn Duangkaew
Keyword(s):  
Artificial Intelligence ◽  
Simplex Method ◽  
Material Removal ◽  
Desirability Function ◽  
Harmony Search ◽  
Process Performance ◽  
Response Level ◽  
Clamp Force ◽  
Downward Pressure ◽  
Current Operating Condition

A study has been made to optimise the influential parameters of surface lapping process. Lapping time, lapping speed, downward pressure, and charging pressure were chosen from the preliminary studies as parameters to determine process performances in terms of material removal, lap width, and clamp force. The desirability functions of the-nominal-the-best were used to compromise multiple responses into the overall desirability function level orDresponse. The conventional modified simplex or Nelder-Mead simplex method and the interactive desirability function are performed to optimise online the parameter levels in order to maximise theDresponse. In order to determine the lapping process parameters effectively, this research then applies two powerful artificial intelligence optimisation mechanisms from harmony search and firefly algorithms. The recommended condition of (lapping time, lapping speed, downward pressure, and charging pressure) at (33, 35, 6.0, and 5.0) has been verified by performing confirmation experiments. It showed that theDresponse level increased to 0.96. When compared with the current operating condition, there is a decrease of the material removal and lap width with the improved process performance indices of 2.01 and 1.14, respectively. Similarly, there is an increase of the clamp force with the improved process performance index of 1.58.

scholarly journals Hybrid Harmony Search–Artificial Intelligence Models in Credit Scoring

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 989
Author(s):  
Rui Ying Goh ◽  
Lai Soon Lee ◽  
Hsin-Vonn Seow ◽  
Kathiresan Gopal
Keyword(s):  
Artificial Intelligence ◽  
Feature Selection ◽  
Credit Scoring ◽  
Harmony Search ◽  
Model Performance ◽  
Hybrid Models ◽  
Performance Model ◽  
Computational Time ◽  
Support Vector ◽  
Artificial Intelligence Models

Credit scoring is an important tool used by financial institutions to correctly identify defaulters and non-defaulters. Support Vector Machines (SVM) and Random Forest (RF) are the Artificial Intelligence techniques that have been attracting interest due to their flexibility to account for various data patterns. Both are black-box models which are sensitive to hyperparameter settings. Feature selection can be performed on SVM to enable explanation with the reduced features, whereas feature importance computed by RF can be used for model explanation. The benefits of accuracy and interpretation allow for significant improvement in the area of credit risk and credit scoring. This paper proposes the use of Harmony Search (HS), to form a hybrid HS-SVM to perform feature selection and hyperparameter tuning simultaneously, and a hybrid HS-RF to tune the hyperparameters. A Modified HS (MHS) is also proposed with the main objective to achieve comparable results as the standard HS with a shorter computational time. MHS consists of four main modifications in the standard HS: (i) Elitism selection during memory consideration instead of random selection, (ii) dynamic exploration and exploitation operators in place of the original static operators, (iii) a self-adjusted bandwidth operator, and (iv) inclusion of additional termination criteria to reach faster convergence. Along with parallel computing, MHS effectively reduces the computational time of the proposed hybrid models. The proposed hybrid models are compared with standard statistical models across three different datasets commonly used in credit scoring studies. The computational results show that MHS-RF is most robust in terms of model performance, model explainability and computational time.

Influence of an Additional Indexing Rotary Axis on Wire EDM Performance for the Automated Manufacture of Fir Tree Slots

2019 ◽  
Author(s):  
T. Bergs ◽  
U. Tombul ◽  
T. Herrig ◽  
A. Klink ◽  
D. Welling
Keyword(s):  
Material Removal ◽  
Technology Development ◽  
Electrical Discharge Machining ◽  
Process Performance ◽  
Wire Edm ◽  
Automated Production ◽  
Rotary Axis ◽  
Rotationally Symmetric ◽  
Cutting Processes ◽  
Mechanical Strengths

Abstract The demand for higher efficiency in aircraft propulsion engines leads to materials with increasing thermo-mechanical strengths and new designs inducing filigree geometries of blisks and disks. Because of new designs which induce tighter tolerances, the high mechanical process forces in conventional cutting processes like broaching cause inacceptable geometrical deviations and high tooling costs. Due to the electro-thermal material removal mechanism, electrical discharge machining (EDM) ensures a force free and thus precise machining. The manufacture of fir tree slots in nickel-based alloys by wire EDM has been investigated in the last few years and the process was verified as an alternative technology for broaching. To get a better competitive position, the productivity can be prospectively increased by using an additional indexing rotary axis which ensures a precise and automated production of rotationally symmetric components and reduce production times e.g. for the manufacture of fir tree slots on a disk. Nevertheless, the application of these axes cause changed flushing conditions and can also affect the electrical contacting as well. Both influence the process performance and demand a technology development or adjustment of standard machining technologies. The influence of these changed machining conditions has not been investigated scientifically to date. In this paper, the surface integrity and process performance of fir tree slots machined by wire EDM on the machine table are compared with the manufacture by using an additional indexing rotary axis. The results of the investigations are supposed to create a basis for technology adaptions when using additional axes in wire EDM.

scholarly journals Understanding the Interaction of Chinese Fiscal and Monetary Policy

2021 ◽  
Vol 14 (9) ◽  
pp. 416
Author(s):  
Zehua Luan ◽  
Xiangyu Man ◽  
Xuan Zhou
Keyword(s):  
Growth Rate ◽  
Monetary Policy ◽  
Response Level ◽  
Positive Effects ◽  
Long Run ◽  
Gdp Growth Rate ◽  
Downward Pressure ◽  
Short Run ◽  
Relative Change ◽  
Fiscal And Monetary Policy

Interaction of fiscal and monetary policy is crucial for macroeconomic stability, especially for an economy with downward pressure as well as a tightened space for macro policy, like China. In this paper, we use a time-varying-parameter (TVP-VAR) model to study Chinese fiscal–monetary interaction and divide it into three periods. We claim that China went through a monetary dominant regime from 1996Q to 2017Q4 since the response of CPI to a fiscal expansion was negative in the short run and about zero in the long run, while the monetary expansion had positive effects on CPI. During this period, the response of government spending and money supply to each other’s shock had the same sign, indicating that the two policies acted as complements. However, we argue that 2008Q4 was a turning point that divided this period into two different periods. The response level of M2 growth rate to a fiscal expansion kept rising from 1996Q1 to 2008Q4, indicating the central bank’s increasingly active cooperation with fiscal policy, while it decreased from 2009Q1 to 2017Q4. Since 2018Q1, the economy has been going through a fiscal dominant regime in that the response of GDP growth rate and CPI to the fiscal expansion has sharply increased. We also argue that the relative change of the role between the two policies should be mainly attributed to the variation in the fiscal authority’s characteristics because fiscal response to a monetary shock has remained at a similar level the whole time, even if there have been changes in the characteristics of the central bank.

scholarly journals Wire electrical discharge machining nickel super alloy

Mechanik ◽  
2018 ◽  
Vol 91 (3) ◽  
pp. 220-222
Author(s):  
Rafał Świercz ◽  
Dorota Oniszczuk-Świercz ◽  
Rafał Nowicki
Keyword(s):  
Electrical Discharge ◽  
Material Removal ◽  
Electrical Discharge Machining ◽  
Removal Rate ◽  
Wire Electrical Discharge Machining ◽  
Machining Parameters ◽  
Process Performance ◽  
Influence Of Process Parameters ◽  
Super Alloy ◽  
Quality Features

This article presents the influence of process parameters of wire electrical discharge machining using coated brass on the surface roughness and material removal rate of Inconel 718. Studies were conducted by design of the experiment. Based on the survey developed mathematical models which allow selecting the most favorable machining parameters depending on the desired process performance and quality features of the surface texture.

scholarly journals Predictive Analytic on Human Resource Department Data Based on Uncertain Numeric Features Classification

2021 ◽  
Vol 15 (08) ◽  
pp. 172
Author(s):  
Asrul Huda ◽  
Noper Ardi
Keyword(s):  
Artificial Intelligence ◽  
Data Mining ◽  
Human Resource ◽  
Business Process ◽  
Business Intelligence ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Process Performance ◽  
Preventive Action ◽  
Human Resource Department

Business Intelligence is very popular and useful for a better understanding of business progress these days, and there are many different methods or tools being used in Business Intelligence. It uses combination of artificial intelligence, data mining, math, and statistic to gain better understanding and insight on the business process performance. As employees have an important role in business process, the desire to have a tool for classifying and predicting their wages are desirable. In this research, we tried to analyzed dataset from Human Resource Department, and this dataset can be used to analyst the data in order to draw a conclusion about whether any employees would prematurely leave the company, and then, a preventive action based on those parameters can be proposed. This is a kind of predictive analytic system which bases on Naïve Bayes, and it can predict whether an employee would leave or stay according to his or her characteristics. But the Naïve Bayes itself does not enough. So we develop a way to solve the problem using uncertain Numeric features classification on it. The accuracy of the result is depended on the amount and effectiveness of the training sets.

scholarly journals Penerapan Harmony Search Algorithm untuk Menyelesaikan Economic Dispatch dengan Memperhitungkan Rugi-Rugi Transmisi

2021 ◽  
Vol 7 (3) ◽  
pp. 415
Author(s):  
Purwoharjono Purwoharjono
Keyword(s):  
Artificial Intelligence ◽  
Quadratic Programming ◽  
Search Algorithm ◽  
Economic Dispatch ◽  
Harmony Search ◽  
Harmony Search Algorithm

Penelitian ini bertujuan untuk menyelesaikan masalah Economic Dispatch (EC) menggunakan metode Artificial Intelligence (AI). Salah satu metode AI tersebut adalah Metode Harmony Search Algorithm (HSA). HSA ini merupakan suatu metode yang terinspirasi dari nada-nada musik yang di dengar. Simulasi HSA ini akan di implementasikan pada  sistem 6 unit generator 425 MW yang ada di IEEE. Hasil simulasi menggunakan metode HSA dan metode Quadratic Programming (QP) dengan rugi-rugi transmisi adalah hasil metode HAS memperoleh biaya bahan bakar sebesar 24057,9070 $/h dan rugi-rugi transmisi sebesar 7,1246 MW. Sedangkan menggunakan metode QP memperoleh biaya bahan bakar sebesar 24059,4257 $/h dan rugi-rugi transmisi    7,1626 MW. Simulasi menggunakan metode HSA memperoleh biaya bahan bakar dan rugi rugi transmisi yang lebih kecil di bandingkan dengan menggunakan metode QP.

scholarly journals Multi-objective parametric optimization for high surface quality and process efficiency in micro-grinding

2020 ◽  
pp. 002029402094495
Author(s):  
Jun Wang ◽  
Qiang Ye ◽  
Man Zhao ◽  
Xusheng Shi ◽  
Tingwei Fei
Keyword(s):  
Genetic Algorithm ◽  
Response Surface Methodology ◽  
Particle Swarm Optimization ◽  
Material Removal Rate ◽  
Material Removal ◽  
Removal Rate ◽  
Desirability Function ◽  
Swarm Optimization ◽  
Multi Objective ◽  
Maximum Material Removal Rate

In this study, for the selection of maximum material removal rate and minimum surface roughness [Formula: see text] in micro-grinding of aluminum alloy through multi-response optimization, two optimization approaches are proposed based on statistical analysis and genetic algorithm. The statistical analysis–based approach applies response surface methodology according to the analysis of variance to propose a mathematical model for [Formula: see text]. In addition, the individual desirability of material removal rate, [Formula: see text], and the global desirability function are calculated, and the inverse analysis is conducted to locate input setting giving maximum desirability function. The genetic algorithm–based approach uses the improved multi-objective particle swarm optimization with the experimental data trained by support vector machine. To demonstrate that the material microstructure is a significant parameter for material removal rate and [Formula: see text], the models with and without Taylor factor consideration are developed and compared. The optimized results achieved from both response surface methodology and improved multi-objective particle swarm optimization demonstrate that the consideration of Taylor factor can significantly improve the optimization process to achieve the maximum material removal rate and minimum [Formula: see text].

Sign in / Sign up

Export Citation Format

Share Document