scholarly journals Genetic algorithm hyper-parameter optimization using Taguchi design for groundwater pollution source identification

2018 ◽  
Vol 19 (1) ◽  
pp. 137-146 ◽  
Author(s):  
Xuemin Xia ◽  
Simin Jiang ◽  
Nianqing Zhou ◽  
Xianwen Li ◽  
Lichun Wang
Keyword(s):  
Genetic Algorithm ◽  
Groundwater Pollution ◽  
Parameter Tuning ◽  
Pollution Source ◽  
Heterogeneous Porous Media ◽  
Optimization Approach ◽  
Human Beings ◽  
Transient Transport ◽  
Tuning Method ◽  
Pollutant Source

Abstract Groundwater pollution has been a major concern for human beings, since it is inherently related to people's health and fitness and the ecological environment. To improve the identification of groundwater pollution, many optimization approaches have been developed. Among them, the genetic algorithm (GA) is widely used with its performance depending on the hyper-parameters. In this study, a simulation–optimization approach, i.e., a transport simulation model with a genetic optimization algorithm, was utilized to determine the pollutant source fluxes. We proposed a robust method for tuning the hyper-parameters based on Taguchi experimental design to optimize the performance of the GA. The effectiveness of the method was tested on an irregular geometry and heterogeneous porous media considering steady-state flow and transient transport conditions. Compared with traditional GA with default hyper-parameters, our proposed hyper-parameter tuning method is able to provide appropriate parameters for running the GA, and can more efficiently identify groundwater pollution.

The Influence of Estimated Pollution Range on the Groundwater Pollution Source Identification Method Based on the Simple Genetic Algorithm

2014 ◽  
Vol 587-589 ◽  
pp. 836-841 ◽  
Author(s):  
Yu Qiao Long ◽  
Chun Yong Wu ◽  
Jian Ping Wang
Keyword(s):  
Genetic Algorithm ◽  
Groundwater Pollution ◽  
Optimization Model ◽  
Solution Method ◽  
Pollution Source ◽  
Local Optimum ◽  
Optimization Approach ◽  
Optimum Location ◽  
Migration Direction ◽  
Slight Movement

The optimization approach is common approach to solve complex PSI issues. Most researches on the optimization approach focus on the solution method of the optimization model and improving modeling efficiency. In this paper, we give our effort on the influence of estimated pollution range on the groundwater PSI problem and discuss the efficiency and accuracy of 1D and 2D PSI problems. The estimated pollution range of PSI problem could affect how much calculated time would be consumed. The bigger the estimated range is, the more time is consumed. Increasing the dimension of the PSI problem will increase the estimated range greatly, and leads to a great time consuming. A slight movement of the estimated source in the direction perpendicular to the major migrate direction leads to big bias between the calculated source location and the real location. The chance that optimization model falls into the local optimum location is growing in the major migration direction.

A PID parameter tuning method for air conditioning system based on annealing genetic algorithm

2014 ◽  
Vol 50 (3/4) ◽  
pp. 264
Author(s):  
Jianbin Nie ◽  
Yuting Zhou ◽  
N.A. Chen ◽  
Ning Han ◽  
Deying Li
Keyword(s):  
Genetic Algorithm ◽  
Air Conditioning ◽  
Parameter Tuning ◽  
Air Conditioning System ◽  
Tuning Method

An almost-parameter-free harmony search algorithm for groundwater pollution source identification

2013 ◽  
Vol 68 (11) ◽  
pp. 2359-2366 ◽  
Author(s):  
Simin Jiang ◽  
Yali Zhang ◽  
Pei Wang ◽  
Maohui Zheng
Keyword(s):  
Groundwater Pollution ◽  
Source Identification ◽  
Search Algorithm ◽  
Harmony Search ◽  
Identification Problem ◽  
Pollution Source ◽  
Harmony Search Algorithm ◽  
Optimization Approach ◽  
Pollution Source Identification

The spatiotemporal characterization of unknown sources of groundwater pollution is frequently encountered in environmental problems. This study adopts a simulation–optimization approach that combines a contaminant transport simulation model with a heuristic harmony search algorithm to identify unknown pollution sources. In the proposed methodology, an almost-parameter-free harmony search algorithm is developed. The performance of this methodology is evaluated on an illustrative groundwater pollution source identification problem, and the identified results indicate that the proposed almost-parameter-free harmony search algorithm-based optimization model can give satisfactory estimations, even when the irregular geometry, erroneous monitoring data, and prior information shortage of potential locations are considered.

scholarly journals An Effective Kalman Filter-Based Method for Groundwater Pollution Source Identification and Plume Morphology Characterization

Water ◽  
2018 ◽  
Vol 10 (8) ◽  
pp. 1063 ◽  
Author(s):  
Simin Jiang ◽  
Jinhong Fan ◽  
Xuemin Xia ◽  
Xianwen Li ◽  
Ruicheng Zhang
Keyword(s):  
Kalman Filter ◽  
Groundwater Pollution ◽  
Source Identification ◽  
Programming Model ◽  
Concentration Field ◽  
Identification Problem ◽  
Pollution Source ◽  
Pollution Sources ◽  
Optimization Approach ◽  
Pollution Source Identification

The identification of unknown groundwater pollution sources and the characterization of pollution plume remains a challenging problem. In this study, we addressed this problem by a linked simulation-optimization approach. This approach couples a contaminant transport simulation model with a Kalman filter-based method to identify groundwater pollution source and characterize plume morphology. In the proposed methodology, the concentration field library, the covariance reduction with a Kalman filter, an alpha-cut technique of fuzzy set, and a linear programming model are integrated for solving this inverse problem. The performance of this methodology is evaluated on an illustrative groundwater pollution source identification problem. The evaluation considered the random hydraulic conductivity filed, erroneous monitoring data, a prior information shortage of potential pollution sources, and an unexpected and unknown pumping well. The identified results indicate that, under these conditions, the proposed Kalman filter-based optimization model can give satisfactory estimations to pollution sources and plume morphology for domains with small and moderate heterogeneity but cannot validate the transport in the relatively high heterogeneous field.

Signal Synthesis Model Reference Adaptive Controller with Genetic Algorithm for a Control of Chemical Tank Reactor

2019 ◽  
Vol 17 (7) ◽  
Author(s):  
Harsh Goud ◽  
Pankaj Swarnkar
Keyword(s):  
Genetic Algorithm ◽  
Steady State ◽  
Parameter Tuning ◽  
Continuous Stirred Tank Reactor ◽  
Model Reference ◽  
Tank Reactor ◽  
Tuning Method ◽  
Design And Implementation ◽  
Signal Synthesis ◽  
Model Reference Adaptive

Abstract Modelling and controlling of Continuous Stirred Tank Reactor (CSTR) is one of the significant problems in the process industry. Chemical reactions inside the CSTR depend on the reference value of the temperature. Design and implementation of suitable control device for such system is a challenge for researchers. This paper proposes the Model Reference Adaptive Control (MRAC) based control strategy as a solution to control problem of CSTR. An enhancement of Signal Synthesis MRAC scheme has been proposed in this study to improve the steady-state and transient-state performance of CSTR. Genetic Algorithm (GA) based controller parameter tuning method is employed to obtain the optimal performance of the controller. This paper presents the design and implementation of conventional Proportional–Integral–Derivative (PID) tuned with Ziegler–Nichols (ZN) tuning method, PID tuned with GA, MRAC, and GA-MRAC for CSTR. Detailed comparison based on simulation studies is also presented to show the improved transient and steady state response with GA-based improved MRAC scheme.

A parameter tuning method for an elevator group control system using a genetic algorithm

1998 ◽  
Vol 124 (1) ◽  
pp. 55-64 ◽  
Author(s):  
Toshimitsu Tobita ◽  
Atsuya Fujino ◽  
Kazuhiro Segawa ◽  
Kenji Yoneda ◽  
Yoshiaki Ichikawa
Keyword(s):  
Genetic Algorithm ◽  
Control System ◽  
Parameter Tuning ◽  
Tuning Method ◽  
Group Control ◽  
Elevator Group Control
Sign in / Sign up

Export Citation Format

Share Document