Multi-objective Genetic Algorithm Technique Research Articles

Optimization of wear parameters for ECAP-processed ZK30 alloy using response surface and machine learning approaches: a comparative study

The present research applies different statistical analysis and machine learning (ML) approaches to predict and optimize the processing parameters on the wear behavior of ZK30 alloy processed through equal channel angular pressing (ECAP) technique. Firstly, The ECAPed ZK30 billets have been examined at as-annealed (AA), 1-pass, and 4-passes of route Bc (4Bc). Then, the wear output responses in terms of volume loss (VL) and coefficient of friction (COF) have been experimentally investigated by varying load pressure (P) and speed (V) using design of experiments (DOE). In the second step, statistical analysis of variance (ANOVA), 3D response surface plots, and ML have been employed to predict the output responses. Subsequently, genetic algorithm (GA), hybrid DOE–GA, and multi-objective genetic algorithm techniques have been used to optimize the input variables. The experimental results of ECAP process reveal a significant reduction in the average grain size by 92.7% as it processed through 4Bc compared to AA counterpart. Furthermore, 4Bc exhibited a significant improvement in the VL by 99.8% compared to AA counterpart. Both regression and ML prediction models establish a significant correlation between the projected and the actual data, indicating that the experimental and predicted values agreed exceptionally well. The minimal VL at different ECAP passes was obtained at the highest condition of the wear test. Also, the minimal COF for all ECAP passes was obtained at maximum wear load. However, the optimal speed in the wear process decreased with the number of billets passes for minimum COF. The validation of predicted ML models and VL regression under different wear conditions have an accuracy range of 70–99.7%, respectively.

Energy audit and management of environmental GHG emissions based on multi-objective genetic algorithm and data envelopment analysis: An agriculture case

This study aimed to address the challenges of energy consumption and environmental emissions in the mushroom production sector through an energy audit analysis and life cycle assessment approach. The main objective of the study was to estimate energy and environmental indicators, optimize their outputs using multi-objective genetic algorithm and data envelopment analysis methods, and identify opportunities for energy savings in the mushroom production process. The energy flow analysis revealed that the total input energy for mushroom production was 1022537.82 MJ/m2, while the total output energy was only 11125.94 MJ/m2, resulting in an energy use efficiency rate of 0.01, indicating significant energy imbalance and inefficiency. Electrical energy consumption had the largest share of total consumed energy, approximately 80.6%. The life cycle assessment results showed that the mushroom production chain emits about 8.50 × 10+3 kg of CO2 GHG. The results of energy optimization demonstrate that between 6.5% and 25% reductions in energy utilization can be achieved during mushroom production. Among the input energies, compost had the largest quota in energy savings of almost 7% and 26% by data envelopment analysis and multi-objective genetic algorithm techniques, respectively. Thus, it is recommended to implement the multi-objective genetic algorithm technique to identify opportunities for energy savings and reduce environmental emissions in the mushroom production sector, which can lead to significant energy savings and contribute to environmental sustainability while reducing operating costs.

Different Path Planning Techniques for an Indoor Omni-Wheeled Mobile Robot: Experimental Implementation, Comparison and Optimization

Omni-wheeled mobile robots (Omni WMRs) are commonly used in indoor navigation applications like surveillance, search and rescue, and autonomous transportation. They are always characterized by their versatility, mobility and high payload. This paper presents the mechatronic design, low-level control and high-level control of an indoor 4 Omni-Wheeled Mobile Robot (4OWMR). Since autonomy and path planning are research necessities for WMRs, four heuristic and probabilistic path-planning techniques are chosen for experimental implementation. The selected techniques are PRM (Probabilistic Roadmaps), RRT (Rapidly exploring Random Tree), RRTSTAR (RRT*), and ASTAR (A*) algorithms. The proposed environments are static, expressed by maps with unknown nodes and obstacles. Local path planning is implemented with simultaneous localization and mapping (SLAM). Path planning techniques are programmed, and the obtained paths are optimized by a multi-objective genetic algorithm technique to ensure the shortest path and its smoothness. The optimized paths are deployed to the 4OWMR. The obtained results are compared in terms of travel time, travel distance, average velocity and convergence error. A ranking technique is utilized to rank the obtained results and show the most preferred technique in terms of energy consumption and convergence accuracy in addition to the overall ranking. Experimental results showed that the Hybrid A* algorithm produced the best-generated paths with respect to other techniques.

Design optimization of prismatic rib turbulators in a rectangular channel based on multi-objective criterion

A multi-objective shape optimization of truncated prismatic ribs in a rectangular channel has been performed to optimize simultaneously, heat transfer and pressure loss. The numerical analysis was performed using Reynolds-averaged Navier-Stokes equations with eddy viscosity-based models for turbulence closure. The optimization was performed using multi-objective genetic algorithm technique, and the fitness functions for the objectives were obtained using surrogate modeling. Using literature survey and preliminary parametric analysis, three design variables related to prismatic ribs viz. ratio of rib-height (e) to hydraulic-diameter (Dh) of a rectangular channel, ratio of rib-pitch (p) to rib-height (e), and ratio of rib-height at end (ep) to rib-height at center (e) were selected. The augmentation Nusselt number (FNu) and friction factor (Ff) ratios were chosen as the multi-objective functions for heat transfer and pressure drop, respectively in the rectangular channel. Numerical analysis and multi-objective optimization have been done at fixed Reynolds number, Re = 42,500. Using the proposed optimization framework, Pareto-optimal front design (POD) signifies the trade-off between the obtained objective functions, and among them, five PODs have been chosen using K-means clustering technique. In the paper, results indicated that the POD which offer high blockage effect to the incoming flow lead to high heat transfer performance, but accompanied by greater pressure losses. The blockage effect is discussed using spatial flow and thermal patterns. An optimum design with a relative thermal performance enhancement of 168.60% compared with the reference design is reported.

Image Fusion by a Hybrid Multiobjective Genetic Algorithm Technique

Sensors used in image acquisition. This sensor technology is going on upgrading as per user need or as per need of an application. Multiple sensors collect the information of their respective wavelength band. But one sensor is not sufficient to acquire the complete information of one scene. To gain the overall data of one part, it becomes essential to cartel the images from multiple sources. This is achieved through merging. It is the method of merging the data from dissimilar input sources to create a more informative image compared with an image from a single input source. These are multisensor photos e.g. panchromatic and multispectral images. The first image offers spatial records whereas the lateral image offers spectral data. Through visible inspections, the panchromatic photo is clearer than a multispectral photo however the grey shade image is. Articles are greater clear however now not recognized whereas multispectral picture displays one of a kind shades however performing distortion. So comparing the characteristics of these two images, the resultant image is greater explanatory than these enter images. Fusion is done using different transform methods as well as the genetic algorithm. Comparing the results obtained by these methods, the output image by the genetic algorithm is clearer. The feature of the resultant image is verified through parameters such as root mean square error, peak signal to noise ratio, mutual information, and spatial frequency. In the subjective analysis, some transform techniques also giving exact fused images. The hybrid approach combines the transform technique and a genetic algorithm is used for image fusion. This is again compared with genetic algorithm results. The same performance parameters are used. And it is observed that the hybrid genetic algorithm is superior to the genetic algorithm. Here the only root means square error parameter is considered under the fitness function of the genetic algorithm so only this parameter is far better than the remaining parameters. If we consider all parameters in the fitness function of the genetic algorithm then all parameters using a hybrid genetic algorithm will give better performance. This method is called a hybrid multiobjective genetic algorithm.

Controllable thermal state design method of flexible shapes of piston cooling galleries

The uneven temperature field is a great contributor to abnormal deformations and local damages of the piston. The piston gallery cooling is one of the effective ways to achieve an acceptable temperature field of the piston head. However, the traditional design of piston cooling gallery cannot accurately control the local thermal state of the piston, such as the temperature in the piston ring zone. In this paper, a flexible design model is adopted to control local thermal state of piston cooling gallery, and 10 parameters are used to completely determine the cross-section shape and the position of the cooling gallery. The maximum temperature and the maximum temperature gradient of the piston are employed as optimization targets to describe the thermal state of the whole piston. Most importantly, the temperature of the first ring zone is adopted as controllable target to monitor the local thermal state of the piston ring zone. The optimal structure variables and position variables were acquired by a Multi-Objective Genetic Algorithm technique. The results show that support vector machine for regression (SVR) model has a very excellent generalization ability with the determination coefficient greater than 0.90 and the relative deviation less than 7%. The SVR model can quickly obtain the cooling performance of each sample point to save calculation cost. The results illustrate that the controllable thermal state design method is effective, resulting in decreasing thermal load of the piston and adding reliability of the engine. For special focusing on the maximum temperature of the first ring zone, three distinctive optimal solutions (denoted A, B, C) are much lower than original model and other optimization models. Solution A has the lowest the temperature of the first ring zone in three optimal solutions to meet stricter cooling requirements of ring zone. Meanwhile, the temperature of the piston is also affected by the controllable thermal state design method, which have the large reduction with 5.40%. The temperature and temperature gradient are contradictory relationship. Thus, solution A possesses highest temperature gradient, which is 11841.3 °C/m. On the contrary, solution C pay attention to optimize the thermal strength of the piston, its temperature gradient is 11445.7 °C/m. The maximum temperature of the piston and the maximum temperature of the first ring zone are 356.5 °C and 298.3 °C, respectively. Solution B is a compromise between the solution A and the solution C, which is a design solution at which three optimization objectives are sufficiently satisfied. The controllable thermal state design method is adopted to control the design goal of the one or more feature regions of the piston.

Development and Evaluation of Combined Adaptive Neuro-Fuzzy Inference System and Multi-Objective Genetic Algorithm in Energy, Economic and Environmental Life Cycle Assessments of Oilseed Production

Energy consumption, economics, and environmental impacts of canola production were assessed using a combined technique involving an adaptive neuro-fuzzy inference system (ANFIS) and a multi-objective genetic algorithm (MOGA). Data were collected from canola farming enterprises in the Mazandaran province of Iran and were used to test the application of the combined modeling algorithms. Life cycle assessment (LCA) for one ha functional unit of canola production from cradle to farm gate was conducted in order to evaluate the impacts of energy, materials used, and their environmental emissions. MOGA was applied to maximize the output energy and benefit-cost ratio, and to minimize environmental emissions. The combined ANFIS–MOGA technique resulted in a 6.2% increase in energy output, a 144% rise in the benefit-cost ratio, and a 19.8% reduction in environmental emissions from the current canola production system in the studied region. A comparison of ANFIS–MOGA with the data envelopment analysis approach was also conducted and the results established that the former is a better system than the latter because of its ability to generate optimum conditions that allow for the assessment of a combination of parameters such as energy, economic, and environmental impacts of agricultural production systems.

A multi-objective model to optimal selection of safety measures in oil and gas facilities

Optimal selection of safety measures (SMs) is a challenging task for safety managers due to its importance, complexity, and incapability of traditional approaches in considering all the aspects of SMs optimal selection. Sophisticated mathematical models can be used to overcome the limitations of traditional approaches. However, setting the objective functions while considering their priorities as well as possible synergistic effects of the SMs on the hazards are still among the main concerns in the development and application of mathematical models.The present study is aimed at developing a methodology to optimize the SMs selection while addressing the aforementioned challenges and considering both the budget and the risks. To do so, first the Pareto set of the solutions is obtained by NSGA-II technique - a multi-objective genetic algorithm technique - where a lexicographic model is used to select the optimal solution from the Pareto set based on the priority of the objective functions. A pessimistic strategy is used to account for the synergistic effects and the overlaps between the selected SMs.Two mathematical models are developed to represent different policies in optimal SMs selection in a gas wellhead and surface facility. The results show a notable difference between the two policies, indicating the importance of setting proper objective functions in multi-objective optimization problems. The results also show that the methodology is able to effectively satisfy different safety management policies and constraints with no need for much extra information except the cost and impact of SMs on the hazards’ risk.

Stable Cutting Zone with Improved Metal Removal Rate in Turning Process

This paper presents a new technique to evaluate the stable cutting zone with enhanced metal removal rate in turning operation. Experiments have been conducted at various levels of cutting parameters: depth of cut, feed rate, and spindle speed. Acquired raw chatter signals have been preprocessed using wavelet transforms in order to remove the ambient noise contents. Response surface methodology has been adopted to develop mathematical models of chatter severity and metal removal rate (MRR). Further, multi-objective genetic algorithm technique has been invoked in order to establish the stable cutting zones with maximized MRR. Good correlation between the predicted and experimental results validates the developed technique of ascertaining tool chatter severity and metal removal rate.

Use of artificial neural network and multi-objective genetic algorithm approach to predict and ascertain stable cutting zone in conventional turning process

This article is focused on the investigation of stable cutting zone in turning operation. Experiments have been conducted to acquire raw chatter signals. Generally, raw chatter signals are contaminated with ambient noise. Wavelet transform has been used for pre-processing and denoising these signals. In order to predict the severity of tool chatter, a new parameter denoted as chatter index has been evaluated considering the aforesaid denoised signals. In the present work, mathematical models have been developed for chatter index and metal removal rate using feedforward backpropagation–based artificial neural network considering three activation functions: TANSIG, LOGSIG and PURELIN. Furthermore, multi-objective genetic algorithm technique has been applied to evaluate stable cutting zones with maximized metal removal rate. TANSIG activation function found to be best option to achieve the aforesaid objectives. Good correlation between the artificial neural network predicted results and experimental ones validate the developed technique.

Multi‐objective design and prototyping of a low cogging torque axial‐flux PM generator with segmented stator for small‐scale direct‐drive wind turbines

The multi-objective design of an axial-flux permanent magnet (PM) generator with the yokeless and segmented armature is done, for use in the small-scale direct-drive wind turbines. Using the multi-objective genetic algorithm technique, an optimisation process is performed for maximising the efficiency and minimising the cost, size, and mass of active materials, considering the practical constraints of the wind generator. The Pareto optimal fronts are used to find the best solutions. Also, a comparative study is performed to determine the most appropriate configuration among 12 configurations with the different combinations of poles and stator segments. Then, the selected optimal configuration is analysed using the three-dimensional (3D) finite element analysis (FEA). The inherent cogging torque of the PM wind generator affects the cut-in speed and start-up of the turbine. Thus, to improve the turbine performance, especially at low starting speeds, the generator cogging torque should be reduced to an acceptable level. In this study, using a new and practical approach, the peak-to-peak value of the cogging torque is reduced largely (81.4%), without notable reduction in the generator loadability. A prototype of the designed generator is fabricated and tested. The experimental results show good agreement with the 3D FEA simulation results.

Optimization of energy consumption and environmental impacts of chickpea production using data envelopment analysis (DEA) and multi objective genetic algorithm (MOGA) approaches

Energy consumption in agricultural products and its environmental damages has increased in recent centuries. Life cycle assessment (LCA) has been introduced as a suitable tool for evaluation environmental impacts related to a product over its life cycle.In this study, optimization of energy consumption and environmental impacts of chickpea production was conducted using data envelopment analysis (DEA) and multi objective genetic algorithm (MOGA) techniques. Data were collected from 110 chickpea production enterprises using a face to face questionnaire in the cropping season of 2014–2015. The results of optimization revealed that, when applying MOGA, optimum energy requirement for chickpea production was significantly lower compared to application of DEA technique; so that, total energy requirement in optimum situation was found to be 31511.72 and 27570.61MJha−1 by using DEA and MOGA techniques, respectively; showing a reduction by 5.11% and 17% relative to current situation of energy consumption. Optimization of environmental impacts by application of MOGA resulted in reduction of acidification potential (ACP), eutrophication potential (EUP), global warming potential (GWP), human toxicity potential (HTP) and terrestrial ecotoxicity potential (TEP) by 29%, 23%, 10%, 6% and 36%, respectively. MOGA was capable of reducing the energy consumption from machinery, farmyard manure (FYM) diesel fuel and nitrogen fertilizer (the mostly contributed inputs to the environmental emissions) by 59%, 28.5%, 24.58% and 11.24%, respectively. Overall, the MOGA technique showed a superior performance relative to DEA approach for optimizing energy inputs and reducing environmental impacts of chickpea production system.

Gapped Motif Discovery with Multi-Objective Genetic Algorithm

Motif discovery is one of the fundamental problems that have important applications in identifying drug targets and regulatory sites. Regulatory sites on DNA sequence normally correspond to shared conservative sequence patterns among the regulatory regions of correlated genes. These conserved sequence patterns are called motifs. Identifying motifs and corresponding instances is very important, so biologists can investigate the interactions between DNA and proteins, gene regulation, cell development and cell reaction under physiological and pathological conditions. In this work, we developed a motif finding algorithm based on a multi-objective genetic algorithm technique and incorporated the hypergeometric scoring function to enable it discover gapped motifs from organisms with challenging genomic structure such as the malaria parasite. The runtime performance of our resulting algorithm, EMOGAMOD (Extended Multi Objective Genetic Algorithm MOtif Discovery) was evaluated with that of some common motif discovery algorithms and the result was remarkable.

A stochastic conflict resolution model for trading pollutant discharge permits in river systems

This paper presents an efficient methodology for developing pollutant discharge permit trading in river systems considering the conflict of interests of involving decision-makers and the stakeholders. In this methodology, a trade-off curve between objectives is developed using a powerful and recently developed multi-objective genetic algorithm technique known as the Nondominated Sorting Genetic Algorithm-II (NSGA-II). The best non-dominated solution on the trade-off curve is defined using the Young conflict resolution theory, which considers the utility functions of decision makers and stakeholders of the system. These utility functions are related to the total treatment cost and a fuzzy risk of violating the water quality standards. The fuzzy risk is evaluated using the Monte Carlo analysis. Finally, an optimization model provides the trading discharge permit policies. The practical utility of the proposed methodology in decision-making is illustrated through a realistic example of the Zarjub River in the northern part of Iran.

Multiobjective Optimal Waste Load Allocation Models for Rivers Using Nondominated Sorting Genetic Algorithm-II

A multiobjective optimization framework for optimal waste load allocation in rivers is proposed, considering (1) the total treatment cost, (2) the equity among the waste dischargers, and (3) a comprehensive performance measure that reflects the dissolved oxygen (DO) violation characteristics. This framework consists of an embedded river water quality simulator that has a gradually varied flow module and a pollutant transport module, which simulates the transport process including reaction kinetics (in terms of biochemical oxygen demand-DO). The outer shell of the framework consists of the two nonseasonal, deterministic, multiobjective waste load allocation planning models, namely, cost-performance model and cost-equity-performance model. These models are solved using a powerful and recently developed multiobjective genetic algorithm technique known as the Nondominated Sorting Genetic Algorithm-II. The practical utility of the multiobjective framework in decision-making is illustrated through a realistic example of the Willamette River in the state of Oregon.

A soft computing method for an AUV navigation system with pseudo-real-time applicability

This paper describes the implementation of a soft computing method based on fuzzy logic and multiobjective genetic algorithm techniques to adapt the parameters of an error-state complementary Kalman filter (ESCKF) to enhance the accuracy of an autonomous underwater vehicle (AUV) navigation system. In the ESCKF, inertially-derived quantities from an inertial navigation system (INS) sensor are combined with direct measurements of the same quantities by use of the global positioning system (GPS) and other aiding sensors. The backlash of the integration processes however, is that errors can grow rapidly and the values obtained therein can drift off the true value significantly. By contrast, the directly-measured data contain high frequency noise with bounded error. This instinctively suggests integrating the two sets of quantities, which is exactly what the ESCKF does. To maintain the stability and performance of the ESCKF, which is likely to deteriorate when the assumed error and noise characteristics do not reflect the true ones, a fuzzy logic based scheme is used to make these values adaptive. The choice of fuzzy membership functions for this scheme is first carried out using a heuristic approach and further refined using a multiobjective genetic algorithm method.

A fuzzy Kalman filter optimized using a multi-objective genetic algorithm for enhanced autonomous underwater vehicle navigation

In an autonomous underwater vehicle integrated navigation system, short-term temporal accuracy is provided by an inertial navigation subsystem (INS) and long-term accuracy by a global positioning system (GPS). The Kalman filter has been a popular method for integrating the data produced by the two systems to provide optimal estimates of autonomous underwater vehicle position and attitude. In this paper, a sequential use of a linear Kalman filter and extended Kalman filter is proposed. The former is used to fuse the data from a variety of INS sensors whose output is used as an input to the latter where integration with GPS data takes place. The use of a fuzzy-rule-based adaptation scheme to cope with the divergence problem caused by the insufficiently known a priori filter statistics is also explored. The choice of fuzzy membership functions for an adaptation scheme is first carried out using a heuristic approach. Multiobjective genetic algorithm techniques are then used to optimize the parameters of the membership functions with respect to a certain performance criteria in order to improve the overall accuracy of the integrated navigation system. Simulation results are presented that show that the proposed algorithms can provide a significant improvement in the overall navigation performance of an autonomous underwater vehicle navigation system.

A fuzzy Kalman filter optimized using a multi-objective genetic algorithm for enhanced autonomous underwater vehicle navigation

In an autonomous underwater vehicle integrated navigation system, short-term temporal accuracy is provided by an inertial navigation subsystem (INS) and long-term accuracy by a global positioning system (GPS). The Kalman filter has been a popular method for integrating the data produced by the two systems to provide optimal estimates of autonomous underwater vehicle position and attitude. In this paper, a sequential use of a linear Kalman filter and extended Kalman filter is proposed. The former is used to fuse the data from a variety of INS sensors whose output is used as an input to the latter where integration with GPS data takes place. The use of a fuzzy-rule-based adaptation scheme to cope with the divergence problem caused by the insufficiently known a priori filter statistics is also explored. The choice of fuzzy membership functions for an adaptation scheme is first carried out using a heuristic approach. Multiobjective genetic algorithm techniques are then used to optimize the parameters of the membership functions with respect to a certain performance criteria in order to improve the overall accuracy of the integrated navigation system. Simulation results are presented that show that the proposed algorithms can provide a significant improvement in the overall navigation performance of an autonomous underwater vehicle navigation system.