Search results

In this paper, a set of safe adaptive genetic algorithms (sGAs) is proposed based on the Splicing/Decomposable encoding scheme and the efficient speed‐up strategies developed by Xu et al.. The proposed algorithms implement the self‐adaptation of the problem representation, selection and recombination operators at the levels of population, individual and component which commendably balance the conflicts between “reliability” and “efficiency”, as well as “exploitation” and “exploration” existed in the evolutionary algorithms. It is shown that the algorithms converge to the optimum solution in probability one. The proposed sGAs are experimentally compared with the classical genetic algorithm (CGA), non‐uniform genetic algorithm (nGA) proposed by Michalewicz, forking genetic algorithm (FGA) proposed by Tsutsui et al. and the classical evolution programming (CEP). The experiments indicate that the new algorithms perform much more efficiently than CGA and FGA do, comparable with the real‐coded GAs — nGA and CEP. All the algorithms are further evaluated through an application to a difficult real‐life application problem: the inverse problem of fractal encoding related to fractal image compression technique. The results for the sGA is better than those of CGA and FGA, and has the same, sometimes better performance compared to those of nGA and CEP.

This study aims to investigate the effects of irregular groove textures on the friction and wear performance of sliding contact surfaces. These textures possess multiple depths and asymmetrical features. To optimize the irregular groove texture structure of the sliding contact surface, an adaptive genetic algorithm was used for research and optimization purposes.

Using adaptive genetic algorithm as an optimization tool, numerical simulations were conducted on surface textures by establishing a dimensionless form of the Reynolds equation and setting appropriate boundary conditions. An adaptive genetic algorithm program in MATLAB was established. Genetic iterative methods were used to calculate the optimal texture structure. Genetic individuals were selected through fitness comparison. The depth of the groove texture is gradually adjusted through genetic crossover, mutation, and mutation operations. The optimal groove structure was ultimately obtained by comparing the bearing capacity and pressure of different generations of micro-convex bodies.

After about 100 generations of iteration, the distribution of grooved textures became relatively stable, and after about 320 generations, the depth and distribution of groove textures reached their optimal structure. At this stage, irregular texture structures can support more loads by forming oil films. Compared with regular textures, the friction coefficient of irregular textures decreased by nearly 47.01%, while the carrying capacity of lubricating oil films increased by 54.57%. The research results show that irregular texture structures have better lubrication characteristics and can effectively improve the friction performance of component surfaces.

Surface textures can enhance the friction and lubrication performance of metal surfaces, improving the mechanical performance and lifespan of components. However, surface texture processing is challenging, as it often requires multiple experimental comparisons to determine the optimal texture structure, resulting in high trial-and-error costs. By using an adaptive genetic algorithm as an optimization tool, the optimal surface groove structure can be obtained through simulation and modeling, effectively saving costs in the process.

The Hermite collocation method of discretization can be used to determine highly accurate solutions to the steady‐state one‐dimensional convection‐diffusion equation (which can be used to model the transport of contaminants dissolved in groundwater). This accuracy is dependent upon sufficient refinement of the finite‐element mesh as well as applying upstream or downstream weighting to the convective term through the determination of collocation locations which meet specified constraints. Owing to an increase in computational intensity of the application of the method of collocation associated with increases in the mesh refinement, minimal mesh refinement is sought. Very often this optimization problem is the one where the feasible region is not connected and as such requires a specialized optimization search technique. This paper aims to focus on this method.

An original hybrid method that utilizes a specialized adaptive genetic algorithm followed by a hill‐climbing approach is used to search for the optimal mesh refinement for a number of models differentiated by their velocity fields. The adaptive genetic algorithm is used to determine a mesh refinement that is close to a locally optimal mesh refinement. Following the adaptive genetic algorithm, a hill‐climbing approach is used to determine a local optimal feasible mesh refinement.

In all cases the optimal mesh refinements determined with this hybrid method are equally optimal to, or a significant improvement over, mesh refinements determined through direct search methods.

Further extensions of this work could include the application of the mesh refinement technique presented in this paper to non‐steady‐state problems with time‐dependent coefficients with multi‐dimensional velocity fields.

The present work applies an original hybrid optimization technique to obtain highly accurate solutions using the method of Hermite collocation with minimal mesh refinement.

Flights are often delayed owing to emergencies. This paper proposes a cooperative slot secondary assignment (CSSA) model based on a collaborative decision-making (CDM) mechanism, and the operation mode of flight waves designs an improved intelligent algorithm to solve the optimal flight plan and minimize the total delay of passenger time.

Taking passenger delays, transfer delays and flight cancellation delays into account comprehensively, the total delay time is minimized as the objective function. The model is verified by a linear solver and compared with the first come first service (FCFS) method to prove the effectiveness of the method. An improved adaptive partheno-genetic algorithm (IAPGA) using hierarchical serial number coding was designed, combining elite and roulette strategies to find pareto solutions.

Comparing and analyzing the experimental results of various scale examples, the optimization model in this paper is greatly optimized compared to the FCFS method in terms of total delay time, and the IAPGA algorithm is better than the algorithm before in terms of solution performance and solution set quality.

Based on the actual situation, this paper considers the operation mode of flight waves. In addition, the flight plan solved by the model can be guaranteed in terms of feasibility and effectiveness, which can provide airlines with reasonable decision-making opinions when reassigning slot resources.

Optimizing both qualitative and quantitative factors is a key challenge in solving construction finance decisions. The semi‐structured nature of construction finance optimization problems precludes conventional optimization techniques. With a desire to improve the performance of the canonical genetic algorithm (CGA) which is characterized by static crossover and mutation probability, and to provide contractors with a profit‐risk trade‐off curve and cash flow prediction, an adaptive genetic algorithm (AGA) model is developed. Ten projects being undertaken by a major construction firm in Hong Kong were used as case studies to evaluate the performance of the genetic algorithm (GA). The results of case study reveal that the AGA outperformed the CGA both in terms of its quality of solutions and the computational time required for a certain level of accuracy. The results also indicate that there is a potential for using the GA for modelling financial decisions should both quantitative and qualitative factors be optimized simultaneously.

This paper addresses issues dealing with genetic algorithm (GA) convergence and the implications of the No Free Lunch Theorem which states that no single algorithm outperforms all others for all possible problem landscapes. In view of this, the authors propose that it is necessary for a GA to have the ability to classify the problem landscape before effective parameter adaptation may occur.

The new hybrid intelligent system for landscape classification is proposed. This system facilitates intelligent operator selection and parameter tuning during run time in order to achieve maximum convergence. This work introduces two adaptive crossover techniques, the runtime adaptation of crossover probability and the participation level of multiple crossover operators in order to refine the quality of the search and to regulate the trade‐off between local and global search respectively. In addition, a Rule‐Based reasoning system (RS) is presented which can be utilised to analyse the problem landscape and provide a supervisory element to a GA. This RS is capable of instigating change by utilising the analysis in order to counteract premature convergence, for various classes of problems.

Results are presented which show that the application of this Rule‐Based system and the adaptive crossover techniques proposed in this paper significantly improve performance for a suite of relatively complex test problems.

This work demonstrates the effectiveness of landscape classification and consequent rule‐based reasoning for GAs, particularly for problems with a difficult path to the optimal. Moreover, both adaptive crossover techniques proposed present improved performance over the traditional static parameter GA.

To improve the accuracy of stock price trend prediction in the field of quantitative financial trading, this paper takes the prediction accuracy as the goal and avoid the enormous number of network structures and hyperparameter adjustments of long-short-term memory (LSTM).

In this paper, an adaptive genetic algorithm based on individual ordering is used to optimize the network structure and hyperparameters of the LSTM neural network automatically.

The simulation results show that the accuracy of the rise and fall of the stock outperform than the model with LSTM only as well as other machine learning models. Furthermore, the efficiency of parameter adjustment is greatly higher than other hyperparameter optimization methods.

(1) The AGA-LSTM algorithm is used to input various hyperparameter combinations into genetic algorithm to find the best hyperparameter combination. Compared with other models, it has higher accuracy in predicting the up and down trend of stock prices in the next day. (2) Adopting real coding, elitist preservation and self-adaptive adjustment of crossover and mutation probability based on individual ordering in the part of genetic algorithm, the algorithm is computationally efficient and the results are more likely to converge to the global optimum.

A novel sexual adaptive genetic algorithm (AGA) based on Baldwin effect for global optimization is proposed to overcome the shortcomings of traditional GAs, such as premature convergence, stochastic roaming, and poor capabilities in local exploring. This paper seeks to discuss the issues.

The proposed algorithm simulates sexual reproduction and adopts an effective gender determination method to divide the population into two subgroups of different genders. Based on the competition, cooperation, and innate differences between two gender subgroups, the proposed algorithm adjusts adaptively sexual genetic operators. Furthermore, inspired by the acquired reinforcement learning theory based on Baldwin effect, the proposed algorithm guides individuals to forward or reverse learning and enables the transmission of fitness information between parents and offspring to adapt individuals' acquired fitness.

Global convergence of the proposed algorithm is proved in detail. Numerical simulations are conducted for a set of benchmark functions with different dimensional decision variables. The performance of the proposed algorithm is compared with that of the other evolutionary algorithms published recently. The results indicate that the proposed algorithm can find optimal or closer‐to‐optimal solutions, and is more competitive than the compared algorithms.

The proposed algorithm introduces, integrates and simulates correctly and adequately, for the first time, the mechanisms of sexual reproduction, Baldwin effect and adaptation to GAs by referring to the latest research results of modern biology and evolution theory.

The purpose of this paper is to accurately obtain the deformation of a hybrid robot and rapidly enable real-time compensation in friction stir welding (FSW). In this paper, a prediction algorithm based on the back-propagation neural network (BPNN) optimized by the adaptive genetic algorithm (GA) is presented.

Via the algorithm, the deformations of a five-degree-of-freedom (5-DOF) hybrid robot TriMule800 at a limited number of positions are taken as the training set. The current position of the robot and the axial force it is subjected to are used as the input; the deformation of the robot is taken as the output to construct a BPNN; and an adaptive GA is adopted to optimize the weights and thresholds of the BPNN.

This algorithm can quickly predict the deformation of a robot at any point in the workspace. In this study, a force-deformation experiment bench is built, and the experiment proves that the correspondence between the simulated and actual deformations is as high as 98%; therefore, the simulation data can be used as the actual deformation. Finally, 40 sets of data are taken as examples for the prediction, the errors of predicted and simulated deformations are calculated and the accuracy of the prediction algorithm is verified.

The entire algorithm is verified by the laboratory-developed 5-DOF hybrid robot, and it can be applied to other hybrid robots as well.

Robots have been widely used in FSW. Traditional series robots cannot bear the large axial force during welding, and the deformation of the robot will affect the machining quality. In some research studies, hybrid robots have been used in FSW. However, the deformation of a hybrid robot in thick-plate welding applications cannot be ignored. Presently, there is no research on the deformation of hybrid robots in FSW, let alone the analysis and prediction of their deformation. This research provides a feasible methodology for analysing the deformation and compensation of hybrid robots in FSW. This makes it possible to calculate the deformation of the hybrid robot in FSW without external sensors.

This study aims to address the challenge of automatic guided vehicle (AGV) scheduling for parcel storage and retrieval in an intelligent warehouse.

This study presents a scheduling solution that aims to minimize the maximum completion time for the AGV scheduling problem in an intelligent warehouse. First, a mixed-integer linear programming model is established, followed by the proposal of a novel genetic algorithm to solve the scheduling problem of multiple AGVs. The improved algorithm includes operations such as the initial population optimization of picking up goods based on the principle of the nearest distance, adaptive crossover operation evolving with iteration, mutation operation of equivalent exchange and an algorithm restart strategy to expand search ability and avoid falling into a local optimal solution. Moreover, the routing rules of AGV are described.

By conducting a series of comparative experiments based on the actual package flow situation of an intelligent warehouse, the results demonstrate that the proposed genetic algorithm in this study outperforms existing algorithms, and can produce better solutions for the AGV scheduling problem.

This paper optimizes the different iterative steps of the genetic algorithm and designs an improved genetic algorithm, which is more suitable for solving the AGV scheduling problem in the warehouse. In addition, a path collision avoidance strategy that matches the algorithm is proposed, making this research more applicable to real-world scheduling environments.