Search results

The purpose of this paper is to improve the performance of the genetic algorithm-based compliant robot path planning (GACRPP) in complex dynamic environment by proposing an improved bidirectional rapidly exploring random tree (Bi-RRT)-based population initialization method.

To achieve GACRPP in complex dynamic environment with high performance, an improved Bi-RRT-based population initialization method is proposed. First, the grid model is adopted to preprocess the working space of mobile robot. Second, an improved Bi-RRT is proposed to create multi-cluster connections between the starting point and the goal point. Third, the backtracking method is used to generate the initial population based on the multi-cluster connections generated by the improved Bi-RRT. Subsequently, some comparative experiments are implemented where the performances of the improved Bi-RRT-based population initialization method are compared with other population initialization methods, and the comparison results of the improved genetic algorithm (IGA) combining with the different population initialization methods are shown. Finally, the optimal path is further smoothed with the help of the technique of quadratic B-spline curves.

It is shown in the experiment results that the improved Bi-RRT-based population initialization method is capable of deriving a more diversified initial population with less execution time and the IGA combining with the proposed population initialization method outperforms the one with other population initialization methods in terms of the length of optimal path and the execution time.

In this paper, the Bi-RRT is introduced as a population initialization method into the GACRPP problem. An improved Bi-RRT is proposed for the purpose of increasing the diversity of initial population. To characterize the diversity of initial population, a new notion of breadth is defined in terms of Hausdorff distance between different paths.

The purpose of this paper is to examine and compare the entire impact of various execution skills of oppositional biogeography-based optimization using the current optimum (COOBBO) algorithm.

The improvement measures tested in this paper include different initialization approaches, crossover approaches, local optimization approaches, and greedy approaches. Eight well-known traveling salesman problems (TSP) are employed for performance verification. Four comparison criteria are recoded and compared to analyze the contribution of each modified method.

Experiment results illustrate that the combination model of “25 nearest-neighbor algorithm initialization+inver-over crossover+2-opt+all greedy” may be the best choice of all when considering both the overall algorithm performance and computation overhead.

When solving TSP with varying scales, these modified methods can enhance the performance and efficiency of COOBBO algorithm in different degrees. And an appropriate combination model may make the fullest possible contribution.

The purpose of this study is to solve NP-Hard drone routing problem for the last-mile distribution. This is suitable for the multi-drones parcel delivery for the various items from a warehouse to many locations.

This study conducts as a mission assignment of the single location per flight with the constraint satisfactions such as various payloads in weight, drone speeds, flight times and coverage distances. A genetic algorithm is modified as the concurrent heuristics approach (GCH), which has the knapsack problem dealing initialization, gene elitism (crossover) and gene replacement (mutation). Those proposed operators can reduce the execution time consuming and enhance the routing assignment of multiple drones. The evaluation value of the routing assignment can be calculated from the chromosome/individual representation by applying the proposed concurrent fitness.

This study optimizes the total traveling time to accomplish the distribution. GCH is flexible and can provide a result according to the first-come-first-served, demanded weight or distance priority.

GCH is an alternative option, which differs from conventional vehicle routing researches. Such researches (traveling time optimization) attempt to minimize the total traveling time, distance or the number of vehicles by assuming all vehicles have the same traveling speed; therefore, a specific vehicle assignment to a location is neglected. Moreover, the main drawback is those concepts can lead the repeated selection of best quality vehicles concerning the speed without considering the vehicle fleet size and coverage distance while this study defines the various speeds for the vehicles. Unlike those, the concurrent concept ensures a faster delivery accomplishment by sharing the work load with all participant vehicles concerning to their different capabilities. If the concurrent assignment is applied to the drone delivery effectively, the entire delivery can be accomplished relatively faster than the traveling time optimization.

Software-define vehicular networks (SDVN) assure the direct programmability for controlling the vehicles with improved accuracy and flexibility. In this research, the resource allocation strategy is focused on which the seek-and-destroy algorithm is implemented in the controller in such a way that an effective allocation of the resources is done based on the multi-objective function.

The purpose of this study is focuses on the resource allocation algorithm for the SDVN with the security analysis to analyse the effect of the attacks in the network. The genuine nodes in the network are granted access to the communication in the network, for which the factors such as trust, throughput, delay and packet delivery ratio are used and the algorithm used is Seek-and-Destroy optimization. Moreover, the optimal resource allocation is done using the same optimization in such a way that the network lifetime is extended.

The security analysis is undergoing in the research using the simulation of the attackers such as selective forwarding attacks, replay attacks, Sybil attacks and wormhole attacks that reveal that the replay attacks and the Sybil attacks are dangerous attacks and in future, there is a requirement for the security model, which ensures the protection against these attacks such that the network lifetime is extended for a prolonged communication. The achievement of the proposed method in the absence of the attacks is 84.8513% for the remaining nodal energy, 95.0535% for packet delivery ratio (PDR), 279.258 ms for transmission delay and 28.9572 kbps for throughput.

The seek-and-destroy algorithm is one of the swarm intelligence-based optimization designed based on the characteristics of the scroungers and defenders, which is completely novel in the area of optimizations. The diversification and intensification of the algorithm are perfectly balanced, leading to good convergence rates.

In the process of fabric spreading, the variance of fabric yardage between fabric rolls may lead to a difference in fabric loss during spreading. As there are numerous combinations the arrangement of the fabric roll sequences for each cutting lay, it is difficult to construct a roll planning to minimise the fabric wastage during spreading in apparel manufacturing. Recent advances in computing technology, especially in the area of computational intelligence, can be used to handle this problem. Among the different computational intelligence techniques, genetic algorithms (GA) are particularly suitable. GAs are probabilistic search methods that employ a search technique based on ideas from natural genetics and evolutionary principles. This paper presents the details of GA and explains how the problem of roll planning can be formulated for GA to solve. The result of the study shows that an optimal roll planning can be worked out by using GA approach. It is possible to save a considerable amount of fabric when the best roll planning is used for the production.

Flexible job-shop scheduling is significant for different manufacturing industries nowadays. Moreover, consideration of transportation time during scheduling makes it more practical and useful. The purpose of this paper is to investigate multi-objective flexible job-shop scheduling problem (MOFJSP) considering transportation time.

A hybrid genetic algorithm (GA) approach is integrated with simulated annealing to solve the MOFJSP considering transportation time, and an external elitism memory library is employed as a knowledge library to direct GA search into the region of better performance.

The performance of the proposed algorithm is tested on different MOFJSP taken from literature. Experimental results show that proposed algorithm performs better than the original GA in terms of quality of solution and distribution of the solution, especially when the number of jobs and the flexibility of the machine increase.

Most of existing studies have not considered the transportation time during scheduling of jobs. The transportation time is significantly desired to be included in the FJSP when the time of transportation of jobs has significant impact on the completion time of jobs. Meanwhile, GA is one of primary algorithms extensively used to address MOFJSP in literature. However, to solve the MOFJSP, the original GA has a possibility to get a premature convergence and it has a slow convergence speed. To overcome these problems, a new hybrid GA is developed in this paper.

The assembly sequence in the product assembly process has effect on the final product quality. To solve the assembly sequence optimization problem, such as rotor blade assembly sequence optimization, this paper proposes a small world networks-based genetic algorithm (SWN_GA) to solve the assembly sequence optimization problem. The proposed approach SWN_GA consists of a combination between the standard Genetic Algorithm and the NW Small World Networks.

The selection operation and the crossover operation are improved in this paper. The selection operation remains the elite individuals that have greater fitness than average fitness and reselects the individuals that have smaller fitness than average fitness. The crossover operation combines the NW Small World Networks to select the crossover individuals and calculate the crossover probability.

In this paper, SWN_GA is used to optimize the assembly sequence of steam turbine rotor blades, and the SWN_GA was compared with standard GA and PSO algorithm in a simulation experiment. The simulation results show that SWN_GA cannot only find a better assembly sequence which have lower rotor imbalance, but also has a faster convergence rate.

Finally, an experiment about the assembly of a steam turbine rotor is conducted, and SWN_GA is applied to optimize the blades assembly sequence. The feasibility and effectiveness of SWN_GA are verified through the experimental result.

Increasing academic communities and practitioners begin to explore a novel method to reduce environmental pollution and realize green logistics delivery. Additionally, China's Statistical Yearbook shows that the number of private cars has reached 165 million in China. Under this background, this study proposes a green delivery method by the combination of sharing vehicle (private cars) and IoT (Internet of things) from the perspective of vehicle energy efficiency and aims to improve the energy efficiency of social vehicles and provides more convenient delivery services.

This study builds an IoT architecture consisting of customer data layer, information collection layer, cloud optimization layer and delivery task execution layer. Especially in the IoT architecture, a clustering analysis method is used to determine the critical value of customers' classification and shared delivery, a routing optimization method is used to solve the initial solution in could layer and shared technology is used in the implementation of shared delivery.

The results show that the delivery method considering shared vehicles has a positive effect on improving the energy utilization of vehicles. But if all of delivery tasks are performed by the shared vehicle, the application effect may be counterproductive, such as delivery cost increases and energy efficiency decreases. This study provides a good reference for the implementation of green intelligent delivery business, which has a positive effect on the improvement of logistics operation efficiency.

This study designs a novel method to solve the green and shared delivery issues under the IoT environment, which integrates the IoT architecture. The proposed methodology is applied in a real case in China.

In general, the optimal reactive power compensation could drastically enhance the performance of distributed network by the reduction of power loss and by enhancement of line loadability and voltage profile. Till now, there exist various reactive power compensation models including capacitor placement, joined process of on-load tap changer and capacitor banks and integration of DG. Further, one of the current method is the allocation of distribution FACTS (DFACTS) device. Even though, the DFACTS devices are usually used in the enhancement of power quality, they could be used in the optimal reactive power compensation with more effectiveness.

This paper introduces a power quality enhancement model that is based on a new hybrid optimization algorithm for selecting the precise unified power quality conditioner (UPQC) location and sizing. A new algorithm rider optimization algorithm (ROA)-modified particle swarm optimization (PSO) in fitness basis (RMPF) is introduced for this optimal selections.

Through the performance analysis, it is observed that as the iteration increases, there is a gradual minimization of cost function. At the 40th iteration, the proposed method is 1.99 per cent better than ROA and genetic algorithm (GA); 0.09 per cent better than GMDA and WOA; and 0.14, 0.57 and 1.94 per cent better than Dragonfly algorithm (DA), worst solution linked whale optimization (WS-WU) and PSO, respectively. At the 60th iteration, the proposed method attains less cost function, which is 2.07, 0.08, 0.06, 0.09, 0.07 and 1.90 per cent superior to ROA, GMDA, DA, GA, WS-WU and PSO, respectively. Thus, the proposed model proves that it is better than other models.

This paper presents a technique for optimal placing and sizing of UPQC. To the best of the authors’ knowledge, this is the first work that introduces RMPF algorithm to solve the optimization problems.

When making sourcing decisions, both cost optimization and customer demand fulfillment are equally important for firm competitiveness. The purpose of this paper is to develop a stochastic search technique, hybrid genetic algorithm (HGA), for cost-optimized decision making in wholesaler inventory management in a supply chain network of wholesalers, retailers and suppliers.

This study develops a HGA by using a mixture of greedy-based and randomly generated solutions in the initial population and a local search method (hill climbing) applied to individuals selected for performing crossover before crossover is implemented and to the best individual in the population at the end of HGA as well as gene slice and integration.

The application of the proposed HGA is illustrated by considering multiple scenarios and comparing with the other commonly adopted methods of standard genetic algorithm, simulated annealing and tabu search. The simulation results demonstrate the capability of the proposed approach in producing more effective solutions.

The pragmatic importance of this method is for the inventory management of wholesaler operations and this can be scalable to address real contexts with multiple wholesalers and multiple suppliers with variable lead times.

The proposed stochastic-based search techniques have the capability in producing good-quality optimal or suboptimal solutions for large-scale problems within a reasonable time using ordinary computing resources available in firms.