The single particleswarmalgorithm exhibits deficiencies in optimality, diversity, and convergence speed when addressing the multi-objective optimal scheduling problem in flexible job shops. In this research, we intr...
详细信息
ISBN:
(纸本)9798350387780;9798350387797
The single particleswarmalgorithm exhibits deficiencies in optimality, diversity, and convergence speed when addressing the multi-objective optimal scheduling problem in flexible job shops. In this research, we introduce a multiobjective Pareto quantum particle swarm algorithm. To aviod the algorithm falling into the problem of local convergence, three initialization strategies are proposed to enhance population quality. Additionally, a crowding degree mechanism is employed to enhance the distribution of the Pareto front, thus improving solution diversity and quality. Experimental results on Kacem and Mk standard examples validate the efficiency of the proposed approach.
In order to diversify the particleswarm during the searching process of quantumparticleswarm optimization (QPSO) and avoid the algorithm being trapped into premature easily, a hybrid quantumparticleswarm optimiza...
详细信息
In order to diversify the particleswarm during the searching process of quantumparticleswarm optimization (QPSO) and avoid the algorithm being trapped into premature easily, a hybrid quantumparticleswarm optimization algorithm based on Lévy flights is proposed in this paper. The new algorithm effectively takes advantage of quantum computing and Lévy flights. We use the probability amplitude encoding method of the quantum bit to initialize the particle position and combine the potential well particle updating formula with the quantum rotation gate to update the particleswarm, which effectively ameliorates the search process and increases the population diversity. Then the Lévy flights strategy is employed to improve the population variation process and enhance the quality of the solution while preventing the algorithm from falling into the precocious convergence. Compared with other algorithms on benchmark functions, it is shown that the algorithm is effective and feasible.
As a new network control and management method for network, software-defined networking (SDN) algorithms have attracted more attention to make networks agile and flexible. To meet the requirements of users and conquer...
详细信息
As a new network control and management method for network, software-defined networking (SDN) algorithms have attracted more attention to make networks agile and flexible. To meet the requirements of users and conquer the physical limitation of network, it is necessary to design an efficient controller placement mechanism of SDN, which is defined as an optimization problem to determine the proper positions and number of its controllers. As a modern optimization tool, quantum-behavior particleswarm optimization (QPSO) algorithm demonstrates power fast convergence rate but limits in global search ability. In this paper, by introducing a full search history and excellent dimension update strategy into the traditional QPSO algorithm which enhances its performance, simulation results show that the proposed algorithm achieves better performance in dozens of different multi-controller placement problems.
Aiming at the tracking task and interception task in air defense antimissile operations,a mathematical model of cooperative combat assignment is *** using the global searching ability of the cuckoo algorithm and the f...
详细信息
Aiming at the tracking task and interception task in air defense antimissile operations,a mathematical model of cooperative combat assignment is *** using the global searching ability of the cuckoo algorithm and the fast and efficient local search ability of the quantum particle swarm algorithm,the framework and process of hybrid optimization,based on quantumparticleswarm optimization and the cuckoo,are ***,an example is given to demonstrate the rationality of the task allocation model and the effectiveness and superiority of the proposed *** provides a method and reference for solving the problem of air defense antimissile assignment.
In the current process of residential building layout design, there are problems such as low design efficiency, excessive manual intervention, and difficulty in meeting personalized needs. To address these issues, a r...
详细信息
In the current process of residential building layout design, there are problems such as low design efficiency, excessive manual intervention, and difficulty in meeting personalized needs. To address these issues, a residential building layout design method based on graph neural network model is proposed to improve the intelligence level of residential building layout design. Firstly, the residential building floor plan layout design data are transformed into graph data suitable for graph neural network model processing. Then, deep learning techniques are used to analyse and identify the spatial distribution characteristics of the main functional areas in the space. Finally, the trained graph neural network model is applied to the actual residential building floor plan layout design and compared with the traditional method. The experimental results show that compared with the traditional computer-aided design method, the residential building floor plan layout design and optimisation method improves the completeness of the design scheme by about 2.3%, the rationality by about 3.6%, the readability by about 1.9%, and the effectiveness by about 10.3%. The method improves the efficiency and accuracy of residential building floor plan layout design, helps to shorten the design cycle and reduce the design cost, and helps to promote technological progress and sustainable development in the field of architectural design.
In order to improve the prediction accuracy and speed of the model, a network security situation prediction model based on chaotic cross quantumparticleswarm optimization optimization bidirectional long short term m...
详细信息
ISBN:
(纸本)9781665464680
In order to improve the prediction accuracy and speed of the model, a network security situation prediction model based on chaotic cross quantumparticleswarm optimization optimization bidirectional long short term memory (CCQPSO-BiLSTM) network is proposed. Logistics is used to map the initial population as a chaotic sequence to search for the optimal solution, and the information exchange of individuals in the population is carried out through the vertical crossover operation. Finally, the hyperparameters of the model are optimized by CCQPSO. Through four standard test functions, the effectiveness of introducing chaotic mapping and crossover operations into quantumparticleswarm optimization is verified. The experimental results show that the fitting degree of the proposed prediction method can reach 0.9977, and the convergence speed is greatly improved compared with the comparison algorithm.
A scheduling model of forest fire extinguishing suitable for Southern forests is proposed in this paper. First of all, according to forest fire fighting strategy, we can determine the extinguishing points that can div...
详细信息
ISBN:
(纸本)9789811945465;9789811945458
A scheduling model of forest fire extinguishing suitable for Southern forests is proposed in this paper. First of all, according to forest fire fighting strategy, we can determine the extinguishing points that can divide the fire field and break them one by one. Then, quantumparticleswarm optimization is used to calculate the optimal path. If there are "flying fire" and other emergencies in the fire extinguishing process, the improved Ant Colony algorithm based on periodically pheromone updating is used to schedule resources including personnel and fire extinguishing materials, so as to improve the efficiency of forest fire-extinguishing resources scheduling in southern China. The simulation results show that compared with the conventional scheduling model of forest fire extinguishing, the proposed model has more iterations per unit time, and the operation time is greatly reduced, which indicates that the efficiency of fire extinguishing resource dispatching has been significantly improved.
The development of internet technology has brought us benefits, but at the same time, there has been a surge in network attack incidents, posing a serious threat to network security. In the real world, the amount of a...
详细信息
The development of internet technology has brought us benefits, but at the same time, there has been a surge in network attack incidents, posing a serious threat to network security. In the real world, the amount of attack data is much smaller than normal data, leading to a severe class imbalance problem that affects the performance of classifiers. Additionally, when using CNN for detection and classification, manual adjustment of parameters is required, making it difficult to obtain the optimal number of convolutional kernels. Therefore, we propose a hybrid sampling technique called Borderline-SMOTE and Gaussian Mixture Model (GMM), referred to as BSGM, which combines the two approaches. We utilize the quantumparticleswarm Optimization (QPSO) algorithm to automatically determine the optimal number of convolutional kernels for each one-dimensional convolutional layer, thereby enhancing the detection rate of minority classes. In our experiments, we conducted binary and multi-class experiments using the KDD99 dataset. We compared our proposed BSGM-QPSO-1DCNN method with ROS-CNN, SMOTE-CNN, RUS-SMOTE-CNN, RUS-SMOTE-RF, and RUS-SMOTE-MLP as benchmark models for intrusion detection. The experimental results show the following: (i) BSGM-QPSO-1DCNN achieves high accuracy rates of 99.93% and 99.94% in binary and multi-class experiments, respectively;(ii) the precision rates for the minority classes R2L and U2R are improved by 68% and 66%, respectively. Our research demonstrates that BSGM-QPSO-1DCNN is an efficient solution for addressing the imbalanced data issue in this field, and it outperforms the five intrusion detection methods used in this study.
Wind energy has become one of the most widely used alternative energy sources in recent years due to its clean and renewable character. In the context of increasing demand for new facilities, the cost of a wind turbin...
详细信息
Wind energy has become one of the most widely used alternative energy sources in recent years due to its clean and renewable character. In the context of increasing demand for new facilities, the cost of a wind turbine is a key factor for the success of new wind farms. The reduction of the amount of material used to build the wind turbine tower is one way to reduce the project cost. This work presents a methodology for the minimization of the weight of the tubular steel towers of wind turbines using a metaheuristic optimization algorithm. The diameters of the cross-section at the base and the top of the conical tower are considered as continuous design variables. Due to constructional aspects, the tower is manufactured in many segments, which wall thicknesses are taken as discrete design variables. Besides the dead load, the design considers the action of wind load, which is taken as an equivalent static force determined using the Brazilian standard NBR6123. The design constraints considered in this work are the maximum admissible displacements at the top of the tower under service condition, the tower's lowest natural frequency and the safety criteria for steel structures defined by the Brazilian standard NBR8800. The mixed-integer nonlinear optimization problem formulated for the structural design in this work is solved using the quantumparticleswarm optimization algorithm (QPSO). On average, the QPSO solution was 12% lighter than designs based on other well-established algorithms in a comparative study. Nonetheless, no significant improvement was observed concerning the standard particleswarm optimization.
In mechanical engineering field, early fault features are extremely weak and submerged in heavy noise, and the weak feature extraction is quite challenging. In this work, we apply the adaptive stochastic resonance in ...
详细信息
In mechanical engineering field, early fault features are extremely weak and submerged in heavy noise, and the weak feature extraction is quite challenging. In this work, we apply the adaptive stochastic resonance in cascaded piecewise-linear system to extract the weak features. The adaptive stochastic resonance is realized by the quantum particle swarm algorithm. By optimizing system parameters, the efficiency of the feature extraction is improved greatly. As a result, the weak features can be easily extracted eventually. The effectiveness and the high-performance of the proposed method are verified by the numerical simulation and experimental data of rolling element bearings. The bearing fault under different motor loads is detected effectively, consequently confirming the robustness of the proposed method.
暂无评论