In a multiple-criteria group decision-making process, it may be unrealistic to assume that all experts are specialized in all aspects of the entire problem and can reach full agreement. To obtain a suitable result wit...
详细信息
In a multiple-criteria group decision-making process, it may be unrealistic to assume that all experts are specialized in all aspects of the entire problem and can reach full agreement. To obtain a suitable result with more flexibility and robustness in group decision-making, this study concerns the introduction of information granules to the best-worst method model, regarded as an essential design asset to reach a consensus in a group decisionmaking scenario. More specifically, each pairwise comparison is performed through information granules instead of single numbers, by using an optimal allocation of information granularity. Further, we develop an optimization model that considers both consistency and consensus in one problem. The particle swarm optimization algorithm is used as an optimization method to find the optimal particle of the granular decision model. Furthermore, a new convergent iterative algorithm is developed to obtain the desired decision matrix. Next, an experimental study is presented to demonstrate the effectiveness, flexibility, and essence of the proposed model. Finally, a case study of *** is conducted to select suitable automobiles for a company based on online reviews. The solving procedures are demonstrated, to further illustrate the feasibility of the proposed method.
In the era of network communication,digital image encryption(DIE)technology is critical to ensure the security of image ***,there has been limited research on combining deep learning neural networks with chaotic mappi...
详细信息
In the era of network communication,digital image encryption(DIE)technology is critical to ensure the security of image ***,there has been limited research on combining deep learning neural networks with chaotic mapping for the encryption of digital ***,this paper addresses this gap by studying the generation of pseudo-random sequences(PRS)chaotic signals using dual logistic chaotic *** signals are then predicted using long and short-term memory(LSTM)networks,resulting in the reconstruction of a new chaotic *** the research process,it was discovered that there are numerous training parameters associated with the LSTM network,which can hinder training *** overcome this challenge and improve training efficiency,the paper proposes an improved particleswarmoptimization(IPSO)algorithm to optimize the LSTM ***,the obtained chaotic signal from the optimized model training is further scrambled,obfuscated,and diffused to achieve the final encrypted *** research presents a digital image encryption(DIE)algorithm based on a double chaotic map(DCM)and *** algorithm demonstrates a high average NPCR(Number of Pixel Change Rate)of 99.56%and a UACI(Unified Average Changing Intensity)value of 33.46%,indicating a strong ability to resist differential ***,the proposed algorithm realizes secure and sensitive digital image encryption,ensuring the protection of personal information in the Internet environment.
The difficulties in determining the compressive strength of concrete are inherited due to the various nonlinearities rooted in the mix designs. These difficulties raise dramatically considering the modern mix designs ...
详细信息
The difficulties in determining the compressive strength of concrete are inherited due to the various nonlinearities rooted in the mix designs. These difficulties raise dramatically considering the modern mix designs of high-performance concrete. Presents study tries to define a simple approach to link the input ingredients of concrete with the resulted compressive with a high accuracy rate and overcome the existing nonlinearity. For this purpose, the radial base function is defined to carry out the modeling process. The optimal results were obtained by determining the optimal structure of radial base function neural networks. This task was handled well with two precise optimizationalgorithms, namely Henry's gas solubility algorithm and particle swarm optimization algorithm. The results defined both models' best performance earned in the training section. Considering the root mean square error values, the best value stood at 2.5629 for the radial base neural network optimized by Henry's gas solubility algorithm, whereas the same value for the the radial base neural network optimized by particleswarmoptimization was 2.6583 although both hybrid models provided acceptable output results, the radial base neural network optimized by Henry's gas solubility algorithm showed higher accuracy in predicting high performance concrete compressive strength.
In this paper, the optimization of the square and squared-off cascades for the separation of stable isotopes with a certain number of gas centrifuges (GCs) using particleswarmoptimization (PSO) and the whale optimiz...
详细信息
In this paper, the optimization of the square and squared-off cascades for the separation of stable isotopes with a certain number of gas centrifuges (GCs) using particleswarmoptimization (PSO) and the whale optimizationalgorithm (WOA) was studied. For this purpose, the "SC-PSO" and "SC-WOA" codes for the square cascade (SC), and the "SOC-PSO" and "SOC-WOA" codes for the squared-off cascade (SOC) were developed. The performance of the PSO and WOA algorithms in the optimization of the square and squared-off cascades as an example for the separation of 124Xe from nine stable isotopes of xenon up to an enrichment of 85% was compared. The recovery coefficient of 124Xe isotope by the codes "SC-PSO", "SC-WOA", "SOC-PSO", and "SOC-WOA" was obtained 86.14, 78.11, 92.84, and 83.41% respectively. The performance of the algorithms indicates the higher yield of the PSO algorithm in the optimization of SC and SOC. The efficiency of the PSO has been demonstrated by the Griewank test function compared with the WOA, the sine cosine algorithm (SCA), and the dragon-fly algorithm ( DA) (PSO>WOA>SCA>DA). Furthermore, the results show that SOC performs better than SC.
As a resource-conserving and environmentally friendly manufacturing paradigm, remanufacturing with the potential to realize sustainability in production has been extensively investigated. Scheduling plays a significan...
详细信息
As a resource-conserving and environmentally friendly manufacturing paradigm, remanufacturing with the potential to realize sustainability in production has been extensively investigated. Scheduling plays a significant role in achieving the remanufacturing benefits. However, the remanufacturing process involves intricate uncertainties because it takes end-of-life products with different qualities as workblanks, which increases the risk of rework and complicates remanufacturing scheduling. Though the traditional stochastic optimization methods or fuzzy theory have been employed to address uncertainties in the remanufacturing scheduling problem, they are constrained with the limited historical data which renders it difficult to describe uncertainties accurately and intuitively. Therefore, a new uncertain remanufacturing scheduling model with rework risk is proposed, in which the interval grey numbers are applied to describe the uncertainty clearly and consider the rework risk in remanufacturing process. To solve this model, a hybrid optimizationalgorithm that combines differential evolution and particle swarm optimization algorithms through an efficient representation scheme is proposed. Besides, this algorithm integrates multiple improvements to maintain the diversity of the population and enhance its performance. Simulation experiments are conducted on 18 sets of instances with different scales, and the results demonstrated that the proposed algorithm obtains a better optimal solution than other baseline algorithms on 17 sets of instances. The main finding of this study is providing a new method for solving uncertain remanufacturing scheduling problem with rework risk practically and effectively.
In the present work, a new hybrid approach combining particleswarmoptimization (PSO) algorithm with recurrent dynamic neural network (RDNN), which is described as PSO-RDNN algorithm, is proposed for multi-performanc...
详细信息
In the present work, a new hybrid approach combining particleswarmoptimization (PSO) algorithm with recurrent dynamic neural network (RDNN), which is described as PSO-RDNN algorithm, is proposed for multi-performance optimization of machining parameters in finish turning of hardened AISI D2. The suggested optimization problem is solved using the weighted sum technique. Process parameters including cutting speed and feed rate are optimized for minimizing operation cost, maximizing tool life, and producing parts with acceptable surface roughness. Based on experimental results, two neural network models were developed for predicting tool flank wear and surface roughness during the machining process. Based on trained neural networks and structured hybrid algorithm, optimum cutting parameters were obtained. The coefficient of determination for trained neural networks was calculated as R-2 = 0.9893 and R-2 = 0.9879 for predicted flank wear and surface roughness, respectively, which proves the efficiency of trained neural models in real industrial applications. Furthermore, the offered methodology returns a Pareto optimality graph, which represents optimized cutting variables for several various cutting conditions.
In this paper,a multi-objective particleswarm optimizer based on adaptive dynamic neighborhood(ADNMOPSO) is proposed to locate multiple Pareto optimal solutions to solve multimodal multi-objective *** the proposed al...
详细信息
In this paper,a multi-objective particleswarm optimizer based on adaptive dynamic neighborhood(ADNMOPSO) is proposed to locate multiple Pareto optimal solutions to solve multimodal multi-objective *** the proposed algorithm,a spatial distance-based non-overlapping ring topology is used to form multiple subpopulations for parallel search to enhance the local search capability of the *** addition,an adaptive dynamic neighborhood selection strategy is proposed to balance the exploration and exploitation capabilities of the algorithm,allowing the size of the subpopulation to change automatically when the neighborhood switch time is *** prevent the algorithm from premature convergence,a stagnation detection strategy is introduced to apply a Gaussian perturbation operation to the particles that fall into the neighborhood ***,the proposed algorithm is used to solve multimodal multi-objective test problems and compared with existing multimodal multiobjective optimization *** results show that the proposed algorithm can obtain more Pareto solutions when solving different types of multimodal multi-objective functions.
This paper is concerned with the periodic event-triggered consensus of multi-agent systems subject to input saturation. Due to the nonlinearity caused by the input saturation constraint, the accuracy of the event-trig...
详细信息
This paper is concerned with the periodic event-triggered consensus of multi-agent systems subject to input saturation. Due to the nonlinearity caused by the input saturation constraint, the accuracy of the event-triggered mechanism to screen data will be reduced. To deal with this problem, a novel dual periodic event-triggered mechanism is first proposed, in which a saturation-assisted periodic event-trigger and a complemental periodic event-trigger work synergistically to screen data more efficiently under the input saturation constraint. In addition, considering the various disturbances in the environment, a more general mixed H infinity and passive performance is introduced to describe the disturbance attenuation level. Based on the Lyapunov-Krasovskii functional, some less conservative consensus criteria are obtained for the multi-agent systems. In addition, under different input satura-tion constraints, the relationship between the disturbance attenuation level and the data transmission rate is explored. After that, a particle swarm optimization algorithm is a first attempt to estimate and enlarge the region of asymptotic consensus. Finally, an example is given to verify the effectiveness and superiority of our proposed method. (c) 2022 ISA. Published by Elsevier Ltd. All rights reserved.
The geomechanical characteristics of a drill formation are uncontrollable factors that are crucial to determining the optimal controllable parameters for a drilling operation. In the present study, data collected in w...
详细信息
The geomechanical characteristics of a drill formation are uncontrollable factors that are crucial to determining the optimal controllable parameters for a drilling operation. In the present study, data collected in wells drilled in the Marun oilfield of southwestern Iran were used to develop adaptive network-based fuzzy inference system (ANFIS) models of geomechanical parameters. The drilling specific energy (DSE) of the formation was calculated using drilling parameters such as weight-on-bit (WOB), rate of penetration (ROP), rotational speed of drilling string (RPM), torque, bit section area, bit hydraulic factor, and bit hydraulic power. A stationary wavelet transform was subsequently used to decompose the DSE signal to the fourth level. The approximation values and details of each level served as inputs for ANFIS models using particleswarmoptimization (PSO) algorithm and genetic algorithm (GA). As model outputs, the Young's Modulus, uniaxial compressive strength (UCS), cohesion coefficient, Poisson's ratio, and internal friction angle were compared to the geomechanical parameters obtained from petrophysical logs using laboratory-developed empirical relationships. Both models predicted the Young's modulus, UCS, and cohesion coefficient with high accuracy, but lacked accuracy in predicting the internal friction angle and Poisson's ratio. The root mean square error (RMSE) and determination coefficient (R-2) were lower for the ANFIS-PSO model than for the ANFIS-GA model, indicating that the ANFIS-PSO model presents higher accuracy and better generalization capability than the ANFIS-GA model. As drilling parameters are readily available, the proposed method can provide valuable information for strategizing a drilling operation in the absence of petrophysical logs.
Nowadays, manufacturing plants should be agile to changes their production mix plan based on dynamic demands. Here, layout design significantly could impact on manufacturing efficiency. When the flows of materials bet...
详细信息
ISBN:
(纸本)9781728117751
Nowadays, manufacturing plants should be agile to changes their production mix plan based on dynamic demands. Here, layout design significantly could impact on manufacturing efficiency. When the flows of materials between departments embed variability during the planning horizon, this problem is known as the dynamic facility layout problem (DFLP). This paper extends such problem with considering multiple transporters, which commonly are used for transportation tasks among facilities. Hence, we extended the classical DFLP objective function in such a way that could encounter total combined rearrangement, material handling and transporting costs. Firstly, the relevant mathematical model is presented and then hybrid metaheuristic algorithms based on particleswarmoptimization (PSO) and genetic algorithm (GA) presented to solve such problem efficiently. To achieve reliable results, a Taguchi's design of experiments is applied to calibrate initial parameters. Also, a few small-sized problems are solved using the CPLEX software. Analysis of the results shows that the proposed hybrid PSO algorithms have good solution quality according to the objective function and CPU time rather than hybrid GA and proved the effectiveness of this algorithm on the set of test problems.
暂无评论