Fuzzy C-Means clustering, FCM, is an unsupervised learning algorithm. The algorithm is easily affected by noise points and depends on the initial values. When the sample value is large, the algorithm is easy to fall i...
详细信息
ISBN:
(纸本)9781450354141
Fuzzy C-Means clustering, FCM, is an unsupervised learning algorithm. The algorithm is easily affected by noise points and depends on the initial values. When the sample value is large, the algorithm is easy to fall into local extremum. In this study, the traditional fuzzy clustering algorithm is improved, and the particle swarm optimization algorithm with global optimization ability is applied to the FCM algorithm, and chaotic technology is added. Chaotic variables produce a chaotic sequence based on the current global optimal position, using chaotic sequence has the best fitness value of particles randomly instead of a particle of the particleswarm, the improved algorithm can effectively avoid the stagnation of particles in the iteration, fast search to the global optimal solution, avoid convergence to local extremum. Experimental results indicate that this algorithm overcomes the dependence on the initial clustering centre of FCM, which brings high robustness and segmentation accuracy, and has more faster convergence speed.
In the process of crop growth, irrational fertilizer application methods have caused waste of fertilizer resources and water, as well as damaged the soil's structure. To puzzle the above problems out, the research...
详细信息
In the process of crop growth, irrational fertilizer application methods have caused waste of fertilizer resources and water, as well as damaged the soil's structure. To puzzle the above problems out, the research constructs the model of water-fertilizer machine by gathering relevant parameters in the field. Considering the system's plenty of defects and combining it with the MATLAB/simulink system, such as non-linearity, time-varying, large inertia, uncertain mathematical model and severe lag, a fuzzy proportional integral differential control based on particleswarmoptimization is proposed in this paper for water and fertilizer integration system. Primarily, the research is done for precision fertilization control of fertilizer integration system and water, and the parameters of fuzzy proportional integral differential gain that schedules controllers are optimized through a particleswarmalgorithm. The effectiveness of the suggested controller has been validated by comparing with the control algorithms (proportional integral differential control, fuzzy proportional integral differential control) commonly applied in current fertilizer application systems. Simulation experiments for this research are devised through MATLAB/Simulink simulation platform. Significant improvement in the system's tuning capabilities by incorporating particleswarmalgorithm in the hysteretic non-linear system. Eventually, four control algorithms are experimentally validated in this research at different pH values through Experiments care designed in the experimental field. The outcomes demonstrate that the control algorithm in this paper possesses better regulation effect, smaller overshoot, excellent stability and more inadequate rising steady state time compared with the previous controls, which can enables precise control of the fertiliser system.
Fault estimation (FE) and fault-tolerant control (FTC) are remarkable techniques, have achieved great success in many applications such as robot, spacecraft, and industrial assembly line. This article aims to design a...
详细信息
Fault estimation (FE) and fault-tolerant control (FTC) are remarkable techniques, have achieved great success in many applications such as robot, spacecraft, and industrial assembly line. This article aims to design an iterative-learning scheme based FE and FTC method for a class of nonlinear system with iteration-variant state delay and additive measurement noise. A Luenberger observer in iterative version is proposed to achieve the reconstruction of system state information, which consider the historical observation error in order to improve the observation performance in current iteration. To deal with bounded iteration-variant state delay, an iterative-learning scheme based fault estimator is designed and the convergence is proved. Compared with relevant methods which use system output observation residual to revise the FE result of last iteration, the proposed approach uses filtered system output observation residual in order to reduce the effect of measurement noise. Based on the FE result, FTC using signal compensation technique is employed. In addition, an improved particle swarm optimization algorithm is employed for parameters adaptive tuning. Compared with traditional manual adjustment of parameters, the proposed method can find the optimal parameters and save time of parameter tuning. Finally, three examples are provided to verify the effectiveness of the proposed approach.
Different from low-temperature electrolysis systems, the large power consumption for the balance of plant (BOP) of the reversible solid oxide cell (RSOC) system for a high-temperature operating condition needs to be c...
详细信息
Different from low-temperature electrolysis systems, the large power consumption for the balance of plant (BOP) of the reversible solid oxide cell (RSOC) system for a high-temperature operating condition needs to be considered in the determination of the capacity configuration of the hybrid renewable energy (HRE) system. To address this issue, a power-based model of the RSOC system is developed and the corresponding capacity configuration strategy especially for the HRE system is also proposed in this paper. An optimization program of a hybrid energy system model composed of the wind turbines (WT), photovoltaic panels (PV), reversible solid oxide cell (RSOC) system, hydrogen storage tank (HST), and battery are presented to urge the minimization of the total system cost, power redundancy, and power shortage. particleswarmoptimization (PSO) algorithm is utilized to determine the optimum size and operational energy management within the system. The results show that after the regulation of the energy storage system, the power redundancy and shortage of the hybrid energy system are greatly reduced with the decreases by 85.08% and 64.42%, respectively. Moreover, the power mismatch is still significantly affected by seasons. It is also found that the energy storage efficiency of the RSOC system is within 20% due to the fact that part of the electric energy is consumed by the BOP to maintain the operation of the RSOC system. Thus, more improvements should focus on simplifying the BOP system of the RSOC system and reducing the excess power consumption in the future.
This paper proposes a bearing fault feature extraction and recognition method based on particleswarmoptimizationoptimization Maximum Correlated Kurtosis Deconvolution (MCKD) and one-dimensional convolutional neural...
详细信息
ISBN:
(纸本)9789811926891;9789811926884
This paper proposes a bearing fault feature extraction and recognition method based on particleswarmoptimizationoptimization Maximum Correlated Kurtosis Deconvolution (MCKD) and one-dimensional convolutional neural network to solve the non-stationarity of rolling bearing fault signals, Non-linear and complex characteristics, as well as the problems of noise interference and unclear fault characteristics in the process of fault identification. First, the multi-channel signals of the rolling bearing is analyzed, in order to select the signal containing the impact component as the fault feature. Next, the signal containing the fault feature is filtered through MCKD, where the best parameters of MCKD are obtained by improving the particleswarmalgorithm to achieve the feature enhancement of the main signal. Finally, a one-dimensional convolutional neural network (One Dimensional Convolutional Neural Network, 1D-CNN) is used to model the characteristic signals under different damage conditions in order to obtain the fault recognition model of the rolling bearing. The experimental results show that the method can effectively extract the main characteristic signals of the faulty bearing, and realize the accurate identification of the bearing fault in the noisy environment.
In order to solve the problem of trajectory shift, a PSO-DRBFNNILC strategy is designed. The first RBFNN is introduced to estimate the output of the ILC system;second RBFNN is built to adaptively adjust the learning g...
详细信息
ISBN:
(纸本)9798350321050
In order to solve the problem of trajectory shift, a PSO-DRBFNNILC strategy is designed. The first RBFNN is introduced to estimate the output of the ILC system;second RBFNN is built to adaptively adjust the learning gain matrix in the input update law. PSO algorithm is used to find the optimal search step for the update of the weight, center and radius of the activation function. Convergence analysis shows that the estimation error of the weight of the network and the tracking error of the ILC system are bounded. The effectiveness of the control strategy is verified by numerical simulation.
Aiming at the hot and difficult issues in Web services and service composition, this paper analyzes and studies the selection of Web services and service composition from the functional and non functional attributes o...
详细信息
ISBN:
(纸本)9798350321456
Aiming at the hot and difficult issues in Web services and service composition, this paper analyzes and studies the selection of Web services and service composition from the functional and non functional attributes of Web services, and mainly makes the following work and innovation. First of all, the functional attributes of Web services are studied, Web services on various service provision platforms are collected, and Web services are classified. Secondly, aiming at the shortcomings of existing Web service QoS attribute evaluation models, an improved method is proposed, which introduces a comprehensive evaluation mechanism of variable weight vector. Based on the constant weight comprehensive evaluation method, the state variable weight vector is established to dynamically adjust the attribute weights of various service QoS indicators, so as to improve the accuracy and objectivity of the Web service QoS attribute evaluation. Finally, in view of the defects and deficiencies of traditional algorithms in the selection of Web service composition, the particle swarm optimization algorithm with linearly decreasing inertia weight and learning factor is introduced, which better balances the self cognition and social learning ability of particles, and improves the search speed and global search ability of particles. And a large number of experiments are carried out to compare it with the traditional algorithm, which verifies the effectiveness and superiority of the improved particle swarm optimization algorithm.
For the hardware and software partitioning problem of single processor embedded systems, a weighted directed acyclic graph is usually used for modeling, and it is reduced to solve the 0/1 knapsack problem with multipl...
详细信息
ISBN:
(纸本)9798400708305
For the hardware and software partitioning problem of single processor embedded systems, a weighted directed acyclic graph is usually used for modeling, and it is reduced to solve the 0/1 knapsack problem with multiple constraints. However, traditional particle swarm optimization algorithms cannot solve the 0/1 knapsack problem. Therefore, this article introduces the ideas of crossover and mutation in genetic algorithms into particle swarm optimization algorithms, and proposes a genetic particleswarmoptimization (GPSO) algorithm for solving discrete combinatorial optimization problems. The two-point crossover operator and non-uniform mutation operator are used to redefine the particle position and velocity update method. The experimental results show that the algorithm proposed in the article can effectively solve software and hardware partitioning problems and has good global search ability, its optimization ability and execution time are superior to genetic algorithms and simulated annealing algorithms.
The 21st century is the century of the ocean, and the marine economy has become a new growth point of the national economy. the ocean has become the focus of world attention, which also intensifies the competition for...
详细信息
The 21st century is the century of the ocean, and the marine economy has become a new growth point of the national economy. the ocean has become the focus of world attention, which also intensifies the competition for reaching the heights of marine industry by major coastal countries. With the high-intensity development and use of marine resources, problems such as overfishing and environmental pollution have resulted in a series of depletions of renewable fishery resources, degradation of species, and even extinction, and the continuous reduction of nonrenewable resources such as marine crude oil. Based on the development status of China's marine industry, this article applies the improved particle swarm optimization algorithm to the study of the correlation between marine industrial clusters and the low-carbon level of the marine economy and then explores the transformation and upgrading path of China's marine industry from the perspective of the low-carbon economy.
particle swarm optimization algorithm (PSO) is a good method to solve complex multi-stage decision problems. But this algorithm is easy to fall into the local minimum points and has slow convergence speed, According t...
详细信息
particle swarm optimization algorithm (PSO) is a good method to solve complex multi-stage decision problems. But this algorithm is easy to fall into the local minimum points and has slow convergence speed, According to the semantic relations, an improved PSO algorithm has been proposed in this paper. In contrast with the traditional algorithm, the improved algorithm is added with a new operator to update its crucial parameters. The new operator is to find out the potential semantic relations behind the history information based on the ontology technology. particleswarmoptimization can be applied to many engineering fields, taking Traveling Salesman Problem (TSP) as example. Our experiments show accuracy of the improved particleswarmalgorithm that is superior to that obtained by the other classical versions, and better than the results achieved by the compared algorithms, besides, this improved algorithm can also improve the searching efficiency.
暂无评论