Pi Sigma artificial neural networks are a type of high-order neural network used in time series forecasting problems. In the Pi Sigma artificial neural networks, the weights between the hidden layer and the output lay...
详细信息
Pi Sigma artificial neural networks are a type of high-order neural network used in time series forecasting problems. In the Pi Sigma artificial neural networks, the weights between the hidden layer and the output layer are taken as constant and one, and the biases as constant and zero. Although this feature of the Pi Sigma artificial neural networks enables it to work with fewer parameters, it can also be seen as an obstacle to obtaining better forecasting performance. In this study, unlike classical Pi Sigma artificial neural networks, a modified Pi Sigma artificial neural network is proposed by taking the weights and biases as variables between the hidden layer and the output layer of the network. Thus, direct processing of the information coming to the output layer is prevented and the information coming to the output layer is weighted using different weights and bias values. The process of optimizing all the weights and bias values between the input and hidden layer, the hidden layer, and the output layer of the network is carried out together with the particleswarmoptimization method. The proposed modified Pi Sigma artificial neural networks are compared with some other artificial neural networks in the literature by analyzing much well-known time series. As a result of the applications, it is seen that the forecasting performance of the modified Pi Sigma artificial neural networks is better than both the classical Pi Sigma artificial neural networks and many other artificial neural networks.
As an important part of coal mining mechanization, the reliability of hydraulic support is an important guarantee for the hydraulic support system of the comprehensive mining face, and the fast, accurate, and intellig...
详细信息
ISBN:
(纸本)9798350363272;9798350363265
As an important part of coal mining mechanization, the reliability of hydraulic support is an important guarantee for the hydraulic support system of the comprehensive mining face, and the fast, accurate, and intelligent selection of hydraulic support determines its reliability. To realize the intelligent selection of hydraulic support for the slow inclined comprehensive mining face, and to improve the efficiency and accuracy of the selection of the hydraulic support, a hydraulic support selection method based on the PSO-BP neural network is proposed in this paper. A relationship model between geological parameters and hydraulic support technical parameters is established, and the model is trained by using hydraulic support selection case data as samples. Based on the training results, the model can be used to input new geological parameters to intelligently recommend the selection plan of hydraulic support technical parameters. The actual selection scheme of a coal mine is analyzed as a case study, and the results are compared with the traditional BP neural network selection results. The results indicate that the PSO-BP neural network can efficiently generate the hydraulic support technical parameter selection program. It outperforms the traditional BP neural network in terms of computational accuracy and convergence speed. This provides a reliable reference for intelligent hydraulic support selection.
The study studied the optimal load balancing control method after the distributed power source was connected to the grid to improve the stability of the network operation. Starting from the perspective of the power ma...
详细信息
ISBN:
(纸本)9798350377040;9798350377033
The study studied the optimal load balancing control method after the distributed power source was connected to the grid to improve the stability of the network operation. Starting from the perspective of the power market, this project studied the mechanism of the effect of multiple power access on the stability of the power network. Factors affecting the stability of the power grid operation were proposed. The particleswarmalgorithm was used to achieve load balancing control. It was proposed to achieve power balance at each node in the network and reduce the degree of fluctuation of the system. A power network stability analysis method that takes into account the characteristics of distributed power sources was established and simulated. Through experimental verification, the research results of this project can effectively improve the stability of the power network under the condition of distributed power access and reduce the safety hazards of the power system. The research results of the project will lay a theoretical and technical support for the coordinated development of new energy and large power grids, and promote the construction of smart grids in China.
With the evolution of AI technology, several emerging applications (such as computational offload and image recognition) place higher demands on the quantity and quality of data transmitted by wireless sensor networks...
详细信息
ISBN:
(纸本)9798400718267
With the evolution of AI technology, several emerging applications (such as computational offload and image recognition) place higher demands on the quantity and quality of data transmitted by wireless sensor networks (WSNs). Existing routing algorithms typically choose the transmission path with fewer hops and shorter distance. For energy-constrained WSN, this will lead to rapid energy loss and loss of several nodes, which will shorten the network life cycle. In this paper, a WSN routing method based on the ant colony optimizationalgorithm and the particle swarm optimization algorithm is proposed to deal with the above-mentioned problems. By establishing the multidimensional pheromone model of node distance, hop number and energy, the nodes can dynamically adjust the routing according to the residual energy in the data transmission process, so as to ensure the balanced decrease of node energy and prolong the lifetime of the WSN network. In order to improve the convergence rate of ant colony algorithm and reduce the energy consumption caused by reconstruction, particleswarmoptimization is applied;the fitness function of particle swarm optimization algorithm is improved to ensure that the path can quickly find the optimal solution of the path when multiple self-repairs or repair failures occur. The simulation shows that this method can improve the network lifetime by 33% by ensuring high transmission effectiveness.
The gas utilization ratio (GUR) in a blast furnace is directly linked to the efficiency, cost-effectiveness and environmental impact on the blast furnace ironmaking process. However, The stability of the published GUR...
详细信息
ISBN:
(纸本)9798350387780;9798350387797
The gas utilization ratio (GUR) in a blast furnace is directly linked to the efficiency, cost-effectiveness and environmental impact on the blast furnace ironmaking process. However, The stability of the published GUR time series prediction models need to be improved. This paper presents an improved particleswarmoptimization (PSO) incorporating linearly decreasing inertia weights (LDIW) to optimize the kernel-based extreme learning machine (KELM) for single-step prediction. This paper uses singular spectrum analysis (SSA) to preprocess the data and extract the key components from the GUR time series to solve the problem of high volatility of the GUR time series. In addition, this paper introduces LDIW to improve the optimization ability of particle swarm optimization algorithm, which enhances the stability of a single-step prediction model. Then this paper uses the improved PSO algorithm to extract the optimal parameters of KELM, and establishes a single-step GUR prediction model based on the improved PSO-KELM. Finally, this paper uses the actual production process data of blast furnace to verify the prediction model. The results show that the prediction accuracy of GUR and the overall stability of the model are significantly improved, providing important guidance for the blast furnace ironmaking process.
Nutrient management is a key measure to achieve the target crop yield. Choosing appropriate predictive models and adjusting nutrient supply according to actual conditions can effectively reduce nutrient loss, improve ...
详细信息
ISBN:
(纸本)9798350387780;9798350387797
Nutrient management is a key measure to achieve the target crop yield. Choosing appropriate predictive models and adjusting nutrient supply according to actual conditions can effectively reduce nutrient loss, improve crop yield and product quality. Therefore, we conducted research on the prediction models of inorganic fertilizers N, P, and K in greenhouse tomatoes based on the target yield. In this paper, we analyzed four different neural network prediction models: the neural network prediction model based on ant, colony optimizationalgorithm, the neural network prediction model based on sparrow search algorithm, neural network prediction model based on genetic algorithm and neural network prediction model based on particle swarm optimization algorithm, and compared and analyzed the prediction results of inorganic fertilizer N, P and K under different soil fertility conditions to understand which neural network prediction model will produce the best prediction effect. The simulation results showed that under medium soil fertility, the neural network prediction model based on genetic algorithm had the best prediction effect of inorganic fertilizer N, P, and K. The verification results showed that its mean square error (MSE) and coefficient of determination (R-2) were the best, which were 0.0031 and 0.8200 respectively. However, under low soil fertility and high soil fertility, the neural network prediction model based on the sparrow search algorithm had the best prediction performance, and its MSE and R-2 were the best.
In this paper, equilibrium strategies and optimal balking strategies of customers in a constant retrial queue with multiple vacations and the N-policy under two information levels, respectively, are investigated. We a...
详细信息
In this paper, equilibrium strategies and optimal balking strategies of customers in a constant retrial queue with multiple vacations and the N-policy under two information levels, respectively, are investigated. We assume that there is no waiting area in front of the server and an arriving customer is served immediately if the server is idle;otherwise (the server is either busy or on a vacation) it has to leave the system to join a virtual retrial orbit waiting for retrials according to the FCFS rules. After a service completion, if the system is not empty, the server becomes idle, available for serving the next customer, either a new arrival or a retried customer from the virtual retrial orbit;otherwise (if the system is empty), the server starts a vacation. Upon the completion of a vacation, the server is reactivated only if it finds at least N customers in the virtual orbit;otherwise, the server continues another vacation. We study this model at two levels of information, respectively. For each level of information, we obtain both equilibrium and optimal balking strategies of customers, and make corresponding numerical comparisons. Through particleswarmoptimization (PSO) algorithm, we explore the impact of parameters on the equilibrium and social optimal thresholds, and obtain the trend in changes, as a function of system parameters, for the optimal social welfare, which provides guiding significance for social planners. Finally, by comparing the social welfare under two information levels, we find that whether the system information should be disclosed to customers depends on how to maintain the growth of social welfare.
Distributed generation is a vital component of the national economic sustainable development strategy and environmental protection, and also the inevitable way to optimize energy structure and promote energy diversifi...
详细信息
Distributed generation is a vital component of the national economic sustainable development strategy and environmental protection, and also the inevitable way to optimize energy structure and promote energy diversification. The power generated by renewable energy is unstable, which easily causes voltage and frequency fluctuations and power quality problems. An adaptive online adjustment particleswarmoptimization (AOA-PSO) algorithm for system optimization is proposed to solve the technical issues of large-scale wind and light abandonment. Firstly, a linear adjustment factor is introduced into the particleswarmoptimization (PSO) algorithm to adaptively adjust the search range of the maximum power point voltage when the environment changes. In addition, the maximum power point tracking method of the photovoltaic generator set with direct duty cycle control is put forward based on the basic PSO algorithm. Secondly, the concept of recognition is introduced. The particles with strong recognition ability directly enter the next iteration, ensuring the search accuracy and speed of the PSO algorithm in the later stage. Finally, the effectiveness of the AOA-PSO algorithm is verified by simulation and compared with the traditional control algorithm. The results demonstrate that the method is effective. The system successfully tracks the maximum power point within 0.89 s, 1.2 s faster than the traditional perturbation and observation method (TPOM), and 0.8 s faster than the incremental admittance method (IAM). The average maximum power point is 274.73 W, which is 98.87 W higher than the TPOM and 109.98 W more elevated than the IAM. Besides, the power oscillation range near the maximum power point is small, and the power loss is slight. The method reported here provides some guidance for the practical development of the system.
The parameters of dielectric response based on extended Debye circuit model can reflect oil-paper insulation state. The model using the initial slop of recovery voltage to estimate circuit parameters, serve as good qu...
详细信息
The parameters of dielectric response based on extended Debye circuit model can reflect oil-paper insulation state. The model using the initial slop of recovery voltage to estimate circuit parameters, serve as good quality consistency with the measured data. However, the model can be applicable for large power transformers but not for distribution transformers. This paper proposed an improved mathematical model using recovery voltage peak, peak time and initial slope characteristics to solve dielectric response equivalent circuit parameters. The identification of equivalent circuit parameters is converted into a mathematical optimization problem. And then particle swarm optimization algorithm is used for solving the problem. The improved mathematical model can decrease sampling data of recovery voltage. To check the validity of the estimated parameters, the on-site measured data of RVM experiments on actual transformers in various capacities is applied. The calculated result shows that the recovery voltage curve calculated and measured recovery voltage curve have good consistency, which can be advantageous to diagnose the oil-paper insulation status of transformer. It illustrates that the improved method proposed in this paper is feasible and effective.
To enhance the control accuracy of strip thickness in the non-stationary process of cold continuous rolling, a PSO-GA-RBF based prediction model for the non-stationary roll gap is proposed. This model combines big dat...
详细信息
暂无评论