The presence of internal fissures holds immense sway over the gas permeability of sustainable cement mortar, which in turn dictates the longevity and steadfastness of associated edifices. Nevertheless, predicting the ...
详细信息
The presence of internal fissures holds immense sway over the gas permeability of sustainable cement mortar, which in turn dictates the longevity and steadfastness of associated edifices. Nevertheless, predicting the gas permeability of sustainable cement mortar that contains internal cracks poses a significant challenge due to the presence of numerous influential variables and intricate interdependent mechanisms. To solve the deficiency, this research establishes an innovative machine learning algorithm via the integration of the mind evolutionary algorithm (MEA) with the Adaptive Boosting algorithm-Back Propagation Artificial Neural Network (ABA-BPANN) ensemble algorithm to predict the gas permeability of sustainable cement mortar that contains internal cracks, based on the results of 1452 gas permeability tests. Firstly, the present study employs the MEA-tuned ABA-BPANN model as the primary tool for gas permeability prediction in cement mortar, a comparative analysis is conducted with conventional machine learning models such as Particle Swarm Optimisation algorithm (PSO) and Genetic algorithm (GA) optimised ABA-BPANN, MEA optimised Extreme Learning Machine (ELM), and BPANN. The efficacy of the MEA-tuned ABA-BPANN model is verified, thereby demonstrating its proficiency. In addition, the sensitivity analysis conducted with the aid of the innovative model has revealed that the gas permeability of durable cement mortar incorporating internal cracks is more profoundly affected by the dimensions and quantities of such cracks than by the stress conditions to which the mortar is subjected. Thirdly, puts forth a novel machine-learning model, which enables the establishment of an analytical formula for the precise prediction of gas permeability. This formula can be employed by individuals who lack familiarity with machine learning skills. The proposed model, namely the MEA-optimised ABA-BPANN algorithm, exhibits significant potential in accurately estimating the gas perm
To investigate the effect of slow tool servo turning process parameters on surface roughness, we established a high precision surface roughness prediction model. A guide to the selection of turning process parameters ...
详细信息
To investigate the effect of slow tool servo turning process parameters on surface roughness, we established a high precision surface roughness prediction model. A guide to the selection of turning process parameters was compiled, and a turning test was conducted based on a response surface method (RSM) central composite design. ANOVA explores the influence law of process parameters on surface roughness. A RSM BP neural network model, and MEA-BP surface roughness model were established and the prediction performance of the three models was evaluated. The results show that the significant process parameters affecting surface roughness are tool radius, discrete angle, feed rate, and cutting depth in descending order;and the prediction errors of RSM, BP, and MEA-BP are 11.41%, 19.67%, and 5.54%. This suggests that the MEA-BP model has the highest prediction accuracy with the same test data, RSM is second, whilst the single BP model struggles to capture multiple data characteristics and its prediction accuracy is poor. In addition, MEA can effectively solve the BP model falling into local optimum and improve the model prediction accuracy.
By analyzing the distributed power of the impact of distribution network planning, A new mind evolutionary algorithm based on considerationwith is proposed to solve the selected location problem and selected capacity ...
详细信息
ISBN:
(纸本)9789881563835
By analyzing the distributed power of the impact of distribution network planning, A new mind evolutionary algorithm based on considerationwith is proposed to solve the selected location problem and selected capacity of the distributed generation. Firstly, the normalized objective function including investment and operating cost, loss cost and purchase is proposed, then the algorithm is achieved by Matlab. The results obtained show that the global search capabilities can achieve balance and the optimal solution can be found quickly.
The inlet and outlet temperature of the mill is an important index in the process of slag powder production. The specific technological process of the production of slag powder is introduced, and the factors that infl...
详细信息
The inlet and outlet temperature of the mill is an important index in the process of slag powder production. The specific technological process of the production of slag powder is introduced, and the factors that influence the inlet and outlet temperature of the mill are analyzed. The actual data of production process is preprocessed by the Pauta criterion. The forecasting model of inlet and outlet temperature of mill is established to predict the temperature in an hour by using the basic BP neural network and BP neural network optimized by mind evolutionary algorithm. Through the simulation of Matlab software, the prediction effect diagram, prediction error chart, prediction mean square error, mean absolute error, mean absolute percentage error, and coefficient of decision of the two algorithms are compared. The results show that the BP neural network optimized by mind evolutionary algorithm is better than the original BP neural network in the prediction accuracy.
Solar energy is a new energy source that is not only renewable but also available everywhere in the world. Thus, this new energy source is used on solar unmanned aerial vehicles. The use of solar photovoltaic systems ...
详细信息
Solar energy is a new energy source that is not only renewable but also available everywhere in the world. Thus, this new energy source is used on solar unmanned aerial vehicles. The use of solar photovoltaic systems (PVS) involves the conversion of solar energy into electricity. A photovoltaic cell is the core part of solar unmanned aerial vehicle (UAV) for providing energy. The solar panels are laid on the wings of solar unmanned aerial vehicles. This paper proposes a new MPPT controller for predicting the voltage to obtain the maximum power from the solar panel. In this paper, on the basis of studying the characteristics of photovoltaic cells, combined with the advantages of the mind evolutionary algorithm (MEA) and back propagation network, this article proposes a new type of BP network modeling structure based on the MEA, which is used for the modeling of photovoltaic cells. First, the MEA is constructed based on topology of a back propagation network. Then, this algorithm is used to obtain the optimal solutions, which are regarded as the initial weights and threshold values of the BP neural network. Finally, the simulation experiment is performed MATLAB software;comparing the different prediction results of the MEA optimization BP Network and genetic algorithm (GA) optimization BP neural network with the simple use of the BP neural network. The simulation results indicate that the optimization of the BP neural network by the MEA decreased the mean absolute percent error (MAPE) and root mean square error (RMSE) evaluation indicators by approximately 64% and 0.0524, respectively, compared with the back propagation neural network (BPNN). Overall, the MEA optimization BP neural network has high precision, small error, and a short training time.
Aiming at the problem that the probabilistic neural network(PNN) is difficult to determine the smoothing factors in the process of partial discharge recognition in GIS. A model of GIS partial discharge recognition bas...
详细信息
Aiming at the problem that the probabilistic neural network(PNN) is difficult to determine the smoothing factors in the process of partial discharge recognition in GIS. A model of GIS partial discharge recognition based on mind evolutionary algorithm(MEA) is proposed to optimize the PNN. The MEA has the strong ability of searching, obtaining the global approximate optimal solution, finding the optimal smoothing factor of PNN, and improving the accuracy of partial discharge classification. In order to verify the validity and practicability of this model, the simulations are carried out using three typical discharge defect samples. Compared with back propagation(BP) neural network and PNN, the results show that the partial discharge recognition accuracy and stability of PNN optimized by MEA are better and with certain research value.
A new transformer fault diagnostic method based on fuzzy neural network and mind evolutionary algorithm was presented. According to the "similartaxis" and "dissimilation",mindevolutionary algorith...
详细信息
A new transformer fault diagnostic method based on fuzzy neural network and mind evolutionary algorithm was presented. According to the "similartaxis" and "dissimilation",mind evolutionary algorithm has been used to optimize the membership function parameters and connection weights of fuzzy neural network,and it benefits to find the global optimal solution *** analysis and experimental results showed that the method can improve processing ability of network,and the convergence of method is faster and diagnosis accuracy is higher than that of the GA-fuzzy neural network and PSO- fuzzy neural ***,the method can be used for the transformer fault diagnosis.
暂无评论