The differential transformation dual reciprocity boundary element method (DT-DRBEm) combined with the levenberg-marquardt (l-m) algorithm is proposed to identify the thermal conductivity for orthotropic functionally g...
详细信息
The differential transformation dual reciprocity boundary element method (DT-DRBEm) combined with the levenberg-marquardt (l-m) algorithm is proposed to identify the thermal conductivity for orthotropic functionally gradient materials (FGms). The original governing equation of two-dimensional transient heat conduction problem is transformed into a time-independent and recursive form equation by the differential transformation method (DTm). The analog equation method is used to convert the partial differential equation to a standard thermal diffusion equation. Then, the DRBEm is applied to solve the direct problem and the measured temperature is obtained. After that, the l-m algorithm is used to minimize the objective function and recover the desired thermal conductivity. The DT-DRBEm is compared with the finite difference DRBEm (FD-DRBEm). The l-m algorithm is also compared with the conjugate gradient method (CGm). The influences of different initial guesses, number of measurement points and random errors on the inverse results are also investigated. The initial guesses have little effect on the number of iteration. With the increase of measurement points and with the decrease of measurement errors, the results are more accurate.
In the traditionalmethod of monitoring the state of electronic voltage transformer, there are problems of large monitoring error and weak robustness. Therefore, a new state monitoring method of electronic voltage tra...
详细信息
In the traditionalmethod of monitoring the state of electronic voltage transformer, there are problems of large monitoring error and weak robustness. Therefore, a new state monitoring method of electronic voltage transformer based on l-m algorithm is proposed. The relationship between input voltage and output voltage of capacitor voltage divider in electronic voltage transformer is obtained by using laplasse transform. The transfer function model of electronic voltage transformer is constructed based on the relationship result and l-m algorithm. The transfer function model is used to analyze the frequency characteristics of the electronic voltage transformer and the range of normalmeasurement frequency, and then the partial pressure ratio of the electronic voltage transformer under the high frequency condition is derived. On this basis, by calculating the over voltage amplitude on the two sides of acquisition card in the electronic voltage transformer, the capacitance value between the two adjacent coaxial cylindrical cylinders of the capacitance divider in the electronic voltage transformer is obtained, thus the monitoring of the state of the electronic voltage transformer is completed. The experimental results show that the proposed method has low detection error and strong robustness, and can effectively improve the reliability of electronic voltage transformer.
Transformers are essential device of the power system. Accurate computation of the hottest temperature (HST) of windings is of great meaning, for the HST is an fundamental parameter to guide the load operation mode an...
详细信息
ISBN:
(纸本)9781509039678
Transformers are essential device of the power system. Accurate computation of the hottest temperature (HST) of windings is of great meaning, for the HST is an fundamental parameter to guide the load operation mode and influence the life expansion of insulation. Based on the analysis of the heat transfer processes and the thermal characteristics inside transformers, influence on the oil-immersed transformers of factors like the sunshine, external wind speed etc. are taken into consideration. Experiment data and the neural network are used in modeling and protesting of the HST, and furthermore, investigations on optimization of the structure and algorithm of neutral network are conducted. Comparison among the measured value and calculation values using the recommended algorithm of IEC60076 and the neural network algorithm is made;it shows that the value computed with network algorithm approximates more to the measured value than the value computed with algorithm of IEC60076.
Wireless Sensor Networks (WSN) are getting more and more attention for various applications. In addition, localization plays an important role in WSN. This article focus on the large errors of DV-Hop (Distance Vector-...
详细信息
Wireless Sensor Networks (WSN) are getting more and more attention for various applications. In addition, localization plays an important role in WSN. This article focus on the large errors of DV-Hop (Distance Vector-Hop) localization algorithm in net topology of randomly distributed notes. A ClDV-Hop (Correct levenberg marquardt DV-Hop) algorithm in DV-Hop based on modifying average hopping distances is proposed. Firstly, hop count threshold is to optimize the anchor node during a data exchange. The weighted average hop distance of unknown nodes nearest the three anchor nodes are selected as its average hop distance according to the minimummean square criteria. Finally, l-m (levenberg marquardt) algorithm is used to optimize the coordinate of unknown node estimated by least squares. The simulation results show that, under the conditions of existing overhead and for a given simulation environment, ClDV-Hop algorithm has higher positioning accuracy than existing improved algorithms. The accuracy is improved 33%-41% compared with DV-Hop algorithm.
PurposeIn this study, a novel grey combined model, termed the logistic-Grey-markov model, is proposed. This model aims to construct a relation function between transition probabilities and residual errors and fully ut...
详细信息
PurposeIn this study, a novel grey combined model, termed the logistic-Grey-markov model, is proposed. This model aims to construct a relation function between transition probabilities and residual errors and fully utilize the information from residual errors to calculate optimal transition probabilities for more accurate ***/methodology/approachTo address this issue, the logistic function is introduced and improved to accommodate different types of samples. Then the improved logistic function is applied to construct a relation function between transition probabilities and sample residual errors. Additionally, to obtain the optimal coefficients in the relation function, a least square objective function is constructed, and the levenberg-marquardt algorithm is employed. With these optimal coefficients, the relation function can fully utilize the information of residual errors and calculate the optimal transition *** improved logistic function in the logistic-Grey-markov model ensures that the information from sample residual errors is fully utilized and case studies demonstrate that the proposed logistic-Grey-markov model can effectively improve the prediction ***/valueOne of the strengths of the Grey-markov model is its ability to predict outcomes with small and highly volatile samples. However, the prediction accuracy is not ideal due to the information waste of residual errors, especially when only a small sample size is available. The proposed logistic-Grey-markov model can fully utilize the information in residual errors to calculate the optimal transition probabilities and improve the accuracy of the Grey-markov model.
The use of traditional reinforcement methods in construction sites often causes problems such as pore water pressure, which can not effectively form a solid foundation. Aiming at this problem, the evaluation model of ...
详细信息
The use of traditional reinforcement methods in construction sites often causes problems such as pore water pressure, which can not effectively form a solid foundation. Aiming at this problem, the evaluation model of soft soil foundation reinforcement effect of prefabricated buildings is established based on BP neural network, combined with the geological characteristics of soft soil and the elements of foundation reinforcement;The l-m algorithm is used to optimize the slow convergence problem of BP neural network, and finally its evaluation effect is verified through practical application. The results show that the strengthening effect of 1550 kN center dot m/m(2) is better than that of 2000 kN center dot m/m(2) with the more times of tamping for marine and river facies, and there is a positive correlation between the times of strengthening and the effect. At the same time, similar qualitative conditions also show that the greater the burial depth, the worse the reinforcement effect. When the overlying soillayer is soft, the shallow buried soillayer can be reinforced by laying a cushion to improve the overall reinforcement effect. The laws reflected in the finalmodel output data are the same as those reflected in the construction, and the accuracy of the proposed model is up to 87%, indicating that the model has superior performance in the reinforcement effect evaluation.
In order to improve the reliability and stability of short-wave ground-to-air communication, ground-to-air wireless networking has become a trend. However, the time-varying ionospheric transmission medium will result ...
详细信息
ISBN:
(纸本)9798400718144
In order to improve the reliability and stability of short-wave ground-to-air communication, ground-to-air wireless networking has become a trend. However, the time-varying ionospheric transmission medium will result in difficult link establishment and easy interruption of HF communication. Aiming at the difficulties in HF ground-to-air network, this paper studies the method of task planning of HF ground-to-air network, proposes an improved BP neural network algorithm based on genetic algorithm optimization and l-m algorithm training, and makes optimization analysis and calculation, so as to obtain the prediction and ranking results of existing stations and available frequency points. Simulation results are proved proves that the method of frequency prediction by neural network can fully meet the accuracy requirements of task planning with the support of real detection values or databases, so as to improve the reliability of ground-to-air HF communication in long-distance flight routes or regions and provide more accurate and reliable reference for task planning of HF ground-to-air network.
The development and implementation of green product certification have created new requirements for risk assessment of the certification process. Conventionalmethods of scoring and subjective evaluation are at odds w...
详细信息
The development and implementation of green product certification have created new requirements for risk assessment of the certification process. Conventionalmethods of scoring and subjective evaluation are at odds with the requirements of timeliness, objectivity, intelligence and authority of green certification risk assessment in the era of "big data." In this study, an improved prototype decision structure was developed based on published literature. Then the Delphi method was used to reach consensus among experts, identify the key risk points of green building materials certification (GBmC), and build a formal decision structure consisting of three aspects and 11 risk points. A conventional back-propagation (BP) neural network model and a levenberg-marquardt (l-m) improved BP model, were used to assess the risk of GBmC. The applicability and characteristics of the two models were compared using empirical data. Both models accurately described the risk of GBmC, but the improved lmBP model performed better. The results showed that the new lmBP model performs better than the conventional BP model in terms of mean square error, gradient to a solution, and training efficiency. The enhancement effects were improved by 99.1%, 91.9%, and 33.3%, respectively. This paper believes that when assessing the risk of GBmC, considerations should include not only the risk in the certification process, but also the internal risk of certification agencies and certification businesses. Furthermore, the proposed lmBP model is suitable for use in assessing the risk assessment of GBmC, especially in the environment of "big data". In order to effectively control the risk of GBmC, the risk of certification institutions, including historical risk, experience risk and ability risk, as well as the risk related to the application enterprise, including its credit risk, satisfaction risk and green index risk, should be taken into account seriously.
This study was devoted to examine pile bearing capacity and to provide a reliable model to simulate pile load-settlement behaviour using a new artificial neural network (ANN) method. To achieve the planned aim, experi...
详细信息
This study was devoted to examine pile bearing capacity and to provide a reliable model to simulate pile load-settlement behaviour using a new artificial neural network (ANN) method. To achieve the planned aim, experimental pile load test were carried out on model open-ended steel piles, with pile aspect ratios of 12, 17, and 25. An optimised second-order levenberg-marquardt (lm) training algorithm has been used in this process. The piles were driven in three sand densities;dense, medium, and loose. A statistical analysis test was conducted to explore the relative importance and the statistical contribution (Beta and Sig) values of the independent variables on the model output. Pile effective length, pile flexural rigidity, applied load, sand-pile friction angle and pile aspect ratio have been identified to be the most effective parameters on model output. To demonstrate the effectiveness of the proposed algorithm, a graphical comparison was performed between the implemented algorithm and the most conventional pile capacity design approaches. The proficiency metric indicators demonstrated an outstanding agreement between the measured and predicted pile-load settlement, thus yielding a correlation coefficient (R) and root mean square error (RmSE) of 0.99, 0.043 respectively, with a relatively insignificant mean square error level (mSE) of 0.0019.
For effective modelling of flowshop scheduling problems, artificial neural networks (ANNs), due to their robustness, parallelism and predictive ability have been successfully used by researchers. These studies reveal ...
详细信息
For effective modelling of flowshop scheduling problems, artificial neural networks (ANNs), due to their robustness, parallelism and predictive ability have been successfully used by researchers. These studies reveal that the ANNs trained with conventional back propagation (CBP) algorithm utilising the gradient descent method are commonly applied to model and solve flowshop scheduling problems. However, the existing scheduling literature has not explored the suitability of some improved neural network training algorithms, such as gradient descent with adaptive learning (GDAl), Boyden, Fletcher, Goldfarb and Shanno updated Quasi-Newton (UQ-N), and levenberg-marquardt (l-m) algorithms to solve the flowshop scheduling problem. In this article, we investigate the use of these training algorithms as competitive neural network learning tools to minimise makepsan in a flowshop. Based on training and testing measures, overall results from extensive computational experiments demonstrate that, in terms of the solution quality and computational effort required, the l-m algorithm performs the best followed by the UQ-N algorithm, GDAlalgorithm, and the CBP algorithm. These computational results also reveal that the average percent deviation of the makespan from its best solution obtained by using the ANN trained with the l-m algorithm is the least among all examined approaches for the benchmark problem instances.
暂无评论