Small and multi-peak nonlinear time series forecasting using a hybrid back propagation neural network

Dong, Xuefan; Lian, Ying; Liu, Yijun

doi:10.1016/j.ins.2017.09.067

Cited by 26 publications

(14 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The stress concentration factor (SCF) is the ratio of the local maximum stress to the nominal stress. Plenty of methods to calculate the stress concentration factors have been developed for elliptic holes at present [22,23], however, the objects of the above studies are concentrated on penetrating small holes, while the pits studied are usually formed on the surface of steel strands that are similar to non-penetrating oval holes. Complicated mechanics of non-penetrating elliptical holes increase the difficulty in finding its analytical solution.…”

Section: The Finite Element Model Of Pitmentioning

confidence: 99%

Numerical and Experimental Study on the Steel Strands under the Coupling Effect of a Salt Spray Environment and Cyclic Loads

Yao

et al. 2020

Materials

View full text Add to dashboard Cite

Composed of multi-strand parallel high-strength wires or steel strands, the stayed cables have been widely used recently in stayed bridges or suspension bridges owing to their light weight and high bearing capacity, especially the steel strands. Meanwhile, chloride-induced corrosion of steel strands is one of the most considerable factors for the durability of the stayed cable exposed to marine environments. The fatigue caused by both cyclic loading and corrosion can affect the life of the steel strands. Besides, the current studies related to the effects of the aforementioned two impact factors on the life of the steel strands either considered the fatigue only, or took the two impact factors into account separately. The coupling effects of fatigue and corrosion on the life of the steel strands are required to be further explored and discussed. Consequently, it is essential to create a model to predict the life of the steel strands with the coupling effects taken into consideration. In this paper, an indoor physical experiment of the steel strand specimens exposed to marine tidal environment was carried out. To avoid accidental errors, the whole specimens were divided into 20 groups, with each group having two steel wires with a 5 days, 10 days, and 15 days cycle for the test. The corrosion of steel strands was observed at various exposure times and it was found that the pits were formed on the surface with the chloride ion erosion to the steel strands. Deeper and sharper pits result in greater pitting-local stress and a shorter fatigue life, which is also the main reason for reducing the carrying capacity of the steel strands. However, a detailed description for this problem is lacking in current domestic and foreign literature, because the pit is hard to predict owing to its complex nature. In order to simulate the evolution of the pits, the stochastic pitting-corrosion model was set up by the neural network method to evaluate the pit evolutions over time. In addition, an empirical formula consisting of length–width ratios, length–depth ratios, and depth-to-width ratios of the pits was obtained to determine the stress concentration factor based on the multi-dimensional linear regression method. The fatigue notch factor of components can be deduced by the stress concentration factor, and the life of the steel strands can be deduced by both of them. The findings are expected to be useful in realistically predicting the durability of wire structures.

show abstract

Section: The Finite Element Model Of Pitmentioning

confidence: 99%

Numerical and Experimental Study on the Steel Strands under the Coupling Effect of a Salt Spray Environment and Cyclic Loads

Yao

et al. 2020

Materials

View full text Add to dashboard Cite

show abstract

“…And x p ∈ R m is an m-dimensional input vector, which consists of system workload level, system performance parameters and system physical resource utilization in D dimensions. The output vector of the hidden layer h p , and the output vector of the output layer y p are [41]:…”

Section: Residual Available Capacity Modelmentioning

confidence: 99%

Energy Efficient Resource Selection and Allocation Strategy for Virtual Machine Consolidation in Cloud Datacenters

Chang

Luo

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYVirtual Machine Placement (VMP) plays an important role in ensuring efficient resource provisioning of physical machines (PMs) and energy efficiency in Infrastructure as a Service (IaaS) data centers. Efficient server consolidation assisted by virtual machine (VM) migration can promote the utilization level of the servers and switch the idle PMs to sleep mode to save energy. The trade-off between energy and performance is difficult, because consolidation may cause performance degradation, even service level agreement (SLA) violations. A novel residual available capacity (RAC) resource model is proposed to resolve the VM selection and allocation problem from the cloud service provider (CSP) perspective. Furthermore, a novel heuristic VM selection policy for server consolidation, named Minimized Square Root available Resource (MISR) is proposed. Meanwhile, an efficient VM allocation policy, named Balanced Selection (BS) based on RAC is proposed. The effectiveness validation of the BS-MISR combination is conducted on CloudSim with real workloads from the CoMon project. Evaluation results of experiments show that the proposed combination BS-MISR can significantly reduce the energy consumption, with an average of 36.35% compared to the Local Regression and Minimum Migration Time (LR-MMT) combination policy. Moreover, the BS-MISR ensures a reasonable level of SLAs compared to the benchmarks.

show abstract

“…A variety of approaches have been then applied in an attempt to accelerating the learning process. For example, the standard BP-based system can be improved by implementing other techniques, such as least square methods, genetic algorithms and particle swam optimisation and Bayesian regularization scheme [36,37]. Nevertheless, a more intelligent training mechanism normally requires extra computational cost, especially for applications to large and complex systems due to the large number of weighting factors (i.e.…”

Section: Robust Learning Mechanismmentioning

confidence: 99%

“…From (34), the total number of parameters which needs to be tune each step is reduced from (9(N1+N2)+3M) to the range [15,36] disregarding the number of input/output MFs. Thus, the decisive vector size minimizer could save remarkably the time to optimize the control parameters.…”

Section: Robust Learning Mechanismmentioning

confidence: 99%

Robust predictive tracking control for a class of nonlinear systems

Dinh

Marco

Yoon³

et al. 2018

Mechatronics

View full text Add to dashboard Cite

show abstract

Small and multi-peak nonlinear time series forecasting using a hybrid back propagation neural network

Cited by 26 publications

References 36 publications

Numerical and Experimental Study on the Steel Strands under the Coupling Effect of a Salt Spray Environment and Cyclic Loads

Numerical and Experimental Study on the Steel Strands under the Coupling Effect of a Salt Spray Environment and Cyclic Loads

Energy Efficient Resource Selection and Allocation Strategy for Virtual Machine Consolidation in Cloud Datacenters

Robust predictive tracking control for a class of nonlinear systems

Contact Info

Product

Resources

About