A radial basis function artificial neural network (RBF ANN) based method for uncertain distributed force reconstruction considering signal noises and material dispersion

Wang, Lei; Liu, Yaru; Gu, Kaixuan; Wu, Tong

doi:10.1016/j.cma.2020.112954

Cited by 60 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RBFNN , one of the efficient ANN schemes with activation function of radial basis function, as described in Figure 4b, possesses the superiority of strong simulation and fast learning speed. [ 32 ] Figure 4b shows a typical RBF network architecture and the topology for our ML process. The RBF network proposed in this work contains three layers, including input layer, hidden layer, and output layer.…”

Section: Methodsmentioning

confidence: 99%

“…As an analytical model technique, artificial neural network (ANN) models exhibit excellent performance in dealing with various types of nonlinear or complex problems, including prediction and optimization problems, or regression and classification ones. [ 31 ] In addition to this, the radial basis function neural network (RBFNN) [ 32,33 ] and fuzzy neural network (FNN) [ 34 ] are also widely used in materials design. Thus, in the present study, to screen out the most suitable ML model for the future design has become the overarching goal.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Phase Prediction of High Carbon Pearlitic Steel: An Improved Model Combining Mind Evolutionary Algorithm and Neural Networks

et al. 2021

View full text Add to dashboard Cite

Accurate phase constitution prediction is crucial for guiding the new steel design with desirable properties. This article uses three machine learning (ML) algorithms, backpropagation neural network (BPNN), radial basis function neural network (RBFNN), and fuzzy neural network (FNN), to compare the accuracy of predictive model. Toward the collected data, statistical measure of correlation is taken in the present work by determining Pearson correlation coefficient (PCC). The results show that the testing accuracy using BPNN is higher than the corresponding testing accuracy using RBFNN and FNN. With these understandings, the well‐known optimization algorithms, namely, mind evolutionary algorithm (MEA), are implemented to find optimal hyperparameters set that is able to induce a higher predictive capability. The resulting MEA‐BPNN further enhances the prediction results in the present dataset and efficiently explores the relationship between alloying elements and phase constitution. Finally, the reliability and practicability of the model are verified by experimental measurement on the ferrite content for prepared steels, and their mechanical properties are tested for engineering applications. As such, the work proposes a useful MEA‐BPNN model for predicting the phases of high carbon pearlite steel and provides an alternative route of designing new steels in a given system.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Phase Prediction of High Carbon Pearlitic Steel: An Improved Model Combining Mind Evolutionary Algorithm and Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…RBFANN is an efficient three-layer forward neural network with the activation function of radial basis function, which can approximate to a nonlinear function accurately with simple topological structure and fast convergence speed. A generalized RBFANN structure is shown in Figure 3, which consists of one input layer, one hidden layer, and one output layer [26][27][28]. e input layer contains the input variable vector X � [X 1 , X 2 ,.…”

Section: A Generalized Rbfann Topologic Structurementioning

confidence: 99%

Robust Chatter Stability Prediction of the Milling Process considering Uncertain Machining Positions

Deng

Zhou

Yang

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Milling stability is a function of the tool point frequency response functions (FRFs), which vary with the movements of the moving parts within the whole machine tool work volume. The position-dependent tool point FRFs result in uncertain prediction of the stability lobe diagram (SLD) for chatter-free machining parameter selection. Taking the variations of modal parameters to represent the variations of tool point FRFs, this paper introduces the edge theorem to predict the robust milling chatter stability. The application of the edge theorem requires the minimum and maximum modal parameters within the machining space defined by the machining position and machining allowance information. Then, radial basis function artificial neural networks (RBFANNs) are used to predict the position-dependent modal parameters in X and Y directions based on the sample information of machining positions and related modal parameters at the tool point. Moreover, sample machining spaces are determined based on the aforementioned sample positions, and the trained RBFANNs are used to obtain corresponding sample extreme modal parameters. On this basis, RBFANNs for predicting the position and machining allowance-dependent extreme modal parameters can also be trained, and they are combined with the edge theorem and zero exclusion condition to calculate robust pairs of the spindle speed (n) and limiting axial cutting depth (aplim) and then plot the robust SLD (RSLD). A case study was performed on a real three-axial vertical machining center, and the plotted RSLD considering position variations was compared with the traditional SLD. Results of the chatter tests show that the RSLD can provide more reliable (ap, n) pairs to guarantee the milling stability, validating the feasibility of the proposed robust milling chatter stability prediction method.

show abstract

“…Considering the transfer effects of uncertainties, the identified dynamic loads are also indeterminate. Numerous researches have been carried out on the uncertain dynamic load identification, 28–30 especially in the context of the nonprobabilistic interval model 31 . Song et al 32 applied the interval perturbation approach to the identification of high‐frequency loads considering measurement errors of damping loss factors and coupling loss factors.…”

Section: Introductionmentioning

confidence: 99%

“…Numerous researches have been carried out on the uncertain dynamic load identification, [28][29][30] especially in the context of the nonprobabilistic interval model. 31 Song et al 32 applied the interval perturbation approach to the identification of high-frequency loads considering measurement errors of damping loss factors and coupling loss factors. Liu et al 33 calculated the lower and upper bounds of dynamic loads using the first-order Taylor expansion in uncertainty intervals with two regularization methods.…”

Section: Introductionmentioning

confidence: 99%

Kalman filter–random forest‐based method of dynamic load identification for structures with interval uncertainties

Liu

Wang

2022

Structural Contr & Hlth

Self Cite

View full text Add to dashboard Cite

Summary It is widely acknowledged that dynamic load identification is a powerful technology for structural health monitoring and reliability analysis. This paper investigates an uncertain dynamic load identification strategy with the combination of the Kalman filter (KF) algorithm and the random forest (RF) model. Enlightened by the concept of the KF, a one‐step delayed identification of dynamic loads is completed in the state space domain. The previous loads can be calculated recursively utilizing the previous state estimation and the current displacement observation based on the least square method. In addition, the optimal state estimation will be achieved synchronously with the classical KF algorithm. In terms of inevitable uncertainties, the interval model is introduced to quantify uncertain system parameters and uncertain input loads. To determine the interval load process, the RF surrogate model is constructed to characterize their functional relationship, which is integrated by massive decision trees (DTs). Particularly, Latin hypercube sampling (LHS) and bootstrap sampling (BS) methods are employed to generate training samples for the RF model. The validity and feasibility of the developed methodology are eventually demonstrated by three numerical examples. The results indicate that the proposed approach has an excellent performance in both accuracy and efficiency.

show abstract

A radial basis function artificial neural network (RBF ANN) based method for uncertain distributed force reconstruction considering signal noises and material dispersion

Cited by 60 publications

References 31 publications

Phase Prediction of High Carbon Pearlitic Steel: An Improved Model Combining Mind Evolutionary Algorithm and Neural Networks

Phase Prediction of High Carbon Pearlitic Steel: An Improved Model Combining Mind Evolutionary Algorithm and Neural Networks

Robust Chatter Stability Prediction of the Milling Process considering Uncertain Machining Positions

Kalman filter–random forest‐based method of dynamic load identification for structures with interval uncertainties

Contact Info

Product

Resources

About