A BP Neural Network Prediction Model Based on Dynamic Cuckoo Search Optimization Algorithm for Industrial Equipment Fault Prediction

Zhang, Wenbo; Han, Guangjie; Wang, Jing; Liu, Yue

doi:10.1109/access.2019.2892729

Cited by 57 publications

(36 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BPNN has been widely used in various forecasting problems 15 . It is assumed that there are n nodes in the input layer, X = ( x 1 , x 2 , …, x n ), the hidden layer has p nodes, S = ( s 1 , s 2 , …, s l ), the output layer has m nodes, Y = ( y 1 , y 2 ,…, y m ), the weight between the output layer and hidden layer is w ij , the weight between the hidden layer and output layer w jk , the thresholds of the hidden layer node and output layer node are b i and r i respectively, then the output of the hidden layer and output layer, H j and C k , can be written as:

H_{j} = f ({false\sum}_{i = 1}^{n} w_{italicij} x_{i} - b_{j}),

C_{k} = f ({false\sum}_{j = 1}^{p} v_{italicjk} H_{j} + r_{k}) .

…”

Section: Seeker Optimization Algorithm‐back Propagation Neural Networmentioning

confidence: 99%

Comparative study on different neural networks for network security situation prediction

Wang

2020

Security and Privacy

View full text Add to dashboard Cite

This article mainly studied the performance of different neural networks in the processing network security situation prediction (NSSP). Radial basis function (RBF) and back propagation neural network (BPNN) models were optimized by particle swarm optimization (PSO) algorithm and seeker optimization algorithm (SOA), respectively. Then the PSO‐RBF model and SOA‐BPNN model were obtained, and comparative experiments were carried out on CNCERT/CC data set. The results suggested that the improved models were more accurate in predicting the situation value compared with RBF and BPNN models; the PSO‐RBF mode had three prediction errors, with 0.05 mean square error (MSE) and 0.05 mean absolute error (MAE), and the SOA‐BPNN model had six prediction errors, with 0.2 MSE and 0.13 MAE, which showed that the PSO‐RBF model had better performance. The experimental results show that the PSO‐RBF model has an excellent performance in processing NSSP and can be promoted and applied in practice.

show abstract

H_{j} = f ({false\sum}_{i = 1}^{n} w_{italicij} x_{i} - b_{j}),

C_{k} = f ({false\sum}_{j = 1}^{p} v_{italicjk} H_{j} + r_{k}) .

…”

Section: Seeker Optimization Algorithm‐back Propagation Neural Networmentioning

confidence: 99%

Comparative study on different neural networks for network security situation prediction

Wang

2020

Security and Privacy

View full text Add to dashboard Cite

show abstract

“…In the past decades, machine learning algorithms have been widely used to solve problems which have multiple variables with no clear relations. Various models have been developed in industrial design [16], disease diagnosis [17], engineering analysis [18], material optimization [19][20][21], etc., which validated the high accuracy and the universal application of machine learning algorithms. Back Propagation Neural Network algorithm (BPNN), which is a multilayer feedforward neural network trained according to the error back propagation algorithm, is one of the most widely used algorithms.…”

Section: Introductionmentioning

confidence: 99%

Porosity Prediction of Granular Materials through Discrete Element Method and Back Propagation Neural Network Algorithm

Liu

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Granular materials are used directly or as the primary ingredients of the mixtures in industrial manufacturing, agricultural production and civil engineering. It has been a challenging task to compute the porosity of a granular material which contains a wide range of particle sizes or shapes. Against this background, this paper presents a newly developed method for the porosity prediction of granular materials through Discrete Element Modeling (DEM) and the Back Propagation Neural Network algorithm (BPNN). In DEM, ball elements were used to simulate particles in granular materials. According to the Chinese specifications, a total of 400 specimens in different gradations were built and compacted under the static pressure of 600 kPa. The porosity values of those specimens were recorded and applied to train the BPNN model. The primary parameters of the BPNN model were recommended for predicting the porosity of a granular material. Verification was performed by a self-designed experimental test and it was found that the prediction accuracy could reach 98%. Meanwhile, considering the influence of particle shape, a shape reduction factor was proposed to achieve the porosity reduction from sphere to real particle shape.

show abstract

“…Optimization methods, which are normally provided by metaheuristic algorithms as one of the intelligent system techniques, can optimize Artificial Neural Network (ANN) models. Many researchers have employed metaheuristic algorithms to train ANN models [1][2][3][4][5][6][7][8][9]. Finding the global optima solution is the most important goal of the optimization process.…”

Section: Introductionmentioning

confidence: 99%

Dual Kidney-Inspired Algorithm for Water Quality Prediction and Cancer Detection

Abdullah

Jaddi

2020

IEEE Access

View full text Add to dashboard Cite

The kidney-inspired algorithm (KA) was presented in a recent research paper as a metaheuristic search algorithm. The KA imitates the physiological process of the kidneys in the human body. The second kidney in the human body filters all the solutes if the other kidney fails. If the second kidney also gets damaged, dialysis can be performed as a treatment. The failure of a kidney is proved by the Glomerular Filtration Rate (GFR) calculation. In this paper, a Dual-population Kidney-inspired Algorithm (Dual-KA), which contributes to the enhancement of a diversity of solutions and, subsequently, better exploration of the search space, is proposed, as a research objective, in the form of a novel simulation of cooperation between kidneys in human body. If GFR is greater than 60 in each iteration, the process in Dual-KA is continued as normal. If this number is between 15 and 60, some treatment is performed. Else, if the GFR is less than 15 and the current sub-population is the first subpopulation with a GFR of less than 15, all the solutions in the current sub-population are sent to the other sub-population in the current iteration. Otherwise, a dialysis or transplant process is carried out. Dual-KA is tested on 12 known test functions, standard classification and time series datasets. Water quality prediction and cancer detection are two real-world applications of this algorithm. The mentioned algorithm is run on these problems and its high ability is proved. INDEX TERMS Dual kidney-inspired algorithm; Artificial neural network; Water quality prediction; Cancer detection.

show abstract

A BP Neural Network Prediction Model Based on Dynamic Cuckoo Search Optimization Algorithm for Industrial Equipment Fault Prediction

Cited by 57 publications

References 28 publications

Comparative study on different neural networks for network security situation prediction

Comparative study on different neural networks for network security situation prediction

Porosity Prediction of Granular Materials through Discrete Element Method and Back Propagation Neural Network Algorithm

Dual Kidney-Inspired Algorithm for Water Quality Prediction and Cancer Detection

Contact Info

Product

Resources

About