Pipeline damage identification based on an optimized back-propagation neural network improved by whale optimization algorithm

Wu, Lei; Mei, Jiangtao; Zhao, Shengdun

doi:10.1007/s10489-022-04188-7

Cited by 7 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by the efforts in [35], [36], adaptive nonlinear weights κ 1 and κ 2 are introduced for updating the positions of individuals (whales) in ( 17)- (22). In addition, these weights are also used for bubble-net attacks and searching for prey.…”

Section: ) Encircle Preymentioning

confidence: 99%

“…When the iteration index t gradually approaches T , κ 2 is closer and closer to zero. Evidently, when t " T , all whales don't search for prey using ( 31)- (36), they encircle prey and perform bubblenet attacks in equal probability. In other words, IWOA only contains two operations consisting of shrinking encirclement and spiral update at this time.…”

Section: A Convergence Analysismentioning

confidence: 99%

See 1 more Smart Citation

International Comparison on the Application of Information Technology in High School Mathematics Textbooks

Zhou

2021

School Mathematics Textbooks in China

View full text Add to dashboard Cite

Ultra-dense networks are widely regarded as a promising solution to explosively growing applications of Internet-of-Things (IoT) mobile devices (IMDs). However, complicated and severe interferences need to be tackled properly in such networks. To this end, both orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) are utilized at first. Then, in order to attain a goal of green and secure computation offloading, under the proportional allocation of computational resources and the constraints of latency and security cost, joint device association, channel selection, security service assignment, power control and computation offloading are done for minimizing the overall energy consumed by all IMDs. It is noteworthy that multi-step computation offloading is concentrated to balance the network loads and utilize computing resources fully. Since the finally formulated problem is in a nonlinear mixed-integer form, it may be very difficult to find its closed-form solution. To solve it, an improved whale optimization algorithm (IWOA) is designed. As for this algorithm, the convergence, computational complexity and parallel implementation are analyzed in detail. Simulation results show that the designed algorithm may achieve lower energy consumption than other existing algorithms under the constraints of latency and security cost.

show abstract

Section: ) Encircle Preymentioning

confidence: 99%

Section: A Convergence Analysismentioning

confidence: 99%

International Comparison on the Application of Information Technology in High School Mathematics Textbooks

Zhou

2021

School Mathematics Textbooks in China

View full text Add to dashboard Cite

show abstract

“…This algorithm offers advantages such as simplicity in principles, fewer parameters, and ease of implementation. It has successfully been applied to solve a variety of problems in fields such as image retrieval 24 , image segmentation 25 , medicine 26 , energy 27 , neural networks 28 , feature selection 29 , wind speed prediction 30 , key recognition 31 , and sentiment analysis 32 , among others. However, WOA still faces challenges when applied to nonlinear, high-dimensional, and complex optimization problems, including issues related to low optimization precision, slow convergence, and susceptibility to local convergence.…”

Section: Introductionmentioning

confidence: 99%

A whale optimization algorithm based on atom-like structure differential evolution for solving engineering design problems

Tang,

Wang

2024

Sci Rep

View full text Add to dashboard Cite

The whale optimization algorithm has received much attention since its introduction due to its outstanding performance. However, like other algorithms, the whale optimization algorithm still suffers from some classical problems. To address the issues of slow convergence, low optimization precision, and susceptibility to local convergence in the whale optimization algorithm (WOA). Defining the optimization behavior of whale individuals as quantum mechanical behavior, a whale optimization algorithm based on atom-like structure differential evolution (WOAAD) is proposed. Enhancing the spiral update mechanism by introducing a sine strategy guided by the electron orbital center. Improving the random-walk foraging mechanism by applying mutation operations to both the electron orbital center and random individuals. Performing crossover operations between the newly generated individuals from the improved mechanisms and random dimensions, followed by a selection process to retain superior individuals. This accelerates algorithm convergence, enhances optimization precision, and prevents the algorithm from falling into local convergence. Finally, implementing a scouting bee strategy, where whale individuals progressively increase the number of optimization failures within a limited parameter L. When a threshold is reached, random initialization is carried out to enhance population diversity. Conducting simulation experiments to compare the improved algorithm with the whale optimization algorithm, other optimization algorithms, and other enhanced whale optimization algorithms. The experimental results indicate that the improved algorithm significantly accelerates convergence, enhances optimization precision, and prevents the algorithm from falling into local convergence. Applying the improved algorithm to five engineering design problems, the experimental results demonstrate that the improved algorithm exhibits good applicability.

show abstract

A Review of Deformations Prediction for Oil and Gas Pipelines Using Machine and Deep Learning

Macêdo,

Boratto,

Saporetti

et al. 2024

Studies in Systems, Decision and Control

View full text Add to dashboard Cite

Pipeline damage identification based on an optimized back-propagation neural network improved by whale optimization algorithm

Cited by 7 publications

References 47 publications

International Comparison on the Application of Information Technology in High School Mathematics Textbooks

International Comparison on the Application of Information Technology in High School Mathematics Textbooks

A whale optimization algorithm based on atom-like structure differential evolution for solving engineering design problems

A Review of Deformations Prediction for Oil and Gas Pipelines Using Machine and Deep Learning

Contact Info

Product

Resources

About