Using LSTM Network for Solving the Multidimentional Time Series Forecasting Problem

Obrubov, M.; Kirillova, Svetlana

doi:10.31618/nas.2413-5291.2021.2.68.450

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e LSTM network is a classical network structure in deep learning. e LSTM contributes to model learning at subsequent moments by passing the weight matrix of the implicit layer at different time steps backward in a coefficient-weighted manner through weight parameter conduction [21]. e accumulation of important information and the abandonment of redundant information are achieved through the collaborative work of input, forgetting and output gates with the help of memory units accumulating the weight states of the implicit layer.…”

Section: Lstm Networkmentioning

confidence: 99%

Visual Monitoring Technology for Substation Vulnerable High-Voltage Electrical Equipment Based on ISSA-LSTM Deep Learning Model Coupling Video Overlay Algorithm

Wang

Ding

Tan

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To enhance the visualization effect of substation high-voltage electrical equipment vulnerability, this study proposes an ISSA-LSTM coupled video overlay algorithm-based substation high-voltage electrical equipment vulnerability visualization and monitoring model. Using the improved α blending algorithm combined with the inverse sampling of video background color, overlaying visible video as well as infrared video, using the improved adaptive weighted two-dimensional principal component analysis (W2DPCA) to fuse the base layer, selecting the detail layer as the final detail layer, obtaining the final fusion frame, and realizing the visualization and monitoring of substation high-voltage electrical equipment vulnerability, and introducing the improved sparrow search algorithm (ISSA) to establish long and short-term memory network prediction model to reduce the prediction error and improve the monitoring accuracy rate. The experimental results show that the monitoring frames obtained by this method can reflect rich details of substation high-voltage electrical equipment, and the texture color and equipment edge contrast are enhanced to facilitate accurate determination of substation high-voltage electrical equipment vulnerability, and the prediction accuracy of ISSA-LSTM model is as high as 99.85%.

show abstract

Section: Lstm Networkmentioning

confidence: 99%

Visual Monitoring Technology for Substation Vulnerable High-Voltage Electrical Equipment Based on ISSA-LSTM Deep Learning Model Coupling Video Overlay Algorithm

Wang

Ding

Tan

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

Development of the computer program for analysis structural integrity of marine engine elements

Mazur,

Velikanov,

Mazur

2023

jour

View full text Add to dashboard Cite

Timely implementation of maintenance processes provides confidence in maintaining performance and integrity throughout the life cycle of the system. Various developments in monitoring and analysis methods are aimed at maintaining the operability of systems by minimizing the failure rate. The developed computer program, presented in the paper, is used as one of the tools for assessing the technical condition of a ship power plant, allowing the use of an integrated approach to predicting and managing the quality of maintenance, including an assessment of the costs and timing of the implementation of repair work. When describing the creation of a computer program for assessing the structural integrity of ship engine elements, special attention is paid to the libraries used and the methods necessary for a comprehensive consideration of the “oil-engine” system. The Makava program, based on laboratory analyzes, allows you to determine the residual life of engine oil according to the actual state, by determining the parameters that mainly affect its aging, wherein setting threshold values for these parameters, forms the degree of deviation of actual values from the boundary values, predicting further wear of certain elements of the system. The program contains a database of typical changes in oil indicators regarding the occurrence of possible structural defects in the elements of the system, helps to expand the information resource by collecting, processing, accumulating and storing information on the degradation of the components of the propulsion complex of various engine models for subsequent planning of measures for the quality of maintenance and repair of shipboard power installations.

show abstract

Using LSTM Network for Solving the Multidimentional Time Series Forecasting Problem

Cited by 2 publications

References 1 publication

Visual Monitoring Technology for Substation Vulnerable High-Voltage Electrical Equipment Based on ISSA-LSTM Deep Learning Model Coupling Video Overlay Algorithm

Visual Monitoring Technology for Substation Vulnerable High-Voltage Electrical Equipment Based on ISSA-LSTM Deep Learning Model Coupling Video Overlay Algorithm

Development of the computer program for analysis structural integrity of marine engine elements

Contact Info

Product

Resources

About