Method and system for predicting service life of tower grounding device based on improved PPO algorithm

The invention discloses a tower grounding device life prediction method and system based on an improved PPO algorithm, and the method comprises the steps: firstly collecting the life cycle historical data of a transmission tower grounding device, constructing a data set, setting a label, constructin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HE LANFEI, ZHOU YINGBO, ZHOU LUO, ZHANG DONGYIN, FANG ZHAO, WANG CHEN, GE YANQIN, JIANG YINGHAN, HU TING, WANG YAJIE, LIAO XIAOHONG, SUN LIPING, MA LI, ZHANG HONG, XIONG YI, LI ZHIWEI, CHEN RAN, XIONG CHUANYU, ZHANG ZHAOYANG, GAO XIAOJING, WANG WEI, QUAN JIANGTAO, WEI CONG, SHU SIRUI, ZHANG TONGYAN, KONG JUAN, ZHAO SHUANG, KE FANGCHAO, XU HANPING, CAI JIE
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a tower grounding device life prediction method and system based on an improved PPO algorithm, and the method comprises the steps: firstly collecting the life cycle historical data of a transmission tower grounding device, constructing a data set, setting a label, constructing a reinforcement learning network model, and improving the reinforcement learning network model, then based on Alpha divergence, expanding the Alpha divergence to multiple continuous action forms to serve as a loss function, then dividing a data set into a training set and a test set, performing training optimization on each agent based on the training set, and finally completing life prediction of the grounding device through the test set; the influence of various soil environment factors on the grounding device is fully considered, the corrosion degree of the grounding device is objectively and accurately evaluated and judged based on the deep reinforcement learning technology and real-time data analysis, automa