Novel Hybrid Physics‑Informed Deep Neural Network for Dynamic Load Prediction of Electric Cable Shovel

作     者：Tao Fu Tianci Zhang Yunhao Cui Xueguan Song Tao Fu;Tianci Zhang;Yunhao Cui;Xueguan Song

作者机构：School of Mechanical EngineeringDalian University of TechnologyDalian 116024China 

出 版 物：《Chinese Journal of Mechanical Engineering》 (中国机械工程学报（英文版）)

年 卷 期：2022年第35卷第6期

页      面：151-164页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081901[工学-采矿工程] 0819[工学-矿业工程] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China(Grant No.52075068) Shanxi Provincial Science and Technology Major Project(Grant No.20191101014) 

主　　题：Hybrid physics-informed deep learning Dynamic load prediction Electric cable shovel(ECS) Long shortterm memory(LSTM) 

摘      要：Electric cable shovel(ECS)is a complex production equipment,which is widely utilized in open-pit *** valuations of load is the foundation for the development of intelligent or unmanned ECS,since it directly influences the planning of digging trajectories and energy *** prediction of ECS mainly consists of two types of methods:physics-based modeling and data-driven *** former approach is based on known physical laws,usually,it is necessarily approximations of reality due to incomplete knowledge of certain processes,which introduces *** latter captures features/patterns from data in an end-to-end manner without dwelling on domain expertise but requires a large amount of accurately labeled data to achieve generalization,which introduces *** addition,some parts of load are non-observable and latent,which cannot be measured from actual system sensing,so they can’t be predicted by data-driven ***,an innovative hybrid physics-informed deep neural network(HPINN)architecture,which combines physics-based models and data-driven methods to predict dynamic load of ECS,is *** the proposed framework,some parts of the theoretical model are incorporated,while capturing the difficult-to-model part by training a highly expressive approximator with *** physics knowledge,such as Lagrangian mechanics and the conservation of energy,is considered extra constraints,and embedded in the overall loss function to enforce model training in a feasible solution *** satisfactory performance of the proposed framework is verified through both synthetic and actual measurement dataset.