A novel hybrid LSTM and masked multi-head attention based network for energy consumption prediction of industrial robots

作     者：Wang, Zuoxue Jiang, Pei Li, Xiaobin He, Yan Wang, Xi Vincent Yang, Xue 

作者机构：Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China KTH Royal Inst Technol Dept Prod Engn SE-10044 Stockholm Sweden Chongqing Polytech Univ Elect Technol Coll Finance & Management Chongqing 401331 Peoples R China 

出 版 物：《APPLIED ENERGY》 (Appl. Energy)

年 卷 期：2025年第383卷

核心收录：

学科分类：0820[工学-石油与天然气工程] 0817[工学-化学工程与技术] 08[工学] 0807[工学-动力工程及工程热物理] 

基　　金：National Key R&D Program of China [2023YFB3308001] National Science Foundation of China [52475511, 52075060] Chongqing Technology Innovation and Application Development Special Key Project [CSTC2021JSCX-GKSBX0046] Natural Science Foundation of Chongqing, China [CSTB2022NSCQ-MSX1283] Scientific and Technological Research Program of Chongqing Municipal Education Commission, China [KJQN202303126] Fundamental Research Funds for the Central Universities [2024CDJZCQ-004, 2023CDJKYJH-101] 

主　　题：Industrial robots Energy consumption prediction Temporal causal relationship Data-driven modeling Transfer learning 

摘      要：Due to the wide application of industrial robots (IRs) in the manufacturing industry and their significant energy consumption (EC), predicting EC under different trajectories and working conditions has attracted increasing attention. Data-driven modeling methods have proven to be a viable approach for revealing the quantitative relationship between IR operating parameters and EC. However, in manufacturing systems, the coexistence of numerous heterogeneous IRs necessitates a substantial amount of data with power labels and sufficient hardware computing resources to model the operational EC of each robot type. Motivated by these requirements, this paper proposes a transfer learning based method for modeling the operational EC of IRs. Based on an analysis of the temporal causal relationship between model input variables and operational EC, a time series information feature extraction method and an industrial robot operational energy consumption prediction network (ROEPN) are proposed, which combines layer normalization (LN), long short-term memory neural network (LSTM) and masked multi-head attention mechanism (MHA). Moreover, a rigorous pre-training- fine-tuning transfer learning scheme is designed and implemented on the target domain data, effectively achieving the transfer of ROEPN from the source domain to the target domain. Experiments were conducted on the HSR-JR612 and HSR-JR603, and the results demonstrate that the proposed EC model transfer method can predict EC for different IRs, trajectories and loads, with the mean absolute percentage error (MAPE) being less than 2.69% in the case of small samples.