Energy-efficient control of pump units based on neural-network parameter observer

被引：0
|
作者：
Burian S.O. [1 ]
Kiselychnyk O.I. [2 ]
Pushkar M.V. [1 ]
Reshetnik V.S. [1 ]
Zemlianukhina H.Y. [1 ]
机构：
[1] National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute, pr. Peremohy, 37, Kyiv
[2] School of Engineering, University of Warwick, Coventry
来源：
Technical Electrodynamics | 2020年 / 2020卷 / 01期
关键词：
Neural network; Observer; Parameter; Pumping unit; Turbomechanism;
D O I：
10.15407/techned2020.01.071
中图分类号：
学科分类号：
摘要：
An observer based on an artificial neural network was designed. The observer determines the pumping unit performance depending on the operating point. Determination is based on the measured technological coordinates of the system and the pressure of the turbomechanism. Three neural networks were designed for three types of the productivity observer. The developed observer was investigated by the simulation method within different variations of disturbing actions, such as hydraulic resistance of the hydraulic system and geodetic pressure. A comparative analysis of three types of the productivity observer, built with using the pressure and different signals of the system with arbitrary change of hydraulic resistance was given. By the use of the pump unit efficiency observer, in addition to the results presented earlier, the efficiency of the productivity observer, which built with using different sensors, in water supply systems with two series-connected pump units, operating for filling the large tank, is researched. In the water supply system one pump speed is regulated, the other is unregulated. References 14, figures 5. © Institute of Electrodynamics, National Academy of Sciences of Ukraine.
引用
收藏
页码：71 / 77
页数：6
相关论文
共 50 条
  • [31] ACCURATE, ENERGY-EFFICIENT CLASSIFICATION WITH SPIKING RANDOM NEURAL NETWORK
    Hussain, Khaled F.
    Bassyouni, Mohamed Yousef
    Gelenbe, Erol
    PROBABILITY IN THE ENGINEERING AND INFORMATIONAL SCIENCES, 2021, 35 (01) : 51 - 61
  • [32] An Energy-Efficient Inference Engine for a Configurable ReRAM-Based Neural Network Accelerator
    Zheng, Yang-Lin
    Yang, Wei-Yi
    Chen, Ya-Shu
    Han, Ding-Hung
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2023, 42 (03) : 740 - 753
  • [33] Optimization of DRAM based PIM Architecture for Energy-Efficient Deep Neural Network Training
    Sudarshan, Chirag
    Sadi, Mohammad Hassani
    Weis, Christian
    Wehn, Norbert
    2022 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 22), 2022, : 1472 - 1476
  • [34] Energy-Efficient Neural Network Inference with Microcavity Exciton Polaritons
    Matuszewski, M.
    Opala, A.
    Mirek, R.
    Furman, M.
    Krol, M.
    Tyszka, K.
    Liew, T. C. H.
    Ballarini, D.
    Sanvitto, D.
    Szczytko, J.
    Pietka, B.
    PHYSICAL REVIEW APPLIED, 2021, 16 (02)
  • [35] An Energy-Efficient Graphene-based Spiking Neural Network Architecture for Pattern Recognition
    Laurenciu, Nicoleta Cucu
    Timmermans, Charles
    Cotofana, Sorin D.
    2024 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS 2024, 2024,
  • [36] ENERGY-EFFICIENT PUMP DESIGN AND APPLICATION
    HALLOCK, DC
    DAY, MW
    TAPPI, 1982, 65 (01): : 39 - 41
  • [37] An energy-efficient convolutional neural network accelerator for speech classification based on FPGA and quantization
    Wen, Dong
    Jiang, Jingfei
    Dou, Yong
    Xu, Jinwei
    Xiao, Tao
    CCF TRANSACTIONS ON HIGH PERFORMANCE COMPUTING, 2021, 3 (01) : 4 - 16
  • [38] Energy-Efficient Makeup Air Units
    Crowther, Hugh
    ASHRAE JOURNAL, 2015, 57 (03) : 26 - 32
  • [39] A NEURAL-NETWORK BASED TOOL
    SHEWHART, M
    IEEE SPECTRUM, 1992, 29 (02) : 6 - 6
  • [40] Energy-Efficient Recurrent Neural Network With MRAM-Based Probabilistic Activation Functions
    Sheikhfaal, Shadi
    Angizi, Shaahin
    DeMara, Ronald F. F.
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING, 2023, 11 (02) : 534 - 540
12345