Unmanned Plant Control and Optimisation by Real-time Deep Neural Networks for Power Saving
Authors: 
Yaqing Luo, Jin Zhang, Gaoyong LuoAuthors Info & Claims
Article No.: 28, Pages 1 - 6
Abstract
Compressed air is essential to a wide range of industries and highly specialised applications where it is a particularly critical resource, such as medical gas systems. However, current control system of unmanned medical compressed air plant mostly using fixed speed compressors is operated inefficiently and without optimisation in terms of power saving. This paper investigates the complexity of unmanned plant control and proposes performance optimisation by an intelligent compressed air system with the integration of advanced communication technology and artificial intelligence (AI), where a new energy-efficient and reliable operation of unmanned plant is developed and implemented by applying intelligent control to provide optimum performance. A deep neural network (DNN) using multilayer perceptron (MLP) model is thus derived and used to train and identify network coefficients for minimizing energy consumption. Experimental results demonstrate that the intelligent control and optimisation by real-time deep neural network can achieve maximum power efficiency leading to a satisfactory solution to unmanned plant.
References
[1]
G. F. Li, J. Y. Kong, G.Z. Jiang, and L. X. Xie (2012). Research of intelligent control of air compressor at constant pressure. Journal of Computers, 7(5), 1147--1154.
[2]
A.T. Rice, P.Y. Li, and C. J. Sanckens (2017). Optimal efficiency-power tradeoff for an air compressor/expander. Journal of Dynamic Systems, Measurement, and Control, 140 (2), 021011.
[3]
F. Doyle, and J. Cosgrove (2017). An approach to optimizing compressed air systems in production operations. International Journal of Ambient Energy, 39(2), 1--32.
[4]
T.Nehler, R. Parra, and P.Thollander (2018). Implementation of energy efficiency measures in compressed air systems: barriers, drivers and non-energy benefits. Energy Efficiency, 11(5), 1281--1302.
[5]
D. Rivera, L. Cruz-Piris, G. Lopez-Civera, E. Hoz, and I. Marsa-Maestre (2015). Applying an unified access control for IoT-based intelligent agent systems. 2015 IEEE 8th International Conference on Service-Oriented Computing and Applications, 247--251.
[6]
I. Chih-Lin, Q. Sun, Z. Liu, S. Zhang, and S. Han (2017). The big-data-driven intelligent wireless network. IEEE Vehicular Technology Magazine, 12(4), 20--29.
[7]
S. Zhong, Z. Peng, and W. Hong (2010). Analysis and design of real-time and reliable industrial wireless control communication network and protocol. Proceedings of the 29th Chinese Control Conference, July 29-31, 4157--4163.
[8]
A. L. Caterini (2017). A Novel Mathematical Framework for the Analysis of Neural Networks, Msc Thesisof Mathematics, University of Waterloo, Waterloo, Ontario, Canada.
[9]
T. Wiatowski, and H. Bolcskei (2018).A mathematical theory of deep convolutionalneural networks for feature extraction.IEEE Transactions on Information Theory, 64(3), 1845--1866.
[10]
S. Ergezinger, and E. Thomsen (1995). An accelerated learning algorithm for multilayer perceptrons: optimization layer by layer.IEEE Transactions on Neural Networks, 6(1), 31--42.
Index Terms
- Unmanned Plant Control and Optimisation by Real-time Deep Neural Networks for Power Saving
Recommendations
Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions
AbstractWe propose a new type of neural networks, Kronecker neural networks (KNNs), that form a general framework for neural networks with adaptive activation functions. KNNs employ the Kronecker product, which provides an efficient way of ...
Symmetric Power Activation Functions for Deep Neural Networks
LOPAL '18: Proceedings of the International Conference on Learning and Optimization Algorithms: Theory and ApplicationsCommon nonlinear activation functions with large saturation regions, like Sigmoid and Tanh, used for Deep Neural Networks (DNNs) can not guarantee useful and efficient training since they suffer from vanishing gradients problem. Rectified Linear Units ...
Deep Elman recurrent neural networks for statistical parametric speech synthesis
Owing to the success of deep learning techniques in automatic speech recognition, deep neural networks (DNNs) have been used as acoustic models for statistical parametric speech synthesis (SPSS). DNNs do not inherently model the temporal structure in ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2019
418 pages
ISBN:9781450372022
DOI:10.1145/3358331
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 17 October 2019
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
AIAM 2019
AIAM 2019: 2019 International Conference on Artificial Intelligence and Advanced Manufacturing
October 17 - 19, 2019
Dublin, Ireland
Acceptance Rates
Overall Acceptance Rate 100 of 285 submissions, 35%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 85Total Downloads
- Downloads (Last 12 months)3
- Downloads (Last 6 weeks)0
Reflects downloads up to 23 Sep 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in