Soft sensor validation for monitoring and resilient control of sequential subway indoor air quality through memory-gated recurrent neural networks-based autoencoders

被引：61

作者：

Loy-Benitez, Jorge ^{[1
]}

Heo, SungKu ^{[1
]}

Yoo, ChangKyoo ^{[1
]}

机构：

[1] Kyung Hee Univ, Coll Engn, Dept Environm Sci Engn, Yongin 446701, South Korea

来源：

CONTROL ENGINEERING PRACTICE | 2020年 / 97卷

基金：

新加坡国家研究基金会;

关键词：

Autoencoders; Faulty sensor; Soft sensor validation; Machine learning; Memory-gated recurrent neural networks; Subway indoor air quality; HEALTH-RISK ASSESSMENT; K-NEAREST NEIGHBOR; VARIATIONAL AUTOENCODER; VENTILATION CONTROL; FAULT-DIAGNOSIS; CONTROL-SYSTEM; PREDICTION; RECONSTRUCTION; MODEL; ENVIRONMENT;

D O I：

10.1016/j.conengprac.2020.104330

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Indoor air quality (IAQ) measurements play an important role in the subway ventilation system control, influencing over crucial factors as ventilation energy consumption and commuters' health. Therefore, faulty sensors may result in misinterpreting the IAQ conditions and misoperating the air delivery rate level in subway stations. However, due to the IAQ data properties of dynamism and non-Gaussian distribution. Linear and fixed structures are not sufficient to extract essential features from the IAQ data. This paper presents a machine learning-based soft sensor validation technique to detect, diagnose, identify, and reconstruct faulty measurements of the multivariate IAQ data in subway stations. The proposed method is memory-gated recurrent neural networks-based autoencoders (MG-RNN-AE), which are capable of processing sequential and dynamic IAQ information. The performance of the sensor validation was evaluated through several metrics to consequently be compared among different methods, being the batch normalization-based gated recurrent unit (BN-GRU) method, the most effective to detect (DRSPE = 100%) and reconstruct faulty IAQ sensors (R-2 = 0.45-0.79). Additionally, the effects of the faulty and repaired measurements in the ventilation system were evaluated to determine that the proposed method is capable of finding a sustainable balance between energy demand and commuters' health level.

引用

页数：17

共 70 条

[11] Industry 4.0 technologies: Implementation patterns in manufacturing companies [J].

Frank, Alejandro German ;

Dalenogare, Lucas Santos ;

Ayala, Nestor Fabian .

INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS, 2019, 210 :15-26

[12] APPROXIMATION OF DYNAMICAL-SYSTEMS BY CONTINUOUS-TIME RECURRENT NEURAL NETWORKS [J].

FUNAHASHI, K ;

NAKAMURA, Y .

NEURAL NETWORKS, 1993, 6 (06) :801-806

[13]

Graves A, 2012, STUD COMPUT INTELL, V385, P1, DOI [10.1007/978-3-642-24797-2, 10.1162/neco.1997.9.1.1]

[14] Indoor environment and passengers' comfort in subway stations in Seoul [J].

Han, Jieun ;

Kwon, Soon-bark ;

Chun, Chungyoon .

BUILDING AND ENVIRONMENT, 2016, 104 :221-231

[15]

Heloulou N, 2014, COMM COM INF SC, V442, P427

[16] A deep reinforcement learning-based autonomous ventilation control system for smart indoor air quality management in a subway station [J].

Heo, SungKu ;

Nam, KiJeon ;

Loy-Benitez, Jorge ;

Li, Qian ;

Lee, SeungChul ;

Yoo, ChangKyoo .

ENERGY AND BUILDINGS, 2019, 202

[17] Reducing the dimensionality of data with neural networks [J].

Hinton, G. E. ;

Salakhutdinov, R. R. .

SCIENCE, 2006, 313 (5786) :504-507

[18] Relevant and independent multi-block approach for plant-wide process and quality-related monitoring based on KPCA and SVDD [J].

Huang, Junping ;

Yan, Xuefeng .

ISA TRANSACTIONS, 2018, 73 :257-267

[19] Hydrogen-based self-sustaining integrated renewable electricity network (HySIREN) using a supply-demand forecasting model and deep-learning algorithms [J].

Hwangbo, Soonho ;

Nam, KiJeon ;

Heo, SungKu ;

Yoo, ChangKyoo .

ENERGY CONVERSION AND MANAGEMENT, 2019, 185 :353-367

[20]

Ioffe Sergey, 2015, P MACHINE LEARNING R, V37, P448, DOI DOI 10.48550/ARXIV.1502.03167

← 1 2 3 4 5 6 7 →