NILM Dashboard: Actionable Feedback for Condition-Based Maintenance

被引：8

作者：

Green, Daisy ^{[1
]}

Kane, Thomas ^{[2
,3
,4
,5
]}

Kidwell, Stephen ^{[2
,6
,7
]}

Lindahl, Peter ^{[8
,9
]}

Donnal, John ^{[10
]}

Leeb, Steven ^{[11
,12
]}

机构：

[1] MIT, Elect Engn, Res Lab Elect, Cambridge, MA 02139 USA

[2] US Coast Guard, Washington, DC USA

[3] USCGC CAMPBELL, Washington, DC USA

[4] USCGC MELLON, Seattle, WA USA

[5] Natl Secur Cutter NSC fleet, Washington, DC USA

[6] MIT, Naval Architecture & Marine Engn, Cambridge, MA 02139 USA

[7] USCGC HAMILTON WMSL 753, N Charleston, SC USA

[8] Exponent, Watertown, MA USA

[9] MIT, Cambridge, MA 02139 USA

[10] US Naval Acad, Weap & Syst Engn, Annapolis, MD 21402 USA

[11] Massachusetts Inst Technol MIT Fac, Dept Elect Engn & Comp Sci, Cambridge, MA USA

[12] MIT, Dept Mech Engn, Cambridge, MA 02139 USA

来源：

IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE | 2020年 / 23卷 / 05期

关键词：

Water heating; Monitoring; Maintenance engineering; Degradation; Reactive power; Heat pumps; FAULT-DETECTION; SIGNAL;

D O I：

10.1109/mim.2020.9153467

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Modern power monitoring systems record vast amounts of equipment operational data. For these systems to improve efficiency and performance, the data must be presented as an intuitive decision aid for watchstanders. The Nonintrusive Load Monitor (NILM) dashboard provides actionable information for energy score-keeping, activity tracking, and equipment condition-based maintenance (CBM). Using a NILM to present metrics that track changes in equipment signature and equipment behavior allows for effective CBM. Electrical monitoring through the NILM dashboard can identify both "soft" faults (the gradual degradation of equipment performance) and "hard" faults (the complete failure of a piece of equipment). This paper presents metrics and visualizations that have proven useful for CBM. Analysis from case studies of fault conditions identified aboard two United States Coast Guard cutters (USCGCs), SPENCER and ESCANABA, are discussed.

引用

页码：3 / 10

页数：8

共 17 条

[1] NILM Dashboard: A Power System Monitor for Electromechanical Equipment Diagnostics [J].

Aboulian, Andre ;

Green, Daisy H. ;

Switzer, Jennifer F. ;

Kane, Thomas J. ;

Bredariol, Gregory V. ;

Lindahl, Peter ;

Donnal, John S. ;

Leeb, Steven B. .

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2019, 15 (03) :1405-1414

[2]

Beebe R., 2008, PUMP MAGAZINE, V58, P20

[3] Prediction of Machine Health Condition Using Neuro-Fuzzy and Bayesian Algorithms [J].

Chen, Chaochao ;

Zhang, Bin ;

Vachtsevanos, George .

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2012, 61 (02) :297-306

[4] From Model, Signal to Knowledge: A Data-Driven Perspective of Fault Detection and Diagnosis [J].

Dai, Xuewu ;

Gao, Zhiwei .

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2013, 9 (04) :2226-2238

[5] Challenges in the industrial applications of fault diagnostic systems [J].

Dash, S ;

Venkatasubramanian, V .

COMPUTERS & CHEMICAL ENGINEERING, 2000, 24 (2-7) :785-791

[6]

de Smith M. J., 2018, STAT ANAL HDB

[7] Electrical Signal Source Separation Via Nonnegative Tensor Factorization Using On Site Measurements in a Smart Home [J].

Figueiredo, Marisa ;

Ribeiro, Bernardete ;

de Almeida, Ana .

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2014, 63 (02) :364-373

[8]

Green D., 2019, IEEE AUTOTESTCON, P1

[9]

Green D., 2019, IEEE T IND INFORM

[10] State-of-the-Art Predictive Maintenance Techniques [J].

Hashemian, H. M. ;

Bean, Wendell C. .

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2011, 60 (10) :3480-3492

← 1 2 →