e-journal

Adaptive Sensor Allocation Strategy for Process Monitoring and Diagnosis in a Bayesian Network

---

Multivariate process control in Distributed Sensor Networks (DSNs) is an important and challenging topic. Although a fully deployed sensor network will minimize information loss, the associated sensing cost can be overwhelming. Many efforts have been made to investigate the optimal sensor allocation
strategy for different process control applications; however, most of them assume that the sensor layout is fixed once sensors are deployed in the system. This paper proposes a novel approach to adaptively reallocate sensor resources based on online observations, which can enhance both monitoring and diagnosis capabilities. The proposed adaptive sensor allocation strategy addresses two fundamental issues: when to reallocate sensors and how to update sensor layout. A max–min criterion is developed
to manage sensor reallocation and process change detection in an integrated manner. To investigate the adaptive strategy, a Bayesian Network (BN) model is assumed available to represent the causal relationships among a set of variables. Case studies are performed on a hot forming process and a cap alignment process to illustrate the procedure and evaluate the performance of the proposed method under different fault scenarios.
Note to Practitioners—Due to the rapid development of sensor technology, DSN has been widely used to monitor process change in complex manufacturing systems. Unlike most of the previous studies on the optimal design of a sensor system, which assume that sensor layout is fixed once sensors are deployed in the DSN, this paper proposes a novel adaptive strategy to update the sensor layout or determine the operating mode (i.e., active/sleep state) of each sensor during online measurements. Two fundamental questions have been addressed in this study: (i) when to reallocate sensors and (ii) how to update sensor layout. The proposed methodology is especially beneficial for monitoring the process change in
a system where variable relationships can be modeled with a BN and a single mean shift may occur at any variable. To implement this methodology, it is necessary: (i) to identify the physical variables
associated with the production system; (ii) to describe the variable relationships via a BN; and (iii) to determine the number of available sensors with the consideration of budget, bandwidth, or energy constraint. Experimental studies have shown that the proposed adaptive strategy has better performance than the fixed strategy in terms of improving detection delay and fault diagnosis accuracy.
Index Terms—Adaptive sensor allocation strategy, Bayesian network (BN), max–min criterion, process monitoring and diagnosis.

---

Ketersediaan

Tidak ada salinan data

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING

No. Panggil

-

Penerbit

New York : IEEE., 2014

Deskripsi Fisik

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, VOL. 11, NO. 2, APRIL 2014

Bahasa

English

ISBN/ISSN

1545-5955

Klasifikasi

-

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

VOL. 11, NO. 2, APRIL 2014

Subjek

TEKNIK

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Yuli/Agus

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar