e-journal

Data-Driven Soft-Sensor Modeling for Product Quality Estimation Using Case-Based Reasoning and Fuzzy-Similarity Rough Sets

---

Efficient operation of the integrated optimization or automation system in an industrial plant depends mainly on good measurement of product quality. However, measuring or estimating the product quality online in many industrial plants is usually not feasible using the available techniques. In this paper,
a data-driven soft-sensor using case-based reasoning (CBR) and fuzzy-similarity rough sets is proposed for product quality estimation. Owning to the sustained learning ability, the modeling of a CBR soft-sensor does not need any additional model correction which is otherwise required by the neural network based methods to overcome the slow time-varying nature of industrial processes.
Because the conventional -nearest neighbor ( -NN) algorithm is strongly influenced by the value of , an improved -NN algorithm with dynamic adjustment of case similarity threshold is proposed to retrieve sufficientmatching cases formaking a correct estimation. Moreover, considering that the estimation accuracy of the CBR soft-sensor system is closely related to the weights of case feature, a feature weighting algorithm using fuzzy-similarity rough sets is proposed in this paper. This feature weighting
method does not require any transcendental knowledge, and its computation complexity is only linear with respect to the number of cases and attributes. The developed soft-sensor system has been successfully applied in a large grinding plant in China. And the application results show that the system has achieved satisfactory estimation accuracy and adaptation ability.
Note to Practitioners—In the process industry, the product quality reflects the operational and economic performance of a manufacturing process. However, online measurement and control of product quality is generally difficult. In this paper, a data-driven soft-sensor is proposed to online estimate the product quality for a typical grinding process with time-varying dynamics. The method combines an improved CBR soft-sensor algorithm and a feature weighting algorithm using fuzzy-similarity rough
sets. First, the weighs of case features in CBR are determined using the fuzzy-similarity rough sets in offline mode, and then they are used in CBR to accurately estimate the PPS online. The CBR soft-sensor system has been applied in a large industrial grinding plant. The application results show that the soft-sensor system has achieved satisfied estimation precision, good adaptability and robustness, and can be easily realized in practice with low cost and maintenance.
Index Terms—Case feature weighting, case-based reasoning (CBR), data-driven, fuzzy-similarity rough sets (FSRS), product quality estimation, soft-sensor modeling.

---

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. 4, OCTOBER 2014

Bahasa

English

ISBN/ISSN

1545-5955

Klasifikasi

-

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

VOL. 11, NO. 4, OCTOBER 2014

Subjek

TEKNIK

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Yuli/Agus

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar