Design of experiments and machine learning to improve robustness of predictive maintenance with application to a real case study

被引：14

作者：

Salmaso, Luigi ^{[1
]}

Pegoraro, Luca ^{[1
]}

Giancristofaro, Rosa Arboretti ^{[3
]}

Ceccato, Riccardo ^{[1
]}

Bianchi, Alberto ^{[2
]}

Restello, Silvio ^{[2
]}

Scarabottolo, Davide ^{[2
]}

机构：

[1] Univ Padua, Dipartimento Tecn & Gest Sistemi Ind, Padua, Italy

[2] Univ Padua, Dipartimento Ingn Civile Edile & Ambientale, Padua, Italy

[3] Carel Ind SpA, Padua, Italy

来源：

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION | 2022年 / 51卷 / 02期

关键词：

Design of Experiments (DOE); Big Data; Machine learning; Predictive maintenance;

D O I：

10.1080/03610918.2019.1656740

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

When deploying predictive analytics in a Big Data context, some concerns may arise regarding the validity of the results obtained. The reason for this is linked to flaws which are intrinsic to the nature of the Big Data Analytics methods themselves. In this article a new approach is proposed with the aim of mitigating new problems which arise. This novel method consists of a two-step workflow in which a Design of Experiments (DOE) study is conducted prior to the usual Big Data Analytics and machine learning modeling phase. The advantages of the new approach are presented and an industrial application of the method in predictive maintenance is described in detail.

引用

页码：570 / 582

页数：13

共 14 条

[1] Guidelines for the responsible application of data analytics [J].

Clarke, Roger .

COMPUTER LAW & SECURITY REVIEW, 2018, 34 (03) :467-476

[2]

Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274

[3] Principles of Experimental Design for Big Data Analysis [J].

Drovandi, Christopher C. ;

Holmes, Christopher C. ;

McGree, James M. ;

Mengersen, Kerrie ;

Richardson, Sylvia ;

Ryan, Elizabeth G. .

STATISTICAL SCIENCE, 2017, 32 (03) :385-404

[4] Statistics in the big data era: Failures of the machine [J].

Dunson, David B. .

STATISTICS & PROBABILITY LETTERS, 2018, 136 :4-9

[5] When small data beats big data [J].

Faraway, Julian J. ;

Augustin, Nicole H. .

STATISTICS & PROBABILITY LETTERS, 2018, 136 :142-145

[6] APPROXIMATION CAPABILITIES OF MULTILAYER FEEDFORWARD NETWORKS [J].

HORNIK, K .

NEURAL NETWORKS, 1991, 4 (02) :251-257

[7] Design of experiments and response surface methodology to tune machine learning hyperparameters, with a random forest case-study [J].

Lujan-Moreno, Gustavo A. ;

Howard, Phillip R. ;

Rojas, Omar G. ;

Montgomery, Douglas C. .

EXPERT SYSTEMS WITH APPLICATIONS, 2018, 109 :195-205

[8] Big Data and the danger of being precisely inaccurate [J].

McFarland, Daniel A. ;

McFarland, H. Richard .

BIG DATA & SOCIETY, 2015, 2 (02)

[9]

Oshiro ThaisMayumi., 2012, Lecture Notes in Computer Science

[10]

RIEDMILLER M, 1993, 1993 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, P586, DOI 10.1109/ICNN.1993.298623

← 1 2 →