Data-driven Predictive Analysis for Smart Manufacturing Processes Based on a Decomposition Approach

10.36227/techrxiv.15045426 ◽

2021 ◽

Author(s):

Mohammadhossein Ghahramani

Keyword(s):

Semiconductor Manufacturing ◽

Data Driven ◽

Smart Manufacturing ◽

Predictive Analysis ◽

Manufacturing Processes ◽

Decomposition Approach

<div>The dataset used in this work is obtained from a semiconductor factory, SECOM (Semiconductor Manufacturing) dataset and is publicly available online.</div>

Download Full-text

An Automated Approach to Enhance Multiscale Signal Monitoring of Manufacturing Processes

Journal of Manufacturing Science and Engineering ◽

10.1115/1.4031797 ◽

2015 ◽

Vol 138 (5) ◽

Cited By ~ 5

Author(s):

Marco Grasso ◽

Bianca Maria Colosimo

Keyword(s):

Kernel Estimation ◽

Optimal Number ◽

Signal Decomposition ◽

Data Driven ◽

Manufacturing Processes ◽

Density Functions ◽

Decomposition Approach ◽

Mode Decomposition ◽

Manufacturing Applications ◽

Original Information

Multiscale signal decomposition represents an important step to enhance process monitoring results in many manufacturing applications. Empirical mode decomposition (EMD) is a data driven technique that gained an increasing interest in this framework. However, it usually yields an-over decomposition of the signal, leading to the generation of spurious and meaningless modes and the possible mixing of embedded modes. This study proposes an enhanced signal decomposition approach that synthetizes the original information content into a minimal number of relevant modes via a data-driven and automated procedure. A criterion based on the kernel estimation of density functions is proposed to estimate the dissimilarities between the intrinsic modes generated by the EMD, together with a methodology to automatically determine the optimal number of final modes. The performances of the method are demonstrated by means of simulated signals and real industrial data from a waterjet cutting application.

Download Full-text

Business Models for Sustainable Innovation in Industry 4.0: Smart Manufacturing Processes, Digitalization of Production Systems, and Data-driven Decision Making

Journal of Self-Governance and Management Economics ◽

10.22381/jsme7320193 ◽

2019 ◽

Vol 7 (3) ◽

pp. 21 ◽

Cited By ~ 26

Keyword(s):

Decision Making ◽

Industry 4.0 ◽

Business Models ◽

Production Systems ◽

Data Driven ◽

Smart Manufacturing ◽

Manufacturing Processes ◽

Data Driven Decision Making ◽

Sustainable Innovation

Download Full-text

An Open Web-Based Repository for Capturing Manufacturing Process Information

Volume 4: 21st Design for Manufacturing and the Life Cycle Conference; 10th International Conference on Micro- and Nanosystems ◽

10.1115/detc2016-59265 ◽

2016 ◽

Cited By ~ 5

Author(s):

William Z. Bernstein ◽

Mahesh Mani ◽

Kevin W. Lyons ◽

K. C. Morris ◽

Björn Johansson

Keyword(s):

Manufacturing Process ◽

Recent Progress ◽

Performance Assessments ◽

Data Driven ◽

Smart Manufacturing ◽

Manufacturing Processes ◽

Process Information ◽

Web Based ◽

Model Consistency ◽

Effective Models

With recent progress in developing more effective models for representing manufacturing processes, this paper presents an approach towards an open web-based repository for storing manufacturing process information. The repository is envisioned to include several new use cases in the context of information use in smart manufacturing. This paper examines several key benefits through usage scenarios engaging existing engineering activities. Based on the scenarios, the desired characteristics of an open web-based repository are presented, namely that it will be (1) complementary to existing practices, (2) open and net-centric, (3) able to enforce model consistency, (4) modular (5) extensible, and (5) able to govern contributions. A repository will support and motivate the ubiquitous and extended use of standardized representations of unit manufacturing processes in order to promote consistency of performance assessments across industries and provide a tangible, data-driven perspective for analysis-related activities. Furthermore, the paper presents additional benefits and possible applications that could result from a shared manufacturing repository.

Download Full-text

Improved Ensemble-Learning Algorithm for Predictive Maintenance in the Manufacturing Process

Applied Sciences ◽

10.3390/app11156832 ◽

2021 ◽

Vol 11 (15) ◽

pp. 6832

Author(s):

Yu-Hsin Hung

Keyword(s):

Quality Management ◽

Ensemble Learning ◽

Manufacturing Process ◽

Semiconductor Manufacturing ◽

Data Communication ◽

Predictive Maintenance ◽

Learning Performance ◽

Smart Manufacturing ◽

Manufacturing Processes ◽

Total Quality

Industrial Internet of Things (IIoT) technologies comprise sensors, devices, networks, and applications from the edge to the cloud. Recent advances in data communication and application using IIoT have streamlined predictive maintenance (PdM) for equipment maintenance and quality management in manufacturing processes. PdM is useful in fields such as device, facility, and total quality management. PdM based on cloud or edge computing has revolutionized smart manufacturing processes. To address quality management problems, herein, we develop a new calculation method that improves ensemble-learning algorithms with adaptive learning to make a boosted decision tree more intelligent. The algorithm predicts main PdM issues, such as product failure or unqualified manufacturing equipment, in advance, thus improving the machine-learning performance. Herein, semiconductor and blister packing machine data are used separately in manufacturing data analytics. The former data help in predicting yield failure in a semiconductor manufacturing process. The blister packing machine data are used to predict the product packaging quality. Experimental results indicate that the proposed method is accurate, with an area under a receiver operating characteristic curve exceeding 96%. Thus, the proposed method provides a practical approach for PDM in semiconductor manufacturing processes and blister packing machines.

Download Full-text

AI-based modeling and data-driven evaluation for smart manufacturing processes

IEEE/CAA Journal of Automatica Sinica ◽

10.1109/jas.2020.1003114 ◽

2020 ◽

Vol 7 (4) ◽

pp. 1026-1037 ◽

Cited By ~ 6

Author(s):

Mohammadhossein Ghahramani ◽

Yan Qiao ◽

MengChu Zhou ◽

Adrian O Hagan ◽

James Sweeney

Keyword(s):

Data Driven ◽

Smart Manufacturing ◽

Manufacturing Processes

Download Full-text

Data-Driven Intelligent 3D Surface Measurement in Smart Manufacturing: Review and Outlook

Machines ◽

10.3390/machines9010013 ◽

2021 ◽

Vol 9 (1) ◽

pp. 13

Author(s):

Yuhang Yang ◽

Zhiqiao Dong ◽

Yuquan Meng ◽

Chenhui Shao

Keyword(s):

High Resolution ◽

High Performance ◽

Sampling Design ◽

Three Dimensional ◽

Measurement Data ◽

Data Driven ◽

Surface Measurement ◽

Smart Manufacturing ◽

Future Research ◽

3D Surface

High-fidelity characterization and effective monitoring of spatial and spatiotemporal processes are crucial for high-performance quality control of many manufacturing processes and systems in the era of smart manufacturing. Although the recent development in measurement technologies has made it possible to acquire high-resolution three-dimensional (3D) surface measurement data, it is generally expensive and time-consuming to use such technologies in real-world production settings. Data-driven approaches that stem from statistics and machine learning can potentially enable intelligent, cost-effective surface measurement and thus allow manufacturers to use high-resolution surface data for better decision-making without introducing substantial production cost induced by data acquisition. Among these methods, spatial and spatiotemporal interpolation techniques can draw inferences about unmeasured locations on a surface using the measurement of other locations, thus decreasing the measurement cost and time. However, interpolation methods are very sensitive to the availability of measurement data, and their performances largely depend on the measurement scheme or the sampling design, i.e., how to allocate measurement efforts. As such, sampling design is considered to be another important field that enables intelligent surface measurement. This paper reviews and summarizes the state-of-the-art research in interpolation and sampling design for surface measurement in varied manufacturing applications. Research gaps and future research directions are also identified and can serve as a fundamental guideline to industrial practitioners and researchers for future studies in these areas.

Download Full-text

Sustainable, Smart, and Sensing Technologies for Cyber-Physical Manufacturing Systems: A Systematic Literature Review

Sustainability ◽

10.3390/su13105495 ◽

2021 ◽

Vol 13 (10) ◽

pp. 5495

Author(s):

Mihai Andronie ◽

George Lăzăroiu ◽

Roxana Ștefănescu ◽

Cristian Uță ◽

Irina Dijmărescu

Keyword(s):

Decision Making ◽

Internet Of Things ◽

Literature Review ◽

Manufacturing Systems ◽

Manufacturing System ◽

Data Driven ◽

Smart Manufacturing ◽

Production Networks ◽

Production Logistics ◽

Time Production

With growing evidence of the operational performance of cyber-physical manufacturing systems, there is a pivotal need for comprehending sustainable, smart, and sensing technologies underpinning data-driven decision-making processes. In this research, previous findings were cumulated showing that cyber-physical production networks operate automatically and smoothly with artificial intelligence-based decision-making algorithms in a sustainable manner and contribute to the literature by indicating that sustainable Internet of Things-based manufacturing systems function in an automated, robust, and flexible manner. Throughout October 2020 and April 2021, a quantitative literature review of the Web of Science, Scopus, and ProQuest databases was performed, with search terms including “Internet of Things-based real-time production logistics”, “sustainable smart manufacturing”, “cyber-physical production system”, “industrial big data”, “sustainable organizational performance”, “cyber-physical smart manufacturing system”, and “sustainable Internet of Things-based manufacturing system”. As research published between 2018 and 2021 was inspected, and only 426 articles satisfied the eligibility criteria. By taking out controversial or ambiguous findings (insufficient/irrelevant data), outcomes unsubstantiated by replication, too general material, or studies with nearly identical titles, we selected 174 mainly empirical sources. Further developments should entail how cyber-physical production networks and Internet of Things-based real-time production logistics, by use of cognitive decision-making algorithms, enable the advancement of data-driven sustainable smart manufacturing.

Download Full-text