A Review of Data Mining with Big Data towards Its Applications in the Electronics Industry

Abstract

Data mining (DM) with Big Data has been widely used in the lifecycle of electronic products that range from the design and production stages to the service stage. A comprehensive analysis of DM with Big Data and a review of its application in the stages of its lifecycle will not only benefit researchers to develop strong research themes and identify gaps in the field but also help practitioners for DM application system development. In this paper, a brief clarification of DM-related topics is presented first. A flowchart of DM and the main content of the flowchart steps are given in which commonly used data preparation and preprocessing approaches, DM functions and techniques, and performances indicators are summarized. Then, a comprehensive review covering 105 articles from 2007 to 2017 on DM or Big Data applications in the electronics industry is provided according to the flowchart from various points of view such as data handling, applications of DM, or Big Data at different lifecycle stages, and the software used in the applications. On this basis, a diagram of data content for different knowledge areas and a framework for DM and Big Data applications in the electronics industry are established. Finally, conclusions and future research directions are given.

Data-Driven Prediction Model of Components Shift during Reflow Process in Surface Mount Technology

“…Despite numerous studies investigating the theoretical fundamentals of components movements during reflow [1][2][3][4][5][6][7][8], there is no apparent justification to address practical challenges of the self-alignment in the real situation. On one side, there is no specific rule listed in the literature that recommends which control variables have a significant contribution in components movement in , -directions as well as rotation.…”

“…With respect to the privilege of data-driven techniques in compare with the conventional statistical methods [4] , there is a few data-driven model for predicting components movement as well as components position after reflow process. For instance, Lv et al presented a comprehensive review of the application of data mining techniques in electronic industries [5]. According to their investigation, a few studies address the applied data mining technique in the printing process as well as the reflow process, but none of them studied components self-alignment from big data standpoints [5].…”

“…For instance, Lv et al presented a comprehensive review of the application of data mining techniques in electronic industries [5]. According to their investigation, a few studies address the applied data mining technique in the printing process as well as the reflow process, but none of them studied components self-alignment from big data standpoints [5]. Moreover, a study has been conducted by Marktinek et al concurrently, which used a neural network model to predict components movement [6].…”

Optimization of Passive Chip Components Placement with Self-Alignment Effect for Advanced Surface Mounting Technology

“…However, numerous studies have investigated chip component self-alignment capability from theoretical [1], simulation and numerical [1,3] models' standpoints, there is no generalized data-driven model in literature to address practical challenges of self-alignment [4]. Lv et al provided a comprehensive survey on machine learning application in SMT [4].…”

“…However, numerous studies have investigated chip component self-alignment capability from theoretical [1], simulation and numerical [1,3] models' standpoints, there is no generalized data-driven model in literature to address practical challenges of self-alignment [4]. Lv et al provided a comprehensive survey on machine learning application in SMT [4]. Based on this survey, there is no research to employ applied machine learning method in self-alignment [4] while applied machine learning methods privilege over conventional statistical methods in SMT [5].…”