[Paper Review] Industrial Big Data Analytics: Challenges, Methodologies, and Applications

Junping Wang, Wensheng Zhang+3 more|arXiv (Cornell University)|Jul 3, 2018

Digital Transformation in Industry44 citations

TL;DR

This paper surveys the challenges, methodologies, and applications of industrial big data analytics, focusing on real-time analysis from heterogeneous data sources and end-to-end data lifecycle management in manufacturing.

ABSTRACT

While manufacturers have been generating highly distributed data from various systems, devices and applications, a number of challenges in both data management and data analysis require new approaches to support the big data era. These challenges for industrial big data analytics is real-time analysis and decision-making from massive heterogeneous data sources in manufacturing space. This survey presents new concepts, methodologies, and applications scenarios of industrial big data analytics, which can provide dramatic improvements in velocity and veracity problem solving. We focus on five important methodologies of industrial big data analytics: 1) Highly distributed industrial data ingestion: access and integrate to highly distributed data sources from various systems, devices and applications; 2) Industrial big data repository: cope with sampling biases and heterogeneity, and store different data formats and structures; 3) Large-scale industrial data management: organizes massive heterogeneous data and share large-scale data; 4) Industrial data analytics: track data provenance, from data generation through data preparation; 5) Industrial data governance: ensures data trust, integrity and security. For each phase, we introduce to current research in industries and academia, and discusses challenges and potential solutions. We also examine the typical applications of industrial big data, including smart factory visibility, machine fleet, energy management, proactive maintenance, and just in time supply chain. These discussions aim to understand the value of industrial big data. Lastly, this survey is concluded with a discussion of open problems and future directions.

Motivation & Objective

• Motivate the need for industrial big data analytics due to highly distributed data across manufacturing systems.
• Identify core challenges in data management, analytics, and decision-making in industrial settings.
• Survey existing methodologies across data ingestion, repositories, management, analytics, and governance.
• Highlight typical industrial applications such as smart factories, machine fleets, energy management, and maintenance.
• Outline open problems and future directions in the field.

Proposed method

• Describe highly distributed industrial data ingestion and integration from diverse sources.
• Propose an industrial big data repository approach handling sampling biases, heterogeneity, and multi-format data.
• Present large-scale industrial data management strategies for organizing and sharing massive heterogeneous data.
• Outline industrial data analytics practices tracking data provenance through generation and preparation stages.
• Discuss industrial data governance to ensure trust, integrity, and security of data.

Experimental results

Research questions

• RQ1 What are the key challenges in industrial big data analytics from data management to decision-making?
• RQ2 What methodologies address ingestion, storage, management, analytics, and governance in industrial contexts?
• RQ3 How are industrial big data analytics applied in smart factories, fleets, energy management, maintenance, and supply chains?
• RQ4 What open problems and future directions exist in industrial big data analytics?

Key findings

• Industrial big data analytics involves five core methodological areas: ingestion, repositories, management, analytics, and governance.
• Real-time analysis from heterogeneous and distributed data sources is a central challenge in manufacturing environments.
• Governance and provenance tracking are important for data trust, security, and integrity throughout the data lifecycle.
• Applications span smart factory visibility, machine fleets, energy management, proactive maintenance, and just-in-time supply chains.
• The survey discusses open problems and directions for future research in industrial big data analytics.