Data-Driven Smart Manufacturing

?INTRODUCTION:

The Introduction of Industry 4.0 and with its smart factories of the future have become an important focus of the world’s industry for the past few years.

The key technologies of Industry 4.0 can have a major impact on an increase in efficiency and the availability of production assets, raising the efficiency of equipment and production, and increasing the value per employee. At the same time, the goal of introducing smart factories is to reduce costs, lead times, delivery times, etc.

The fourth industrial revolution combines various technologies, such as the digitalization of production processes and systems (digital twins of production processes and systems), cloud computing in combination with new mathematical algorithms, artificial intelligence, digital agents, the Internet of Things (IoT), big data to create cyber‐physical systems (CPS) and smart factories. Industry 4.0 also includes various automated systems that allow the automatic exchange of data.

Along with the rise of IoT technologies, cloud computing, big-data analytics, AI, and other technological advances, came the age of big data. In manufacturing, big data refers to large amounts of multi-source, heterogeneous data generated through-out the product lifecycle, which is characterized by 5 V’s.

v?Volume?: Huge quantities of data

v?Variety???????????: The data itself comes in different forms and is generated by ??????????????????????????????diverse sources.

v?Velocity?????????: The data is generated and renewed at very high speed.

v?Veracity?????????: The data is associated with a level of bias, inconsistency, incompleteness, ??????????????????????????????ambiguities, latency, noises and approximation.

v?Value?????????????: Huge value hidden in the data.

MANUFACTURING DATA LIFE CYCLE

Manufacturing data is exploited at various points in the data life cycle. A typical manufacturing data consists of Data collection, Transmission, Storage, Processing, Visualization, and Application.

Various sources of Data in the Industry

??Management data collected from manufacturing information systems (e.g., MES, ERP, CRM, SCM). Information systems possess a variety of data that is related to product planning, order dispatch, material management, production planning.

??Equipment data collected from smart factories by Industrial IoT technologies, which includes data related to real-time performance, operating conditions, and the maintenance history of production equipment.

??User data collected from internet sources such as ecommerce platforms (e.g., Amazon, Flipkart, ebay, etc.) and social networking platforms (e.g., Twitter, Facebook, LinkedIn, and YouTube). This type of data encompasses user demographics, user profiles, user preferences towards products/services, as well as user behavior (e.g., data about online browsing, searching, purchasing, and reviewing history).

??Product data collected from smart products and product-service systems by IoT technologies, including product performance, context of use (e.g., time, location, and weather), environmental data (e.g., temperature, humidity, and air quality) and user biological data.

??Public data collected from governments through open databases. Such datasets deal with data related to intellectual property, civic infrastructure, scientific development, environmental protection, and health-care. For manufacturers, public data can be used to guarantee that manufacturing processes and manufactured products strictly comply with government regulations and industry standards.

Data Collection

Data from different sources collected in various ways, such as data collected through IoT devices, where equipment and product data can be instantly collected by using sensors, RFID detectors and other sensing devices making it possible to simultaneously collect data from equipment and product health in real time.

Data Storage

The large volume of data collected from various sources should be securely stored and effectively integrated. Most of the manufacturing data comes in the form of Structured, Semi-structured and unstructured formats. Traditionally most of the industries focus on structured data. But object based storage architecture enables collection of data to be stored as objects, this provides more flexible way to manage Semi-structured and Unstructured data. Also through Cloud Computing, data storage can be achieved in a cost effective manner.

Data processing

Data processing refers to a series of operations conducted to discover knowledge from a large volume of data. Data must be converted to information and knowledge for manufacturers to make informed and rational decisions. Above all, data must be care-fully preprocessed to remove redundant, misleading, duplicate, and inconsistent information. Data reduction is the process of transforming the massive volume of data into ordered, meaningful, and simplified forms by means of feature or case selection [34]. After data reduction had been completed, the cleaned and simplified data is exploited through data analysis to generate new information.

Data Visualization

Visualization is intended to clearly convey and communicate information through graphical means, enabling end users to comprehend data in a much more explicit fashion. Through visualization, the results of data processing are made more accessible, straight-forward, and user-friendly.

Data Applications

Data has enormous applications in the smart industry. During design phase, Design of Experiments, process optimization, and through data analytics new insights have been revealed about customers, competitors and markets. As a result manufacturers can become much closer to customers. During production process, product quality and equipment maintenance can be monitored and tracked in real time. In this way the manufacturers can be aware of the changes.

DATA DRIVEN SMART MANUFACTURING

Manufacturing enterprises utilize big data analytics to exploit the data from manufacturing to refine manufacturing process, improving the flexibility and smart level of manufacturing.

The manufacturing data is collected, stored, processed, and analyzed by means of big data technologies. As a result, the degree of manufacturing intelligence can be significantly elevated.

The smart manufacturing framework consists of 4 modules.

1.????Manufacturing module

2.????Data driver module

3.????Real time monitor module

4.????Problem processing module

Manufacturing module

The manufacturing module can be summarized by the following flow:

?During manufacturing process, starting from Input of the Raw materials and getting desired product as an output, data can be generated through different sources, such as Customer Relationship Management (CRM), Enterprise Resource Planning (ERP), Manufacturing Execution System (MES) and Product Lifecycle Management (PLM). These information systems and manufacturing resources can be summarized as MAN-MACHINE-MATERIAL ENVIRONMENT. During manufacturing process, data can be collected from human operators, production equipment, information systems, and industrial networks.

?Data Driver Module

This module is the driving force for smart manufacturing throughout the different stages of manufacturing data life cycle.

The Data driver module can be summarizes by the following flow:

As input data from the manufacturing module is transmitted to cloud based data centers to be further analyzed, afterwards, useful information and actionable recommendations exploited from different kinds of raw data are used to direct the actions (e.g., product design, production planning, and manufacturing execution) in the manufacturing module.

Real time monitoring module

This module plays a role in monitoring the manufacturing process in real time in order to ensure product quality. Driven by the data driver module, this module is enabled to analyze the real-time running status of manufacturing facilities. As a result, manufacturers can keep abreast of changes in the manufacturing process, so as to develop the optimal operational control strategies. For example, when a machine is idle, material is distributed and a trajectory is tracked. The manufacturing process can be adjusted in correspondence to specific product quality defects. As a result, the real-time monitoring module can make the manufacturing facilities run more efficiently.

?Problem Solving Module

This module functions to identify and predict emerging problems (e.g., equipment faults or quality defects), diagnose root causes, recommend possible solutions, estimate solution effectiveness, and evaluate potential impacts on other manufacturing activities. Based on real-time information and analysis of historical and ongoing data provided by the data driver module, either human operators or artificial intelligence applications can make informed decisions, not only to address current problems, but also to prevent similar problems from happening in the future. Proactive maintenance enabled by this process will enhance the smooth functioning of the manufacturing process.

?CONCLUSION

The structured process of data collection, integration, storage, analysis, visualization and application is generally applicable for a variety of different industries. With respect to the distinction between SMEs and big companies, depending on the resource availability, they can choose different strategies to achieve the data-driven smart manufacturing in different scales. For example, unlike those bigger companies that can afford to build an exclusive cloud infrastructure for data storage and analysis, SMEs can employ on-demand cloud computing services that are provided by third parties such as Azure, AWS, Alibaba, etc.

Regardless where and how data is processed, the key value propositions of data-driven manufacturing are essentially the same for both SMEs and big companies.

Manufacturing data helps decision makers understand changes in the shortest possible time, make accurate judgments regarding them, and develop rapid response measures to troubleshoot issues. As a consequence, production plans, manufacturing activities, and resources can be closely coordinated to promote smart manufacturing.?????????????????????????????????????????????????????????????????????????????????????????