Big Data in Intelligent Operations Management and Smart Industry

2019-06-07

big Data in Intelligent Operations Management and Smart Industry

The new black gold: that’s the moniker ascribed to big data based on the vast potential and benefits it brings to an enterprise. And big data is also the lifeblood of intelligent manufacturing, logistics and Smart Industry. Data-driven solutions are expanding in enterprises and are crucial for digital transformation initiatives and automation using Industry 4.0 principles and technologies. Big data offers multiple opportunities – from deeper insights, traceability and digital product birth certificates to intelligent operations management in manufacturing and logistics. However, to extract maximum value from big data, enterprises need to focus on four crucial areas.

Digital transformation opened up a universe of possibilities for intelligent industries. At the centre of the current digital and industrial revolution lies data, which enterprises now have unprecedented access to in terms of content, extent and speed of collection, processing and analytics.

The possibilities and benefits of data analytics are so significant that enterprises have begun to incorporate data-driven solutions and revisit data-oriented business models. And data plays just as significant a role within the framework of intelligent manufacturing and logistics (supply chain management).

According to a Market Research Future (MRFR) study, the global data analytics market should see 30% growth between 2017-2023. The Internet of Things (IoT) market will undergo a parallel hike, multiplying the possibilities for data collection and the affordability and accessibility of a variety of (smart) sensors.

The market intelligence firm IDC expects that 80% of major manufacturers will implement Internet of Things (IoT) and data analytics into their processes by 2020. The pace of adoption of both technologies confirms the benefits they offer to industrial enterprises.

Internet of Things (IoT) connected devices installed base worldwide

Growth prediction of Internet of Things (IoT) connected devices worldwide 2015-2025 (source: Statista)

 

The decrease in operational costs, improved quality of services for end-users or the creation of simulations and prognosis using historic data to optimize established processes and speed up complex decision-making are among the most frequently listed reasons for implementation and integration of data-driven solutions in enterprises. Data can yield necessary insights and bring further added value to established processes.

The Industrial Internet of Things (IIoT) and big data are integral to intelligent industry and Smart Industry solutions, as they enable the optimization and automation of processes in manufacturing and material flows. They also enable faster decision-making and problem-solving at all levels of management due to widespread data democratization and real-time data analytics available that offer high-quality reporting and predictive capabilities.

Cyber-physical systems represent the next generation of Smart Industry systems (or Manufacturing Execution Systems (MES)/Manufacturing Operations Management (MOM) systems). These consist of integrated computerized and physical elements that generate a surge of manufacturing (or logistics) data that a complex IT infrastructure must collect, process, analyse and store.

In addition, data collection and its analysis offers an entry point to digital transformation, enabling horizontal and vertical integration of value chains in manufacturing enterprises and supply chains (logistics).

Top Industry Based on 2019 Big Data Market Share

                                Top Industry Based on 2019 Big Data Market Share (source: IDC)

 

If an enterprise aims to benefit from its data, it should focus on 4 crucial areas:

  • Data Management
  • Data Analytics
  • Data Visualization
  • Data Security

Data Management in Smart industry

The basic prerequisite of functional and successful digitalisation is correct data management, which usually consists of:

  • Data Integration
  • Data Contextualisation
  • Data Semantization

Data Integration

Due to the dramatic increase in installed sensors, the volumes of data generated is inflating multifold each year across all industries. The outcome has been a huge upsurge in collected data.

However, manufacturing and logistics (supply chain) data have a diverse assortment of data sources, most significantly the enterprise´s disparate IT systems (MES/MOM systems, WMS, MRP, ERP, APS, SCADA among others).

Parallel to the growing quantity and types of machinery and equipment connected to the enterprise´s Internet of Things (IoT) network is the increased diversity and format incompatibility of the collected data. Data can be heterogeneous – in formats such as texts, notes, reports, or records created by operators or other personnel on the shop floor – as well as in structure.

Thus, Smart Industry systems must be able to process structured and unstructured data alike, while being still capable of coping with missing data. Therefore, data integration is a key procedure in data processing that must be carried out in order to extract usable information.

Data integration reduces the heterogeneity (in terms of form and structure) of the collected and stored data. Simultaneously, Smart Industry systems assure data centralization, which enables data to be standardized for subsequent processing and operations.

Data Contextualisation

In order to adequately incorporate the collected and processed data into decision-making and problem-solving processes by employees or algorithms, standardized data needs a context. Hence, data contextualization process must follow.

The presented information is supposed to help employees or Smart Industry systems acknowledge a certain situation (positioning of material or machinery, time sequence in operations, potential impact on production plans, etc.) that has or might have occurred. Based on this information, an employee or a system can adjust their reaction to the given situation.

Another example of data contextualisation is generation of a product´s digital birth certificate.

Contemporary Smart Industry systems are equipped with the functionality of traceability. Traceability is an essential part of informational transparency, which is a design principle of Industry 4.0. Traceability enables companies to track the full manufacturing history of a particular product and trace all material movements across the supply chain (logistics routes).

Globálny trh s veľkými dátami 2011-2027

                 Big Data Market Size Revenue Forecast Worldwide 2011-2027 (zdroj: Statista)

 

A digital birth certificate contains precise information about where, when, how, by whom and under what conditions (tools, operating procedures, physical values etc.) a particular product was manufactured (or transported, in the case of logistics and supply chain management).

Using a set of contextualized data, a Smart Industry system can uncover patterns, correlations and tendencies in materials and the manufacturing flux in relation to a product (or a whole batch) or to manufacturing or logistics machinery (e.g., the interrelationship between decreases in quality and the timing of equipment maintenance).

Data Semantization

Contextualized data allows companies to mine information which, when processed correctly by semantic models, can generate further knowledge. Smart Industry systems use semantic models to perform autonomous and auto-regulated planning and production and material and human resources management, including manufacturing asset management. Moreover, the application of semantic models to contextualized data permits the identification of relevant knowledge and rules for complex processes.

Data in Manufacturing Logistics – Milk Run 4.0

To the data management process, let’s look at an example of autonomous synchronization of manufacturing flow and internal logistics (inventory and warehouse management along intralogistics).

To set up a fully functioning solution featuring autonomous integration of manufacturing and in-plant logistics to boost productivity performance, production quality and agility, ANASOFT implemented its Smart Industry solution EMANS in an automotive factory.

The first step was to collect data from the manufacturing and (intra)logistics machinery and equipment. This gave staff immediate access to precise and actual information about stock status in compact storage, the central warehouse and workstations (production lines) in real time. All material and semi-product transfers between workstations (production lines) were recorded in detail. Smart Industry system processes controlled them for other required operations in the manufacturing flux.

                              Big Data in Manufacturing Logistics

Based on the integration of data from the manufacturing machinery and intralogistics, a precise virtual copy of the material flows – a so-called digital twin – of the factory’s manufacturing processes could be generated. The processing of integrated and contextualized data using semantic models allows the Smart Industry system EMANS to optimize manufacturing processes and effectively manage materials, machines and human resources on the shop floor.

The correctly configured data collection and data processing allows EMANS to autonomously, continuously and seamlessly synchronize manufacturing and logistics equipment. Thus, the factory can follow through on its production plan, since it has precise, on-time fulfilment of the material transfer requirements assured in its manufacturing processes by intelligent operations management system.

Harnessing the value of its data enabled the company to upgrade intralogistics operated by forklifts using more agile form of Milk Run 4.0 (or dynamic Milk Run). The result for the Tier 1 company in automotive industry was flexible manufacturing planning and precise production line monitoring, as well as a 23% boost in overall production performance, a 30% reduction in vehicle downtime, and minimized idle time on production lines due to a lack of input material.

Data can make enterprises that are not solely based on big data analytics smarter by democratizing data for all management levels. This accelerates decision-making processes and provides deeper insights, as well as and simulations and predictive modelling while bridging shop-floor and the top-floor. As Smart Industry´s lifeblood, data also provides value in manufacturing and supply chain processes that are instrumental to intelligent operations management and innovative solutions boosting further the enterprise´s overall performance. 

SEE ALSO

 Smart Industry Trends Header Data Analytics in Manufacturing and Logistics