Successful BI Implementations
Big data in manufacturing systems
Manufacturing can be defined as the hard segment of an economy which applies resources such as labor, machines, tools, and raw materials in order to produce physical products. The manufacturing industry contains a huge volume of data created by sensors, electronic devices, and digital machines in factories. Manufacturing is a traditional industry which can be highly affected by big data, since the approach for many companies has been changed to operate based on forecasts. Moreover, big data could simplify data visualizations and improve automation applications regarding production design and engineering.
Manufacturing plants collect data using different channels such as manufacturing processes, supply chain management systems, and tracking the products sold. Using big data can help to develop new products based on customer needs. Moreover, manufacturers have the opportunity to better plan out their supply chain with a more accurate demand forecast. Managers believe that using big data can help diagnose defective products, improve process quality, and better plan supply chains.
Manufacturing processes can't be firmly separated from either logistics processes or supply chain management activities. For example, many of the logistics processes in manufacturing plants are performed by tools with radio-frequency identification (RFID) tags, which allows real-time tracking of the products. Using data analysis on the shop floor enables the system to efficiently implement real-time manufacturing, planning, and scheduling, which is directly affected by both the material delivery time and the real-time information coming from the manufacturing processes. Moreover, analyzing the big data can level the material flow and help the plant manager to better plan space limitations regarding material flow and warehousing operations.
There are a lot of process, personnel, and departments data generated during a product's lifecycle. The nine stages of a product's lifecycle were introduced by Tao et al.: product concept, design, raw material purchase, manufacturing, transportation, sale, utilization, after-sale service, and recycle/disposal. In each stage, a lot of data is generated, and by collecting this data for all products, we can have a dataset with big data characteristics. Five areas of big data application in manufacturing are: 1- using data to forecast a complex process's output; 2- using data to capture that which is difficult to measure under regular conditions, 3- developing algorithms which can more accurately control the quality and safety of the final product; 4- using image metrology to reduce the amount of human supervision required; and finally, 5- obtaining the optimal time for doing predictive maintenance.
The continued growth of the Internet of Things has also influenced the amount of data available to manufacturing companies. It has been forecasted that by 2025, about 175 trillion gigabytes of data will be available, and the manufacturing industry will be the second-fastest-growing sector for data generation, after the healthcare industry. In spite of this huge volume of data - which is generated and kept by manufacturing plants - the number of studies on big data applications in the manufacturing industry is still considerably less than that in the service industries such as finance, information technology, and E-commerce. However, despite the lack of big data studies in the manufacturing industry, data mining has been used frequently in manufacturing decision making problems.
There are several different areas of manufacturing - including new product development, smart manufacturing, cloud-based manufacturing, process improvement, predictive manufacturing , and redistributed manufacturing - in which the application of big data analytics can improve system outputs. Belhadi et al., studied the major contributions of big data analytics in manufacturing systems by examining several case studies. In order to have a better overview of the recent applications of big data in manufacturing systems, the Thomson Reuters Web of Science was used to categorize the most frequent big data studies in manufacturing. Figure 4 shows the relative frequency of published studies on big data analytics as applied to manufacturing. Studies are categorized based on their research focus in Figure 4, with most categories explained afterwards. It is worth noting that review papers are not being discussed further, since we are studying research contributions in the literature and "review" categories as mentioned in Figure 4 are just there to give further insight. Moreover, the "Marketing" and "Flexibility" categories are not discussed further, since each makes up less than 5% of the total publications.
Figure 4 Publication frequencies with "big data" in title and "manufacturing" in topic (Thomson Reuters Web of Science).
Operations improvement
A number of studies show that big data analytics can improve the entire operational performance in manufacturing systems. Yadegaridehkordi et al., developed a hybrid approach to study the effect of the adoption of big data analytics on manufacturing companies' performance. Popovič et al., showed that big data analytics' capability, along with organizational readiness and certain design factors, could enhance a business's performance. In another study, Guo et al. applied data visualization and machine learning algorithms to better inform the operations manager of the product's market situation. Some other applications of big data analytics in manufacturing systems are shown by implementing big data analytics in a manufacturing company and using big data to improve the trading performance of emitting companies.
Sustainability
Big data can provide useful tools for manufacturers to perform their operations in a sustainable manner, keeping the environment better for future generations. Xu et al. showed how using the available big data on used products can increase the efficiency of remanufacturing systems and save more resources. Dubey et al. performed a field study and used the responses by 405 senior managers to develop a framework that could use big data to determine the most important factors for maintaining a sustainable manufacturing system. Lowering service costs, increasing the level of trust between stakeholders, respecting customers' privacy, and increasing data-sharing security are among the benefits that big data analytics may bring to sustainable manufacturing systems. In another study, developed a theoretical approach to demonstrate the application of big data analytics in the area of production safety management.
The application of big data analytics in Bosch Car Multimedia's (Braga-Portugal) organization reviews the challenges of collecting, integrating, storing and processing the data in a manufacturing environment. The Bosch organization study shows the potential opportunity that is created when the volume, variety, and velocity of data is used for sustainable innovations in a future manufacturing environment. In another article, the importance of risk management in developing sustainable manufacturing supply chains was studied. The paper showed that applying big data analytics in order to mitigate the supply chain's social risk can help improve social and economic sustainability.
Smart manufacturing, strategy development, and agile manufacturing
Big data analytics can be used in smart manufacturing to solve company problems at the speed the business requires. However, there are some organizational and technological barriers that may prevent manufacturing companies from using big data solutions to initiate a smart factory. Big data analytics has been proven to be a valuable tool for manufacturers to help them develop strategies, share data, design predictive models, and connect factories in order to control processes. A study by Bumblauskas et al. studies big data applied to designing a smart maintenance decision support system, which is shown to improve an asset's lifecycle. Liu et al. used big data analytics for routing order pickup and delivery as well as assigning orders to laundry terminals in smart laundry service enterprises. Big data applications in strategy development and agile manufacturing have also been studied by Opresnik & Taisch, Waller & Fawcett, Guha & Kumar, and Gunasekaran et al.. Ren et al. reviewed the available research in big data applications that support sustainable smart manufacturing. Agility in a manufacturing system is the capability to better deal with unpredictable events, and deal with them in a business environment that can even turn these events into benefits.
Several other studies developed quality research on using big data analytics in the manufacturing field. Some of the selected journal articles and conference proceedings are summarized in Table 1. The criterion for us consider a paper in the current review is that it must have been cited, on average, more than 10 times each year.
Table 1 High-quality articles using big data in manufacturing processes (Citation count is as of March 2020).
| Author / Journal | Contribution | Study approach | Case study (NA stands for Not Applicable) | Citation# | Future research topic(s) in the article |
|---|---|---|---|---|---|
| Lee et al. (2013)/ Manufacturing letters | Studying the applications of big data in predictive manufacturing systems | Analytical study | NA | 697 | -Developing systems to integrate, manage, and analyze machinery data during different stages of machine life cycle |
| O’Donovan et al. (2015)/Journal of Big Data | Studying the requirements for implementing equipment maintenance | Analytic field study / Simulation | DePuy manufacturing facility in Ireland | 84 | -Deployment of big data pipeline in DePuy |
| -Using data pipeline to feed predictive maintenance applications | |||||
| Dubey et al. (2016)/The International Journal of Advanced Manufacturing Technology | Studying the role of big data in sustainable manufacturing | Statistical analysis / Field study | NA | 174 | -Using big data to redefine the focus of advanced manufacturing technology |
| -Using big data innovations like new materials development | |||||
| Kumar et al. (2016)/International Journal of Production Research | Solving a data imbalance problem in cloud-based manufacturing systems | RHadoop programming / MapReduce framework | Steel plate manufacturing company | 56 | -Executing the dissimilar types of feature selection approaches |
| -Improving performance of classifiers | |||||
| Mourtzis et al. (2016)/Procedia CIRP | Studying the applications of the Internet of Things in developing industrial big data | Analytic field study | Mould-making industry | 131 | NA |
| Zhang et al. (2017)/Journal of Cleaner Production | Integrating big data analytics and service-driven patterns to create cleaner manufacturing and maintenance processes | Analytical study / Product life cycle analysis | Unnamed axial compressor manufacturer | 170 | -Using big data analytics to work out a mathematical model to discover rules for making cleaner production decisions |
| -Representing and visualizing knowledge gained from big data | |||||
| Zhong et al. (2017)/International Journal of Production Research | Creating a RFID-enabled intelligent shop floor using the Internet of Things | Smart manufacturing objects / Wireless network | Unnamed collaborative company | 177 | -Developing a mathematical model to formulate physical internet-based logistics systems |
| -Developing a systematic procedure to examine big data analytical approaches | |||||
| Gunasekaran et al. (2018)/International Journal of Production Research | Studying the role of big data in agile manufacturing | Analytic field study | Four organizations in United Kingdom | 46 | -Studying the applications of the Internet of Things, Industry 4, and Blockchain technologies in developing agile manufacturing systems |
| Moktadir et al. (2019)/Computers & Industrial Engineering | Studying the barriers to applying big data analytics in manufacturing supply chains | Delphi-based analytic hierarchy process (AHP) / Sensitivity analysis | Five manufacturing companies in Bangladesh | 20 | -Using international data to examine big data analytics barriers |
| -Utilizing the extensions of AHP method to further explore the direction of the studied research | |||||
| Popovič et al. (2018)/Information Systems Frontiers | Using a qualitative approach to study the impact of big data analytics in manufacturing sector | Comparative analytic field study | Three manufacturing companies in Europe | 70 | -Studying the impact of big data analytics on low-performing firms |
| -Studying failed cases instead of successful cases | |||||
| Tao et al. (2018)/The International Journal of Advanced Manufacturing Technology | Developing a method using a digital twin to design a product, manufacture, and service it | Product life cycle analysis | Author created applications as case | 434 | -Digital twin data construction and management |
| -Developing smart service analysis based on digital twin data | |||||
| Dubey et al. (2019a)/Technological Forecasting and Social Change | Studying the impact of big data analytics on the social performance and environmental performance of manufacturing companies | Partial Least Squares / Hypothesis testing | Sample of 205 manufacturing companies in India | 84 | -Studying the exact role of the flexibility or control orientation on big data and predictive analytics on manufacturers’ social and environmental performance |
| Moktadir et al. (2019)/Computers & Industrial Engineering | Studying the critical barriers to the adoption of big data analytics in manufacturing systems | Delphi-based analytic hierarchy process | Five manufacturing companies in Bangladesh | 20 | -Using international data in the same study |
| -Using other decision-making techniques to study the interaction among barriers | |||||
| (Raut et al., 2019) / Journal of cleaner production | Using big data analytics to improve manufacturing sustainability in terms of operations management | Structural equation modelling-artificial neural network | Survey data from 316 Indian experts | 16 | -Studying this same issue in other geographical locations besides India |
| -Studying other technologies that firms may adopt for sustainable purposes |