Predictive Maintenance in Industry 4.0 for the SMEs: A Decision Support System Case Study Using Open-Source Software
Abstract
:1. Introduction
2. State of the Art of Predictive Maintenance
2.1. Predictive Maintenance Overview
- Data acquisition,
- Data processing, and
- Maintenance decision making.
- IoT and Big Data techniques and
- Machine learning-based techniques.
- Condition monitoring technology and predictive maintenance techniques;
- Internet of Things (IoT) technology;
- Predictive algorithms.
- Collection of condition data on the equipment;
- Increase in knowledge about failure reasons and causes;
- About the effects and deterioration patterns of equipment.
- Online—refers to the monitoring process performed during the operational state of the machine, system, or equipment, i.e., during its running state.
- Offline—refers to the monitoring process performed during the phase when the machine, system, or equipment is not in operation.
- Periodic—refers to the monitoring process conducted at specified intervals, such as every 30 min, every hour, at the end of a work shift, etc., and conducted using portable indicators such as vibration pens, acoustic emission devices, handheld meters, etc.
- Continuous—refers to the monitoring process that is performed automatically and continuously based on specialized measuring devices, such as vibration and acoustic sensors.
- vibration monitoring and dynamic analysis,
- oil analysis and lubricant monitoring,
- sound, ultrasonic, and acoustic monitoring,
- motor circuit analysis,
- different variations of thermography and thermal analysis,
- electromagnetic measurements,
- radiography and radiation analysis,
- laser interferometry, and
- different performance measurements.
- monitors working conditions using installed sensors,
- detects and predicts patterns characterized by data anomalies,
- generates warnings when deviations from established thresholds occur.
2.2. Predictive Maintenance Advantages and Disadvantages
- improved safety for workers and the environment,
- increased availability,
- increased reliability,
- reduced cost of parts and labor,
- improved product quality,
- reduced waste of raw materials and consumables such as lubricants,
- energy savings from quieter machines (e.g., alignment, which in some cases is reported as 3–5%; balancing, 1–2%).
- Minimizes the occurrence of unplanned downtime and maximizes the uptime of machines, equipment, and systems;
- Provides the company with a real-time view of the current condition of its plant, machinery, equipment, and systems;
- Ensures minimal disruption to productivity by allowing some predictive maintenance activities to be performed on running assets;
- Optimizes the amount of time the company spends on maintenance activities;
- Optimizes the use of spare parts;
- Improves equipment reliability.
2.3. Predictive Maintenance in Industry 4.0
- Data collection, storage, and analysis can be accomplished using powerful data servers and software; and
- Presenting and communicating the results of these analyses to decision-makers inside and outside the organization.
- As a maintenance management tool—when its use is limited to preventing spontaneous downtime and/or catastrophic failures;
- As a business optimization tool—when its use relates to establishing best production practices and procedures for all critical production systems within an organization;
- As a reliability improvement tool—when its use is to quantify even the smallest deviations from standard operating parameters. This enables company personnel (e.g., reliability engineers, repair planners) to prepare and plan for minor changes to prevent machine and equipment failures, thus avoiding extensive rebuilds and associated downtime.
3. IoT Devices and Sensors as a Pillar of Predictive Maintenance
3.1. IoT Concept
- device interoperability
- network interoperability
- syntactic interoperability
- semantic interoperability
- platform interoperability
- Adapters and gateways—they take care of interoperability by developing a method known as a mediator to increase interoperability between IoT devices. Among other things, they aim to establish a connection between different specifications, data, standards, and middleware;
- Virtual networks or overlay-based solutions—the main idea is to build a virtual network on top of a physical network that can communicate with other types of devices, such as sensor nodes. The main goal is to seamlessly connect sensors and actuators, as well as other smart IP objects, to the Internet to enable end-to-end communication that is possible within each virtual network using different protocols;
- Network technologies—include various network technologies and protocols such as IP-based approaches, software-defined networking (SDN), network functions virtualization, and Fog computing;
- Open API—refers to an interface provided by service providers that exposes functions or data to an application written in a high-level language;
- Service-Oriented Architecture (SOA)—interaction with the end operations of various wireless devices is divided into different service components, and application layer software can access resources provided by the devices as services;
- Semantic Web Technologies—refers to the Semantic Web of Things (swot) paradigm, which is proposed to integrate the semantic web with the Web of Things (wot), with the further goal of achieving a common understanding of the various entities that make up the IoT;
- Open standard—nowadays numerous standardization bodies, consortia, and alliances are trying to find a solution to the IoT standard problems, such as IPSO, OIC, seen Alliance, etc.
- IoT network protocols—used to connect devices over a network, usually the Internet;
- IoT data protocols—used to connect to low-power IoT devices by allowing users to communicate with hardware over a cellular or wired network without requiring an Internet connection.
3.2. Analysis and Identification of IoT Devices and Sensors Available in the Market
- temperature sensors,
- proximity sensors,
- pressure sensors,
- water quality sensors,
- chemical sensors,
- gas sensors,
- smoke sensors,
- infrared sensors,
- level sensors,
- image sensors,
- motion detection sensors,
- accelerometers,
- gyroscope sensors,
- humidity sensors,
- optical sensors.
4. Prototyping a Decision Support System (DSS) for Predictive Maintenance
4.1. Case Study Description
4.2. Architecture of the Application
- Shiny—Shiny is an open-source R package that provides an elegant and powerful framework for building web applications with R [55].
- shinyWidgets—the family of pre-built widgets in the Shiny package, each created with a transparently named R function.
- Shinycustomloader—a custom file for loading the screen in the R Shiny package.
- bs4Dash—the R package for developing modern dashboards in R Shiny.
- echarts4r—a package for interactive charts.
- echarts4r.maps—a dataset with the latitude and longitude of all cities used for interactive charts.
- Reactable—creates a table from tabular data with default sorting and pagination. The data table is an HTML widget that can be used in R Markdown documents and Shiny applications or displayed via an R console.
- Fresh—used for Custom ‘Bootstrap” themes in Shiny.
4.3. Machine Learning Deployment
- Dataset creation—The small company for which the DSS was developed chose to keep its data anonymous. Therefore, we created an illustrative dataset.
- Prediction of data—The DSS predicts the observed data for the selected time period in the future.
- Warnings for devices—The DSS generates warnings for the devices in the future based on the observed data in the past and the predicted data.
4.3.1. Dataset Generation
4.3.2. Forecasting Data
4.3.3. Warning for Devices
4.4. Graphical User Interface
5. Use Case of the DSS Platform Usage
- Step 1: Location selection
- Step 2: Checking devices based on energy consumption
- Step 3: Checking devices based on temperature
- Step 4: Overview of key performance indicators
- Step 5: Inspecting devices by age and cost
- Step 6: Inspecting devices by age and cost
- Step 7: Forecasting data
- Step 8: User feedback
5.1. Step 1: Location Selection
5.2. Step 2: Checking Devices Based on Energy Consumption
- Device 29—29.4 kWh/day % share
- Device 46—20.9 kWh/day % share
- Device 42—20.7 kWh/day % share
- Device 36—19.6 kWh/day % share
- Device 22—9.5 kWh/day % share
5.3. Step 3: Checking Devices Based on Temperature
5.4. Step 4: Overview of Key Performance Indicators
5.5. Step 5: Inspecting Devices by Age and Cost
5.6. Step 6: Inspecting Devices by Regions
- West—45 (30.82%)
- Central—45 (30.82%)
- South—34 (23.29%)
- East—21 (14.38%)
5.7. Step 7: Forecasting Data
5.8. Step 8: Generating Warnings for Devices
5.9. Step 8: User Feedback
- “… looking for a cost-effective and efficient solution, and R was able to deliver just that … helped us save a significant amount of money compared to proprietary alternatives.”
- “…… a wide range of statistical and machine learning methods, we are now able to make more accurate predictions about equipment failure and significantly reduce downtime ……”
- “…The open-source community, of which R is a part, is an extremely useful resource...”
- “… the integration of the predictive maintenance solution into our existing infrastructure, which allows us to make it a seamless part of our business processes ……”
- “… People who have no experience in programming or statistics may find the learning curve to be quite high...”
- “… is constantly evolving and changing, which can be both beneficial and annoying… the solution became more difficult to maintain and keep up to date ……”
6. Open-Source Predictive Maintenance Playbook for SMEs
- Define the problem—Determine which devices or systems need predictive maintenance and clearly define the maintenance goals.
- Data collection—Identify the necessary data sources for the system and set up a data collection infrastructure to collect real-time data.
- Data pre-processing—Remove outliers, missing numbers, and discrepancies from the data and normalize or scale the data to ensure consistency and comparability between features. Develop new features.
- Flagging and anomaly detection—Define criteria for flagging errors and maintenance events. Label historical data to indicate normal operation or specific failure scenarios. Identify aberrant data points.
- Model selection—Evaluate different machine learning algorithms suitable for predictive maintenance, considering tradeoffs between accuracy, interpretability, scalability, and real-time capabilities.
- Model Training—Split the labeled dataset into two parts: Training and Validation. Train the selected machine learning model on the labeled data, modifying hyperparameters and the model architecture as necessary.
- Model evaluation—Select metrics to evaluate the model, such as F1 score, accuracy, precision, recall, or similar, and evaluate the model.
- Integration and deployment—Integrate the trained model into the Industry 4.0 ecosystem by creating an inference API to obtain real-time predictions.
- Monitoring and maintenance—Continuously monitor the performance of the predictive maintenance system, including data quality, model accuracy, and false positive/negative rates. Retrain models as needed using updated data.
- Continuous Improvement—Analyze feedback from the installed predictive maintenance system, including maintenance activities performed and their consequences. Incorporate findings into future iterations of the system to increase accuracy, efficiency, and effectiveness.
7. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Shyjith, K.; Ilangkumaran, M.; Kumanan, S. Multi-criteria decision-making approach to evaluate optimum maintenance strategy in textile industry. J. Qual. Maint. Eng. 2008, 14, 375–386. [Google Scholar] [CrossRef]
- Jerman, A.; Bertoncelj, A.; Erenda, I. The influence of critical factors on business model at a smart factory: A case study. Bus. Syst. Res. Int. J. Soc. Adv. Innov. Res. Econ. 2019, 10, 42–52. [Google Scholar]
- Mobley, R.K. An Introduction to Predictive Maintenance; Elsevier: Amsterdam, The Netherlands, 2002. [Google Scholar]
- Roblek, V.; Thorpe, O.; Bach, M.P.; Jerman, A.; Meško, M. The fourth industrial revolution and the sustainability practices: A comparative automated content analysis approach of theory and practice. Sustainability 2020, 12, 8497. [Google Scholar] [CrossRef]
- Moore, W.; Starr, A. An intelligent maintenance system for continuous cost-based prioritisation of maintenance activities. Comput. Ind. 2006, 57, 595–606. [Google Scholar] [CrossRef] [Green Version]
- Selcuk, S. Predictive maintenance, its implementation and latest trends. Proc. Inst. Mech. Eng. Pt. B J. Eng. Manuf. 2017, 231, 1670–1679. [Google Scholar] [CrossRef]
- Christiansen, B. A Complete Guide to Predictive Maintenance. Limble CMMS. Available online: https://limblecmms.com/predictive-maintenance/ (accessed on 21 March 2023).
- Nunes, P.; Santos, J.; Rocha, E. Challenges in predictive maintenance—A review. CIRP J. Manuf. Sci. Technol. 2023, 40, 53–67. [Google Scholar] [CrossRef]
- Ahmad, R.; Kamaruddin, S. An overview of time-based and condition-based maintenance in industrial application. Comput. Ind. Eng. 2012, 63, 135–149. [Google Scholar] [CrossRef]
- Market Research Future. Global Predictive Maintenance (PdM) Market Research Report. 2020. Available online: https://www.marketresearchfuture.com/reports/predictive-maintenance-market-2377 (accessed on 21 March 2023).
- Turgis, F.; Auder, P.; Coutadeur, Q.; Verdun, C. Industrialization of condition based maintenance for complex systems in a complex maintenance environment, example of NAT. In Proceedings of the 12th World Congress on Railway Research, Tokyo, Japan, 28 October 2019. [Google Scholar]
- Chen, D.; Trivedi, K.S. Closed-form analytical results for condition-based maintenance. Reliab. Eng. Syst. Saf. 2002, 76, 43–51. [Google Scholar] [CrossRef]
- Parpala, R.C.; Iacob, R. Application of IoT concept on predictive maintenance of industrial equipment. In Proceedings of the MATEC Web of Conferences, Bucharest, Rumania, 9 August 2017; p. 02008. [Google Scholar]
- Jardine, A.K.; Lin, D.; Banjevic, D. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech. Syst. Signal Process. 2006, 20, 1483–1510. [Google Scholar] [CrossRef]
- Chuang, S.-Y.; Sahoo, N.; Lin, H.-W.; Chang, Y.-H. Predictive maintenance with sensor data analytics on a Raspberry Pi-based experimental platform. Sensors 2019, 19, 3884. [Google Scholar] [CrossRef] [Green Version]
- Pech, M.; Vrchota, J.; Bednář, J. Predictive maintenance and intelligent sensors in smart factory. Sensors 2021, 21, 1470. [Google Scholar] [CrossRef]
- Kanawaday, A.; Sane, A. Machine learning for predictive maintenance of industrial machines using IoT sensor data. In Proceedings of the 2017 8th IEEE international conference on software engineering and service science (ICSESS), Beijing, China, 24–26 November 2017; pp. 87–90. [Google Scholar]
- Christiansen, B. Complete List of Condition Monitoring Techniques. Machinery and Equipment MRO. Available online: https://www.mromagazine.com/features/complete-list-of-condition-monitoring-techniques (accessed on 21 March 2023).
- Davies, A. Handbook of Condition Monitoring: Techniques and Methodology; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2012. [Google Scholar]
- Hodge, V.J.; O’Keefe, S.; Weeks, M.; Moulds, A. Wireless sensor networks for condition monitoring in the railway industry: A survey. IEEE Trans. Intell. Transp. Syst. 2014, 16, 1088–1106. [Google Scholar] [CrossRef]
- Mukhopadhyay, S.C.; Suryadevara, N.K. Internet of things: Challenges and Opportunities; Springer: Berlin/Heidelberg, Germany, 2014; pp. 2347–4718. [Google Scholar]
- Khalil, N.; Abid, M.R.; Benhaddou, D.; Gerndt, M. Wireless sensors networks for Internet of Things. In Proceedings of the 2014 IEEE ninth international conference on Intelligent sensors, sensor networks and information processing (ISSNIP), Singapore, Singapore, 21–24 April 2014; pp. 1–6. [Google Scholar]
- Kocakulak, M.; Butun, I. An overview of Wireless Sensor Networks towards internet of things. In Proceedings of the 2017 IEEE 7th annual computing and communication workshop and conference (CCWC), Las Vegas, NV, USA, 9–11 January 2017; pp. 1–6. [Google Scholar]
- Civerchia, F.; Bocchino, S.; Salvadori, C.; Rossi, E.; Maggiani, L.; Petracca, M. Industrial Internet of Things monitoring solution for advanced predictive maintenance applications. J. Ind. Inf. Integr. 2017, 7, 4–12. [Google Scholar] [CrossRef]
- Dong, L.; Mingyue, R.; Guoying, M. Application of internet of things technology on predictive maintenance system of coal equipment. Procedia Eng. 2017, 174, 885–889. [Google Scholar] [CrossRef]
- Passlick, J.; Dreyer, S.; Olivotti, D.; Grützner, L.; Eilers, D.; Breitner, M.H. Predictive maintenance as an internet of things enabled business model: A taxonomy. Electron. Mark. 2021, 31, 67–87. [Google Scholar] [CrossRef]
- Chehri, A.; Jeon, G. The industrial internet of things: Examining how the IIoT will improve the predictive maintenance. In Proceedings of the Innovation in Medicine and Healthcare Systems, and Multimedia: Proceedings of KES-InMed-19 and KES-IIMSS-19 Conferences, Berlin/Heidelberg, Germany, 6 June 2019; pp. 517–527. [Google Scholar]
- Lade, P.; Ghosh, R.; Srinivasan, S. Manufacturing analytics and industrial internet of things. IEEE Intell. Syst. 2017, 32, 74–79. [Google Scholar] [CrossRef]
- Grambau, J.; Hitzges, A.; Otto, B. Predictive Maintenance in the Context of Service. In Proceedings of the 20th International Conference on Enterprise Information Systems (ICEIS 2018), Dortmund, Germany, 21–24 March 2018; pp. 223–230. [Google Scholar]
- Demoly, F.; Kiritsis, D. Asset optimization and predictive maintenance in discrete manufacturing industry. IFAC Proc. Vol. 2012, 45, 1–6. [Google Scholar] [CrossRef]
- Noura, M.; Atiquzzaman, M.; Gaedke, M. Interoperability in internet of things: Taxonomies and open challenges. Mob. Netw. Appl. 2019, 24, 796–809. [Google Scholar] [CrossRef] [Green Version]
- Gregersen, C. A Complete Guide to IoT Protocols & Standards in 2021. Available online: https://www.nabto.com/guide-iot-protocols-standards/ (accessed on 21 March 2023).
- Vermesan, O.; Friess, P.; Guillemin, P.; Gusmeroli, S.; Sundmaeker, H.; Bassi, A.; Jubert, I.S.; Mazura, M.; Harrison, M.; Eisenhauer, M. Internet of things strategic research roadmap. In Internet of Things-Global Technological and Societal Trends from Smart Environments and Spaces to Green ICT; River Publishers: Aalborg, Denmark, 2022; pp. 9–52. [Google Scholar]
- Ferretti, M.; Schiavone, F. Internet of Things and business processes redesign in seaports: The case of Hamburg. Bus. Process Manag. J. 2016, 22, 271–284. [Google Scholar] [CrossRef]
- Sethi, P.; Sarangi, S.R. Internet of things: Architectures, protocols, and applications. J. Electr. Comput. Eng. 2017, 2017, 9324035. [Google Scholar]
- Uppalapati, K. How IoT Protocols and Standards Support Secure Data Exchange in the IoT Ecosystem? Available online: https://www.kelltontech.com/kellton-tech-blog/internet-of-things-protocols-standards (accessed on 21 March 2023).
- Alkhalil, A.; Ramadan, R.A. IoT data provenance implementation challenges. Procedia Comput. Sci. 2017, 109, 1134–1139. [Google Scholar] [CrossRef]
- Udoh, I.S.; Kotonya, G. Developing IoT applications: Challenges and frameworks. IET Cyber-Phys. Syst. Theory Appl. 2018, 3, 65–72. [Google Scholar] [CrossRef]
- Cheruvu, S.; Kumar, A.; Smith, N.; Wheeler, D.M.; Cheruvu, S.; Kumar, A.; Smith, N.; Wheeler, D.M. IoT frameworks and complexity. Demystifying Internet of Things Security: Successful IoT Device/Edge and Platform Security Deployment; Springer: Berlin/Heidelberg, Germany, 2020; pp. 23–148. [Google Scholar]
- Gil, D.; Johnsson, M.; Mora, H.; Szymański, J. Review of the complexity of managing big data of the internet of things. Complexity 2019, 4592902. [Google Scholar] [CrossRef] [Green Version]
- Zhang, K.; Han, D.; Feng, H. Research on the complexity in Internet of Things. In Proceedings of the 2010 International Conference on Advanced Intelligence and Awarenss Internet (AIAI 2010), Beijing, China, 23–25 October 2010; pp. 395–398. [Google Scholar]
- Song, S.; Zhang, A. IoT data quality. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, Virtual Event Ireland, 19 October 2020; pp. 3517–3518. [Google Scholar]
- Ding, X.; Wang, H.; Li, G.; Li, H.; Li, Y.; Liu, Y. IoT data cleaning techniques: A survey. In Intelligent and Converged Networks 2022, 3, 325–339. [Google Scholar] [CrossRef]
- Jane, V. Survey on iot data preprocessing. Turk. J. Comput. Math. Educ. 2021, 12, 238–244. [Google Scholar]
- Chu, X.; Ilyas, I.F.; Krishnan, S.; Wang, J. Data cleaning: Overview and emerging challenges. In Proceedings of the 2016 international conference on management of data, San Francisco, CA, USA, 26 June–1 July 2016; pp. 2201–2206. [Google Scholar]
- Khare, S.; Totaro, M. Big data in IoT. In Proceedings of the 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kanpur, India, 6–8 July 2019; pp. 1–7. [Google Scholar]
- Alharam, A.K.; Elmedany, W. Complexity of cyber security architecture for IoT healthcare industry: A comparative study. In Proceedings of the 2017 5th international conference on future internet of things and cloud workshops (FiCloudW), Prague, Czech Republic, 21–23 August 2017; pp. 246–250. [Google Scholar]
- Pappas, N.; Caputo, A.; Pellegrini, M.M.; Marzi, G.; Michopoulou, E. The complexity of decision-making processes and IoT adoption in accommodation SMEs. J. Bus. Res. 2021, 131, 573–583. [Google Scholar] [CrossRef]
- Gartner. Internet of Things: Unlocking True Digital Business Potential. Available online: https://www.gartner.com/en/information-technology/insights/internet-of-things (accessed on 21 March 2023).
- Arm. Arm Glossary. IoT devices. Available online: https://www.arm.com/glossary/iot-devices (accessed on 21 March 2023).
- Sharma, R. Top 15 Sensor Types Being Used Most by IoT Application Development Companies. Available online: https://www.finoit.com/blog/top-15-sensor-types-used-iot/ (accessed on 21 March 2023).
- Ihaka, R.; Gentleman, R. R: A language for data analysis and graphics. J. Comput. Graph. Stat. 1996, 5, 299–314. [Google Scholar]
- Wickham, H.; Averick, M.; Bryan, J.; Chang, W.; McGowan, L.D.A.; François, R.; Grolemund, G.; Hayes, A.; Henry, L.; Hester, J. Welcome to the Tidyverse. J. Open Source Softw. 2019, 4, 1686. [Google Scholar] [CrossRef] [Green Version]
- Wickham, H.; Wickham, M.H. Package Tidyverse, Easily Install and Load the ‘Tidyverse, Version 1.2.0. Available online: https://tidyverse.tidyverse.org/ (accessed on 21 March 2023).
- Chang, W.; Cheng, J.; Allaire, J.; Xie, Y.; McPherson, J. Package Shiny, Version 1.7.4.1. Available online: https://cran.r-project.org/web/packages/shiny/index.html (accessed on 21 March 2023).
- Anderson, J.W.; Kennedy, K.E.; Ngo, L.B.; Luckow, A.; Apon, A.W. Synthetic data generation for the internet of things. In Proceedings of the 2014 IEEE International Conference on Big Data (Big Data), Washington, DC, USA, 27–30 October 2014; pp. 171–176. [Google Scholar]
- Kannan, S. Synthetic time series data generation for edge analytics. F1000Research 2022, 11, 67. [Google Scholar] [CrossRef]
- Bolón-Canedo, V.; Sánchez-Maroño, N.; Alonso-Betanzos, A. A review of feature selection methods on synthetic data. Knowl. Inf. Syst. 2013, 34, 483–519. [Google Scholar] [CrossRef]
- Camacho, V.T. Synthetic dataset generation methodology for Recommender Systems using statistical sampling methods, a Multinomial Logit model, and a Fuzzy Inference System. arXiv 2022, arXiv:14350.2212. [Google Scholar]
- Panagiotakis, C.; Papadakis, H.; Fragopoulou, P. Unsupervised and supervised methods for the detection of hurriedly created profiles in recommender systems. Int. J. Mach. Learn. Cybern. 2020, 11, 2165–2179. [Google Scholar] [CrossRef]
- La Russa, F.M.; Santagati, C. An AI-based DSS for preventive conservation of museum collections in historic buildings. J. Archaeol. Sci. Rep. 2021, 35, 102735. [Google Scholar] [CrossRef]
- Li, D.-C.; Lin, L.-S.; Peng, L.-J. Improving learning accuracy by using synthetic samples for small datasets with non-linear attribute dependency. Decis. Support Syst. 2014, 59, 286–295. [Google Scholar] [CrossRef]
- Agarwal, P.; Gao, B.; Huo, S.; Reddy, P.; Dechu, S.; Obeidi, Y.; Muthusamy, V.; Isahagian, V.; Carbajales, S. A Process-Aware Decision Support System for Business Processes. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, 14 August 2022; pp. 2673–2681. [Google Scholar]
- Jabbari, M.; Sheikh, S.; Rabiee, M.; Oztekin, A. A collaborative decision support system for multi-criteria automatic clustering. Decis. Support Syst. 2022, 153, 113671. [Google Scholar] [CrossRef]
- Piri, S.; Delen, D.; Liu, T. A synthetic informative minority over-sampling (SIMO) algorithm leveraging support vector machine to enhance learning from imbalanced datasets. Decis. Support Syst. 2018, 106, 15–29. [Google Scholar] [CrossRef]
- Forootan, M.M.; Larki, I.; Zahedi, R.; Ahmadi, A. Machine learning and deep learning in energy systems: A review. Sustainability 2022, 14, 4832. [Google Scholar] [CrossRef]
- Jha, B.K.; Pande, S. Time series forecasting model for supermarket sales using FB-prophet. In Proceedings of the 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, 8–10 April 2021; pp. 547–554. [Google Scholar]
- Saiktishna, C.; Sumanth, N.S.V.; Rao, M.M.S.; Thangakumar, J. Historical Analysis and Time Series Forecasting of Stock Market using FB Prophet. In Proceedings of the 2022 6th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 25–27 May 2022; pp. 1846–1851. [Google Scholar]
- Schafer, J.B.; Frankowski, D.; Herlocker, J.; Sen, S. Collaborative filtering recommender systems. In The Adaptive Web: Methods and Strategies of Web Personalization; Springer: Berlin/Heidelberg, Germany, 2007; pp. 291–324. [Google Scholar]
- Deshpande, M.; Karypis, G. Item-based top-n recommendation algorithms. ACM Trans. Inf. Syst. 2004, 22, 143–177. [Google Scholar] [CrossRef]
- Gong, F.; Han, N.; Li, D.; Tian, S. Trend analysis of building power consumption based on prophet algorithm. In Proceedings of the 2020 Asia Energy and Electrical Engineering Symposium (AEEES), Chengdu, China, 29–31 May 2020; pp. 1002–1006. [Google Scholar]
- Pearl, J. The limitations of opaque learning machines. Possible Minds 2019, 25, 13–19. [Google Scholar]
- D Macredie, R.; Mijinyawa, K. A theory-grounded framework of Open Source Software adoption in SMEs. Eur. J. Inf. Syst. 2011, 20, 237–250. [Google Scholar] [CrossRef]
- Carvalho, T.P.; Soares, F.A.; Vita, R.; Francisco, R.d.P.; Basto, J.P.; Alcalá, S.G. A systematic literature review of machine learning methods applied to predictive maintenance. Comput. Ind. Eng. 2019, 137, 106024. [Google Scholar] [CrossRef]
- Paolanti, M.; Romeo, L.; Felicetti, A.; Mancini, A.; Frontoni, E.; Loncarski, J. Machine Learning approach for Predictive Maintenance in Industry 4.0. In Proceedings of the 2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), Oulu, Finland, 2–4 July 2018; pp. 1–6. [Google Scholar]
- Wu, S.-j.; Gebraeel, N.; Lawley, M.A.; Yih, Y. A neural network integrated decision support system for condition-based optimal predictive maintenance policy. IEEE Trans. Syst. Man Cybern. -Part A Syst. Hum. 2007, 37, 226–236. [Google Scholar] [CrossRef]
- Kellner, D.; Lowin, M.; von Zahn, M.; Chen, J. Towards designing a user-centric decision support system for predictive maintenance in SMEs. INFORMATIK 2021 2021, 1255–1260. [Google Scholar] [CrossRef]
- Carnero, M.C. Selection of diagnostic techniques and instrumentation in a predictive maintenance program. A case study. Decis. Support Syst. 2005, 38, 539–555. [Google Scholar] [CrossRef]
- Susto, G.A.; Schirru, A.; Pampuri, S.; Pagano, D.; McLoone, S.; Beghi, A. A predictive maintenance system for integral type faults based on support vector machines: An application to ion implantation. In Proceedings of the 2013 IEEE International Conference on Automation Science and Engineering (CASE), Madison, WI, USA, 17–20 August 2013; pp. 195–200. [Google Scholar]
- Chaudhuri, A. Predictive maintenance for industrial iot of vehicle fleets using hierarchical modified fuzzy support vector machine. arXiv 2018, arXiv:1806.09612. [Google Scholar]
- Yoo, J.-H.; Park, Y.-K.; Han, S.-S. Predictive maintenance system for wafer transport robot using k-means algorithm and neural network model. Electronics 2022, 11, 1324. [Google Scholar] [CrossRef]
- Arena, S.; Florian, E.; Zennaro, I.; Orrù, P.F.; Sgarbossa, F. A novel decision support system for managing predictive maintenance strategies based on machine learning approaches. Saf. Sci. 2022, 146, 105529. [Google Scholar] [CrossRef]
- Di Nardo, M.; Murino, T.; Osteria, G.; Santillo, L.C. A New Hybrid Dynamic FMECA with Decision-Making Methodology: A Case Study in An Agri-Food Company. Appl. Syst. Innov. 2022, 5, 45. [Google Scholar] [CrossRef]
- Nardo, M.; Converso, G.; Castagna, F.; Murino, T. Development and implementation of an algorithm for preventive machine maintenance. Eng. Solid Mech. 2021, 9, 347–362. [Google Scholar] [CrossRef]
- Irsa, W.; Dalaqmeh, N. Impact of Additive Manufacturing on the Strategic Alignment of Business Processes in the Logistics Industry in Europe. ENTRENOVA-ENTerprise REsearch InNOVAtion 2022, 8, 188–199. [Google Scholar]
Savings Area | Savings |
---|---|
Return on investment (ROI) | 10 times |
Reduction in maintenance costs | 25–30% |
Elimination of breakdowns | 70–75% |
Reduction in downtime | 35–45% |
Increase in production | 20–25% |
Variable | Description of the Variable | Format | Modality of (Nominal) Variables |
---|---|---|---|
Location | Location of the device | Numeric | |
Device | Device number id | Numeric | |
Energy | Energy consumption of the device | Numeric | |
Temperature | The temperature of the device | Numeric | |
Humidity | The humidity of the device | Numeric | |
Region | Region of the device | Nominal | South, Central, West, East |
Age | Device age | Numeric | |
Cost | The average cost of maintenance for the device | Numeric | Home Office, Corporate, Consumer… |
Warnings | Detected warnings on the device | Numeric |
no | ds | Energy | Temperature | Humidity | Warnings |
---|---|---|---|---|---|
<int> | <date> | <int> | <int> | <int> | <dbl> |
1 | 11 February 2022 | 32.5 | 13 | 67.6 | 0 |
2 | 12 February 2022 | 16.9 | 10.4 | 70.2 | 0 |
3 | 13 February 2022 | 14.3 | 7.8 | 78 | 0 |
4 | 14 February 2022 | 13 | 7.8 | 67.6 | 0 |
5 | 15 February 2022 | 24.7 | 5.2 | 76.7 | 0 |
6 | 16 February 2022 | 32.5 | 13 | 58.5 | 0 |
7 | 17 February 2022 | 36.4 | 7.8 | 67.6 | 1 |
8 | 18 February 2022 | 16.9 | 2.6 | 59.8 | 0 |
9 | 19 February 2022 | 36.4 | 6.5 | 63.7 | 0 |
10 | 20 February 2022 | 26 | 6.5 | 65 | 0 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Pejić Bach, M.; Topalović, A.; Krstić, Ž.; Ivec, A. Predictive Maintenance in Industry 4.0 for the SMEs: A Decision Support System Case Study Using Open-Source Software. Designs 2023, 7, 98. https://doi.org/10.3390/designs7040098
Pejić Bach M, Topalović A, Krstić Ž, Ivec A. Predictive Maintenance in Industry 4.0 for the SMEs: A Decision Support System Case Study Using Open-Source Software. Designs. 2023; 7(4):98. https://doi.org/10.3390/designs7040098
Chicago/Turabian StylePejić Bach, Mirjana, Amir Topalović, Živko Krstić, and Arian Ivec. 2023. "Predictive Maintenance in Industry 4.0 for the SMEs: A Decision Support System Case Study Using Open-Source Software" Designs 7, no. 4: 98. https://doi.org/10.3390/designs7040098