Abstract
The application of Artificial Intelligence (AI) approaches in industrial maintenance for fault detection and prediction has gained much attention from scholars and practitioners. This survey systematically assesses and classifies the state-of-the-art algorithms applied to data-driven maintenance in recent literature. The taxonomy provides a so far not existing overview and decision aid for research and practice regarding suitable AI approaches for each maintenance application. Moreover, we consider trends and further research demand in this area. Finally, a newly developed holistic maintenance framework contributes to a practice-oriented implementation of AI and considers crucial managerial aspects of an efficient maintenance system.
- [1] . 2018. Distinct bearing faults detection in induction motor by a hybrid optimized SWPT and aiNet-DAG SVM. IEEE Trans. Energy Convers. 33, 4 (2018), 1692–1699. Google ScholarCross Ref
- [2] . 2002. Tool wear monitoring using genetically-generated fuzzy knowledge bases. Eng. Appl. Artif. Intell. 15, 3–4 (2002), 303–314. Google ScholarCross Ref
- [3] . 2018. Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process. Int. J. Adv. Manuf. Technol. 98, 9–12 (October 2018), 3217–3227. http://10.0.3.239/s00170-018-2420-0Google ScholarCross Ref
- [4] . 2012. An investigation on gearbox fault detection using vibration analysis techniques: A review. Aust. J. Mech. Eng. 10, 2 (December 2012), 169–183. http://10.0.27.246/M11-830.2012.10.2Google ScholarCross Ref
- [5] . 2022. Degradation stage classification via interpretable feature learning. J. Manuf. Syst. 62, (February 2022), 972–983. Google ScholarCross Ref
- [6] . 2021. What is MLOps? BT - Beginning MLOps with MLFlow: Deploy Models in AWS SageMaker, Google Cloud, and Microsoft Azure. In Sridhar Alla and Suman Kalyan Adari (Eds.). Apress, Berkeley, CA, 79–124. Google ScholarCross Ref
- [7] . 2010. Introduction to Machine Learning (2nd ed.). MIT Press, Cambridge. Google ScholarCross Ref
- [8] . 2020. A review of artificial intelligence methods for condition monitoring and fault diagnosis of rolling element bearings for induction motor. Shock Vib. 2020, Cm (2020). Google ScholarCross Ref
- [9] . 2020. Uncertainty quantification in deep convolutional neural network diagnostics of journal bearings with ovalization fault. Mech. Mach. Theory 149, (2020). Google ScholarCross Ref
- [10] . 2009. A brief status on condition monitoring and fault diagnosis in wind energy conversion systems. Renew. Sustain. Energy Rev. 13, 9 (2009), 2629–2636. Google ScholarCross Ref
- [11] . 2019. PriMa: A prescriptive maintenance model for cyber-physical production systems. Int. J. Comput. Integr. Manuf. 32, 4–5 (2019), 482–503. Google ScholarCross Ref
- [12] . 2020. A relative entropy based feature selection framework for asset data in predictive maintenance. Comput. Ind. Eng. 145 (2020), 106536. Google ScholarDigital Library
- [13] . 2003. Application of AI tools in fault diagnosis of electrical machines and drives—An overview. IEEE Trans. Energy Convers. 18, 2 (2003), 245. http://10.0.4.85/TEC.2003.811739Google ScholarCross Ref
- [14] . 2015. Combined intelligent methods based on wireless sensor networks for condition monitoring and fault diagnosis. J. Intell. Manuf. 26, 4 (August 2015), 717–729. http://10.0.3.239/s10845-013-0829-8Google ScholarDigital Library
- [15] . 2021. Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time. Expert Syst. Appl. 173, (January 2021), 114598. Google ScholarDigital Library
- [16] . 2021. Friction stir welding tool condition monitoring using vibration signals and random forest algorithm - A machine learning approach. Mater. Today Proc. 46, (2021), 1174–1180. Google ScholarCross Ref
- [17] . 2002. Tool condition monitoring using artificial intelligence methods. Eng. Appl. Artif. Intell. 15, 1 (February 2002), 73. http://10.0.3.248/S0952-1976(02)00004-0Google ScholarCross Ref
- [18] . 2021. A deep learning model for predictive maintenance in cyber-physical production systems using LSTM autoencoders. Sensors (Switzerland) 21, 3 (2021), 1–14. Google ScholarCross Ref
- [19] . 2020. A survey on IoT big data: Current status, 13 V's challenges, and future directions. ACM Comput. Surv. 53, 6 (2020). Google ScholarDigital Library
- [20] . 2021. Generative adversarial networks based remaining useful life estimation for IIoT. Comput. Electr. Eng. 92, June (2021), 107195. Google ScholarCross Ref
- [21] . 2009. Machine ensemble approach for simultaneous detection of transient and gradual abnormalities in end milling using multisensor fusion. J. Mater. Process. Technol. 209, 10 (2009), 4728–4738. Google ScholarCross Ref
- [22] . 2020. Smart maintenance: An empirically grounded conceptualization. Int. J. Prod. Econ. 223, August 2019 (2020), 107534. Google ScholarCross Ref
- [23] . 2020. Deep digital twins for detection, diagnostics and prognostics. Mech. Syst. Signal Process. 140, (2020), 106612. Google ScholarCross Ref
- [24] . 2019. Decision making in predictive maintenance: Literature review and research agenda for industry 4.0. IFAC-PapersOnLine 52, 13 (2019), 607–612. Google ScholarCross Ref
- [25] . 2002. AI-based condition monitoring of the drilling process. J. Mater. Process. Technol. 124, 3 (June 2002), 305. http://10.0.3.248/S0924-0136(02)00201-7Google ScholarCross Ref
- [26] . 2018. The link between industry 4.0 and lean manufacturing: Mapping current research and establishing a research agenda. Int. J. Prod. Res. 56, 8 (2018), 2924–2940. Google ScholarCross Ref
- [27] . 2022. Contrastive sensor transformer for predictive maintenance of industrial assets. ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc. 2022-May, (2022), 3558–3562. Google ScholarCross Ref
- [28] . 2018. Machine learning approach based on fractal analysis for optimal tool life exploitation in CFRP composite drilling for aeronautical assembly. CIRP Ann. 67, 1 (2018), 483–486. Google ScholarCross Ref
- [29] . 2020. The experimental application of popular machine learning algorithms on predictive maintenance and the design of IIoT based condition monitoring system. Comput. Ind. Eng. 151, (2020), 106948. Google ScholarCross Ref
- [30] . 2019. A systematic literature review of machine learning methods applied to predictive maintenance. Comput. Ind. Eng. 137, (November 2019). http://10.0.3.248/j.cie.2019.106024Google ScholarCross Ref
- [31] . 2011. LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 3 (2011). Google ScholarDigital Library
- [32] . 2021. Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images. Meas. J. Int. Meas. Confed. 176, (January 2021), 109196. Google ScholarCross Ref
- [33] . 2019. Predictive maintenance with sensor data analytics on a Raspberry Pi-based experimental platform. Sensors. http://10.0.13.62/s19183884Google ScholarCross Ref
- [34] . 2020. Machine learning in predictive maintenance towards sustainable smart manufacturing in industry 4.0. Sustain. 12, 19 (2020). Google ScholarCross Ref
- [35] . 2017. Study of spindle power data with neural network for predicting real-time tool wear/breakage during inconel drilling. J. Manuf. Syst. 43, (2017), 287–295. Google ScholarCross Ref
- [36] . 2017. Physics-based integrated vehicle health management system for predicting the remaining useful life of an aircraft planetary gear transmission. Int. J. Struct. Integr. 8, 4 (2017), 484–495. Google ScholarCross Ref
- [37] . 2020. Machine learning and reasoning for predictive maintenance in industry 4.0: Current status and challenges. Comput. Ind. 123, (2020), 103298. Google ScholarCross Ref
- [38] . 2020. A self-evolving mutually-operative recurrent network-based model for online tool condition monitoring in delay scenario. Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. (2020), 2775–2783. Google ScholarDigital Library
- [39] . 2012. Smart manufacturing, manufacturing intelligence and demand-dynamic performance. Comput. Chem. Eng. 47, (2012), 145–156. Google ScholarCross Ref
- [40] . 2020. Journal bearing seizure degradation assessment and remaining useful life prediction based on long short-term memory neural network. Meas. J. Int. Meas. Confed. 166, (2020), Google ScholarCross Ref
- [41] . 2022. Machine learning approach in non-intrusive monitoring of tool wear evolution in massive CFRP automatic drilling processes in the aircraft industry. J. Manuf. Syst. 65, (2022).Google ScholarCross Ref
- [42] . 2009. Review of prognostic problem in condition-based maintenance. 2009 Eur. Control Conf. (2009), 1587–1592. Google ScholarCross Ref
- [43] . 2022. Machine learning and deep learning based methods toward industry 4.0 predictive maintenance in induction motors: Α state of the art survey. J. Ind. Eng. Manag. 15, 1 (2022), 31–57. Google ScholarCross Ref
- [44] . 1999. Signal understanding and tool condition monitoring. Eng. Appl. Artif. Intell. 12, 5 (1999), 585–597. Google ScholarCross Ref
- [45] . 2015. Towards definitions for release engineering and DevOps. Proc. - 3rd Int. Work. Release Eng. RELENG 2015 (2015), 3. Google ScholarDigital Library
- [46] . 2011. Evaluation of expert system for condition monitoring of a single point cutting tool using principle component analysis and decision tree algorithm. Expert Syst. Appl. 38, 4 (2011), 4450–4459. Google ScholarDigital Library
- [47] . 2019. Prognosis of a wind turbine gearbox bearing using supervised machine learning. Sensors (14248220) 19, 14 (July 2019), 3092. http://10.0.13.62/s19143092Google Scholar
- [48] . 2018. Prognosis of bearing acoustic emission signals using supervised machine learning. IEEE Trans. Ind. Electron. 65, 7 (July 2018), 5864–5871. http://10.0.4.85/TIE.2017.2767551Google ScholarCross Ref
- [49] . 2005. Infotronic technologies for e-maintenance regarding the cost aspects. IFAC. Google ScholarCross Ref
- [50] . 2018. How research in production and operations management may evolve in the era of big data. Prod. Oper. Manag. 27, 9 (2018), 1670–1684. Google ScholarCross Ref
- [51] . 2022. Remaining useful life prediction and challenges: A literature review on the use of machine learning methods. J. Manuf. Syst. 63, (March 2022), 550–562. Google ScholarCross Ref
- [52] . 2022. Using supervised and one-class automated machine learning for predictive maintenance. Appl. Soft Comput. 131, (November 2022). Google ScholarDigital Library
- [53] . 2021. Prediction of Maintenance Equipment Failures Using Automated Machine Learning BT - Intelligent Data Engineering and Automated Learning – IDEAL 2021. Springer International Publishing, Cham, 259–267.Google Scholar
- [54] . 2015. Efficient and Robust Automated Machine Learning. (2015). Retrieved from https://papers.neurips.cc/paper/2015/hash/11d0e6287202fced83f79975ec59a3a6-Abstract.htmlGoogle Scholar
- [55] . 2019. Hyperparameter optimization. In Automated Machine Learning: Methods, Systems, Challenges, Challenges. Springer, Cham, 3–33. Google ScholarCross Ref
- [56] . 2020. Conducting Research Literature Reviews: From the Internet to Paper (5th ed.). Sage Publications, Los Angeles, CA.Google Scholar
- [57] . 2020. Potential, challenges and future directions for deep learning in prognostics and health management applications. Eng. Appl. Artif. Intell. 92, (May 2020), 103678. Google ScholarCross Ref
- [58] . 2020. Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review. Mech. Syst. Signal Process. 144, (2020), 106908. Google ScholarCross Ref
- [59] . 2021. A hybrid of FEM simulations and generative adversarial networks to classify faults in rotor-bearing systems. ISA Trans. 108, (2021), 356–366. Google ScholarCross Ref
- [60] . 2015. Model development based on evolutionary framework for condition monitoring of a lathe machine. Meas. J. Int. Meas. Confed. 73, (2015), 95–110. Google ScholarCross Ref
- [61] . 2022. Towards big industrial data mining through explainable automated machine learning. Int. J. Adv. Manuf. Technol. 120, 1–2 (2022), 1169–1188. Google ScholarCross Ref
- [62] . 2020. DCNN for condition monitoring and fault detection in rotating machines and its contribution to the understanding of machine nature. Heliyon 6, 2 (2020), e03395. Google ScholarCross Ref
- [63] . 2018. Beyond the hype: PdM 4.0 delivers results. Predict. Maint. 4.0 (September 2018). https://www.pwc.de/de/industrielle-produktion/pwc-predictive-maintenance-4-0.pdfGoogle Scholar
- [64] . 2022. PredMaX: Predictive maintenance with explainable deep convolutional autoencoders. Adv. Eng. Informatics 54, (2022). Google ScholarDigital Library
- [65] . 2020. Building Machine Learning Pipelines. O'Reilly Media.Google Scholar
- [66] . 2021. Research on tool wear prediction based on temperature signals and deep learning. Wear 478–479 (2021), 203902. Google ScholarCross Ref
- [67] . 2018. Deep learning for fault detection in wind turbines. Renew. Sustain. Energy Rev. 98, (December 2018), 189–198. http://10.0.3.248/j.rser.2018.09.012Google ScholarCross Ref
- [68] . 2020. A general anomaly detection framework for fleet-based condition monitoring of machines. Mech. Syst. Signal Process. 139, (May 2020). http://10.0.3.248/j.ymssp.2019.106585Google ScholarCross Ref
- [69] . 2019. Exploring blockchain implementation in the supply chain: Learning from pioneers and RFID research. Int. J. Oper. Prod. Manag. 39, 6 (2019), 829–859. Google ScholarCross Ref
- [70] . 2020. A new online approach for classification of pumps vibration patterns based on intelligent IoT system. Meas. J. Int. Meas. Confed. 151, (2020), 107138. Google ScholarCross Ref
- [71] . 2020. Mechanical fault diagnosis and prediction in IoT based on multi-source sensing data fusion. Simul. Model. Pract. Theory 102. Google ScholarCross Ref
- [72] . 2021. Diagnosis of rotating machine unbalance using machine learning algorithms on vibration orbital features. JVC/Journal Vib. Control 27, 3–4 (2021), 468–476. Google ScholarCross Ref
- [73] . 2021. Feature-based performance of SVM and KNN classifiers for diagnosis of rolling element bearing faults. Vibroengineering Procedia 39, (2021), 36–42. Google ScholarCross Ref
- [74] . 2015. Thermal image based fault diagnosis for rotating machinery. Infrared Phys. Technol. 73, (2015), 78–87. Google ScholarCross Ref
- [75] . 2016. Convolutional neural network based fault detection for rotating machinery. J. Sound Vib. 377, (2016), 331–345. Google ScholarCross Ref
- [76] . 2005. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech. Syst. Signal Process. 20, 7 (2005), 1483–1510. Google ScholarCross Ref
- [77] . 2010. Application of ANN, fuzzy logic and wavelet transform in machine fault diagnosis using vibration signal analysis. J. Qual. Maint. Eng. 16, 2 (2010), 190–213. Google ScholarCross Ref
- [78] . 2018. Sparse filtering with the generalized lp/lq norm and its applications to the condition monitoring of rotating machinery. Mech. Syst. Signal Process. 102, (March 2018), 198–213. http://10.0.3.248/j.ymssp.2017.09.018Google ScholarCross Ref
- [79] . 2017. Challenges and opportunities of digital information at the intersection of big data analytics and supply chain management. Int. J. Oper. Prod. Manag. 37, 1 (2017), 10–36. Google ScholarCross Ref
- [80] . 2014. A machine learning approach for the condition monitoring of rotating machinery. J. Mech. Sci. Technol. 28, 1 (January 2014), 61–71. http://10.0.3.239/s12206-013-1102-yGoogle ScholarCross Ref
- [81] . 2017. Estimation of remaining useful lifetime of piezoelectric transducers based on self-sensing. IEEE Trans. Reliab. 66, 3 (September 2017), 914–923. http://10.0.4.85/TR.2017.2710260Google ScholarCross Ref
- [82] . 2020. Sensitivity analysis of sensors in a hydraulic condition monitoring system using CNN models. Sensors (Switzerland) 20, 11 (2020), 1–19. Google ScholarCross Ref
- [83] . 2021. Data-driven wear monitoring for sliding bearings using acoustic emission signals and long short-term memory neural networks. Wear 476, (January 2021), 203616. Google ScholarCross Ref
- [84] . 2018. Application of audible sound signals for tool wear monitoring using machine learning techniques in end milling. Int. J. Adv. Manuf. Technol. 95, 9–12 (April 2018), 3797–3808. http://10.0.3.239/s00170-017-1460-1Google ScholarCross Ref
- [85] . 2022. Machine Learning Operations (MLOps): Overview, Definition, and Architecture. (2022). http://arxiv.org/abs/2205.02302Google Scholar
- [86] . 2015. Development of predictive model for vibro-acoustic condition monitoring of lathe. J. Vibroengineering 17, 1 (2015), 229–242. http://search.ebscohost.com/login.aspx?direct=true&db=afh&AN=101028285&site=ehost-liveGoogle Scholar
- [87] . 2020. Latest developments in gear defect diagnosis and prognosis: A review. Meas. J. Int. Meas. Confed. 158, (2020), 107735. Google ScholarCross Ref
- [88] . 2013. Advancement and current status of wear debris analysis for machine condition monitoring: A review. Ind. Lubr. Tribol. 65, 1 (2013), 3–11. http://10.0.4.84/00368791311292756Google ScholarCross Ref
- [89] . 2001. A framework for managing maintenance using performance measurement systems. Int. J. Oper. Prod. Manag. 21, 1–2 (2001), 173–194. Google ScholarCross Ref
- [90] . 2015. LS-SVM based spectral clustering and regression for predicting maintenance of industrial machines. Eng. Appl. Artif. Intell. 37, (2015), 268–278. Google ScholarCross Ref
- [91] . 2006. Intelligent prognostics tools and e-maintenance. Comput. Ind. 57, (2006), 476–489. Google ScholarDigital Library
- [92] . 2021. Development of a speed invariant deep learning model with application to condition monitoring of rotating machinery. J. Intell. Manuf. 32, 2 (2021), 393–406. Google ScholarDigital Library
- [93] . 2018. Machinery health prognostics: A systematic review from data acquisition to RUL prediction. Mech. Syst. Signal Process. 104, (2018), 799–834. Google ScholarCross Ref
- [94] . 2013. Condition-based maintenance systems: Application at a German sea port. Int. J. Ind. Eng. 20, 1–2 (2013), 2–11.Google Scholar
- [95] . 2022. A novel prediction network for remaining useful life of rotating machinery. Int. J. Adv. Manuf. Technol. (2022). Google ScholarCross Ref
- [96] . 2020. A two-stage approach for predicting the remaining useful life of tools using bidirectional long short-term memory. Meas. J. Int. Meas. Confed. 164, (January 2020), 108029. Google ScholarCross Ref
- [97] . 2020. A semi-supervised support vector data description-based fault detection method for rolling element bearings based on cyclic spectral analysis. Mech. Syst. Signal Process. 140, (June 2020). http://10.0.3.248/j.ymssp.2020.106682Google ScholarCross Ref
- [98] . 2020. Production planning and scheduling in multi-factory production networks: A systematic literature review. Int. J. Prod. Res. (2020), 1–27. Google ScholarCross Ref
- [99] . 2016. Condition monitoring of face milling tool using K-star algorithm and histogram features of vibration signal. Eng. Sci. Technol. an Int. J. 19, 3 (2016), 1543–1551. Google ScholarCross Ref
- [100] . 2020. Predicting remaining useful life of rolling bearings based on deep feature representation and transfer learning. IEEE Trans. Instrum. Meas. 69, 4 (2020), 1594–1608. Google ScholarCross Ref
- [101] . 2022. MLOps: A guide to its adoption in the context of responsible AI. Proc. - Work. Softw. Eng. Responsible AI, SE4RAI 2022 (2022), 45–49. Google ScholarDigital Library
- [102] . 2021. Condition-based monitoring in variable machine running conditions using low-level knowledge transfer with DNN. IEEE Trans. Autom. Sci. Eng. 18, 4 (2021), 1983–1997. Google ScholarCross Ref
- [103] . 2018. Blockchains for business process management - Challenges and opportunities. ACM Trans. Manag. Inf. Syst. 9, 1 (February 2018). Google ScholarDigital Library
- [104] . 2018. Blockchain and the internet of things in the industrial sector. IT Prof. 20, 3 (2018), 15–18. Google ScholarDigital Library
- [105] . 2021. Development of tool condition monitoring system in end milling process using wavelet features and Hoelder's exponent with machine learning algorithms. Meas. J. Int. Meas. Confed. 173, (2021), 108671. Google ScholarCross Ref
- [106] . 2014. Support vector machine and K-nearest neighbour for unbalanced fault detection. J. Qual. Maint. Eng. 20, 1 (2014), 65–75. Google ScholarCross Ref
- [107] . 2021. Condition monitoring and intelligent diagnosis of rolling element bearings under constant/variable load and speed conditions. Mech. Syst. Signal Process. 149, Cm (2021), 1–36. Google ScholarCross Ref
- [108] . 2010. Empirical analysis of maintenance performance measurement in Belgian industries. Int. J. Prod. Res. 48, 20 (2010), 5905–5924. Google ScholarCross Ref
- [109] . 2020. Induction motor bearing faults. IEEE Trans. Instrum. Meas. 69, 5 (2020), 1908–1919. Google ScholarCross Ref
- [110] . 2018. PriMa-X: A reference model for realizing prescriptive maintenance and assessing its maturity enhanced by machine learning. Procedia CIRP 72, (2018), 1039–1044. Google ScholarCross Ref
- [111] . 2021. One-shot learning for acoustic diagnosis of industrial machines. Expert Syst. Appl. 178, (March 2021), 114984. Google ScholarCross Ref
- [112] . 2014. Tool condition monitoring using K-star algorithm. Expert Syst. Appl. 41, 6 (2014), 2638–2643. Google ScholarDigital Library
- [113] . 2018. Prediction of flow blockages and impending cavitation in centrifugal pumps using Support Vector Machine (SVM) algorithms based on vibration measurements. Meas. 130, (December 2018), 44–56. http://10.0.3.248/j.measurement.2018.07.092Google ScholarCross Ref
- [114] . 2021. VisioRed: A visualisation tool for interpretable predictive maintenance. IJCAI Int. Jt. Conf. Artif. Intell. (2021), 5004–5007. Google ScholarCross Ref
- [115] . 2018. Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things (2nd ed.). John Wiley and Sons Ltd, Hoboken, NJ. Google ScholarCross Ref
- [116] . 2021. Deep learning for machine health prognostics using Kernel-based feature transformation. J. Intell. Manuf. Ml (2021). Google ScholarDigital Library
- [117] . 2018. A survey on deep learning: Algorithms, techniques, and applications. ACM Comput. Surv. 51, 5 (September 2018). Google ScholarDigital Library
- [118] . 2012. Condition based maintenance: A survey. J. Qual. Maint. Eng. 18, 4 (2012), 384–400. Google ScholarCross Ref
- [119] . 2019. Metacognitive learning approach for online tool condition monitoring. J. Intell. Manuf. 30, 4 (2019), 1717–1737. http://10.0.3.239/s10845-017-1348-9Google ScholarDigital Library
- [120] . 2022. AutoML loss landscapes. ACM Trans. Evol. Learn. Optim. 2, 3 (2022), 1–30. Google ScholarDigital Library
- [121] . 2016. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings. Tribol. Int. 96, (2016), 289–306. Google ScholarCross Ref
- [122] . 2016. Make Your Own Neural Network. CreateSpace Independent Publishing Platform.Google ScholarDigital Library
- [123] . 2023. From knowledge-based to big data analytic model: A novel IoT and machine learning based decision support system for predictive maintenance in Industry 4.0. J. Intell. Manuf. 34, 1 (2023), 107–121. Google ScholarDigital Library
- [124] . 2016. Continuous maintenance and the future – Foundations and technological challenges. CIRP Ann. - Manuf. Technol. 65, 2 (2016), 667–688. Google ScholarCross Ref
- [125] . 2020. A predictive model for the maintenance of industrial machinery in the context of industry 4.0. Eng. Appl. Artif. Intell. 87 (2020), 103289. Google ScholarDigital Library
- [126] . 2010. Comparison of decision tree-fuzzy and rough set-fuzzy methods for fault categorization of mono-block centrifugal pump. Mech. Syst. Signal Process. 24, 6 (August 2010), 1887–1906. http://10.0.3.248/j.ymssp.2010.01.008Google ScholarCross Ref
- [127] . 2017. Conditional inference trees for knowledge extraction from motor health condition data. Eng. Appl. Artif. Intell. 62, (June 2017), 26–37. http://10.0.3.248/j.engappai.2017.03.008Google ScholarDigital Library
- [128] . 2021. Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions. SN Comput. Sci. 2, 6 (2021), 1–20. Google ScholarDigital Library
- [129] . 2014. Performance evaluation for fleet-based and unit-based prognostic methods. Second Eur. Conf. Progn. Heal. Manag. Soc. (2014), 1–12.Google Scholar
- [130] . 2020. Supervised machine learning for knowledge-based analysis of maintenance impact on profitability. IFAC-PapersOnLine 53, Ml (2020), 10651–10657. Google ScholarCross Ref
- [131] . 2018. Detection of wear parameters using existing sensors in the machines environment to reach higher machine precision. J. Mach. Eng. 18, 2 (2018), 85–96. Google ScholarCross Ref
- [132] . 2021. A survey of machine-learning techniques for condition monitoring and predictive maintenance of bearings in grinding machines. Comput. Ind. 125, (2021), 103380. Google ScholarCross Ref
- [133] . 2020. Review of tool condition monitoring in machining and opportunities for deep learning. Int. J. Adv. Manuf. Technol. 109, 3–4 (2020), 953–974. Google ScholarCross Ref
- [134] . 2022. Methodology for data-driven predictive maintenance models design, development and implementation on manufacturing guided by domain knowledge. Int. J. Comput. Integr. Manuf. (2022), 1–25. Google ScholarCross Ref
- [135] . 2022. Data-driven failure prediction and RUL estimation of mechanical components using accumulative artificial neural networks. Eng. Appl. Artif. Intell. 119, (2022). Google ScholarDigital Library
- [136] . 2019. Prediction of cutting tool wear during milling process using artificial intelligence techniques. Int. J. Comput. Integr. Manuf. 32, 2 (2019), 174–182. Google ScholarCross Ref
- [137] . 2022. The role of artificial intelligence in supply chain management: Mapping the territory. Int. J. Prod. Res. (2022). Google ScholarCross Ref
- [138] . 2022. A hybrid deep learning framework for intelligent predictive maintenance of cyber-physical systems. ACM Trans. Cyber-Physical Syst. 6, 2 (2022), 1–22. Google ScholarDigital Library
- [139] . 2017. Data-Driven Remaining Useful Life Prognosis Techniques: Stochastic Models, Methods and Applications. Springer Verlag, Berlin.Google ScholarCross Ref
- [140] . 2013. A review of flank wear prediction methods for tool condition monitoring in a turning process. Int. J. Adv. Manuf. Technol. 65, 1–4 (2013), 371–393. http://10.0.3.239/s00170-012-4177-1Google ScholarCross Ref
- [141] . 2011. Prognostic modelling options for remaining useful life estimation by industry. Mech. Syst. Signal Process. 25, (2011), 1803–1836. Google ScholarCross Ref
- [142] . 2021. Service computing for industry 4.0: State of the art, challenges, and research opportunities. ACM Comput. Surv. 54, 9 (2021). Google ScholarDigital Library
- [143] . 2018. Simulation-driven machine learning: Bearing fault classification. Mech. Syst. Signal Process. 99, (January 2018), 403–419. http://10.0.3.248/j.ymssp.2017.06.025Google ScholarCross Ref
- [144] . 2019. Health monitoring of bearing and gear faults by using a new health indicator extracted from current signals. Meas. J. Int. Meas. Confed. 141, (2019), 37–51. Google ScholarCross Ref
- [145] . 2019. Machine learning methods for wind turbine condition monitoring: A review. Renew. Energy an Int. J. 133, (April 2019), 620–635. http://10.0.3.248/j.renene.2018.10.047Google ScholarCross Ref
- [146] . 2022. Modeling and fault detection of brushless direct current motor by deep learning sensor data fusion. Sensors 22, 9 (2022), 1–17. Google ScholarCross Ref
- [147] . 2020. Anomalous sound detection based on machine activity detection. Eur. Signal Process. Conf. (2020), 269–273. Google ScholarCross Ref
- [148] . 2011. Effect of number of features on classification of roller bearing faults using SVM and PSVM. Expert Syst. Appl. 38, 4 (April 2011), 4088–4096. http://10.0.3.248/j.eswa.2010.09.072Google ScholarDigital Library
- [149] . 2022. Blockchain-based digital twins: Research trends, issues, and future challenges. ACM Comput. Surv. (2022). Google ScholarDigital Library
- [150] . 2019. A novel method for tool condition monitoring based on long short-term memory and hidden Markov model hybrid framework in high-speed milling Ti-6Al-4V. Int. J. Adv. Manuf. Technol. 105, 7/8 (December 2019), 3165–3182. http://10.0.3.239/s00170-019-04464-wGoogle ScholarCross Ref
- [151] . 2016. Conducting systematic literature review in operations management. Prod. Plan. Control 27, 5 (2016), 408–420. Google ScholarCross Ref
- [152] . 2021. A deep autoencoder-based convolution neural network framework for bearing fault classification in induction motors. Sensors 21, 24 (2021). Google ScholarCross Ref
- [153] . 2016. Sequential fuzzy clustering based dynamic fuzzy neural network for fault diagnosis and prognosis. Neurocomputing 196, (July 2016), 31–41. http://10.0.3.248/j.neucom.2016.02.036Google ScholarDigital Library
- [154] . 2012. Machine performance degradation assessment and remaining useful life prediction using proportional hazard model and support vector machine. Mech. Syst. Signal Process. 32, (October 2012), 320–330. http://10.0.3.248/j.ymssp.2012.02.015Google ScholarCross Ref
- [155] . 2003. Towards a methodology for developing evidence-informed management knowledge by means of systematic review. Br. J. Manag. 14, (2003), 207–222.Google ScholarCross Ref
- [156] . 2019. Application of spectral kurtosis and improved extreme learning machine for bearing fault classification. IEEE Trans. Instrum. Meas. 68, 11 (November 2019), 4222–4233. http://10.0.4.85/TIM.2018.2890329Google ScholarCross Ref
- [157] . 2019. A bearing data analysis based on kurtogram and deep learning sequence models. Meas. 145, (October 2019), 665–677. http://10.0.3.248/j.measurement.2019.05.039Google ScholarCross Ref
- [158] . 2021. Using deep learning to value free-form text data for predictive maintenance. Int. J. Prod. Res. 0, 0 (2021), 1–28. Google ScholarCross Ref
- [159] . 2020. Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks. Nucl. Eng. Technol. 52, 9 (2020), 1998–2008. Google ScholarCross Ref
- [160] . 2021. Tool life stage prediction in micro-milling from force signal analysis using machine learning methods. J. Manuf. Sci. Eng. Trans. ASME 143, 5 (2021), 1–7. Google ScholarCross Ref
- [161] . 2015. Maintenance strategy selection and its impact in maintenance function: A conceptual framework. Int. J. Oper. Prod. Manag. 35, 12 (2015), 1622–1661. Google ScholarCross Ref
- [162] . 2018. Engine gearbox fault diagnosis using machine learning approach. J. Qual. Maint. Eng. 24, 3 (July 2018), 345–357. http://10.0.4.84/JQME-11-2015-0058Google ScholarCross Ref
- [163] . 2019. A review on lubricant condition monitoring information analysis for maintenance decision support. Mech. Syst. Signal Process. 118, (March 2019), 108–132. http://10.0.3.248/j.ymssp.2018.08.039Google ScholarCross Ref
- [164] . 2019. Hybrid approach for remaining useful life prediction of ball bearings. Qual. Reliab. Eng. Int. 35, 7 (November 2019), 2494–2505. http://10.0.3.234/qre.2538Google ScholarCross Ref
- [165] . 2017. Virtual sensing for gearbox condition monitoring based on kernel factor analysis. Pet. Sci. 14, 3 (August 2017), 539–548. http://10.0.3.239/s12182-017-0163-4Google ScholarCross Ref
- [166] . 2017. Multisensory fusion based virtual tool wear sensing for ubiquitous manufacturing. Robot. Comput. Manuf. 45, (June 2017), 47–58. http://10.0.3.248/j.rcim.2016.05.010Google ScholarDigital Library
- [167] . 2012. CHMM for tool condition monitoring and remaining useful life prediction. International J. Adv. Manuf. Technol. 59, (2012), 463–471. Google ScholarCross Ref
- [168] , Ananya, . 2017. Virtualization and deep recognition for system fault classification. J. Manuf. Syst. 44, (April 2017), 310–316. Google ScholarCross Ref
- [169] . 2020. Transfer learning for enhanced machine fault diagnosis in manufacturing. CIRP Ann. 69, 1 (2020), 413–416. Google ScholarCross Ref
- [170] . 2020. Remaining useful life prediction using deep learning approaches: A review. Procedia Manuf. 49 (2020), 81–88. Google ScholarCross Ref
- [171] . 2020. Blockchain at the shop floor for maintenance. Proc. - 2020 Int. Conf. Cyber-Enabled Distrib. Comput. Knowl. Discov. CyberC. 2020 0, (2020), 15–22. Google ScholarCross Ref
- [172] . 2018. Cloud-based parallel machine learning for tool wear prediction. J. Manuf. Sci. Eng. 140, 4 (April 2018), 1–10. http://10.0.4.91/1.4038002Google ScholarCross Ref
- [173] . 2021. A joint classification-regression method for multi-stage remaining useful life prediction. J. Manuf. Syst. 58, PA (2021), 109–119. Google ScholarCross Ref
- [174] . 2017. Intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder. IET Sci. Meas. Technol. 11, 6 (September 2017), 687–695. http://10.0.4.25/iet-smt.2016.0423Google ScholarCross Ref
- [175] . 2007. Basis pursuit-based intelligent diagnosis of bearing faults. J. Qual. Maint. Eng. 13, 2 (2007), 152–162. Google ScholarCross Ref
- [176] . 2022. Integrating machine learning techniques into optimal maintenance scheduling. Comput. Chem. Eng. 166, (2022). Google ScholarCross Ref
- [177] . 2010. Evaluation of thermography image data for machine fault diagnosis. Nondestruct. Test. Eval. 25, 3 (September 2010), 231–247. http://10.0.4.56/10589750903473617Google ScholarCross Ref
- [178] . 2020. Towards developing an automated faults characterisation framework for rotating machines. Part 1: Rotor-Related Faults. Energies (2020). Google ScholarCross Ref
- [179] . 2021. An online transfer learning-based remaining useful life prediction method of ball bearings. Meas. J. Int. Meas. Confed. 176, (February 2021), 109201. Google ScholarCross Ref
- [180] . 2019. Machine learning based concept drift detection for predictive maintenance. Comput. Ind. Eng. 137, (August 2019), Google ScholarCross Ref
- [181] . 2021. Enabling predictive maintenance integrated production scheduling by operation-specific health prognostics with generative deep learning. J. Manuf. Syst. (January 2021). Google ScholarCross Ref
- [182] . 2019. A cost-sensitive deep belief network for imbalanced classification. IEEE Trans. Neural Networks Learn. Syst. 30, 1 (2019), 109–122. Google ScholarCross Ref
- [183] . 2022. Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism. Reliab. Eng. Syst. Saf. 221, December 2021 (2022), Google ScholarCross Ref
- [184] . 2019. Data-driven methods for predictive maintenance of industrial equipment: A survey. IEEE Syst. J. 13, 3 (2019), 2213–2227. Google ScholarCross Ref
- [185] . 2014. Application of an improved Levenberg-Marquardt back propagation neural network to gear fault level identification. J. Vibroengineering 16, 2 (March 2014), 855–868. http://search.ebscohost.com/login.aspx?direct=true&db=afh&AN=95382647&site=ehost-liveGoogle Scholar
- [186] . 2022. Cross-condition and cross-platform remaining useful life estimation via adversarial-based domain adaptation. Sci. Rep. 12, 1 (2022), 1–13. Google ScholarCross Ref
- [187] . 2020. Predictive maintenance in the Industry 4.0: A systematic literature review. Comput. Ind. Eng. 150, (August 2020), 106889. Google ScholarCross Ref
Index Terms
- Tackling Industrial Downtimes with Artificial Intelligence in Data-Driven Maintenance
Recommendations
A review of artificial intelligence methods for engineering prognostics and health management with implementation guidelines
AbstractThe past decade has witnessed the adoption of artificial intelligence (AI) in various applications. It is of no exception in the area of prognostics and health management (PHM) where the capacity of AI has been highlighted through numerous ...
Artificial intelligence
AbstractArtificial intelligence (AI) is the Science and Engineering domain concerned with the theory and practice of developing systems that exhibit the characteristics we associate with intelligence in human behavior. Starting with a brief history of ...
Hybrid Bionic Cognitive Architecture for Artificial General Intelligence Agents
AbstractThe article describes the author’s proposal on cognitive architecture for the development of a general-level artificial intelligent agent («strong» artificial intelligence). New principles for the development of such an architecture are proposed — ...
Comments