Machine Learning for Predictive and Prescriptive Analytics of Operational Data in Smart Manufacturing

Lepenioti, Katerina; Pertselakis, Minas; Bousdekis, Alexandros; Louca, Andreas; Lampathaki, Fenareti; Apostolou, Dimitris; Mentzas, Gregoris; Anastasiou, Stathis

doi:10.1007/978-3-030-49165-9_1

Cited by 35 publications

(24 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used the changes in natural frequencies based on time-frequency processing extracted from vibrating beams. Most recently, Lepenioti et al [ 76 ] implements a RNN for predictive analytic and a multi-objective RL method for prescriptive analytic. The proposed method was implemented for a PdM scenario in a steel-making company.…”

Section: Data-driven Pdmmentioning

confidence: 99%

A Survey on Data-Driven Predictive Maintenance for the Railway Industry

Davari

Veloso

Costa

et al. 2021

Sensors

View full text Add to dashboard Cite

In the last few years, many works have addressed Predictive Maintenance (PdM) by the use of Machine Learning (ML) and Deep Learning (DL) solutions, especially the latter. The monitoring and logging of industrial equipment events, like temporal behavior and fault events—anomaly detection in time-series—can be obtained from records generated by sensors installed in different parts of an industrial plant. However, such progress is incipient because we still have many challenges, and the performance of applications depends on the appropriate choice of the method. This article presents a survey of existing ML and DL techniques for handling PdM in the railway industry. This survey discusses the main approaches for this specific application within a taxonomy defined by the type of task, employed methods, metrics of evaluation, the specific equipment or process, and datasets. Lastly, we conclude and outline some suggestions for future research.

show abstract

Section: Data-driven Pdmmentioning

confidence: 99%

A Survey on Data-Driven Predictive Maintenance for the Railway Industry

Davari

Veloso

Costa

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…To build these parts there are 28 machines for lapping, milling, turning, sinking, wire cutting, turning and milling, laser marking, and round and flat grinding [17] [18]. The wide adoption of IoT devices, sensors and actuators in manufacturing environments has fostered an increasing research interest on real-time data analytics; however, event logs contain information regarding the whole factory cycle, either they have sensors installed or not, thus, having the credentials to move towards providing an all-around view of manufacturing operations on the shopfloor [19]. In this way, they may provide valuable information for planning and resource allocation [18].…”

Section: Application To a Manufacturing Business Processmentioning

confidence: 99%

Visual Analytics in Process Mining for Supporting Business Process Improvement

Kaouni

Theodoropoulou

Bousdekis

et al. 2021

Frontiers in Artificial Intelligence and Applications

Self Cite

View full text Add to dashboard Cite

The increasing amounts of data have affected conceptual modeling as a research field. In this context, process mining involves a set of techniques aimed at extracting a process schema from an event log generated during process execution. While automatic algorithms for process mining and analysis are needed to filter out irrelevant data and to produce preliminary results, visual inspection, domain knowledge, human judgment and creativity are needed for proper interpretation of the results. Moreover, a process discovery on an event log usually results in complicated process models not easily comprehensible by the business user. To this end, visual analytics has the potential to enhance process mining towards the direction of explainability, interpretability and trustworthiness in order to better support human decisions. In this paper we propose an approach for identifying bottlenecks in business processes by analyzing event logs and visualizing the results. In this way, we exploit visual analytics in the process mining context in order to provide explainable and interpretable analytics results for business processes without exposing to the user complex process models that are not easily comprehensible. The proposed approach was applied to a manufacturing business process and the results show that visual analytics in the context of process mining is capable of identifying bottlenecks and other performance-related issues and exposing them to the business user in an intuitive and non-intrusive way.

show abstract

“…Beyond that, our future work will be oriented towards the following directions: First, we will evaluate our proposed approach in the context of different business contexts having deployed predictive analytics systems that may process big data of various levels of volume, velocity, variety and veracity. We have already some preliminary results in predictive maintenance [70] and in logistics management [71]. Second, we will develop a knowledge-based mechanism in order to further enrich the prescriptive data analytics.…”

Section: Vι Future Research Directionsmentioning

confidence: 99%

Human-Augmented Prescriptive Analytics With Interactive Multi-Objective Reinforcement Learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

The rise of Artificial Intelligence (AI) enables enterprises to manage large amounts of data in order to derive predictions about future performance and to gain meaningful insights. In this context, descriptive and predictive analytics has gained a significant research attention; however, prescriptive analytics has just started to emerge as the next step towards increasing data analytics maturity and leading to optimized decision making ahead of time. Although machine learning for decision making has been identified as one of the most important applications of AI, up to now, prescriptive analytics is mainly addressed with domain-specific optimization models. On the other hand, existing literature lacks generalized prescriptive analytics models capable of being dynamically adapted according to the human preferences. Reinforcement Learning, as the third machine learning paradigm alongside supervised learning and unsupervised learning, has the potential to deal with the dynamic, uncertain and time-variant environments, the huge states space of sequential decision making processes, as well as the incomplete knowledge. In this paper, we propose a human-augmented prescriptive analytics approach using Interactive Multi-Objective Reinforcement Learning (IMORL) in order to cope with the complexity of real-life environments and the need for optimized human-machine collaborations. The decision making process is modelled in a generalized way in order to assure scalability and applicability in a wide range of problems and applications. We deployed the proposed approach in a stock market case study in order to evaluate the proactive trading decisions that will lead to the maximum return and the minimum risk that the user's experience and the available data can yield in combination.INDEX TERMS Big data, data analytics, human-augmented analytics, machine learning, prescriptive analytics, reinforcement learning.

show abstract

Machine Learning for Predictive and Prescriptive Analytics of Operational Data in Smart Manufacturing

Cited by 35 publications

References 20 publications

A Survey on Data-Driven Predictive Maintenance for the Railway Industry

A Survey on Data-Driven Predictive Maintenance for the Railway Industry

Visual Analytics in Process Mining for Supporting Business Process Improvement

Human-Augmented Prescriptive Analytics With Interactive Multi-Objective Reinforcement Learning

Contact Info

Product

Resources

About