Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry

Theissler, Andreas; Pérez-Velázquez, Judith; Kettelgerdes, Marcel; Elger, Gordon

doi:10.1016/j.ress.2021.107864

Cited by 223 publications

(77 citation statements)

References 125 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chen et al [25] proposed a maintenance decision method considering performance degradation, which determined the optimal time to conduct maintenance activities through an online evaluation of maintenance costs. Theissler et al [26] proposed a maintenance strategy for automotive systems based on machine learning methods that could ensure product functional safety and control maintenance costs in the life cycle. Ayvaz et al [27] developed a datadriven predictive maintenance system for manufacturing production lines.…”

Section: Introductionmentioning

confidence: 99%

A Dynamic Maintenance Strategy for Multi-Component Systems Using a Genetic Algorithm

Shi¹,

Ma²,

Ma³

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

In multi-component systems, the components are dependent, rather than degenerating independently, leading to changes in maintenance schedules. In this situation, this study proposes a grouping dynamic maintenance strategy. Considering the structure of multi-component systems, the maintenance strategy is determined according to the importance of the components. The strategy can minimize the expected depreciation cost of the system and divide the system into optimal groups that meet economic requirements. First, multi-component models are grouped. Then, a failure probability model of multi-component systems is established. The maintenance parameters in each maintenance cycle are updated according to the failure probability of the components. Second, the component importance indicator is introduced into the grouping model, and the optimization model, which aimed at a maximum economic profit, is established. A genetic algorithm is used to solve the non-deterministic polynomial (NP)-complete problem in the optimization model, and the optimal grouping is obtained through the initial grouping determined by random allocation. An 11-component series and parallel system is used to illustrate the effectiveness of the proposed strategy, and the influence of the system structure and the parameters on the maintenance strategy is discussed.

show abstract

Section: Introductionmentioning

confidence: 99%

A Dynamic Maintenance Strategy for Multi-Component Systems Using a Genetic Algorithm

Shi¹,

Ma²,

Ma³

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

“…Further, due to the tremendous amount of data generated by sensors over time, machine learning models yield superior results at many tasks due to their capability to capture long-as well as short-term patterns in the data [12]. Thus, such models can outperform experts in certain time series tasks, enabling their application in various use cases, e.g., in predictive maintenance [8], [13], heartbeat anomaly detection [10], or texture recognition [14]. The research field of XAI for time series classification has become more popular since around 2019, a variety of valuable papers have been published in recent years (see Figure 1).…”

Section: Introductionmentioning

confidence: 99%

Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions

et al. 2022

Self Cite

View full text Add to dashboard Cite

Time series data is increasingly used in a wide range of fields, and it is often relied on in crucial applications and high-stakes decision-making. For instance, sensors generate time series data to recognize different types of anomalies through automatic decision-making systems. Typically, these systems are realized with machine learning models that achieve top-tier performance on time series classification tasks. Unfortunately, the logic behind their prediction is opaque and hard to understand from a human standpoint. Recently, we observed a consistent increase in the development of explanation methods for time series classification justifying the need to structure and review the field. In this work, we (a) present the first extensive literature review on Explainable AI (XAI) for time series classification, (b) categorize the research field through a taxonomy subdividing the methods into time points-based, subsequences-based and instance-based, and (c) identify open research directions research directions regarding the type of explanations and the evaluation of explanations and interpretability.

show abstract

“…The driver is part of the dynamic environment as well. So, PdM in vehicles needs to address additional challenges due to the dynamic environment the VF operates (Theissler et al, 2021), which results in changes in the vehicle's behavior over time. However, such changes should be considered along with their context; they may not correspond to failures and interestingly, non-changes may also denote anomalous behavior.…”

Section: Introductionmentioning

confidence: 99%

A context-aware unsupervised predictive maintenance solution for fleet management

Giannoulidis

Gounaris

2022

J Intell Inf Syst

View full text Add to dashboard Cite

We deal with the problem of predictive maintenance (PdM) in a vehicle fleet management setting following an unsupervised streaming anomaly detection approach. We investigate a variety of unsupervised methods for anomaly detection, such as proximity-based, hybrid (statistical and proximity-based) and transformers. The proposed methods can properly model the context in which each member of the fleet operates. In our case, the context is both crucial for effective anomaly detection and volatile, which calls for streaming solutions that take into account only the recent values. We propose two novel techniques, a 2-stage proximity-based one and context-aware transformers along with advanced thresholding. In addition, to allow for testing PdM techniques for vehicle fleets in a fair and reproducible manner, we build a new fleet-like benchmarking dataset based on an existing dataset of turbofan simulations. Our evaluation results show that our proposals reduce the maintenance costs compared to existing solutions.

show abstract

Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry

Cited by 223 publications

References 125 publications

A Dynamic Maintenance Strategy for Multi-Component Systems Using a Genetic Algorithm

A Dynamic Maintenance Strategy for Multi-Component Systems Using a Genetic Algorithm

Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions

A context-aware unsupervised predictive maintenance solution for fleet management

Contact Info

Product

Resources

About