We present a novel Explainable methodology for Condition Monitoring, relying on healthy data only. Since faults are rare events, we propose to focus on learning the probability distribution of healthy observations only, and detect Anomalies at runtime. This objective is achieved via the definition of probabilistic measures of deviation from nominality, which allow to detect and anticipate faults. The Bayesian perspective underpinning our approach allows us to perform Uncertainty Quantification to inform decisions. At the same time, we provide descriptive tools to enhance the interpretability of the results, supporting the deployment of the proposed strategy also in safety-critical applications. The methodology is validated experimentally on two use cases: a publicly available benchmark for Predictive Maintenance, and a real-world Helicopter Transmission dataset collected over multiple years. In both applications, the method achieves competitive detection performance with respect to state-of-the-art anomaly detection methods.
Figures & tables
Strategy
G
I
F
H
Ad-Hoc Indicators (e.g., Soo Lon Wah et al. [22] )
✗
✓
✗
✗
Multi-class Learning (e.g., Yessoufou and Zhu [31] )
✓
✗
✓
✗
Single-class Learning (e.g., Jung et al. [11] )
✓
✗
✓
✓
Table 1: Condition Monitoring (CM) Strategies and their typical Advantages ( G : General applicability; I : Interpretability; F : Flexibility; H : requiring a Healthy sample only).
Term
Definition
Failure
A window of consecutive samples in which the machinery failed.
Alert
A window of consecutive samples for which the detection algorithm raised a warning.
Validity Window
All observations within a given number of days ( w ) prior to a fault; depending on the observed data, gaps may be present.
True Positive ( TP )
Number of failure instances for which at least an alert was active in the related validity window.
False Negative ( FN )
Number of failure instances for which no alert was raised in the related validity window
False Positive ( FP )
Number of recorded days outside validity windows, for which at least one alert was active.
Table 2: Glossary of Definitions Relating to Failure Detection Metrics.
Figure 1: Illustrative example of Failure Detection-related concepts.
Figure 2: Predictive Inference for the Vibration Index of the Azure Train Dataset.
Figure 3: Predictive Inference Results for the Pressure (First Row), Rotate (Second Row), Vibration (Third Row), and Volt (Last Row) Indices of the Azure Test Dataset.
Train
Test
1 Day to Event
↑↓ 95% CIC
↑↓ 95% CIC
↑ Prec. [%]
↑ Rec. [%]
↑ F1 [%]
pressure
0.96±0.01
0.95±0.01
0.00
0.00
0.00
rotate
0.96±0.01
0.93±0.01
100.00
25.00
40.00
vibration
0.94±0.02
0.87±0.01
100.00
75.00
85.71
volt
0.95±0.02
0.96±0.01
0.00
0.00
0.00
Table 3: Train and Test Metrics for each Index of the Azure Dataset.
Figure 4: Anomaly Scores and Alerts on Pooled Indices of the Azure Dataset (Test Set).
Days to Event
Samples in Range
↑ Prec. [%]
↑ Rec. [%]
↑ F1 [%]
4-1
384
100.00
100.00
100.00
Table 4: Fault Detection Metrics for the Azure Test Dataset.
Variable
Details
[ Alphanumeric Identifier ]
Health Index, e.g., “ENHKUR”, “S1R”
Engine 1 Torque
Engine 2 Torque
MGB 1 Oil Temperature
MGB: Main Gearbox Bearing
MGB 2 Oil Temperature
Main Rotor Torque
Table 5: List of flight parameters in the datasets
Figure 5: Predictive Inference for the ENHKUR Health Index of First Helicopter on the Train (top), Validation (middle), and Test (bottom) Sets.
Train
Test
60 Days to Event
↑↓ 95% CIC
↑↓ 95% CIC
↑ Prec. [%]
↑ Rec. [%]
↑ F1 [%]
ENHKUR
0.96±0.01
0.94±0.03
100.00
100.00
100.00
ENHM6
0.96±0.02
0.94±0.03
0.00
0.00
0.00
ENHP2P
0.95±0.02
1.00±0.00
0.00
0.00
0.00
ENHSTD
0.98±0.01
0.99±0.01
0.00
0.00
0.00
Table 6: Train and Test Metrics for each Health Index of the First Helicopter.
Figure 6: CoCoAFusE Anomaly Scores and Alerts on Pooled Health Indices of the First Helicopter (Test Set).
Days to Event
Samples in Range
↑ Prec. [%]
↑ Rec. [%]
↑ F1 [%]
1
2
0.00
0.00
0.00
89-17
46
100.00
100.00
100.00
Table 7: Fault Detection Metrics for the First Helicopter (CoCoAFusE).
Days to Event
Samples in Range
↑ Prec. [%]
↑ Rec. [%]
↑ F1 [%]
89-1
48
100.00
100.00
100.00
Table 8: Fault Detection Metrics for the First Helicopter (from Leoni et al. [14] ).
Figure 7: Predictive Inference for the OREB1A Health Index of the Second Helicopter on the Train (top), Validation (middle), and Test (bottom) Sets.
Train
Test
60 Days to Event
↑↓ 95% CIC
↑↓ 95% CIC
↑ Prec. [%]
↑ Rec. [%]
↑ F1 [%]
BPEB1A
0.96±0.01
0.87±0.03
50.00
100.00
66.67
BPEB1B
0.98±0.01
0.86±0.03
0.00
0.00
0.00
FTEB1A
1.00±0.00
0.99±0.01
0.00
0.00
0.00
FTEB1B
0.98±0.01
0.97±0.01
0.00
0.00
0.00
Table 9: Train and Test Metrics for each Health Index of the Second Helicopter.
Days to Event
Samples in Range
↑ Prec. [%]
↑ Rec. [%]
↑ F1 [%]
89-4
68
100.00
100.00
100.00
Table 10: Fault Detection Metrics for the Second Helicopter (CoCoAFusE).
Days to Event
Samples in Range
↑ Prec. [%]
↑ Rec. [%]
↑ F1 [%]
70-4
49
50.00
100.00
66.67
89-71
19
100.00
100.00
100.00
Table 11: Fault Detection Metrics for the Second Helicopter (from Leoni et al. [14] ).
Figure 8: Test Anomaly Scores and Alerts on Pooled Indices of the Second Helicopter.
Figure 9: Explanatory Analysis on the ENHKUR Model for the First Helicopter.
Figure 10: Explanatory Analysis on the OREB1A Model for the Second Helicopter.
Operational anomaly detection in spacecraft telemetry typically requires labeled historical anomalies or extended warm-up periods. These requirements are rarely met in practice. We propose an unsupervised, deployment-ready framework that produces predictions from the second month of operation without any labels, prior fault knowledge, or mission-specific tuning. The approach combines incremental monthly retraining, statistical model selection, and adaptive Extreme Value Theory (EVT) thresholding for false alarm control. On the ESA Anomalies Dataset (ESA-AD), it achieves F0.5=0.700 on Mission1 and F0.5=0.698 on Mission2 under strict chronological evaluation.
Óscar Alcarria, Rafael Sánchez, Javier Sempere +5
Universidad de Castilla-La Mancha, Albacete, Spain · GMV GmbH, Darmstadt, Germany · GMV, Madrid, Spain
Most public benchmarks for machine-condition monitoring come from test rigs, where faults are induced on purpose and every event is known. Real production fields rarely offer that. They give you sensor histories with no fault log attached, which is exactly the situation where an anomaly-detection method has to invent its own labels, and where quiet assumptions can slip in unnoticed. We work with the open Volve field data released by Equinor and take two things seriously that such datasets usually skip. First, we build anomaly labels that are not just patterns in the numbers but are checked against what the field's own engineering documents say can physically go wrong, and we release the reasoning behind every label. Second, we test whether those constructed labels are learnable at all, using both an unsupervised baseline and a small dual-head model that marks when an event happens and what kind it is, an idea we carry over from earlier work on defect detection in metal parts. The results are honest. An unsupervised detector that never sees the labels still lands on the same regions our rules flagged, which tells us the labels are not arbitrary. A compact supervised model recovers event presence and event type well across wells it has never seen, and locates events in time only roughly. We report what worked, what did not, and every assumption in between. The dataset, grounded labels, per-label provenance, baseline scores, trained model, and code are released publicly under CC-BY-NC-SA 4.0.
Gospel Bassey, Samuel Bassey, Vincent Fakiyesi
Independent Researcher. · College of Engineering, Biochemical Engineering. University of Georgia. · College of Engineering, EETI. University of Georgia.
Artificial Intelligence (AI)-based prospective anomaly detection methods are increasingly deployed in high-dimensional and nonlinear settings. Among these approaches, AI-based statistical process monitoring (SPM) is widely used, providing a structured framework for prospective monitoring. Once an anomaly is detected, a diagnosis method is needed to identify the features driving the flagged observation away from normal behaviour. Traditional SPM diagnosis methods are typically designed for specific detection models and cannot be directly applied to AI-based methods. Model-agnostic explainable AI (XAI) offers a general framework for feature relevance explanation. However, existing methods suffer from scalability limitations or assign relevance to noise features, reducing diagnosis accuracy. We propose a scalable, baseline-referenced diagnosis method that uses both the anomalous observation and normal baseline information. We provide mathematical guarantees that under a mean-shift anomaly setting, the proposed method achieves higher faithfulness in detecting the features causing the anomaly compared to LIME. Simulation studies and a real-world case study validate the effectiveness of the proposed method and show that it generates more faithful and accurate diagnosis results for AI-based prospective anomaly detection methods.
Jiaqi Qiu, Rob Goedhart, Jannis Kurtz +1
Department of Business Analytics, Amsterdam Business School, University of Amsterdam, Amsterdam, The Netherlands