Federico Incardona

Emilio Mastriani, Alessandro Costa, Federico Incardona et al.

Objective: ServiMon is designed to offer a scalable and intelligent pipeline for data collection and auditing to monitor distributed astronomical systems such as the ASTRI Mini-Array. The system enhances quality control, predictive maintenance, and real-time anomaly detection for telescope operations. Methods: ServiMon integrates cloud-native technologies-including Prometheus, Grafana, Cassandra, Kafka, and InfluxDB-for telemetry collection and processing. It employs machine learning algorithms, notably Isolation Forest, to detect anomalies in Cassandra performance metrics. Key indicators such as read/write latency, throughput, and memory usage are continuously monitored, stored as time-series data, and preprocessed for feature engineering. Anomalies detected by the model are logged in InfluxDB v2 and accessed via Flux for real-time monitoring and visualization. Results: AI-based anomaly detection increases system resilience by identifying performance degradation at an early stage, minimizing downtime, and optimizing telescope operations. Additionally, ServiMon supports astrostatistical analysis by correlating telemetry with observational data, thus enhancing scientific data quality. AI-generated alerts also improve real-time monitoring, enabling proactive system management. Conclusion: ServiMon's scalable framework proves effective for predictive maintenance and real-time monitoring of astronomical infrastructures. By leveraging cloud and edge computing, it is adaptable to future large-scale experiments, optimizing both performance and cost. The combination of machine learning and big data analytics makes ServiMon a robust and flexible solution for modern and next-generation observational astronomy.

Alessandro Costa, Emilio Mastriani, Federico Incardona et al.

This study introduces a predictive maintenance strategy for high pressure industrial compressors using sensor data and features derived from unsupervised clustering integrated into classification models. The goal is to enhance model accuracy and efficiency in detecting compressor failures. After data pre processing, sensitive clustering parameters were tuned to identify algorithms that best capture the dataset's temporal and operational characteristics. Clustering algorithms were evaluated using quality metrics like Normalized Mutual Information (NMI) and Adjusted Rand Index (ARI), selecting those most effective at distinguishing between normal and non normal conditions. These features enriched regression models, improving failure detection accuracy by 4.87 percent on average. Although training time was reduced by 22.96 percent, the decrease was not statistically significant, varying across algorithms. Cross validation and key performance metrics confirmed the benefits of clustering based features in predictive maintenance models.

Emilio Mastriani, Alessandro Costa, Federico Incardona et al.

Concerning machine learning, segmentation models can identify state changes within time series, facilitating the detection of transitions between normal and anomalous conditions. Specific techniques such as Change Point Detection (CPD), particularly algorithms like ChangeFinder, have been successfully applied to segment time series and improve anomaly detection by reducing temporal uncertainty, especially in multivariate environments. In this work, we explored how the integration of segmentation techniques, combined with a heterogeneous ensemble, can enhance anomaly detection in an industrial production context. The results show that applying segmentation as a pre-processing step before selecting heterogeneous ensemble algorithms provided a significant advantage in our case study, improving the AUC-ROC metric from 0.8599 (achieved with a PCA and LSTM ensemble) to 0.9760 (achieved with Random Forest and XGBoost). This improvement is imputable to the ability of segmentation to reduce temporal ambiguity and facilitate the learning process of supervised algorithms. In our future work, we intend to assess the benefit of introducing weighted features derived from the study of change points, combined with segmentation and the use of heterogeneous ensembles, to further optimize model performance in early anomaly detection.