Enabling Predictive Maintenance in District Heating Substations: A Labelled Dataset and Fault Detection Evaluation Framework based on Service Data

TL;DR

This paper introduces an open-source framework with a labelled dataset, evaluation metrics, and baseline models for early fault detection in district heating substations, aiming to improve predictive maintenance.

Contribution

It provides a publicly available dataset, a comprehensive evaluation framework, and baseline results for fault detection in district heating systems, facilitating reproducible research.

Findings

High normal-behaviour accuracy of 0.98

Fault detection with an F-score of 0.83

Detection of 60% of faults 3-5 days early

Abstract

Early detection of faults in district heating substations is imperative to reduce return temperatures and enhance efficiency. However, progress in this domain has been hindered by the limited availability of public, labelled datasets. We present an open-source framework combining a service report validated public dataset, an evaluation method based on accuracy, reliability, and earliness, and baseline results implemented with EnergyFaultDetector, an open-source Python framework developed for automated anomaly detection in operational data from energy systems. The dataset contains time series of operational data from 93 substations across two manufacturers, annotated with a list of disturbances due to faults and maintenance actions, a set of normal-event examples and detailed fault metadata. We evaluate the EnergyFaultDetector using three metrics: accuracy for recognising normal behaviour, an eventwise F-score for reliable fault detection with few false alarms, and earliness for early detection. The framework also supports root cause analysis using ARCANA, a feature-attribution method for autoencoders. We demonstrate three use cases to assist operators in interpreting anomalies and identifying underlying faults. The models achieve high normal-behaviour accuracy (0.98) and eventwise F-score (beta = 0.5) of 0.83 and could detect 60% of the faults in the dataset before the customer reported a problem, with an average lead time of 3 to 5 days. Integrating an open dataset, metrics, open-source code, and baselines establishes a reproducible, fault-centric benchmark with operationally meaningful evaluation, enabling consistent comparison and development of early fault detection and diagnosis methods for district heating substations.