Fault detection in district heating(DH)substations is crucial for maintaining energy efficiency.However,existing methods often fall short and rely on labelled data or global analysis that may miss subtle anomalies.We ...Fault detection in district heating(DH)substations is crucial for maintaining energy efficiency.However,existing methods often fall short and rely on labelled data or global analysis that may miss subtle anomalies.We introduce HEAT,a Hierarchical-constrained Encoder-Assisted Time series clustering method designed to enhance fault detection in DH substations.HEAT operates in a two-phase approach:first,it approximates a relative network topology using a constraint hierarchical clustering algorithm on supply temperature profiles.HEAT incorporates a Convolutional AutoEncoder(CAE)for dimensionality reduction of the time series data and uses adaptive soft constraints in the linkage function,enabling both minimum and maximum cluster size constraints while supporting domain knowledge,e.g.,must-link and cannot-link constraints,using a constraint matrix.Second,we use the topology approximation to perform intra-cluster analysis using Mean Absolute Deviation(MAD)z-scores,with neighbouring substations serving as a validation mechanism,allowing for robust analysis without requiring labelled data.Experimental results demonstrate that HEAT outperforms conventional clustering methods while achieving 74.1%sensitivity and 95.5%specificity in fault detection,significantly improving over typical global analysis.HEAT not only identified major faults(e.g.,sensor issues,valve failures)but also detected subtle anomalies(e.g.,secondary leakages)while minimising false positives.This unsupervised method offers a viable and flexible solution for DH networks,improving operational efficiency and energy sustainability without disclosing sensitive information.展开更多
The paper presents a novel demand-responsive control strategy to be equipped centrally at the district level for district heating systems.The demand-responsive feature was maintained as to both the direct and the indi...The paper presents a novel demand-responsive control strategy to be equipped centrally at the district level for district heating systems.The demand-responsive feature was maintained as to both the direct and the indirect substation configurations(by basing on their rating measures)in order to achieve lowest possible return temper-ature degrees from the end-user substations.Different than the traditional weather-compensation based supply temperature resetting,the new control strategy was formulated to adjust the supply temperature at the district level as to the cooling performance at the end-user substations.Two different simulations were carried out in order to quantify the benefits of the novel control strategy as compared to the traditional weather-compensation,equipped both at the substation level and the district level.The results obtained showed that the new control strategy,when considering the electricity loss at the heat production plant,shows superiority when compared to other control strategies.展开更多
文摘Fault detection in district heating(DH)substations is crucial for maintaining energy efficiency.However,existing methods often fall short and rely on labelled data or global analysis that may miss subtle anomalies.We introduce HEAT,a Hierarchical-constrained Encoder-Assisted Time series clustering method designed to enhance fault detection in DH substations.HEAT operates in a two-phase approach:first,it approximates a relative network topology using a constraint hierarchical clustering algorithm on supply temperature profiles.HEAT incorporates a Convolutional AutoEncoder(CAE)for dimensionality reduction of the time series data and uses adaptive soft constraints in the linkage function,enabling both minimum and maximum cluster size constraints while supporting domain knowledge,e.g.,must-link and cannot-link constraints,using a constraint matrix.Second,we use the topology approximation to perform intra-cluster analysis using Mean Absolute Deviation(MAD)z-scores,with neighbouring substations serving as a validation mechanism,allowing for robust analysis without requiring labelled data.Experimental results demonstrate that HEAT outperforms conventional clustering methods while achieving 74.1%sensitivity and 95.5%specificity in fault detection,significantly improving over typical global analysis.HEAT not only identified major faults(e.g.,sensor issues,valve failures)but also detected subtle anomalies(e.g.,secondary leakages)while minimising false positives.This unsupervised method offers a viable and flexible solution for DH networks,improving operational efficiency and energy sustainability without disclosing sensitive information.
基金supported by the‘European Union’,the‘Euro-pean Regional Development Fund(ERDF)’,‘Flanders Innovation&En-trepreneurship’and the‘Province of Limburg’.
文摘The paper presents a novel demand-responsive control strategy to be equipped centrally at the district level for district heating systems.The demand-responsive feature was maintained as to both the direct and the indirect substation configurations(by basing on their rating measures)in order to achieve lowest possible return temper-ature degrees from the end-user substations.Different than the traditional weather-compensation based supply temperature resetting,the new control strategy was formulated to adjust the supply temperature at the district level as to the cooling performance at the end-user substations.Two different simulations were carried out in order to quantify the benefits of the novel control strategy as compared to the traditional weather-compensation,equipped both at the substation level and the district level.The results obtained showed that the new control strategy,when considering the electricity loss at the heat production plant,shows superiority when compared to other control strategies.
