Underground power cables are a widely-deployed class of assets in electric power distribution systems. They are robust in adverse weather conditions and are an aesthetically pleasing alternative to overhead power lines. Unfortunately, the physical observability of underground cables is poor. Current methods for detecting and localizing defects known to progress to failure are cumbersome and expensive, both financially and operationally. In-service cable failures can lead to lengthy power outages and financial losses and can endanger utility staff and the general public. There is thus a need for non-invasive condition monitoring techniques that will allow for early detection of defects likely to progress to a fault, so cost-effective repair or replacement interventions can be planned. In this study, insulation overheating is specifically considered. Thermal damage of XLPE insulation is a prominent damage mechanism for extruded dielectric cable and is thus well studied and understood. A defect detection solution combining powerline modems with semi-supervised anomaly detection for underground cables is proposed. The performance of five well-regarded machine-learning-based anomaly detection algorithms is analyzed through simulation of a real-world 15 kV distribution network. The best-performing algorithm studied had a false alarm rate of under 0.1% with no missed alarms across a range of damage scenarios.
Background: With the growing proportion of Canadians aged >65 years, smart home and health monitoring technologies may help older adults manage chronic disease and support aging in place. Localization technologies have been used to support the management of frailty and dementia by detecting activities in the home. Objective: This systematic review aims to summarize the clinical evidence for in-home localization technologies, review the acceptability of monitoring, and summarize the range of technologies being used for in-home localization. Methods: The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology was followed. MEDLINE, Embase, CINAHL, and Scopus were searched with 2 reviewers performing screening, extractions, and quality assessments. Results: A total of 1935 articles were found, with 36 technology-focused articles and 10 articles that reported on patient outcomes being included. From moderate- to high-quality studies, 2 studies reported mixed results on identifying mild cognitive dementia or frailty, while 4 studies reported mixed results on the acceptability of localization technology. Technologies included ambient sensors; Bluetooth- or Wi-Fi–received signal strength; localizer tags using radio frequency identification, ultra-wideband, Zigbee, or GPS; and inertial measurement units with localizer tags. Conclusions: The clinical utility of localization remains mixed, with in-home sensors not being able to differentiate between older adults with healthy cognition and older adults with mild cognitive impairment. However, frailty was detectable using in-home sensors. Acceptability is moderately positive, particularly with ambient sensors. Localization technologies can achieve room detection accuracies up to 92% and linear accuracies of up to 5-20 cm that may be promising for future clinical applications. Trial Registration: PROSPERO CRD42022339845; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=339845
Transient operation of machinery can greatly complicate the task of vibration-based online condition monitoring. Because the operating mode of a machine affects the physical response and hence the diagnostic parameters, real-time information regarding the operating mode is likely to improve the performance of an online fault detection system. This paper proposes a method for automated operating mode classification to augment the performance of vibration-based online condition monitoring systems for applications such as gearboxes, motors, and their constituent components. Experimental work has been carried out on the swing machinery of an electromechanical excavator, which demonstrates how such a method might function on actual dynamic signals gathered from an operating machine. Several variations of the system have been tested and found to be successful.