Search Results (7)

This article presents a novel method for detecting series arc faults (SAFs) in residential applications using time-domain imaging (TDI) and Long Short-Term Memory (LSTM) networks. The proposed method transforms current signals into grayscale images by filtering out the fundamental frequency, allowing key arc fault characteristics—such as high-frequency noise and waveform distortions—to become visually apparent. The use of Ensemble Empirical Mode Decomposition (EEMD) helped isolate meaningful signal components, although it was computationally intensive. To address real-time requirements, a simpler yet effective TDI method was developed for generating 2D images from current data. These images were then used as inputs to an LSTM network, which captures temporal dependencies and classifies both arc faults and appliance types. The proposed TDI-LSTM model was trained and tested on 7000 labeled datasets across five common household appliances. The experimental results show an average detection accuracy of 98.1%, with reduced accuracy for loads using thyristors (e.g., dimmers). The method is robust across different appliance types and conditions; comparisons with prior methods indicate that the proposed TDI-LSTM approach offers superior accuracy and broader applicability. Trade-offs in sampling rates and hardware implementation were discussed to balance accuracy and system cost. Overall, the TDI-LSTM approach offers a highly accurate, efficient, and scalable solution for series arc fault detection in smart home systems. Full article

Knowledge graph technology holds significant importance for efficient fault diagnosis in household appliances. However, the scarcity of public fault diagnosis data and the lack of automated knowledge extraction pose major challenges to knowledge graph construction. To address issues such as ambiguous entity boundaries, severe entity nesting, and poor entity extraction performance in fault diagnosis texts, this paper proposes a dual-strategy progressive knowledge extraction framework. First, to tackle the high complexity of fault diagnosis texts, an entity recognition model named RoBERTa-zh-BiLSTM-MUL-CRF is designed, improving the accuracy of nested entity extraction. Second, leveraging the semantic understanding capability of large language models, a progressive prompting strategy is adopted for ontology alignment and relation extraction, achieving automated knowledge extraction. Experimental results show that the proposed named entity recognition model outperforms traditional models, with improvements of 3.87%, 5.82%, and 2.05% in F1-score, recall, and precision, respectively. Additionally, the large language model demonstrates better performance in ontology alignment compared to traditional machine learning models. The constructed knowledge graph for household appliance fault diagnosis integrates structured fault diagnosis information. It effectively processes unstructured fault texts and supports visual queries and entity tracing. This framework can assist maintenance personnel in making rapid judgments, thereby improving fault diagnosis efficiency. Full article

Electrical arc fault detector development requires many tests to develop and validate detection algorithms. The use of artificial intelligence or mathematical transformation requires the use of consequential datasets of current signatures corresponding to as many different situations as possible. In addition, one of the main drawbacks is that these experiments take a great deal of time and are often laborious in the laboratory. To overcome these limitations, a virtual test bench based on the modeling of a modular 230 VAC electrical circuit has been developed. The simulated network is composed of different home appliances (resistor, vacuum cleaner, dimmer, etc.) and its configurations are those of single and combined loads. The fault modeled is an electric arc, modeled by active diode switching, which can be inserted at any point of the circuit. This arc model takes into account the random variations in the restrike and arc voltage. All the appliance models are validated by comparing the frequential (harmonic distortion) and temporal (agreement index) signatures of the measured currents in real situations to those obtained by modeling. The results obtained using the model and experiment network show that the current signatures are comparable in both cases. Further, two detection algorithms are tested on those current signatures obtained by the modeling and experimentation. The results are comparable and provide identical detection thresholds. Full article

Within the context of a smart home, detecting the operating status of appliances in the environment plays a pivotal role, estimating power consumption, issuing overuse reminders, and identifying faults. The traditional contact-based approaches require equipment updates such as incorporating smart sockets or high-precision electric meters. Non-constant approaches involve the use of technologies like laser and Ultra-Wideband (UWB) radar. The former can only monitor one appliance at a time, and the latter is unable to detect appliances with extremely tiny vibrations and tends to be susceptible to interference from human activities. To address these challenges, we introduce HomeOSD, an advanced appliance status-detection system that uses mmWave radar. This innovative solution simultaneously tracks multiple appliances without human activity interference by measuring their extremely tiny vibrations. To reduce interference from other moving objects, like people, we introduce a Vibration-Intensity Metric based on periodic signal characteristics. We present the Adaptive Weighted Minimum Distance Classifier (AWMDC) to counteract appliance vibration fluctuations. Finally, we develop a system using a common mmWave radar and carry out real-world experiments to evaluate HomeOSD’s performance. The detection accuracy is 95.58%, and the promising results demonstrate the feasibility and reliability of our proposed system. Full article

Traditionally, the choices to balance the grid and meet its peaking power needs are by installing more spinning reserves or perform load shedding when it becomes too much. This problem becomes worse as more intermittent renewable energy resources are installed, forming a substantial amount of total capacity. Advancements in Energy Storage System (ESS) provides the utility new ways to balance the grid and to meet its peak demand by storing un-used off peak energy for peak usage. Large sized ESS—mega watt (MW) level—are installed by different utilities at their substations to provide the high speed grid stabilization to balance the grid to avoid installing more capacity or triggering any current load shedding schemes. However, such large sized ESS systems and their required inverters are costly to install, require much space and their efficacy could also be limited due to network fault current limits and impedances. In this paper, we propose a novel approach and trial for 3000+ homes in Singapore of achieving a large capacity of demand management by developing a smart distribution board (DB) in each home with the high speed metering sensors (>6 kHz sampling rate) and non-intrusive load monitoring (NILM) algorithm, that can assist home users to perform the load/appliance profile identification with daily usage patterns and allow targeted load interruption using the smart sockets/plugs provided. By allowing load shedding at device or appliance level, while knowing their usage profile and preferences, this can allow such an approach to become part of a new voluntary interruptible load management system (ILMS) that requires little user intervention, while minimizing disruption to them, allowing ease of mass participation and thus achieving the intended MW demand management capacities for the grid. This allows for a more cost effective way to better balance the grid without the need for generation capacity growth, large ESS investment while improving the way to perform load shedding without disruptions to entire districts. Simply, home users can now know and participate with the grid in interruptible load (IL) schemes to target specific home appliance, such as water heaters or air conditioning, allowing interruptions during certain times of the day, instead of the entire house, albeit with the right incentives. This allows utilities to achieve MW capacity load shedding with millions of appliances with their preferences, and most importantly, with minimal disruptions to their consumers quality of life. In our paper, we will also consider coupling a small sized Home Energy Storage System (HESS) to amplify the demand management capacity. The proposed approach does not require any infrastructure or wiring changes and is highly scalable. Simulation results demonstrate the effectiveness of the NILM algorithm and achieving high capacity grid demand management. This approach of taking user preferences for appliance level load shedding was developed from the results of a survey of 500 households that indicates >95% participation if they were able to control their choices, possibly allowing this design to be the most successful demand management program than any large ESS solution for the utility. The proposed system has the ability to operate in centralized as part of a larger Energy Management System (EMS) Supervisory Control And Data Acquisition (SCADA) that decide what to dispatch as well as in autonomous modes making it simpler to manage than any MW level large ESS setup. With the availability of high-speed sampling at the DB level, it can rely on EMS SCADA dispatch or when disconnected, rely on the decaying of the grid frequency measured at the metering point in the Smart DB. Our simulation results demonstrate the effectiveness of our proposed approach for fast grid balancing. Full article

Smart meters (SMs) are key components of the smart grid (SG) which gather electricity usage data from residences and businesses. Home area networks (HANs) are used to support two-way communications between SMs and devices within a building such as appliances. This can be implemented using power line communications (PLCs) via home wiring topologies. In this paper, a bottom-up approach is designed and a HAN-PLC channel model is obtained for a split-phase power system which includes branch circuits, an electric panel with circuit breakers and bars, a secondary transformer and the wiring of neighboring residences. A cell division (CD) method is proposed to construct the channel model. Furthermore, arc fault circuit interrupter (AFCI) and ground fault circuit interrupter (GFCI) circuit breaker models are developed. Several HAN-PLC channels are presented and compared with those obtained using existing models. Full article

Demand Side Management (DSM) through optimization of home energy consumption in the smart grid environment is now one of the well-known research areas. Appliance scheduling has been done through many different algorithms to reduce peak load and, consequently, the Peak to Average Ratio (PAR). This paper presents a Comprehensive Home Energy Management Architecture (CHEMA) with integration of multiple appliance scheduling options and enhanced load categorization in a smart grid environment. The CHEMA model consists of six layers and has been modeled in Simulink with an embedded MATLAB code. A single Knapsack optimization technique is used for scheduling and four different cases of cost reduction are modeled at the second layer of CHEMA. Fault identification and electricity theft control have also been added in CHEMA. Furthermore, carbon footprint calculations have been incorporated in order to make the users aware of environmental concerns. Simulation results prove the effectiveness of the proposed model. Full article