Fault indicator

About: Fault indicator is a research topic. Over the lifetime, 10057 publications have been published within this topic receiving 143482 citations. The topic is also known as: FCI & power line fault indicator.

Efficient Placement of Fault Indicators in an Actual Distribution System Using Evolutionary Computing

Abstract: This paper proposes an evolutionary computing strategy to solve the problem of fault indicator (FI) placement in primary distribution feeders. More specifically, a genetic algorithm (GA) is employed to search for an efficient configuration of FIs, located at the best positions on the main feeder of a real-life distribution system. Thus, the problem is modeled as one of optimization, aimed at improving the distribution reliability indices, while, at the same time, finding the least expensive solution. Based on actual data, the results confirm the efficiency of the GA approach to the FI placement problem.

Fault type selection system for identifying faults in an electric power system

Abstract: The fault identification system includes a first logic circuit which is responsive to conventional protective elements which recognize the presence of low resistance single line-to-ground faults for the A, B and C phases on a power transmission line. The first logic circuit includes a portion thereof for recognizing and providing an output indication of single line-to-ground faults, faults involving two phases and three-phase faults, in response to the occurrence of different combinations of outputs from the protective elements. A calculation circuit, when enabled, is used to determine the angular difference between the total zero sequence current and the total negative sequence current for high resistance faults when the protective elements themselves cannot identify fault conditions. The angular difference is in one of three pre-selected angular sectors. An angular difference in the first sector indicates an A phase-to-ground fault or a BC phase-to-phase to ground fault; an angular difference in the second sector indicates a B phase-to-ground fault or a C phase-to-phase to ground fault; and a signal in the third sector indicates a C phase-to-ground fault or an AB phase-to-phase to ground fault. A processor is used to determine which of the two possible for each angle determination is the actual fault type. An output indication of the actual fault type is then provided.

Qualitative model-based fault detection in air-handling units

Abstract: The feasibility of a qualitative approach for detecting faults in an air-conditioning system is considered. The system considered is a multi-zone variable air volume air-handling unit, and the faults investigated include types which result in deterioration of operation, as distinct from actual failure. The operating modes of the sequential controller for the central air-handling plant can be matched to a corresponding qualitative classification of steady-state temperatures. Observed mismatches indicate the presence of faults. Trials of the method in an air-conditioning test laboratory are reported. >

Deep Learning Method for Fault Detection of Wind Turbine Converter

Abstract: The converter is an important component in wind turbine power drive-train systems, and usually, it has a higher failure rate. Therefore, detecting the potential faults for prediction of its failure has become indispensable for condition-based maintenance and operation of wind turbines. This paper presents an approach to wind turbine converter fault detection using convolutional neural network models which are developed by using wind turbine Supervisory Control and Data Acquisition (SCADA) system data. The approach starts with the selection of fault indicator variables, and then the fault indicator variables data are extracted from a wind turbine SCADA system. Using the data, radar charts are generated, and the convolutional neural network models are applied to feature extraction from the radar charts and characteristic analysis of the feature for fault detection. Based on the analysis of the Octave Convolution (OctConv) network structure, an improved AOctConv (Attention Octave Convolution) structure is proposed in this paper, and it is applied to the ResNet50 backbone network (named as AOC–ResNet50). It is found that the algorithm based on AOC–ResNet50 overcomes the issues of information asymmetry caused by the asymmetry of the sampling method and the damage to the original features in the high and low frequency domains by the OctConv structure. Finally, the AOC–ResNet50 network is employed for fault detection of the wind turbine converter using 10 min SCADA system data. It is verified that the fault detection accuracy using the AOC–ResNet50 network is up to 98.0%, which is higher than the fault detection accuracy using the ResNet50 and Oct–ResNet50 networks. Therefore, the effectiveness of the AOC–ResNet50 network model in wind turbine converter fault detection is identified. The novelty of this paper lies in a novel AOC–ResNet50 network proposed and its effectiveness in wind turbine fault detection. This was verified through a comparative study on wind turbine power converter fault detection with other competitive convolutional neural network models for deep learning.