![]() The results show that the proposed method has high identification accuracy and feasibility.Įlectrical power generated from the generating station has to be carried to reach the loads at the distribution side through transmission lines. The accuracy of the proposed method is 98.33/95.62% for simulated data/measured data, and is 1.66/1.09%, 3.33/1.76%, 17.31/28.48% and 40.17/46.1% higher than the accuracies of convolutional neural network, deep belief network, random forest and back propagation neural network, respectively. In addition, the performance of the proposed method is compared with other methods. Finally, a well‐trained SAE network is used to learn deep features from the input data to identify cable incipient fault, and softmax outputs identification result. Then, the compressed data is used as the input of SAE, and the optimal network parameters are obtained through layer‐by‐layer pre‐training and fine‐tuning. Firstly, disturbance current waveforms data is effectively compressed by RBM, which can improve analysis efficiency and obtain the shallow features of the data. A cable incipient fault identification method is proposed in this study, using restricted Boltzmann machine (RBM) and stacked autoencoder (SAE). Due to the short duration of the fault, the conventional overcurrent protection device cannot detect it. It is suggested that the increase of vulcanization network density and elastic modulus with ambient temperature may have great influence on the treeing characteristics (including growth rate, fractal dimension and treeing proportion).Ĭable incipient fault is an intermittent arc fault, and may evolve into a permanent fault. The growth rate of the tree is closely related to the ambient temperature. Meanwhile, the cumulative inception probability within the same time decreases obviously with the increase of ambient temperature. The occurrence of tree structures changes with the increase of ambient temperature, in which branch tree takes up a great proportion at 30☌ while bush tree becomes dominated as the temperature rises up to 90☌. Four typical tree structures, namely branch, bush, pine branch and bush-pine mixed tree, were observed within the sample. Obtained results show that the tree initiates from a single branch with a white gap. Both the structures and the growth characteristics were observed by using a digital microscope system. An ac voltage with a frequency of 50 Hz was applied between a needle-plate electrode to initiate the electrical tree at different ambient temperatures. In this paper, electrical treeing was investigated in room temperature vulcanized (RTV) silicone rubber (SiR) over a range of ambient temperatures. ![]() The simulation results in EMTPWorks environment demonstrate that the proposed approach has a strong capability in distinguishing the cable incipient faults from other similar conditions in distribution systems. In addition to its high-speed detection ability, the proposed approach is simple in practical on-line implementation and does not have the complication of other approaches. In this paper, a precise approach based on CU-SUM (CUmulative SUM) and ADAptive Linear NEuron (ADALINE) has been proposed. Therefore, one of the most important considerations of utilities in the monitoring process is to recognize these types of faults from other conditions as soon as possible. Therefore, precise well-timed protection decisions cannot be made. Appearance of such faults as current spikes in short periods can lead to permanent faults or they may disturb electricity transmissions because of detection delays. Positive locking feature to insure proper application and to discourage reuse.Incipient faults in underground cables are often resulted from electric stress and cable aging.Pre-filled with POLY-BEE Sealant field proven for over 14 years. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |