Search

The distribution network is recognized for its inherent fragility and challenging management compared to the transmission network. This challenge arises from the complex topology of the distribution network, involving thousands of nodes to monitor by predictive maintenance. This article introduces the implementation of an artificial neural network (ANN) for predictive maintenance of medium-voltage (MV) switchgears. In particular, the study here presented consists in proposing a new approach that correlates temperature measurements, at different positions within the switchgear, to potential faults. The specific cause of temperature change is the variable fastening in a single point of the MV switchgear. Thus, starting from experimental measurements, the ANN is thoroughly analyzed, compared, and validated to provide a proper classification of the switchgear health status. The obtained results affirm the efficacy of the proposed approach and highlight the benefits of its application in practical predictive maintenance scenarios.

Accurate identification of complex power quality disturbances (PQDs) is highly important for the pollution control of modern power systems. However, the occurrence of nonlinear loads causes the grid signals distorted and unstable, resulting in the difficulty of efficient classification. This article aims to develop an effective detection method for complex PQD automatic classification. First, a modified Kaiser window-based S-Transform (MKS) is proposed for converting the PQD time-series signals to time–frequency feature matrix, where the time–frequency performance of MKS can be improved through setting different window control functions in low-frequency and high-frequency parts, respectively. Next, a multiscale parallel attention residual network (MPARN) is presented to extract and classify disturbance information based on the optimized residual structure. Integrating MKS and MPARN, an automatic classification framework is further proposed to identify various PQDs. Simulation and hardware platform experiments demonstrate that our classification strategy can obtain superior performance than several state-of-the-art methods for complex even nonlinear PQD identification under different noise levels.

Intelligent classification of multiple power quality disturbances (PQDs) is a top priority in pollution control of the power grid. However, the large-scale application of renewable energy introduces lots of nonlinear and impact loads, which makes the PQDs more complex and challenges the effectiveness of conventional detection frameworks. In this article, a novel framework based on optimized Kaiser-window-based $S$-transform (OKST) and multiple fusion convolutional neural network (MFCNN) is proposed to identify multiple complex PQDs. First, the OKST is used for the time–frequency positioning of PQDs, where an improved control function is proposed to meet different detection requirements of time–frequency. Additionally, the parameters of the control function are adjusted automatically using maximum energy concentration. Then, the MFCNN based on residual networks (ResNets) is further proposed to extract and classify these time–frequency features automatically. In MFCNN, feature information is fused using different convolution kernels at a two-dimensional level, which can effectively reduce information loss and improve classification performance. The network model is set up using the Pytorch platform, and the dataset containing 28 types of PQDs and 2 types of nonlinearly mixed PQDs is built to test our framework. The result shows that the proposed OKST-MFCNN obtains an average accuracy of 99.38% under the 20-dB noise level, which is more accurate and robust than some advanced PQDs detection frameworks. Moreover, the accuracy of 97.94% is achieved with satisfactory real-time performance in hardware platform experiments, proving its superior identification performance for complex PQDs.

The widespread utilization of renewable energy sources can cause serious power quality problems. It presents new challenges for detecting power quality. A deep fractional multidimensional spectrum convolutional neural fusion network (FMSNet) method for automatically identifying and classifying complex power quality disturbance (PQD) signals is proposed in this article. It includes a 1-D spatial sense convolution block (SSCB), streamline sandwich block (SSB), and spatial fractional Fourier transform (SFRFT). Specifically, the SFRFT extracts the fractional domain features of the PQD signal. The issue of complex disturbance signals lacking detailed feature information is overcome by utilizing dynamic spatial fractional domain information. Moreover, the properties of FMSNet are further improved by combining the proposed SSCB and SSB. It is shown based on a large number of simulation experiments and hardware test experiments that the method presents significant detection capability and excellent noise immunity for the identification of complex PQD signals under different noise conditions.