The autoencoder identified most of the arc faults.įigure 10: Detection performance for the autoencoder using raw load signal.įinally, we generated a 50 second long anomalous signal with 40 arc fault regions (this data is not included with the example). The red line in the plot indicates where the transition due to anomaly is detected. We can observe the prediction from the block adding a scope to the model. The anomaly detection block then calculates the root-mean-square error (RMSE) for each frame and declares the presence of an arc fault if the error is above some predefined threshold. The Predict block has been preloaded with the network pretrained using the load signal under normal conditions. The detail projection is then segmented in 100 sample frames that are the test features for the Predict block. The discrete time signal is then buffered to the LWTFeatureGen block that obtains the desired level 4 detail projection after preprocessing. The load voltage is then converted into a discrete-time signal sampled at 20kHz by the Rate transition block in DSP System Toolbox™. The first block generates noisy DC load signal with arc fault in continuous time. For training and testing purposes, the wavelet-filtered signals are segmented into 100-sample frames.įigure 7: DCArcModelFinal for arc fault detection. The wavelet-filtered faulty signal captures the variation due to arc faults. The following figures show the wavelet-filtered load signals under normal and faulty conditions. Following, the Daubechies db3 wavelet was used. The wavelet-based autoencoder was trained and tested on signals filtered using the discrete wavelet transform (DWT). Just like in a real-time DC system, the load signals from both normal and faulty conditions have added white noise. The contact separation times of the models are such that they are triggered randomly throughout the simulation period. For arc fault signal generation, we add a Cassie arc model in every load branch. For training and testing the network, we assume that the load consists of 10 parallel resistive branches with randomly chosen resistance values.
Arc fault detection is subsequently done on wavelet features as opposed to the raw data. The second autoencoder was trained using wavelet features. This encoder uses the raw faulty load signal to detect arc faults. One autoencoder was trained using the raw load signal as training data. In this example, we used root-mean-square error (RMSE) as the reconstruction error metric.įor this example, we trained two autoencoders using the load signal under normal conditions without arc fault. If the error is above the threshold in the anomaly detection block, the encoder declares it to be an anomaly.
Every time the autoencoder encounters an anomaly in the testing data, it produces a large reconstruction error. The statistics of the reconstruction error for the training data can be used to select the threshold in the anomaly detection block that determines the detection performance of the autoencoder. The network weights are calculated such that the reconstruction error is minimized. To this end, the autoencoder accepts training data without anomalies as input and tries to reconstruct the input signal using a neural network. As training the network and arc detection in larger signals can take significantly long simulation time, in this example we only report the detection results.Īutoencoders are used to detect anomalies in a signal. The DC arc model used to generate the fault signal and the pretrained network used to detect the arc faults are provided in the example folder. Further, an autoencoder trained with signal features under normal conditions is used to detect arc faults in load signals. The feature extraction involves filtering the load signals using the Daubechies db3 wavelet followed by normalization.
This example follows the feature extraction procedure detailed in. As a result, these signals can exist in the system for hours without being detected.Īrc fault detection using the wavelet transform was studied in. Unlike the fault signals in AC distribution systems, these prefault arc flash signals are difficult to identify as they do not generate significant power to trigger the circuit breakers.
These arc faults can result in shock, fires, and system failures in the microgrid. For the safe operation of DC distribution systems, it is important to identify arc faults and prefault signals that can be caused by deterioration of wire insulation due to aging, abrasion, or rodent bites. This example shows how wavelet features can be used to detect arc faults in a DC system.