Issue link: https://resources.mouser.com/i/1437726
19 INTEL 2021 Figure 3: Comparisons between recurrent neural network (RNN) predictions (orange lines) and ground truth (blue lines) of variational time serials for the same channel's peak data (upper chart) and RMS data (lower chart). 4. Evaluate the model and detect anomalies on test data or full dataset. Anomalies are defined when the collected data points are distant from RNN predictions. In this project, we set the expected proportion of anomalies among the entire dataset to be 10 percent; that is, the 10 percent most distant ground truth from predictions are selected as anomalies. The threshold is a parameter that should be adjusted according to each use case. Test Results Figure 3 shows comparisons between LSTM model predictions and ground truth of vibration time series. Only two statistics are shown here, namely, peak and RMS of the same channel. Other statistics show similar fluctuations. The red points are anomalies detected. The orange line is prediction of the LSTM model. The blue line represents the ground truth. The model successfully detects the failure of the device at the end, as well as spikes after 600 timesteps. Some of the early fluctuations give warnings. Conclusion By adopting an unsupervised deep-learning approach, we can efficiently apply time-series anomaly detection for big data at scale, using the end-to-end Spark and BigDL pipeline provided by Analytics Zoo, and running directly on standard Hadoop/Spark clusters based on Intel Xeon processors. These functionalities and solutions–for example collecting and processing massive time-series data (such as logs, sensor readings) –and the application of RNN to learn the patterns and predict the expected values to identify anomalies, are critical for many emerging smart systems, such as industrial, manufacturing, artificial intelligence for AI operations (AIOps), Internet of Things (IoT), etc. Anomaly detection of time series would likely to play a key role in the use cases such as monitoring and predictive maintenance. (Here is one simple example of unsupervised anomaly detection using the Analytics Zoo Keras-style API.) Figure 2: Vibrational signals with four channels at the second of 2004.02.13.14.32.39