Anomaly event detector
Embodiments are directed to a computer-based tool that can identify an anomalous state of a component in a real-world environment, even if the component experiences gradual and/or seasonal trends. The tool receives data from sensors monitoring a component. The tool uses a trained machine learning model to calculate a predicted behavior of the monitored component. Actual behavior of the component, captured by current sensor readings, is compared to the predicted behavior of the component, calculated by the machine learning model, to compute a divergence. The computed divergence is used by a statistical learning method to determine if the component in the real-world environment is in an anomalous state.
1. A computer-implemented predictive method for identifying an anomalous state of a component in a real-world environment, the method comprising:
receiving data from at least one sensor of a component in a real-world environment;
executing a machine learning model to calculate, using the received data from the at least one sensor of the component in the real-world environment, a predicted normal behavior of the component at a future time;
at or after the future time, computing a divergence based on a difference between an actual behavior of the component at the future time and the predicted normal behavior of the component at the future time; and
determining, using a statistic learning method, and indicating if the component in the real-world environment is in an anomalous state based upon (i) a scale of the divergence and (ii) a variation of the divergence.
2. The method of claim 1 further comprising:
accessing historic operating data of the component in the real-world environment; and
training the machine learning model using the accessed historic operating data to predict one or more normal behaviors of the component at one or more future times based on the data from the at least one sensor of the component in the real-world environment.
3. The method of claim 2 wherein the accessed historic operating data includes at least one of: data of the component in the real-world environment operating in a normal state and data of the component in the real-world environment operating in an anomalous state.
4. The method of claim 1 wherein the machine learning model is a LSTM recurrent neural network.
5. The method of claim 1 further comprising preprocessing the received data based upon at least one of oscillations, seasonal trends, correlations, and historical anomalous states of the component in the real-world environment.
6. The method of claim 1 wherein the statistic learning method is a gaussian mixture model.
7. The method of claim 1 wherein the actual behavior of the component is real time information.
8. The method of claim 1 further comprising determining and indicating a contribution score for the at least one sensor of the component in the real-world environment, the contribution score measuring a contribution to the divergence.
9. The method of claim 1 further comprising determining and indicating a confidence in the determination if the component in the real-world environment is in the anomalous state based upon i) the scale of divergence and ii) the variation of the divergence.
10. The method of claim 1 wherein the predicted normal behavior of the component at the future time is a predicted value of a manipulated variable of a proportional-integral-derivative controller of the component and the actual behavior of the component is an actual value of the manipulated variable of the proportional-integral-derivative controller of the component.
11. A computer-based system for identifying an anomalous state of a component in a real-world environment, the system comprising:
a processor; and
a memory with computer code instructions stored thereon, the processor and the memory, with the computer code instructions being configured to cause the system to:
receive data from at least one sensor of a component in a real-world environment;
execute a machine learning model to calculate, using the received data from the at least one sensor of the component in the real-world environment, a predicted normal behavior of the component at a future time;
at or after the future time, compute a divergence based on a difference between an actual behavior of the component at the future time and the predicted normal behavior of the component at the future time; and
determine, using a statistic learning method, and indicate if the component in the real-world environment is in an anomalous state based upon (i) a scale of the divergence and (ii) a variation of the divergence.
12. The system of claim 11 wherein, the processor and the memory, with the computer code instructions, are further configured to cause the system to:
access historic operating data of the component in the real-world environment; and
train the machine learning model using the accessed historic operating data to predict one or more normal behaviors of the component at one or more future times based on the data from the at least one sensor of the component in the real-world environment.
13. The system of claim 12 wherein, in training the machine learning model, the processor and the memory, with the computer code instructions, are further configured to cause the system to:
interface, via a network, with one or more computing devices to perform the training.
14. The system of claim 12 wherein the accessed historic operating data includes at least one of: data of the component in the real-world environment operating in a normal state and data of the component in the real-world environment operating in an anomalous state.
15. The system of claim 11 wherein, the processor and the memory, with the computer code instructions, are further configured to cause the system to:
encrypt the machine learning model with a public key; and
decrypt the machine learning model with a private key.
16. The system of claim 11 wherein the machine learning model is a LSTM recurrent neural network.
17. The system of claim 11 wherein, the processor and the memory, with the computer code instructions, are further configured to cause the system to:
preprocess the received data based upon at least one of oscillations, seasonal trends, correlations, and historical anomalous states of the component in the real-world environment.
18. The system of claim 11 wherein the statistic learning method is a gaussian mixture model.
19. The system of claim 11 wherein the predicted normal behavior of the component at the future time is a predicted value of a manipulated variable of a proportional-integral-derivative controller of the component and the actual behavior of the component is an actual value of the manipulated variable calculated by the proportional-integral-derivative controller of the component.
20. A computer program product for identifying an anomalous state of a component in a real-world environment, the computer program product comprising:
one or more non-transitory computer-readable storage devices and program instructions stored on at least one of the one or more non-transitory computer-readable storage devices, the program instructions, when loaded and executed by a processor, cause an apparatus associated with the processor to:
receive data from at least one sensor of a component in a real-world environment;
execute a machine learning model to calculate, using the received data from the at least one sensor of the component in the real-world environment, a predicted normal behavior of the component at a future time;
at or after the future time, compute a divergence based on a difference between an actual behavior of the component at the future time and the predicted normal behavior of the component at the future time; and
determine, using a statistic learning method, and indicate if the component in the real-world environment is in an anomalous state based upon (i) a scale of the divergence and (ii) a variation of the divergence.