System and method for recognizing and forecasting anomalous sensory behavioral patterns of a machine
A system and method for recognizing and forecasting anomalous sensory behavioral patterns of a machine, including: monitoring a first set of time-stamped sensory input data related to at least one machine; determining, upon analysis of the first set of time-stamped sensory input data, a first suspicious pattern of a first anomalous sensory input behavior associated with the first set of time-stamped sensory input data; comparing the first suspicious pattern to a second pattern of a second anomalous sensory input behavior that is associated with a second set of time-stamped sensory input data, wherein the second pattern previously determined to be indicative of a machine failure; and, determining if the first suspicious pattern is correlated above a predetermined threshold with the second pattern.
1. A method for recognizing anomalous sensory behavior patterns of a machine, comprising:
monitoring a first set of time-stamped sensory input data related to at least one machine;
determining, upon analysis of the first set of time-stamped sensory input data, a first suspicious pattern of a first anomalous sensory input behavior associated with the first set of time-stamped sensory input data;
comparing the first suspicious pattern to a second pattern of a second anomalous sensory input behavior that is associated with a second set of time-stamped sensory input data, wherein the second pattern previously determined to be indicative of a machine failure;
determining if the first suspicious pattern is correlated above a predetermined threshold with the second pattern; and
generating a notification that forecasts an upcoming machine failure of the at least one machine upon determination that the first suspicious pattern is correlated above a predetermined threshold with the second pattern.
2. The method of claim 1 , wherein the notification indicates on at least one of: a determined pattern that is indicative of an upcoming machine failure, a root cause, and at least one corrective solution recommendation.
3. The method of claim 1 , wherein the analysis of the first set of time-stamped sensory input data is achieved using at least one of: a machine learning model and a deep learning model.
4. The method of claim 1 , wherein the determination of the first suspicious pattern is achieved using a correlation function.
5. The method of claim 1 , wherein the comparison further comprises applying at least one machine learning algorithm on the first suspicious pattern and a second pattern.
6. The method of claim 1 , wherein determining if the first suspicious pattern is correlated above a predetermined threshold with the second pattern further includes determining the time period in which the first suspicious pattern and the second pattern occurred.
7. The method of claim 1 , wherein the first suspicious pattern includes at least one of: one or more arrays of sensor anomalies, anomalous groups that reflect the time at which each anomaly occurred, and abnormal parameter values associated with the anomalies.
8. The method of claim 1 , further comprising:
preprocessing the first set of time-stamped sensory input data, wherein the preprocessing includes at least one of: data cleansing, normalization, rescaling, re-trending, reformatting, and noise filtering.
9. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to perform a process, the process comprising:
monitoring a first set of time-stamped sensory input data related to at least one machine;
determining, upon analysis of the first set of time-stamped sensory input data, a first suspicious pattern of a first anomalous sensory input behavior associated with the first set of time-stamped sensory input data;
comparing the first suspicious pattern to a second pattern of a second anomalous sensory input behavior that is associated with a second set of time-stamped sensory input data, wherein the second pattern previously determined to be indicative of a machine failure;
determining if the first suspicious pattern is correlated above a predetermined threshold with the second pattern; and
generating a notification that forecasts an upcoming machine failure of the at least one machine upon determination that the first suspicious pattern is correlated above a predetermined threshold with the second pattern.
10. A system for recognizing anomalous sensory behavior patterns of a machine, comprising:
a processing circuitry; and
a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:
monitor a first set of time-stamped sensory input data related to at least one machine;
determine, upon analysis of the first set of time-stamped sensory input data, a first suspicious pattern of a first anomalous sensory input behavior associated with the first set of time-stamped sensory input data;
compare the first suspicious pattern to a second pattern of a second anomalous sensory input behavior that is associated with a second set of time-stamped sensory input data, wherein the second pattern previously determined to be indicative of a machine failure;
determine if the first suspicious pattern is correlated above a predetermined threshold with the second pattern; and
generate a notification that forecasts an upcoming machine failure of the at least one machine upon determination that the first suspicious pattern is correlated above a predetermined threshold with the second pattern.
11. The system of claim 10 , wherein the notification indicates at least one of: a determined pattern that is indicative of an upcoming machine failure, a root cause, and at least one corrective solution recommendation.
12. The system of claim 10 , wherein the analysis of the first set of time-stamped sensory input data is achieved using at least one of: a machine learning model and a deep learning model.
13. The system of claim 10 , wherein the determination of the first suspicious pattern is achieved using a correlation function.
14. The system of claim 10 , wherein the comparison further comprises applying at least one machine learning algorithm on the first suspicious pattern and a second pattern.
15. The system of claim 10 , wherein determining if the first suspicious pattern is correlated above a predetermined threshold with the second pattern further includes determining the time period in which the first suspicious pattern and the second pattern occurred.
16. The system of claim 10 , wherein the first suspicious pattern includes at least one of: one or more arrays of sensor anomalies, anomalous groups that reflect the time at which each anomaly occurred, and abnormal parameter values associated with the anomalies.
17. The system of claim 10 , wherein the system is further configured to: preprocessing the first set of time-stamped sensory input data, wherein the preprocessing includes at least one of: data cleansing, normalization, rescaling, re-trending, reformatting, and noise filtering.