System and method for proactive repair of sub optimal operation of a machine

1. A computer-implemented method for repairing suboptimal operation of an industrial machine, comprising:

monitoring sensory input data related to an industrial machine;

analyzing, using an unsupervised machine learning model, the monitored sensory inputs, wherein the output of the unsupervised machine learning model includes at least one indicator;

identifying, based on the at least one indicator, at least one behavioral pattern related to the industrial machine, wherein each of the at least one behavioral pattern is indicative of at least one suboptimal operation of the industrial machine;

selecting at least one corrective action based on the at least one behavioral pattern, wherein selecting at least one corrective action further comprises: extracting one or more characteristics associated with the at least one machine behavioral pattern that is indicative of the at least one suboptimal operation of the at least one machine;

searching in at least one data source that comprises a plurality of corrective actions for one or more corrective actions based on extracted characteristics; and, selecting at least one corrective action having a first probability score that is above a first predetermined threshold to repair the at least one suboptimal operation of the machine, and a second probability score that is below a second predetermined threshold to damage the machine; and

performing the at least one corrective action on the industrial machine.

2. The computer-implemented method of claim 1 , further comprising:

monitoring the sensory input data associated with the industrial machine to determine an influence of the corrective action on the at least one machine.

3. The computer-implemented method of claim 2 , further comprising:

ranking the at least one corrective action responsive of its effectiveness.

4. The computer-implemented method of claim 3 , further comprising:

storing in a data source at least one of: the at least one behavioral pattern, the at least one corrective action, and the ranking of the at least one corrective action.

5. The computer-implemented method of claim 1 , further comprising:

predicting, based on the at least one behavioral pattern and the monitored sensory input data, a failure of the industrial machine; and

selecting at least one corrective action based on the industrial machine failure prediction.

6. The computer-implemented method of claim 1 , further comprising:

preprocessing raw sensory input data received from the sensors; and

storing the preprocessed raw sensory input data in a data source.

7. The computer-implemented method of claim 6 , wherein the preprocessing includes at least one of: data cleansing, normalization, rescaling, re-trending, reformatting, and noise filtering.

8. The computer-implemented method of claim 1 , further comprising:

determining normal machine behavioral patterns based on the sensory input data of the machine; and

identifying, based on the normal machine behavioral patterns, at least one machine behavioral pattern that is indicative of the at least a suboptimal operation of the machine.

9. The computer-implemented method of claim 1 , further comprising:

determining a maximum threshold and a minimum threshold based on at least one repeated sequence from sensory input data; and

detecting an anomaly indicative of the at least one suboptimal operation of the machine based on the determined maximum and minimum thresholds.

10. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to perform a process, the process comprising:

monitoring sensory input data related to a machine;

analyzing, using unsupervised machine learning, the monitored sensory inputs, wherein the output of the unsupervised machine learning includes at least one indicator;

identifying, based on the at least one indicator, at least one machine behavioral pattern that is indicative of at least one suboptimal operation of the machine;

selecting at least one corrective action based on the at least one machine behavioral pattern, wherein the system is further configured to: extract one or more characteristics associated with the at least one machine behavioral pattern that is indicative of the at least one suboptimal operation of the at least one machine; search in at least one data source that comprises a plurality of corrective actions for one or more corrective actions based on extracted characteristics; and, select at least one corrective action having a first probability score that is above a first predetermined threshold to repair the at least one suboptimal operation of the machine, and a second probability score that is below a second predetermined threshold to damage the machine; and,

performing the at least one corrective action on the machine.

11. A system for identifying and repairing suboptimal operation 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 sensory input data related to an industrial machine;

analyze, using an unsupervised machine learning model, the monitored sensory inputs, wherein the output of the unsupervised machine learning model includes at least one indicator;

identify, based on the at least one indicator, at least one behavioral pattern related to the industrial machine, wherein each of the at least one behavioral pattern is indicative of at least one suboptimal operation of the industrial machine;

select at least one corrective action based on the at least one behavioral pattern, wherein selecting at least one corrective action further comprises: extracting one or more characteristics associated with the at least one machine behavioral pattern that is indicative of the at least one suboptimal operation of the at least one machine; searching in at least one data source that comprises a plurality of corrective actions for one or more corrective actions based on extracted characteristics; and, selecting at least one corrective action having a first probability score that is above a first predetermined threshold to repair the at least one suboptimal operation of the machine, and a second probability score that is below a second predetermined threshold to damage the machine; and

perform the at least one corrective action on the industrial machine.

12. The system of claim 11 , wherein the system is further configured to:

monitor the sensory input data associated with the industrial machine to determine an influence of the corrective action on the at least one machine.

13. The system of claim 12 , wherein the system is further configured to:

rank the at least one corrective action responsive of its effectiveness.

14. The system of claim 13 , wherein the system is further configured to:

store in a data source at least one of: the at least one behavioral pattern, the at least one corrective action, and the ranking of the at least one corrective action.

15. The system of claim 11 , wherein the system is further configured to:

predict, based on the at least one behavioral pattern and the monitored sensory input data, a failure of the industrial machine; and

select at least one corrective action based on the industrial machine failure prediction.

16. The system of claim 11 , wherein the system is further configured to:

preprocess raw sensory input data received from the sensors; and

store the preprocessed raw sensory input data in a data source.

17. The system of claim 16 , wherein the preprocessing includes at least one of: data cleansing, normalization, rescaling, re-trending, reformatting, and noise filtering.

18. The system of claim 11 , wherein the system is further configured to:

determine normal machine behavioral patterns based on the sensory input data of the machine; and

identify, based on the normal machine behavioral patterns, at least one machine behavioral pattern that is indicative of the at least a suboptimal operation of the machine.

19. The system of claim 11 , wherein the system is further configured to:

determine a maximum threshold and a minimum threshold based on at least one repeated sequence from sensory input data; and

detect an anomaly indicative of the at least one suboptimal operation of the machine based on the determined maximum and minimum thresholds.