Method, systems and apparatus for intelligently emulating factory control systems and simulating response data
A simulated process is initiated. The simulated process includes generating, by an emulator, a control signal based on external inputs. The simulated process further includes processing, by a simulator, the control signal to generate simulated response data. The simulated process further includes generating, by a deep learning processor, expected behavioral pattern data based on the simulated response data. An actual process is initiated by initializing setpoints for a process station in a manufacturing system. The actual process includes generating, by the deep learning processor, actual behavioral pattern data based on actual process data from the at least one process station. The deep learning processor compares the expected behavioral pattern to the actual behavioral pattern. Based on the comparing, the deep learning processor determines that anomalous activity is present in the manufacturing system. Based on the anomalous activity being present, the deep learning processor initiates an alert protocol.
1. A method of detecting unexpected activity in a manufacturing environment, comprising:
simulating, by a computing system, response data for a manufacturing process executing within a manufacturing system based on a control signal;
generating, by a deep learning processor of the computing system, expected behavioral pattern data based on the simulated response data;
receiving, by the computing system, actual response data for the manufacturing process executing within the manufacturing system;
generating, by the deep learning processor of the computing system, actual behavioral pattern data based on actual process data;
comparing, by the deep learning processor, the expected behavioral pattern data to the actual behavioral pattern data;
based on the comparing, generating, by the deep learning processor, a confidence level that represents a confidence that unexpected activity is present in the manufacturing system; and
initiating, by the computing system, one or more remedial actions in accordance with the confidence level associated with the unexpected activity.
2. The method of claim 1 , further comprising:
generating, by the computing system, an emulated control signal for the manufacturing process using an emulator, wherein the control signal used by the computing system to generate the response data is the emulated control signal.
3. The method of claim 1 , wherein initiating, by the computing system, the one or more remedial actions in accordance with the confidence level associated with the unexpected activity comprises:
determining that the confidence level associated with the unexpected activity exceeds a threshold level of confidence that the unexpected activity exists; and
based on the determining, issuing an alert protocol to signal existence of the unexpected activity.
4. The method of claim 1 , wherein initiating, by the computing system, the one or more remedial actions in accordance with the confidence level associated with the unexpected activity comprises:
determining that the confidence level associated with the unexpected activity exceeds a threshold level of confidence that the unexpected activity exists; and
based on the determining, prompting a human operator to review the unexpected activity.
5. The method of claim 1 , wherein generating, by the deep learning processor, the confidence level that represents the confidence that the unexpected activity is present in the manufacturing system comprises:
predicting, by the deep learning processor, that the unexpected activity is present in the manufacturing system based on the comparing; and
generating a numerical probability that represents an accuracy of the predicting.
6. The method of claim 1 , wherein initiating, by the computing system, the one or more remedial actions in accordance with the confidence level associated with the unexpected activity comprises:
determining that the confidence level associated with the unexpected activity exceeds a threshold level of confidence that the unexpected activity exists; and
based on the determining, causing the manufacturing system to shut down.
7. The method of claim 1 , wherein the one or more remedial actions comprises one or more of a mechanical action, a digital action, or a functional action.
8. A non-transitory computer readable medium comprising one or more sequences of instructions, which, when executed by a processor, causes a computing system to perform operations comprising:
simulating, by the computing system, response data for a manufacturing process executing within a manufacturing system based on a control signal;
generating, by a deep learning processor of the computing system, expected behavioral pattern data based on the simulated response data;
receiving, by the computing system, actual response data for the manufacturing process executing within the manufacturing system;
generating, by the deep learning processor of the computing system, actual behavioral pattern data based on actual process data;
comparing, by the deep learning processor, the expected behavioral pattern data to the actual behavioral pattern data;
based on the comparing, generating, by the deep learning processor, a confidence level that represents a confidence that unexpected activity is present in the manufacturing system; and
initiating, by the computing system, one or more remedial actions in accordance with the confidence level associated with the unexpected activity.
9. The non-transitory computer readable medium of claim 8 , further comprising:
generating, by the computing system, an emulated control signal for the manufacturing process using an emulator, wherein the control signal used by the computing system to generate the response data is the emulated control signal.
10. The non-transitory computer readable medium of claim 8 , wherein initiating, by the computing system, the one or more remedial actions in accordance with the confidence level associated with the unexpected activity comprises:
determining that the confidence level associated with the unexpected activity exceeds a threshold level of confidence that the unexpected activity exists; and
based on the determining, issuing an alert protocol to signal existence of the unexpected activity.
11. The non-transitory computer readable medium of claim 8 , wherein initiating, by the computing system, the one or more remedial actions in accordance with the confidence level associated with the unexpected activity comprises:
determining that the confidence level associated with the unexpected activity exceeds a threshold level of confidence that the unexpected activity exists; and
based on the determining, prompting a human operator to review the unexpected activity.
12. The non-transitory computer readable medium of claim 8 , wherein generating, by the deep learning processor, the confidence level that represents the confidence that the unexpected activity is present in the manufacturing system comprises:
predicting, by the deep learning processor, that the unexpected activity is present in the manufacturing system based on the comparing; and
generating a numerical probability that represents an accuracy of the predicting.
13. The non-transitory computer readable medium of claim 8 , wherein initiating, by the computing system, the one or more remedial actions in accordance with the confidence level associated with the unexpected activity comprises:
determining that the confidence level associated with the unexpected activity exceeds a threshold level of confidence that the unexpected activity exists; and
based on the determining, causing the manufacturing system to shut down.
14. The non-transitory computer readable medium of claim 8 , wherein the one or more remedial actions comprises one or more of a mechanical action, a digital action, or a functional action.
15. A system comprising:
a processor; and
a memory having one or more programming instructions stored thereon, which, when executed by the processor, causes the system to perform operations comprising:
simulating response data for a manufacturing process executing within a manufacturing system based on a control signal;
generating, by a deep learning processor, expected behavioral pattern data based on the simulated response data;
receiving actual response data for the manufacturing process executing within the manufacturing system;
generating, by the deep learning processor, actual behavioral pattern data based on actual process data;
comparing, by the deep learning processor, the expected behavioral pattern data to the actual behavioral pattern data;
based on the comparing, generating, by the deep learning processor, a confidence level that represents a confidence that unexpected activity is present in the manufacturing system; and
initiating one or more remedial actions in accordance with the confidence level associated with the unexpected activity.
16. The system of claim 15 , further comprising:
generating an emulated control signal for the manufacturing process using an emulator, wherein the control signal used to generate the response data is the emulated control signal.
17. The system of claim 15 , wherein initiating the one or more remedial actions in accordance with the confidence level associated with the unexpected activity comprises:
determining that the confidence level associated with the unexpected activity exceeds a threshold level of confidence that the unexpected activity exists; and
based on the determining, issuing an alert protocol to signal existence of the unexpected activity.
18. The system of claim 15 , wherein initiating the one or more remedial actions in accordance with the confidence level associated with the unexpected activity comprises:
determining that the confidence level associated with the unexpected activity exceeds a threshold level of confidence that the unexpected activity exists; and
based on the determining, prompting a human operator to review the unexpected activity.
19. The system of claim 15 , wherein generating, by the deep learning processor, the confidence level that represents the confidence that the unexpected activity is present in the manufacturing system comprises:
predicting, by the deep learning processor, that the unexpected activity is present in the manufacturing system based on the comparing; and
generating a numerical probability that represents an accuracy of the predicting.
20. The system of claim 15 , wherein initiating the one or more remedial actions in accordance with the confidence level associated with the unexpected activity comprises:
determining that the confidence level associated with the unexpected activity exceeds a threshold level of confidence that the unexpected activity exists; and
based on the determining, causing the manufacturing system to shut down.