Dynamic monitoring and securing of factory processes, equipment and automated systems
A training set that includes at least two data types corresponding to operations and control of a manufacturing process is obtained. A deep learning processor is trained to predict expected characteristics of output control signals that correspond with one or more corresponding input operating instructions. A first input operating instruction is received from a first signal splitter. A first output control signal is received from a second signal splitter. The deep learning processor correlates the first input operating instruction and the first output control signal. Based on the correlating, the deep learning processor determines that the first output control signal is not within a range of expected values based on the first input operating instruction. Responsive to the determining, an indication of an anomalous activity is provided as a result of detection of the anomalous activity in the manufacturing process.
1. A method for detecting unexpected activity in a manufacturing environment, comprising:
receiving, by a deep learning processor deployed in a manufacturing environment from a first signal splitter disposed between a data processing server and a first controller in the manufacturing environment, a first duplicated input signal instance of a first input operating instruction generated by the data processing server, wherein the first signal splitter generates the first duplicated input signal instance of the first input operating instruction and a second duplicated input signal instance of the first input operating instruction;
receiving, by the deep learning processor from a second signal splitter disposed between the first controller and a first process station in the manufacturing environment, a first output control signal generated by the first controller;
receiving, by the deep learning processor from a third signal splitter disposed between the first process station and the first controller, a control value measured by a sensor at the first process station;
correlating, by the deep learning processor, the first input operating instruction and the first output control signal;
based on the correlating, determining, by the deep learning processor, that the first output control signal is within a range of expected values based on the first input operating instruction;
further correlating, by the deep learning processor, the first input operating instruction, the first output control signal, and the control value;
based on the further correlating, determining, by the deep learning processor, that the control value is not within a range of expected control values; and
responsive to determining that the control value is not within the range of expected control values, providing an indication of an unexpected activity.
2. The method of claim 1 , wherein the first signal splitter forwards the second duplicated input signal instance to the first controller.
3. The method of claim 1 , further comprising:
generating a suggested action to eliminate or address the unexpected activity.
4. The method of claim 1 , wherein providing the indication of the unexpected activity comprises:
determining a component in the manufacturing environment that triggered the unexpected activity; and
flagging the component in the indication of the unexpected activity.
5. The method of claim 1 , wherein determining, by the deep learning processor, that the control value is not within the range of expected control values comprises:
identifying components of the control value that are not within the range of expected components of the expected control values.
6. The method of claim 5 , wherein providing the indication of the unexpected activity comprises:
generating an alert specifying the components of the control value.
7. The method of claim 1 , further comprising:
generating a confidence level associated with a determination that the control value is not within the range of expected control values.
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:
receiving, by a deep learning processor deployed in a manufacturing environment from a first signal splitter disposed between a data processing server and a first controller in the manufacturing environment, a first duplicated input signal instance of a first input operating instruction generated by the data processing server, wherein the first signal splitter generates the first duplicated input signal instance of the first input operating instruction and a second duplicated input signal instance of the first input operating instruction;
receiving, by the deep learning processor from a second signal splitter disposed between the first controller and a first process station in the manufacturing environment, a first output control signal generated by the first controller;
receiving, by the deep learning processor from a third signal splitter disposed between the first process station and the first controller, a control value measured by a sensor at the first process station;
correlating, by the deep learning processor, the first input operating instruction and the first output control signal;
based on the correlating, determining, by the deep learning processor, that the first output control signal is within a range of expected values based on the first input operating instruction;
further correlating, by the deep learning processor, the first input operating instruction, the first output control signal, and the control value;
based on the further correlating, determining, by the deep learning processor, that the control value is not within a range of expected control values; and
responsive to determining that the control value is not within the range of expected control values, providing an indication of an unexpected activity.
9. The non-transitory computer readable medium of claim 8 , wherein the first signal splitter forwards the second duplicated input signal instance to the first controller.
10. The non-transitory computer readable medium of claim 8 , further comprising:
generating a suggested action to eliminate or address the unexpected activity.
11. The non-transitory computer readable medium of claim 8 , wherein providing the indication of the unexpected activity comprises:
determining a component in the manufacturing environment that triggered the unexpected activity; and
flagging the component in the indication of the unexpected activity.
12. The non-transitory computer readable medium of claim 8 , wherein determining, by the deep learning processor, that the control value is not within the range of expected control values comprises:
identifying components of the control value that are not within the range of expected components of the expected control values.
13. The non-transitory computer readable medium of claim 12 , wherein providing the indication of the unexpected activity comprises:
generating an alert specifying the components of the control value.
14. The non-transitory computer readable medium of claim 8 , further comprising:
generating a confidence level associated with a determination that the control value is not within the range of expected control values.
15. A system comprising:
a deep learning processor; and
a memory having programming instructions stored thereon, which, when executed by the deep learning processor, causes the system to perform operations comprising:
receiving, by the deep learning processor deployed in a manufacturing environment from a first signal splitter disposed between a data processing server and a first controller in the manufacturing environment, a first duplicated input signal instance of a first input operating instruction generated by the data processing server, wherein the first signal splitter generates the first duplicated input signal instance of the first input operating instruction and a second duplicated input signal instance of the first input operating instruction;
receiving, by the deep learning processor from a second signal splitter disposed between the first controller and a first process station in the manufacturing environment, a first output control signal generated by the first controller;
receiving, by the deep learning processor from a third signal splitter disposed between the first process station and the first controller, a control value measured by a sensor at the first process station;
correlating, by the deep learning processor, the first input operating instruction and the first output control signal;
based on the correlating, determining, by the deep learning processor, that the first output control signal is within a range of expected values based on the first input operating instruction;
further correlating, by the deep learning processor, the first input operating instruction, the first output control signal, and the control value;
based on the further correlating, determining, by the deep learning processor, that the control value is not within a range of expected control values; and
responsive to determining that the control value is not within the range of expected control values, providing an indication of an unexpected activity.
16. The system of claim 15 , wherein the first signal splitter forwards the second duplicated input signal instance to the first controller.
17. The system of claim 15 , wherein the operations further comprise:
generating a suggested action to eliminate or address the unexpected activity.
18. The system of claim 15 , wherein providing the indication of the unexpected activity comprises:
determining a component in the manufacturing environment that triggered the unexpected activity; and
flagging the component in the indication of the unexpected activity.
19. The system of claim 15 , wherein determining, by the deep learning processor, that the control value is not within the range of expected control values comprises:
identifying components of the control value that are not within the range of expected components of the expected control values; and
generating an alert specifying the components of the control value.
20. The system of claim 15 , wherein the operations further comprise:
generating a confidence level associated with a determination that the control value is not within the range of expected control values.