Predictive process control for a manufacturing process
Aspects of the disclosed technology encompass the use of a deep-learning controller for monitoring and improving a manufacturing process. In some aspects, a method of the disclosed technology includes steps for: receiving control values associated with a process station in a manufacturing process, predicting an expected value for an article of manufacture output from the process station, and determining if the deep-learning controller can control the manufacturing process based on the expected value. Systems and computer-readable media are also provided.
1. A computer-implemented method for detecting unexpected activity in a manufacturing process executed in a manufacturing system comprising a plurality of process stations, the computer-implemented method comprising:
receiving a set of control values generated at a first process station of the plurality of process stations;
projecting a final output value or intermediate output value for an article of manufacture undergoing the manufacturing process based on the set of control values;
determining that the final output value of the intermediate output value is out of specification;
based on the determining, identifying a key influencer in the set of control values that impacts the final output value or the intermediate output value; and
based on the identifying, generating updated control inputs for a second process station downstream of the first process station to bring the article of manufacture within specification based on the identified key influencer.
2. The computer-implemented method of claim 1 , wherein identifying the key influencer in the set of control values that impacts the final output value or the intermediate output value comprises:
identifying one or more parameters that affect the final output value or the intermediate output value.
3. The computer-implemented method of claim 2 , further comprising:
ranking the one or more parameters based on their influence on the final output value or the intermediate output value.
4. The computer-implemented method of claim 3 , further comprising:
identifying a highest ranked parameter of the one or more parameters, wherein the highest ranked parameter is the identified key influencer.
5. The computer-implemented method of claim 3 , further comprising:
identifying a subset of the one or more parameters that exceed a threshold level of influence on the final output value or the intermediate output value, wherein the subset of the one or more parameters comprises the identified key influencer.
6. The computer-implemented method of claim 1 , further comprising:
predicting one or more control inputs for controlling the key influencer to bring the article of manufacture within specification.
7. The computer-implemented method of claim 6 , wherein the updated control inputs are based on the predicted one or more control inputs.
8. A system comprising:
a processor; and
a memory having programming instructions stored thereon, which, when executed by the processor, causes the system to perform operations comprising:
receiving a set of control values generated at a first process station of a plurality of process stations;
projecting a final output value or intermediate output value for an article of manufacture undergoing a manufacturing process based on the set of control values;
determining that the final output value of the intermediate output value is out of specification;
based on the determining, identifying a key influencer in the set of control values that impacts the final output value or the intermediate output value; and
based on the identifying, generating updated control inputs for a second process station downstream of the first process station to bring the article of manufacture within specification based on the identified key influencer.
9. The system of claim 8 , wherein identifying the key influencer in the set of control values that impacts the final output value or the intermediate output value comprises:
identifying one or more parameters that affect the final output value or the intermediate output value.
10. The system of claim 9 , further comprising:
ranking the one or more parameters based on their influence on the final output value or the intermediate output value.
11. The system of claim 10 , further comprising:
identifying a highest ranked parameter of the one or more parameters, wherein the highest ranked parameter is the identified key influencer.
12. The system of claim 10 , further comprising:
identifying a subset of the one or more parameters that exceed a threshold level of influence on the final output value or the intermediate output value, wherein the subset of the one or more parameters comprises the identified key influencer.
13. The system of claim 8 , wherein the operations further comprise:
predicting one or more control inputs for controlling the key influencer to bring the article of manufacture within specification.
14. The system of claim 13 , wherein the updated control inputs are based on the predicted one or more control inputs.
15. 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 a set of control values generated at a first process station of a plurality of process stations;
projecting a final output value or intermediate output value for an article of manufacture undergoing a manufacturing process based on the set of control values;
determining that the final output value of the intermediate output value is out of specification;
based on the determining, identifying a key influencer in the set of control values that impacts the final output value or the intermediate output value; and
based on the identifying, generating updated control inputs for a second process station downstream of the first process station to bring the article of manufacture within specification based on the identified key influencer.
16. The non-transitory computer readable medium of claim 15 , wherein
identifying the key influencer in the set of control values that impacts the final output value or the intermediate output value comprises:
identifying one or more parameters that affect the final output value or the intermediate output value.
17. The non-transitory computer readable medium of claim 16 , further comprising:
ranking the one or more parameters based on their influence on the final output value or the intermediate output value.
18. The non-transitory computer readable medium of claim 17 , further comprising:
identifying a highest ranked parameter of the one or more parameters, wherein the highest ranked parameter is the identified key influencer.
19. The non-transitory computer readable medium of claim 17 , further comprising:
identifying a subset of the one or more parameters that exceed a threshold level of influence on the final output value or the intermediate output value, wherein the subset of the one or more parameters comprises the identified key influencer.
20. The non-transitory computer readable medium of claim 15 , wherein the operations further comprise:
predicting one or more control inputs for controlling the key influencer to bring the article of manufacture within specification, wherein the updated control inputs are based on the predicted one or more control inputs.