Predictive maintenance for semiconductor manufacturing equipment

Abstract

[0006] Various embodiments herein relate to systems and methods for predictive maintenance of semiconductor manufacturing equipment. In some embodiments, the predictive maintenance system includes a processor configured to: receive offline data indicative of historical operating conditions and historical manufacturing information corresponding to manufacturing equipment performing a manufacturing process; calculate predicted equipment health information using a trained model that receives the offline data as input; receive real-time data indicative of current operating conditions of the manufacturing equipment; calculate estimated equipment health information using the trained model that receives the real-time data as input; calculate regulated equipment health information by combining the predicted equipment health information and the estimated equipment health information; and present the regulated equipment health information including an expected remaining useful life (RUL) of at least one component of the manufacturing equipment.

Claims

1. It is a predictive maintenance system, Memory and Processor and Equipped with, When the processor executes a computer-executable instruction stored in the memory, The system receives offline data indicating historical operating conditions and historical manufacturing information corresponding to the manufacturing equipment that performs the manufacturing process. Using a trained model that receives the aforementioned offline data as input, predictive device health status information related to the manufacturing equipment is calculated. The system receives real-time data indicating the current operating conditions and current manufacturing information corresponding to the aforementioned manufacturing equipment. Using the trained model that receives the real-time data as input, estimated device health status information related to the manufacturing device is calculated. By combining the predicted device health status information calculated based on the offline data and the estimated device health status information calculated based on the real-time data, the adjustment device health status information related to the manufacturing device is calculated. The aforementioned adjustment device is configured to display health status information. The adjustment device health status information includes the expected remaining useful life (RUL) of at least one component of the manufacturing device, in a system.

2. A predictive maintenance system according to claim 1, wherein the offline data indicating historical operating conditions and the real-time data indicating current operating conditions include data received from one or more sensors of the manufacturing apparatus.

3. A predictive maintenance system according to claim 1 or 2, wherein the model is trained using physically based simulation data.

4. A predictive maintenance system according to claim 3, wherein the physical-based simulation data includes estimated data at a first spatial location of the manufacturing apparatus, estimated based on sensor data measured at one or more other spatial locations of the manufacturing apparatus where physical sensors are located.

5. A predictive maintenance system according to claim 4, wherein the estimated data is an interpolation of the measured sensor data.

6. A predictive maintenance system according to claim 1 or 2, wherein the model is trained using measurement data relating to a substrate including an electronic device processed using the manufacturing process.

7. A predictive maintenance system according to claim 1 or 2, wherein the processor is further configured to extract features of the offline data indicating historical operating conditions and features of the real-time data indicating current operating conditions, and the trained model receives the extracted features as input.

8. A predictive maintenance system according to claim 1 or 2, wherein the processor further comprises: Based on the real-time data indicating the current operating conditions, abnormal conditions of the manufacturing apparatus are detected. A system configured to identify the type of failure associated with the manufacturing apparatus in response to the detection of the abnormal conditions of the manufacturing apparatus.

9. A predictive maintenance system according to claim 8, wherein detecting the abnormal conditions of the manufacturing apparatus is based on a comparison of real-time data indicating current operating conditions and offline data indicating historical operating conditions.

10. A predictive maintenance system according to claim 8, wherein identifying the type of failure related to the manufacturing apparatus includes classifying the real-time data indicating current operating conditions using a historical failure database.

11. A predictive maintenance system according to claim 8, wherein identifying the type of failure related to the manufacturing apparatus includes classifying the real-time data indicating current operating conditions using physically based simulation data.

12. A predictive maintenance system according to claim 1 or 2, wherein the processor further comprises: Identify the changes in the current operating conditions of the manufacturing apparatus and the possibility that the changes in the current operating conditions may change the expected remaining useful life of at least one component of the manufacturing apparatus. A system configured to present the identified changes to the current operating conditions.

13. A predictive maintenance system according to claim 12, wherein the change in the current operating conditions of the manufacturing apparatus is identified based on physical-based simulation data.

14. A predictive maintenance system according to claim 1 or 2, wherein the processor further comprises: The health status information of the second adjustment device related to the second manufacturing device that performs the aforementioned manufacturing process is calculated. The health status information of the second adjustment device is based on the fact that the second manufacturing device has at least one of the components of the manufacturing device, A system configured to suggest, based on the health status information of the second adjustment device, that at least one component be removed from the manufacturing device for use in the second manufacturing device.

15. A predictive maintenance system according to claim 14, wherein the health status information of the second adjustment device is calculated in response to a determination that the RUL of at least one component is lower than a predetermined threshold.

16. A predictive maintenance system according to claim 15, wherein the proposal is presented in response to a determination that the second RUL corresponding to the at least one component when used in the second manufacturing apparatus exceeds the RUL of the at least one component when used in the manufacturing apparatus.

17. It is a predictive maintenance system, Memory and Processor and Equipped with, When the processor executes a computer-executable instruction stored in the memory, The system receives offline data indicating historical operating conditions and historical manufacturing information corresponding to the manufacturing equipment that performs the manufacturing process. The offline data includes offline sensor data from a plurality of sensors related to the manufacturing apparatus. Using one or more physical-based simulation models that model each component of the manufacturing apparatus, multiple physical-based simulation values ​​are generated. A system configured to train a neural network that generates a predictive device health status score using the aforementioned offline data and the aforementioned multiple physically based simulation values.

18. A predictive maintenance system according to claim 17, wherein each training sample used to train the neural network includes the offline data and the plurality of physically based simulation values ​​as inputs and measurement data as a target output.

19. A predictive maintenance system according to any one of claims 17 or 18, wherein the physical-based simulation values ​​among the plurality of physical-based simulation values ​​are estimated values ​​of measurements corresponding to the sensors among the plurality of sensors.

20. A predictive maintenance system according to claim 19, wherein the sensor among the plurality of sensors is located at a first position of the manufacturing apparatus, and the estimated value of the measurement is at a second position of the manufacturing apparatus.

21. A predictive maintenance system according to any one of claims 17 or 18, wherein the historical manufacturing information includes failure mode and effects analysis (FMEA) information corresponding to the manufacturing equipment.

22. A predictive maintenance system according to any one of claims 17 or 18, wherein the historical manufacturing information includes design information relating to the manufacturing apparatus.

23. A predictive maintenance system according to any one of claims 17 or 18, wherein the historical manufacturing information includes quality information retrieved from a quality database.

Images