System and method for casual inference in manufacturing process

1. A computer-implemented method, the method comprising:

receiving, by a computer, data associated with a processing system which includes a set of interconnected machines and an associated set of processes;

generating, based on the data, a graph indicating flows of outputs between the machines as part of the processes;

determining, based on a set of variables, one or more candidate clusters in the graph, wherein a candidate cluster is provided with one or more variables of interest;

performing, based on the one or more variables of interest, root cause analysis on the one or more candidate clusters by:

applying, based on the one or more variables of interest, an additive noise model to prune the one or more candidate clusters from the graph; and

determining, based on the pruned graph, a candidate pathway likely to cause an issue in at least one process, thereby facilitating improved efficiency in the processing system.

2. The computer-implemented method of claim 1 , wherein the set of set of variables includes one or more of:

an issue associated with a respective machine;

a number of times a respective pathway including a group of machines is applied in the processing system;

redundant pathways applied;

a number of times maintenance event is performed on machines in a respective pathway; and

temporal information.

3. The computer-implemented method of claim 1 , wherein the data includes timestamp information, machine status information, product-batch information, parts processed by different machines.

4. The computer-implemented method of claim 3 ,

wherein the product-batch information comprises a lot number which corresponds to a plurality of physical objects of the processing system, wherein the physical objects share at least one common characteristic, and

wherein the machine status information comprises one or more of an identifier of an issue and a fault type.

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

providing a feedback, based on the candidate pathway, to indicate one or more root causes for a given stop-code;

displaying, via a graphical user interface, a visual representation of the feedback, wherein the visual representation of the feedback includes:

a pruned graph of the one or more candidate clusters; and

a visual representation of a selection of a most likely causal pathway in the pruned graph.

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

determining, based on the additive noise model, a set of scores for each pathway in the one or more candidate clusters, wherein a respective score indicates a degree of causality associated with a pair of machines in a process flow with respect to a variable of interest; and

displaying the set of scores associated with each pathway in the one or more candidate clusters.

7. The computer-implemented method of claim 1 , wherein the processing system comprises one or more of:

a manufacturing system;

a cloud computing system; and

a supply chain system.

8. The computer-implemented method of claim 1 ,

wherein the graph represents a network topology corresponding to the processing system;

wherein a respective node in the graph indicates, for a respective output, a machine which processes the respective output, a process associated with the machine, and a stop-code associated with the machine and the process; and

wherein a respective edge in the graph indicates, for the respective output, a logical flow of a process from a source node to a target node;

wherein a number indicated in the respective node in the graph corresponds to a machine number; and

wherein a weight of a respective edge associated with the one or more candidate clusters in the graph indicates a degree of causality associated with the source node and the target node.

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

receiving, via a graphical user interface, a selection of one or more pathways in a visual representation of the graph.

10. The computer-implemented method of claim 1 , wherein the outputs comprise materials and include physical objects upon which the machines of the processing system perform the processes, and

wherein a respective physical object is associated with a lot number and a production line of the processing system.

11. A computer system, comprising:

a processor; and

a storage device coupled to the processor and storing instructions which when executed by the processor cause the processor to perform a method, the method comprising:

receiving data associated with a processing system which includes a set of interconnected machines and an associated set of processes;

generating, based on the data, a graph indicating flows of outputs between the machines as part of the processes;

determining, based on a set of variables, one or more candidate clusters in the graph, wherein a candidate cluster is provided with one or more variables of interest;

performing, based on the one or more variables of interest, root cause analysis on the one or more candidate clusters by:

applying, based on the one or more variables of interest, an additive noise model to prune the one or more candidate clusters from the graph; and

determining, based on the pruned graph, a candidate pathway likely to cause an issue in at least one process, thereby facilitating improved efficiency in the processing system.

12. The computer system of claim 11 , wherein the set of variables includes one or more of:

an issue associated with a respective machine;

a number of times a respective pathway including a group of machines is applied in the processing system;

redundant pathways applied;

a number of times maintenance event is performed on machines in a respective pathway; and

temporal information.

13. The computer system of claim 11 , wherein the data includes timestamp information, machine status information, product-batch information, parts processed by different machines.

14. The computer system of claim 13 ,

wherein the product-batch information comprises a lot number which corresponds to a plurality of physical objects of the processing system, wherein the physical objects share at least one common characteristic, and

wherein the machine status information comprises one or more of an identifier of an issue and a fault type.

15. The computer system of claim 11 , wherein the method further comprising:

providing a feedback, based on the candidate pathway, to indicate one or more root causes for a given stop-code;

displaying, via a graphical user interface, a visual representation of the feedback, wherein the visual representation of the feedback includes:

a pruned graph of the one or more candidate clusters; and

a visual representation of a selection of a most likely causal pathway in the pruned graph.

16. The computer system of claim 11 , the method further comprising:

determining, based on the additive noise model, a set of scores for each pathway in the one or more candidate clusters, wherein a respective score indicates a degree of causality associated with a pair of machines in a process flow with respect to a variable of interest; and

displaying the set of scores associated with each pathway in the one or more candidate clusters.

17. The computer system of claim 11 , wherein the processing system comprises one or more of:

a manufacturing system;

a cloud computing system; and

a supply chain system.

18. The computer system of claim 11 ,

wherein the graph represents a network topology corresponding to the processing system;

wherein a respective node in the graph indicates, for a respective output, a machine which processes the respective output, a process associated with the machine, and a stop-code associated with the machine and the process; and

wherein a respective edge in the graph indicates, for the respective output, a logical flow of a process from a source node to a target node;

wherein a number indicated in the respective node in the graph corresponds to a machine number; and

wherein a weight of a respective edge associated with the one or more candidate clusters in the graph indicates a degree of causality associated with the source node and the target node.

19. The computer system of claim 11 , wherein the method further comprising:

receiving, via a graphical user interface, a selection of one or more pathways in a visual representation of the graph.

20. The computer system of claim 11 , wherein the outputs comprise materials and include physical objects upon which the machines of the processing system perform the processes, and

wherein a respective physical object is associated with a lot number and a production line of the processing system.