Automated design of process automation facilities
Implementations herein leverage knowledge about historical process automation facilities to automate designing a new process automation facility. A first level design input may be processed to generate a first embedding that encodes design aspect(s) of the requested process automation facility with a degree of detail commensurate with a first level of a hierarchy reflected by design documents typically used to design a process automation facility. The first embedding may be used to find first level reference embeddings that encode design aspects of reference process automation facilities. Second level reference embedding(s) may be identified based on mapping(s) from the selected first level reference embedding(s). Each second level reference embedding may encode design aspect(s) of a respective reference process automation facility with a degree of detail that is commensurate with a second level of the design document hierarchy. Based on the second level reference embedding(s), template design document(s) may be provided.
1 . A method for designing at least part of a requested process automation facility, the method implemented using one or more processors and comprising:
receiving, at one or more input components, one or more inputs that describe the requested process automation facility;
based on the one or more inputs, generating a graph that includes a set of design aspects of the requested process automation facility that are conveyed in the one or more inputs;
processing the graph based on one or more machine learning models to identify one or more reference process automation facilities that are useable to generate design template documents for the requested process automation facility;
identifying one or more additional design aspects of one or more of the reference process automation facilities that were not contained in the set of design aspects of the requested process automation facility; and
providing one or more of the identified additional design aspects of one or more of the reference process automation facilities via one or more output devices.
2 . The method of claim 1 , wherein one or more of the machine learning models comprises a graph neural network (GNN).
3 . The method of claim 1 , wherein the graph includes a plurality of nodes representing a plurality of processes to be implemented in the requested process automation facility, and a plurality of edges that define relationships between the plurality of processes.
4 . The method of claim 1 , wherein the graph includes a plurality of nodes representing a plurality of process automation nodes to be implemented in the requested process automation facility, and a plurality of edges that represent network communication channels between the plurality of process automation nodes.
5 . The method of claim 1 , wherein the graph includes one or more nodes representing one or more modular automated process assemblies to be implemented in the requested process automation facility, and a plurality of edges that define relationships between the one or more modular process automation assemblies and other elements of the requested process automation facility.
6 . The method of claim 1 , wherein the providing includes, based on the identified additional design aspects of one or more of the reference process automation facilities, providing one or more template design documents for the requested process automation facility.
7 . The method of claim 1 , wherein the one or more reference process automation facilities comprise a plurality of reference process automation facilities.
8 . The method of claim 7 , wherein the one or more additional design aspects comprise intransient design aspects that are shared among the plurality of reference process automation facilities.
9 . The method of claim 1 , further comprising comparing a first embedding generated based on the set of the design aspects of the requested process automation facility using one or more of the machine learning models with reference embeddings generated based on design aspects of a plurality of candidate reference process automation facilities using one or more of the machine learning models, wherein the one or more reference process automation facilities are selected from the plurality of candidate reference process automation facilities based on measures of similarity between the first embedding and the reference embeddings.
10 . A system for designing at least part of a requested process automation facility, the system comprising one or more processors and memory storing instructions that, in response to execution of the instructions, cause the one or more processors to
receive, at one or more input components, one or more inputs that describe the requested process automation facility;
based on the one or more inputs, generate a graph that includes a set of design aspects of the requested process automation facility that are conveyed in the one or more inputs;
process the graph based on one or more machine learning models to identify one or more reference process automation facilities that are useable to generate design template documents for the requested process automation facility;
identify one or more additional design aspects of one or more of the reference process automation facilities that were not contained in the set of design aspects of the requested process automation facility; and
provide one or more of the identified additional design aspects of one or more of the reference process automation facilities via one or more output devices.
11 . The system of claim 10 , wherein one or more of the machine learning models comprises a graph neural network (GNN).
12 . The system of claim 10 , wherein the graph includes a plurality of nodes representing a plurality of processes to be implemented in the requested process automation facility, and a plurality of edges that define relationships between the plurality of processes.
13 . The system of claim 10 , wherein the graph includes a plurality of nodes representing a plurality of process automation nodes to be implemented in the requested process automation facility, and a plurality of edges that represent network communication channels between the plurality of process automation nodes.
14 . The system of claim 10 , wherein the graph includes one or more nodes representing one or more modular automated process assemblies to be implemented in the requested process automation facility, and a plurality of edges that define relationships between the one or more modular process automation assemblies and other elements of the requested process automation facility.
15 . The system of claim 10 , wherein the instructions to provide include, based on the identified additional design aspects of one or more of the reference process automation facilities, instructions to provide one or more template design documents for the requested process automation facility.
16 . The system of claim 10 , wherein the one or more reference process automation facilities comprise a plurality of reference process automation facilities.
17 . The system of claim 16 , wherein the one or more additional design aspects comprise intransient design aspects that are shared among the plurality of reference process automation facilities.
18 . The system of claim 10 , further comprising instructions to compare a first embedding generated based on the set of the design aspects of the requested process automation facility using one or more of the machine learning models with reference embeddings generated based on design aspects of a plurality of candidate reference process automation facilities using one or more of the machine learning models, wherein the one or more reference process automation facilities are selected from the plurality of candidate reference process automation facilities based on measures of similarity between the first embedding and the reference embeddings.
19 . A non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by a processor, cause the processor to:
receive, at one or more input components, one or more inputs that describe the requested process automation facility;
based on the one or more inputs, generate a graph that includes a set of design aspects of the requested process automation facility that are conveyed in the one or more inputs;
process the graph based on one or more machine learning models to identify one or more reference process automation facilities that are useable to generate design template documents for the requested process automation facility;
identify one or more additional design aspects of one or more of the reference process automation facilities that were not contained in the set of design aspects of the requested process automation facility; and
provide one or more of the identified additional design aspects of one or more of the reference process automation facilities via one or more output devices.
20 . The non-transitory computer-readable medium of claim 19 , wherein one or more of the machine learning models comprises a graph neural network (GNN).