System and method for chaining discrete models
Systems, computer program products, and computer-implemented methods for determining relationships between one or more outputs of a first model and one or more inputs of a second model that collectively represent a real world system, and chaining the models together. For example, the system described herein may determine how to chain a plurality of models by training an artificial intelligence system using the nodes of the models such that the trained artificial intelligence system predicts related output and input node connections. The system may then link related nodes to chain the models together. The systems, computer program products, and computer-implemented methods may thus, according to various embodiments, enable a plurality of discrete models to be optimally chained.
1. A computer-implemented method for model chaining, the method comprising:
obtaining a plurality of models, wherein the plurality of models comprises a first model and a second model, wherein the first model comprises at least one or more first objects, and wherein the second model comprises at least one or more second objects that are different than the at least one or more first objects;
simulating one or more first objects of the first model using first error detection data that indicates one or more errors that occurred in historical operation of the first model and one or more second objects of the second model using second error detection data that indicates one or more errors that occurred in historical operation of the second model to obtain a parameter output node of the first model and a parameter input node of the second model;
training an artificial intelligence model using the parameter output node of the first model and the parameter input node of the second model, wherein the trained artificial intelligence model, when executed, generates a prediction that the parameter output node of the first model is related to the parameter input node of the second model; and
based at least in part on the generated prediction of the trained artificial intelligence model and an ontological layer, chaining the first and second models by linking the parameter output node of the first model with the parameter input node of the second model, wherein the ontological layer comprises a mapping of a nodal relationship between parameter output and input nodes,
wherein the method is performed using one or more processors.
2. The computer-implemented method of claim 1 , further comprising optimizing the chained first and second models by recurrently linking related parameter output nodes with related parameter input nodes.
3. The computer-implemented method of claim 1 , further comprising optimizing the chained first and second models by iteratively optimizing a converging series of the chained first and second models.
4. The computer-implemented method of claim 3 , wherein the converging series of the chained first and second models converges towards an optima, wherein a gradient on the series of the chained first and second models converges towards the optima.
5. The computer-implemented method of claim 1 , wherein the artificial intelligence model is a recurrent neural network.
6. The computer-implemented method of claim 5 , wherein training an artificial intelligence model further comprises unrolling the recurrent neural network.
7. The computer-implemented method of claim 6 , wherein training an artificial intelligence model further comprises applying a backpropagation to the unrolled recurrent neural network to calculate and accumulate one or more gradients.
8. The computer-implemented method of claim 1 , wherein the first model is one of a known or black box system.
9. The computer-implemented method of claim 1 , wherein the at least one or more first objects are one of physical or virtual devices.
10. The computer-implemented method of claim 9 , wherein the at least one or more first objects at least one of detect, measure, position, signal, gauge, or sense external stimuli.
11. The computer-implemented method of claim 10 , wherein the at least one or more first objects are at least one of user configurable, editable, or removable.
12. The computer-implemented method of claim 1 , wherein the first and second models are simulated for a time range or a point in time.
13. The computer-implemented method of claim 1 , further comprising causing display of the chained first and second models in a graphical user interface that depicts at least one of interconnections between the first and second models, the parameter input node, the parameter output node, or the at least one or more first objects.
14. The computer-implemented method of claim 1 , wherein the first model is associated with a health value that indicates a health of the first model.
15. The computer-implemented method of claim 14 , further comprising generating a model hierarchy based on the health of the first model and a health of the second model.
16. The computer-implemented method of claim 15 , further comprising grouping a third model in the plurality of models and a fourth model in the plurality of models that share related parameter nodes.
17. A system for model chaining comprising:
one or more non-transitory computer readable storage mediums storing program instructions; and
one or more processors configured to execute the program instructions, wherein the program instructions, when executed, cause the system to:
obtain a plurality of models, wherein the plurality of models comprises a first model and a second model, wherein the first model comprises at least one or more first objects, and wherein the second model comprises at least one or more second objects that are different than the at least one or more first objects;
simulate one or more first objects of the first model using first error detection data that indicates one or more errors that occurred in historical operation of the first model and one or more second objects of the second model using second error detection data that indicates one or more errors that occurred in historical operation of the second model to obtain a parameter output node of the first model and a parameter input node of the second model;
train an artificial intelligence model using the parameter output node of the first model and the parameter input node of the second model, wherein the trained artificial intelligence model, when executed, generates a prediction that the parameter output node of the first model is related to the parameter input node of the second model; and
based at least in part on the generated prediction of the trained artificial intelligence model and an ontological layer, chain the first and second models by linking the parameter output node of the first model with the parameter input node of the second model, wherein the ontological layer comprises a mapping of a nodal relationship between parameter output and input nodes.
18. The computer-implemented method of claim 2 , wherein recurrently linking related parameter output nodes with related parameter input nodes comprises:
training the artificial intelligence model using current nodal relationships to predict new nodal relationships between parameter output nodes and parameter input nodes; and
chaining related parameter input nodes and parameter output nodes by re-linking the parameter output nodes with the parameter input nodes based on the current nodal relationships and predicted new nodal relationships.