System and method to predict clearance when transporting equipment on railway

1 . A computer-implemented method, comprising:

obtaining input data with one or more interfaces in a computing environment, the input data at least including (i) clearance data associated with one or more railway routes, and (ii) one or more schematic drawings at least associated with a load to be transported; and

operating one or more artificial intelligence models on one or more processors in the computing environment to:

process the one or more schematic drawings at least associated with the load;

determine dimensional parameters at least associated with the load based on the processing of the one or more schematic drawings;

define a transport envelope of the load carried on a railcar based on the dimensional parameters;

determine that one or more metrics characterizing the transport envelope of the load carried on the railcar fail to meet a criterion to clear the clearance data on each of the one or more railway routes;

determine, based on the one or more metrics, at least one recommendation for the transport envelope of the load carried on the railcar to clear the clearance data on the one or more railway routes by operating the one or more artificial intelligence models to:

define at least a maximum clearance window along at least one of the one or more railway routes having the one or more metrics closest to meeting the criterion; and

determine at least one alternative railcar to replace at least the railcar to transport the load to match the maximum clearance window; and

generate output information, based on the at least one recommendation, indicative of the at least one of the one or more railway routes to transport the load carried on the at least one alternative railcar.

2 . The computer-implemented method of claim 1 , wherein obtaining the one or more schematic drawings comprises at least one of:

accessing the one or more schematic drawings from an interface with storage in the computing environment;

obtaining the one or more schematic drawings with an image capture interface; and

obtaining the one or more schematic drawings with a network interface.

3 . The computer-implemented method of claim 1 , wherein operating the one or more artificial intelligence models to determine the dimensional parameters comprises:

determining first of the dimensional parameters associated with the load by processing the one or more schematic drawings at least associated with the load; and

adding second of the dimensional parameters associated with the railcar to the first dimensional parameters associated with the load.

4 . The computer-implemented method of claim 1 , wherein operating the one or more artificial intelligence models to determine the dimensional parameters comprises at least one of:

receiving a user-based selection of the railcar from one or more railcars in railcar data in the computing environment, and adding second of the dimensional parameters associated with the railcar in the user-based selection to first of the dimensional parameters associated with the load;

processing the one or more schematic drawings depicting the load carried on the railcar, and determining the dimensional parameters for the load and the railcar from the processing; and

processing one or more separate schematic drawings of the railcar in the railcar data, and adding second of the dimensional parameters associated with the railcar to first of the dimensional parameters associated with the load.

5 . The computer-implemented method of claim 1 , wherein to determine the dimensional parameters, define the transport envelope, determine the one or more metrics, and determine the at least one recommendation, the method comprises operating the one or more artificial intelligence models to automatically select the railcar to transport the load based on characteristics of the load, the railcar, and the one or more railway routes.

6 . The computer-implemented method of claim 5 , wherein to automatically select the railcar comprises accounting for one or more of: a weight of the load relative to a capacity of the railcar selected, a length of the load relative to a platform size of the at railcar selected, a height of the load compared to a platform height of the railcar selected, a weight distribution per axle of the railcar selected, a location of a center of gravity (COG) of the load, availability of the railcar selected, and a cost of the railcar selected.

7 . The computer-implemented method of claim 1 , wherein obtaining the input data comprises obtaining (iii) mapping data associated with the one or more railway routes, the mapping data including an origin and a destination for transport of the load; and wherein operating the one or more artificial intelligence models comprises operating the one or more artificial intelligence models to determine, based on the mapping data, the one or more railway routes connecting between the origin and the destination.

8 . The computer-implemented method of claim 7 , wherein operating the one or more artificial intelligence models to determine the one or more railway routes connecting between the origin and the destination comprises:

discovering any one or more sections of any of the one or more railway routes being interconnected to one another between the origin and the destination; and

outlining the any one or more sections of the any of the one or more railway routes connecting the origin to the destination.

9 . The computer-implemented method of claim 1 , wherein operating the one or more artificial intelligence models to determine the one or more metrics comprises fitting the transport envelope of the load carried on the railcar in a comparative fit to the clearance data on the one or more railway routes; and characterizing, based on the comparative fit, the one or more metrics for each of the one or more railway routes.

10 . The computer-implemented method of claim 1 ,

wherein, in response to the one or more metrics failing to meet the criterion, operating the one or more artificial intelligence models to determine the at least one recommendation comprises discovering at least one alternate railway route to replace at least the one or more railway routes; and

wherein generating the output information based on the at least one recommendation comprises generating the output information indicative of the at least one alternate railway route to transport the load carried on the railcar.

11 . The computer-implemented method of claim 1 , wherein operating the one or more artificial intelligence models to determine the one or more metrics comprises determining that the one or more metrics of at least one of the one or more railway routes meet a criterion; and wherein generating the output information based on the at least one recommendation comprises generating the output information indicative of the at least one of the one or more railway routes to transport the load carried on the railcar.

12 . The computer-implemented method of claim 1 , wherein operating the one or more artificial intelligence models comprises at least utilizing one or more of:

a first model trained to determine dimensions from image data and to calculate envelopes from the dimensions;

a second model trained to find optimal paths along the one or more railway routes; and

a third model trained to predict clearance based on an analysis of the clearance data, the envelopes, and the optimal paths.

13 . The computer-implemented method of claim 1 , wherein to determine the dimensional parameters based on the processing, the method comprises operating the one or more artificial intelligence models to extract, using at least one of a transform and a language model, one or more dimension values of at least the load from one or more of tabular information, textual information, and visual depictions in the one or more schematic drawings.

14 . The computer-implemented method of claim 13 , wherein the one or more dimension values comprise a height of the load, a height of the railcar, a width of the load, a width of the railcar, a length of the load, a combined height of the load and railcar above rail, a horizontal center of gravity relative to a geometric center, and a combined vertical center of gravity of the load and railcar above rail.

15 . The computer-implemented method of claim 13 , wherein to determine the dimensional parameters based on the processing, the method comprises operating the one or more artificial intelligence models to extract, using the at least one of the transform and the language model, one or more weight values of at least the load in the one or more schematic drawings.

16 . The computer-implemented method of claim 1 , wherein obtaining the input data comprises obtaining (iv) railcar data from technical information accessed directly from a railcar manufacturer; and wherein operating the one or more artificial intelligence models comprises using the railcar data to determine the one or more metrics.

17 . The computer-implemented method of claim 1 , wherein obtaining the input data comprises obtaining (iv) one or more guidelines at least associated with one or more railways for the one or more railway routes; and wherein operating the one or more artificial intelligence models comprises using the one or more guidelines to determine the one or more metrics.

18 . A non-transitory machine-readable medium, on which are stored instructions for a machine, comprising instructions that when executed cause the machine to:

obtain input data, the input data at least including (i) clearance data associated with one or more railway routes, and (ii) one or more schematic drawings at least associated with a load to be transported on a railcar; and

operate one or more artificial intelligence models to:

process the one or more schematic drawings of at least the load;

determine dimensional parameters associated with the load carried on the railcar based on the processing of the one or more schematic drawings;

define a transport envelope of the load carried on the railcar based on the dimensional parameters;

determine that one or more metrics characterizing the transport envelope of the load carried on the railcar fail to meet a criterion to clear the clearance data on each of the one or more railway routes;

determine, based on the one or more metrics, at least one recommendation for the transport envelope of the load carried on the railcar to clear the clearance data on the one or more railway routes by operating the one or more artificial intelligence models to:

define at least a maximum clearance window along at least one of the one or more railway routes having the one or more metrics closest to meeting the criterion; and

determine at least one alternative railcar to replace at least the railcar to transport the load to match the maximum clearance window; and

generate output information, based on the at least one recommendation, indicative of the at least one of the one or more railway routes to transport the load carried on the at least one alternative railcar.

19 . A system comprising:

one or more databases storing clearance data for one or more railway routes;

one or more interfaces being configured to obtain input data, the input data at least including one or more schematic drawings at least associated with a load to be transported on a railcar; and

one or more processors operatively couped to the one or more databases and the one or more interfaces, the one or more processors being configured to operate one or more artificial intelligence models to:

process the one or more schematic drawings of at least the load;

determine dimensional parameters associated with the load carried on the railcar based on the processing of the one or more schematic drawings;

define a transport envelope of the load carried on the railcar based on the dimensional parameters;

determine that one or more metrics characterizing the transport envelope of the load carried on the railcar fail to meet a criterion to clear the clearance data on each of the one or more railway routes; and

determine, based on the one or more metrics, at least one recommendation for the transport envelope of the load carried on the railcar to clear the clearance data on the one or more railway routes by operating the one or more artificial intelligence models to:

define at least a maximum clearance window along at least one of the one or more railway routes having the one or more metrics closest to meeting the criterion; and

determine at least one alternative railcar to replace at least the railcar to transport the load to match the maximum clearance window; and

generate output information, based on the at least one recommendation, indicative of the at least one of the one or more railway routes to transport the load carried on the at least one alternative railcar.

20 . A computer-implemented method, comprising:

obtaining input data with one or more interfaces in a computing environment, the input data at least including (i) clearance data associated with one or more railway routes, (ii) one or more schematic drawings at least associated with a load to be transported, and (iii) railcar data associated with one or more railcars; and

operating one or more artificial intelligence models on one or more processors in the computing environment to:

process the one or more schematic drawings at least associated with the load;

determine first dimensional parameters at least associated with the load based on the processing of the one or more schematic drawings;

obtain second dimensional parameters associated with at least one of the one or more railcars in the railcar data;

define a transport envelope of the load carried on the at least one railcar based on the first dimensional parameters associated with the load combined with the second dimensional parameters associated with the at least one railcar;

compare the transport envelope to the clearance data for the one or more railway routes to determine one or more metrics characterizing the transport envelope clearing the clearance data on the one or more railway routes;

determine at least one first prediction that the one or more metrics characterizing the transport envelope of the load carried on the at least one railcar fails to meet a first criterion to clear the clearance data on each of the one or more railway routes;

in response to the at least one first prediction, define at least a maximum clearance window along at least one of the one or more railway routes having the one or more metrics closest to meeting the first criterion, and determine at least one alternative railcar to replace at least the at least one railcar to transport the load to match the maximum clearance window; and

generate output information based on the at least one first prediction, the output information being indicative of the at least one of the one or more railway routes to transport the load carried on the at least one alternative railcar.

21 . The computer-implemented method of claim 20 , wherein operating the one or more artificial intelligence models to obtain the second dimensional parameters associated with the at least one railcar in the railcar data comprises at least one of:

receiving a user-based selection of the at least one railcar in the railcar data in the computing environment;

processing the one or more schematic drawings depicting the load carried on the at least one railcar; and

processing one or more separate schematic drawings of the at least one railcar; and

automatically selecting the at least one railcar to transport the load based on characteristics of the load, the at least one railcar, and the one or more railway routes.

22 . The computer-implemented method of claim 20 , wherein obtaining the input data comprises obtaining (iv) mapping data associated with the one or more railway routes, the mapping data including an origin and a destination for transport of the load; and wherein operating the one or more artificial intelligence models comprises operating the one or more artificial intelligence models to determine, based on the mapping data, the one or more railway routes connecting between the origin and the destination.

23 . The computer-implemented method of claim 20 , wherein operating the one or more artificial intelligence models to determine the one or more metrics comprises fitting the transport envelope of the load carried on the at least one railcar in a comparative fit to the clearance data on the one or more railway routes; and characterizing, based on the comparative fit, the one or more metrics for each of the one or more railway routes.

24 . The computer-implemented method of claim 20 , comprising operating the one or more artificial intelligence models to:

determine at least one second prediction that the one or more metrics for each of the one or more railway routes fails to meet a second criterion;

discover, in response to the at least one second prediction, at least one alternate railway route to meet the second criterion to replace at least the one or more railway routes; and

generate the output information based on the at least one second prediction, the output information being further indicative of the at least one alternate railway route.

25 . The computer-implemented method of claim 20 , wherein operating the one or more artificial intelligence models comprises at least utilizing one or more of:

a first model trained to determine dimensions from image data and to calculate envelopes from the dimensions;

a second model trained to find optimal paths along the one or more railway routes; and

a third model trained to predict clearance based on an analysis of the clearance data, the envelopes, and the optimal paths.