Systems and methods for controlling production
Example embodiments of the present disclosure provide for an example method for controlling the activity of a production facility, such as a production facility having one or more automation environments. The example method includes receiving data indicative of a current production environment. The data can include data of a sensor representing a time since last unit or fill level at one or more processing stations in a production facility. The example method can include determining an impact probability of a downtime event based at least in part on data indicative of the current production environment. The example method can include determining the impact probability of a downtime event and performing a control action associated with the production facility in response to determining the impact probability of the downtime event.
1 . A computer-implemented method comprising:
receiving, by a computing system comprising one or more processors, data indicative of a current production environment, wherein the data indicative of the current production environment comprises (i) data from a sensor indicative of time since last unit from an upstream processing station and (ii) a fill level at one or more downstream processing stations in a production facility;
determining, by the computing system, a predictive impact probability indicative of a likelihood that a current downtime event at a first processing station will cause a future downtime event at a second processing station, wherein the predictive impact probability of the current downtime event is based at least in part on the data indicative of the current production environment; and
in response to determining the predictive impact probability of the current downtime event, performing, by the computing system, a control action associated with the production facility.
2 . The computer-implemented method of claim 1 , wherein the control action associated with the production facility comprises at least one of (i) providing a notification of a downtime, (ii) controlling automation equipment in response to an impact alert, or (iii) providing one or more recommendations on one or more production resources.
3 . The computer-implemented method of claim 1 , wherein the control action associated with the production facility comprises accessing a machine-learned model to provide analytics associated with a future use state.
4 . The computer-implemented method of claim 1 , wherein determining the impact probability comprises:
determining a time that has passed since a last unit has left a first upstream processing station of the one or more processing stations;
determining a downstream fill level for a first downstream processing station; and
determining the predictive impact probability of the downtime event based on at least one of the time that has passed since the last unit has left the first upstream processing station or the downstream fill level for the first downstream processing station.
5 . The computer-implemented method of claim 4 , wherein determining the downstream fill level for the first downstream processing station is based on (i) data indicative of a unit arriving at the first downstream processing station, (ii) data indicative of a processing station capacity of the first downstream processing station, and (iii) data indicative of the unit leaving a processing station checkpoint of the first downstream processing station.
6 . The computer-implemented method of claim 4 , comprising:
determining that the downstream fill level for the first downstream processing station is at a maximum capacity; and
in response to determining that the downstream fill level for the first downstream processing station is at maximum capacity, determining that the predictive impact probability of the downtime event for the production facility is a first probability.
7 . The computer-implemented method of claim 6 , comprising:
determining that a second downstream fill level for a second downstream processing station contains no unit; and
in response to determining that the downstream fill level for the second downstream processing station contains no unit, determining that the predictive impact probability of the downtime event for the production facility is a second probability is greater than the first probability.
8 . The computer-implemented method of claim 1 , wherein the control action comprises transmitting data which causes information to be provided for display via a Graphical User Interface (GUI).
9 . The computer-implemented method of claim 8 , wherein the GUI comprises a plurality of selectable user interface components and wherein the GUI is configured to receive input from a user indicative of a response to the information provided for display.
10 . The computer-implemented method of claim 1 , comprising:
training at least one machine-learned model to determine a predictive impact probability based on fill level data, downtime data, and data indicative of time since last unit left in a processing station.
11 . The computer-implemented method of claim 10 , wherein the predictive impact probability is indicative of at least one of an upstream block or a downstream blockage.
12 . The computer-implemented method of claim 1 , wherein the predictive impact probability is determined using a machine-learned model.
13 . A computing system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions that are executable to cause the one or more processors to perform operations, the operations comprising:
receiving, by the computing system, data indicative of a current production environment, wherein the data indicative of the current production environment comprises (i) data from a sensor indicative of time since last unit from an upstream processing station and (ii) a fill level at one or more downstream processing stations in a production facility;
determining, by the computing system, a predictive impact probability indicative of a likelihood that a current downtime event at a first processing station will cause a future downtime event at a second processing station, wherein the predictive impact probability of the current downtime event is based at least in part on the data indicative of the current production environment; and
in response to determining the predictive impact probability of the current downtime event, performing, by the computing system, a control action associated with the production facility.
14 . The computing system of claim 13 , wherein the predictive impact probability is a normalized score between 1 and 100.
15 . The computing system of claim 13 , wherein determining the predictive impact probability comprises:
determining a downtime event has occurred at a first processing station;
determining that the downtime event will result in a stall of production for an entire facility; and
performing the control action based on the determination that the downtime event will result in a stall production for the entire facility.
16 . The computing system of claim 13 , wherein determining the predictive impact probability comprises:
determining a downtime event has occurred at a first processing station;
determining that the downtime event has a 0% impact probability of a stall of production for an entire facility; and
performing no control action based on the determination that the predictive impact probability is 0%.
17 . The computing system of claim 13 , wherein the control action comprises transmitting data which causes information to be provided for display via a Graphical User Interface (GUI), wherein data comprises a forecast of a workflow of the production facility.
18 . The computing system of claim 17 , wherein the forecast of the workflow of the production facility comprises predicted fill levels for the one or more processing stations.
19 . The computing system of claim 13 , wherein a forecast of a workflow of the production facility comprises a totem chart, wherein the totem chart comprises data indicative of the one or more processing stations in a processing order of the production facility, wherein the processing order is indicative of the processing order in which a unit arrives and departs from the respective processing stations of the one or more processing stations to move through the production facility.
20 . One or more non-transitory computer readable media embodied in a computer-readable storage device and comprising instructions that, when executed by a processor, cause the processor to perform operations, the operations comprising:
receiving, by a computing system comprising one or more processors, data indicative of a current production environment, wherein the data indicative of the current production environment comprises (i) data from a sensor indicative of time since last unit from an upstream processing station and (ii) a fill level at one or more downstream processing stations in a production facility;
determining, by the computing system, a predictive impact probability indicative of a likelihood that a current downtime event at a first processing station will cause a future downtime event at a second processing station, wherein the predictive impact probability of the current downtime event is based at least in part on the data indicative of the current production environment; and
in response to determining the predictive impact probability of the current downtime event, performing, by the computing system, a control action associated with the production facility.