WORKSITE INEFFICIENCY IDENTIFICATION

Abstract

Systems and methods to identify inefficiencies in a worksite and generate recommended actions to improve the inefficiencies are provided herein. The inefficiencies may be identified by analyzing equipment data from mobile equipment and fixed equipment associated with the worksite. The equipment data may be used to generate one or more routes through the worksite. The equipment data and one or more routes may be used to generate a cycle time for the worksite. The equipment data, one or more routes, and cycle time may be used to identify an inefficiency in the worksite, and the identified inefficiency may be used to generate a recommended action to improve and thus remedy the inefficiency.

Description

Claims

1. A method comprising: receiving first equipment data from each of a plurality of mobile equipment associated with a worksite;receiving second equipment data from at least one of a plurality of fixed equipment associated with the worksite;generating, based on at least the first equipment data and the second equipment data, a representation of a current route for each of the plurality of mobile equipment;generating — based on the representation of the current route, the first equipment data, and the second equipment data — a cycle time for each of the plurality of mobile equipment;identifying — based on the representation of the current route, the cycle time, the first equipment data, and the second equipment data — at least one inefficient aspect of the route, wherein the at least one inefficient aspect relates to one or more of: the cycle time,a wait time of at least one of the mobile equipment of the plurality of mobile equipment,operation of at least one of the mobile equipment of the plurality of mobile equipment,a wait time of at least one of the fixed equipment included in the plurality of fixed equipment, andoperation of the at least one fixed equipment of the plurality of fixed equipment;generating, based on the at least one inefficient aspect, one or more recommended actions to remedy the inefficient aspect;identifying, based on the one or more recommended actions, an operating parameter of one or more of: at least one of the mobile equipment of the plurality of mobile equipment and the at least one fixed equipment of the plurality of fixed equipment; andcausing, based on the one or more recommended actions, the identified operating parameter to change.

2. The method of claim 1, wherein identifying the at least one inefficient aspect of the route further comprises: applying the representation of the current route, the first equipment data, the second equipment data, and the cycle time to a machine learning model trained to identify at least one inefficient aspect of a route based on a current route, first equipment data, second equipment data, and a cycle time; andobtaining, from the machine learning model, the identified at least one inefficient aspect of the route.

3. The method of claim 1, wherein generating the one or more recommended actions further comprises: applying the identified at least one inefficient aspect to a machine learning model trained to generate one or more recommended actions based on at least one identified inefficient aspect; andobtaining, from the machine learning model, the recommended one or more actions.

4. The method of claim 1, wherein generating the representation of the current route further comprises: obtaining first location data from the first equipment data;obtaining second location data from the second equipment data; andgenerating the representation of a current route based on the first location data and the second location data.

5. The method of claim 4, wherein generating the representation of the current route further comprises: identifying one or more waypoints along the current route based on the representation of the current route, the first equipment data, and the second equipment data.

6. The method of claim 1, wherein identifying the at least one inefficient aspect of the route further comprises: identifying at least one inefficient aspect of the route and the plurality of mobile equipment.

7. The method of claim 1, wherein identifying the at least one inefficient aspect of the route further comprises: identifying at least one inefficient aspect of the route and the plurality of fixed equipment.

8. The method of claim 1, further comprising: displaying, via a user interface, the identified at least one inefficient aspect and the one or more recommended actions to remedy the inefficient aspect.

9. The method of claim 1, wherein causing the identified operating parameter to change further comprises: determining at least one equipment of the plurality of mobile equipment or the plurality of fixed equipment which is associated with the identified operating parameter; andtransmitting a message to the at least one equipment to change the identified operating parameter.

10. A computing device, comprising: a memory configured to store computer instructions; anda processor configured to execute the computer instructions to: receive first equipment data from at least one piece of mobile equipment;receive second equipment data from at least one piece of fixed equipment;generate, based on the first equipment data and the second equipment data, a representation of a current route for the at least one piece of mobile equipment;generate — based on the representation of the current route, the first equipment data, and the second equipment data — a cycle time for the at least one piece of mobile equipment;identify — based on the representation of the current route, the cycle time, the first equipment data, and the second equipment data — at least one inefficient aspect of one or more of the route, the at least one piece of mobile equipment, and the at least one piece of fixed equipment;generate, based on the at least one inefficient aspect, one or more recommended actions to remedy the inefficient aspect; anddisplay, via a user interface, the identified at least one inefficient aspect and the one or more recommended actions to remedy the inefficient aspect.

11. The computing device of claim 10, wherein the processor identifies the at least one inefficient aspect by further executing the computer instructions to: identify at least one inefficient aspect based on a current route, first equipment data, second equipment data, and a cycle time by using a machine learning model trained to identify at least one inefficient aspect based on a representation of a current route, first equipment data, second equipment data, and cycle time; andobtain, from the machine learning model, the identified at least one inefficient aspect.

12. The computing device of claim 10, wherein the processor generates the one or more recommended actions by further executing the computer instructions to: generate one or more recommended actions based on the at least one identified inefficient aspect by using a machine learning model trained to identify one or more recommended actions based on an identified inefficient aspect; andobtain, from the machine learning model, the recommended one or more actions.

13. The computing device of claim 10, wherein the processor generates a representation of a current route by further executing the computer instructions to: obtain first location data from the first equipment data;obtain second location data from the second equipment data; andgenerate the representation of a current route based on the first location data and the second location data.

14. The computing device of claim 13, wherein the processor generates the representation of a current route by further executing the computer instructions to: identify one or more waypoints along the current route based on the representation of the current route, the first equipment data, and the second equipment data.

15. The computing device of claim 13, the processor identifies the at least one inefficient aspect by further executing the computer instructions to: identify at least one inefficient aspect of the route and the plurality of mobile equipment.

16. The computing device of claim 13, the processor identifies the at least one inefficient aspect by further executing the computer instructions to: identify at least one inefficient aspect of the route and the plurality of fixed equipment.

17. A non-transitory computer-readable medium storing computer instructions that, when executed by at least one processor, cause the at least one processor to perform actions, the actions comprising: receiving first equipment data from at least one piece of mobile machinery in a worksite;receiving second equipment data from at least one piece of fixed machinery in the worksite;generating, based on the first equipment data and the second equipment data, a representation of a current route for the at least one piece of mobile machinery;generating — based on the representation of the current route, the first equipment data, and the second equipment data — a cycle time for the at least one piece of mobile machinery;identifying — based on the representation of the current route, the cycle time, the first equipment data, and the second equipment data - at least one inefficient aspect of one or more of the route, the at least one piece of mobile machinery, and the at least one piece of fixed machinery;generating, based on the at least one inefficient aspect, one or more recommended actions to remedy the inefficient aspect; anddisplaying, via a user interface, the identified at least one inefficient aspect and the one or more recommended actions to remedy the inefficient aspect.

18. The non-transitory computer-readable medium of claim 17, wherein identifying the at least one inefficient aspect further comprises: applying the representation of the current route, the first equipment data, the second equipment data, and the cycle time to a machine learning model trained to identify at least one inefficient aspect based on a current route, first equipment data, second equipment data, and a cycle time; andobtaining, from the machine learning model, the identified at least one inefficient aspect.

19. The non-transitory computer-readable medium of claim 17, wherein generating the one or more recommended actions further comprises: applying the identified at least one inefficient aspect to a machine learning model trained to generate one or more recommended actions based on at least one identified inefficient aspect; andobtaining, from the machine learning model, the recommended one or more actions.

20. The non-transitory computer-readable medium of claim 17, wherein generating the representation of the current route further comprises: obtaining first location data from the first equipment data;obtaining second location data from the second equipment data; andgenerating the representation of a current route based on the first location data and the second location data.

21. The non-transitory computer-readable medium of claim 20, wherein generating the representation of the current route further comprises: identifying one or more waypoints along the current route based on the representation of the current route, the first equipment data, and the second equipment data.