System and method for optimizing energy reserve for battery electric machine

Abstract

A method and system for optimizing an energy reserve of a battery electric machine (BEM) are provided. The method includes determining a location of a BEM allocated to a production circuit; determining a location of a charging station; determining a planned task energy amount associated with one or more planned tasks of the BEM executing the production circuit including a travel by the BEM to the location of the charging station; calculating an unplanned energy usage associated with a plurality of unplanned events of the BEM that are different from the one or more planned tasks; based on the planned task energy amount and the unplanned energy usage, determining an energy reserve for one or more batteries of the BEM, determining, whether a current charge state of the one or more batteries is below the energy reserve; and causing the machine to execute an opportunistic charging.

Description

SYSTEM AND METHOD FOR OPTIMIZING ENERGY RESERVE FOR BATTERY ELECTRIC MACHINETechnical Field

[0001] The present disclosure relates generally to a system and method for managing battery energy of a machine, and more particularly, to a system and method for reserving appropriate amount of battery energy for unplanned events during operation of the machine to be able to reach a charging station.Background

[0002] Electric vehicles, such as battery electric machines (BEMs), are commonly charged at a charging station. BEMs may be driven to the charging station and charged at the location of the charging station. BEM Operators may lose time and money if the BEM runs out of stored energy before reaching the charging station, requiring transporting the BEM to the charging station or transporting power supplies large enough to recharge the BEM to the location of the BEM. For a planned work, or a production circuit, amount of energy may be reasonably predicted, however, there may be unexpected events requiring the BEM to stop for extended periods. To avoid running out of stored energy before reaching the charging station, some stored energy may be reserved. However, if too much energy is reserved, the BEM may have a very limited range and may require frequent charging, while if no energy is reserved, BEM may frequently run out of energy during operation.

[0003] One example of a stored energy management system is disclosed in US Patent Application Publication No. 20230202329A1 of Bahei-Eldin et al., that was published on June 29, 2023 (“the ’329 publication”). In particular, the ’329 publication discloses an energy control unit for dynamically establishing and / or adjusting a reserve battery level responsive to vehicle usage information for providing the vehicle with reserve power for travelling to selected destinations.

[0004] Although useful in determining the reserve battery level, the control unit of the ’329 publication may be limited. In particular, the ’329 publication describes, by a battery of avehicle, supplying power to a device external to the vehicle in a power outage area until a threshold battery level is reached, then determining a reserve battery level required for the vehicle to reach a charging station unaffected by the power outage.

[0005] The systems and methods described herein are directed to addressing one or more of the drawbacks set forth above.Summary

[0006] According to a first aspect, a method for optimizing energy reserve of a battery electric machine (BEM) is provided. The method includes determining a location of a BEM allocated to a production circuit; determining a location of a charging station compatible with the BEM; determining, based at least in part on the location of the BEM and the location of the charging station, a planned task energy amount associated with one or more planned tasks of the BEM executing the production circuit, the one or more planned tasks including a travel by the BEM to the charging station along a predetermined route; calculating an unplanned energy usage associated with a plurality of unplanned events of the BEM, the plurality of unplanned events different from the one or more planned tasks; based at least in part on the planned task energy amount and the unplanned energy usage, determining an energy reserve for one or more batteries of the BEM, determining whether a current charge state of the one or more batteries is below the energy reserve; and causing the BEM to execute an opportunistic charging.

[0007] According to another aspect, a system is provided for optimizing energy reserve of a battery electric machine (BEM). The system includes one or more processors and memory communicatively coupled to the one or more processors. The memory stores processorexecutable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations. The operations include determining a location of a battery electric machine (BEM) allocated to a production circuit; determining a location of a charging station compatible with the BEM; determining, based at least in part on the location of the BEM and the location of the charging station, a planned task energy amount associated with one or more planned tasks of the BEM executing the production circuit; calculating an unplanned energy usage associated with a plurality of unplanned events of the BEM; based at least in parton the planned task energy amount and the unplanned energy usage, determining an energy reserve for one or more batteries of the BEM; determining whether a current charge state of the one or more batteries is below the energy reserve; and causing the BEM to execute an opportunistic charging.

[0008] According to yet another aspect, non-transitory computer-readable medium is provided that stores thereon processor-executable instructions that, when executed by one or more processors of a system, cause the one or more processors to perform certain operations for optimizing energy reserve of a battery electric machine (BEM). The operations include determining a location of the BEM allocated to a production circuit; determining a location of a charging station compatible with the BEM; determining, based at least in part on the location of the BEM and the location of the charging station, a planned task energy amount associated one or more planned tasks of the BEM executing the production circuit; calculating an unplanned energy usage associated with a plurality of unplanned events of the BEM; based at least in part on the planned task energy amount and the unplanned energy usage, determining an energy reserve for one or more batteries of the BEM; determining whether a current charge state of the one or more batteries is below the energy reserve; and causing the BEM to execute an opportunistic charging.Brief Description of the Drawings

[0009] The detailed description is described with reference to the accompanying figures. In the figures, the left-most digit of a reference number identifies the figure in which the reference number first appears. The same reference numbers in different figures indicate similar or identical items.

[0010] FIG. l is a side view of an exemplary machine that may utilize reserving power for a battery electric machine.

[0011] FIG. 2 is an example worksite where a set of machines are deployed.

[0012] FIG. 3 is a flowchart illustrating a process for optimizing energy reserve for a battery electric machine.

[0013] FIG. 4 is a flowchart representing an example detail process of one of the blocks of FIG. 3.

[0014] FIG. 5 is a flowchart representing an example detail process of another block of FIG. 3.

[0015] FIG. 6 is a block diagram of a computing system for optimizing an energy reserve of a BEM.Detailed Description

[0016] FIG. 1 is a side view of an exemplary battery electric machine (BEM) 100, according to one embodiment of the present disclosure. While the BEM 100 is depicted as a haul truck, it should be noted that the BEM 100 may include any type of battery electric machine, such as an automobile, a truck, an agricultural vehicle, an aircraft, a watercraft, and / or work vehicles, such as a track loader, a skid-steer loader, a grader, an on-highway truck, an off-highway truck, and / or any other machine known to a person skilled in the art.

[0017] The BEM 100 may include a chassis and / or a frame 102. A dump body 104 may be fixedly or pivotally mounted on the frame 102. The dump body 104 may be used for transportation of a payload of material like sand, gravel, stones, soil, excavated material, and the like from one location to another on a worksite on which the BEM 100 is deployed.

[0018] Hydraulic and / or pneumatic cylinders 106 may be mounted on the frame 102 and connected to the dump body 104 to enable movement in the form of tilting of the dump body 104 with respect to the frame 102 of the BEM 100. The tilting of the dump body 104 may result in the payload contained within the dump body 104 to be deposited on a ground surface behind the BEM 100. In some embodiments, the distance behind the BEM 100 that the payload is deposited may be determined and stored for more accurate positioning of the BEM 100 at a target position.

[0019] A powertrain or a drivetrain 108 (shown in a cutout) may be provided on the BEM 100 for the production and transmission of motive power. The powertrain 108 may include an electric motor 110 and one or more batteries 112. An enclosure 114 may be provided on the frame 102 of the BEM 100 which may house the electric motor and batteries.

[0020] A set of ground engaging members 116, like wheels, may be provided to the BEM 100 for the purpose of mobility. The set of ground engaging members 116 may be steerable, or configured to turn, in order to turn the frame of the BEM 100 along a turning profile. In some embodiments, the front two ground engaging members 116 are configured to turn. The powertrain 108 may further include a torque convertor, transmission inclusive of gearing, drive shafts, propeller shaft, differentials, and other known drive links for transmission of motive power from the electric motor 110 to the at least one ground engaging member 116 in the plurality of ground engaging members 116. An operator cabin 118 may be provided on the BEM 100 which may house the various controls of the BEM 100.

[0021] For example, the BEM 100 may include an electronic control module (ECM) 120, with which the various controls of the BEM 100 may be performed. The ECM 120 may house one or more processors 122, which may execute any modules, components, or systems associated with the BEM 100, some of which may be housed in the ECM 120 as shown as modules 124. In some examples, the processors 122 may include a central processing unit (CPU), a graphics processing unit (GPU), both CPU and GPU, or other processing units or components known in the art. Additionally, each of the processors 122 may possess its own local memory, which also may store program modules, program data, and / or one or more operating systems. The ECM 120 may additionally include a user interface, such as a display 128 that displays various information and receives inputs via a touch-sensitive screen.

[0022] Computer-readable media, such as memory 126, associated with the BEM 100 may include volatile memory (e.g., RAM), non-volatile memory (e.g., ROM, flash memory, miniature hard drive, memory card, or the like), or some combination thereof. The computer-readable media may be non-transitory computer-readable media. The computer-readable media may include or be associated with the one or more of the above-noted modules, which perform various operations associated with the BEM 100. In some examples, one or more of the modules may include or be associated with computer-executable, or processor-executable, instructions that are stored by the computer-readable media and that are executable by one or more processors to perform such operations.

[0023] The BEM 100 may be configured to receive a task, such as to transport materials from one location to another at a worksite. The task, which is associated with a correspondingmovement pattern of the BEM 100, may be received via the ECM 120. For example, the BEM 100 may maneuver to a first target position to receive a payload in its dump body 104 from an excavating machine, transport the payload to a second target position, and dump the payload at the second target position. Each of the first and second target positions may be associated with a target location for the BEM 100 and a target orientation for the BEM 100 (e.g., a heading direction for the BEM 100). Other example target positions may include parking spots, maintenance spots, refueling spots, any other pre-decided destination, and the like.

[0024] BEMs 100 may be manned machines, autonomous machines, and / or semi- autonomous machines. Human operators may operate, control, or direct some or all of the functions of manned or semi-autonomous machines. However, in examples in which the BEM 100 is autonomous or semi-autonomous, the speed, steering, work tool positioning / movement, and / or other functions of the BEM 100 may be fully or partially controlled automatically or semi-automatically by on-board or off-board controllers or other computing devices, such as computing devices with processors executing computer-readable instructions configured to control the BEM 100 autonomously or semi -autonomously.

[0025] FIG. 2 depicts an example worksite 200 where machines, such as BEMs 100 and 202 may be deployed. The worksite 200 may be a construction site, a mine site, a quarry, or any other type of worksite or work environment where one or more BEMs 100 and 202 may be deployed to perform one or more work tasks. In some examples, a worksite 200 may be considered to be a process site or a project site. In a process site, one or more machines may repeatedly perform a set of tasks. As an example, a process site may be a quarry or a mine site where the BEM 100 repeatedly moves rocks away from a rock face. In a project site, one or more BEMs 100 and 202 may perform different tasks as a project progresses over time. As an example, a project site can be a construction site, a paving site, or other work environment where the BEMs 100 and 202 perform different tasks as different stages of construction are reached. In other examples, the worksite 200 may have elements of both a process site and a project site.

[0026] As discussed above, the BEMs 100 and 202 on the worksite 200 may perform a variety of tasks. In some examples, the BEMs 100 may repeatedly perform a set of planned tasks associated with segments of a production circuit, where a planned task energy amount, i.e., an amount of energy required to perform each of the planned tasks or segments, is known, forexample, from historical performance of the planned task, a heuristic algorithm for estimating the planned task energy amount, a simulation of the planned task, a stochastic model, or modeling, for the planned task, or a machine learning for the planned task. A production circuit has an associated energy use profile (by segment) including nominal target charge range for charging, charge range for operation, reserve energy limit, and predicted energy use and / or gain. A production circuit is a sequence of activities to be performed by a machine one or more times, and where a production circuit is to be performed more than once, the production circuit starts and ends at the same location. For instance, an example simple production circuit may include a loading segment, a loaded transit segment, an unloading segment, and an unloaded transit segment. Such an example production circuit 204 is shown in FIG. 2, where the BEM 100 can be loaded with dirt or other material 206 at a loading zone 208 within the worksite 200, the BEM 100 can transport the material 206 from the loading zone 208 to a separate delivery zone 210 within the worksite 200, the BEM 100 can unload the material 206 at the delivery zone 210, and the BEM 100 can then travel back to the loading zone 208 to be loaded with more material 206 for a next iteration of the production circuit 204.

[0027] In some examples, the BEM 100 may load and / or unload material 206 by itself during one or more segments of the production circuit 204. However, in other examples, the BEM 202 may load and / or unload material 206 for the BEM 100 during the production circuit 204. For instance, an excavator or other loading machine can be positioned at a loading zone 208 and be configured to load material 206 onto trucks, such as the BEM 100, which can then transport the material 206 to one or more delivery zones 210. In some examples, such trucks may themselves dump or otherwise deliver the material 206 at delivery zones 210. However, in other examples, another excavator or other type of unloading machine can be positioned at a delivery zone 210 to unload material 206 from trucks.

[0028] Other examples of a production circuit include, but not limited to: a complex circuit - starting at a first loading tool, loading, travelling to a dump, dumping, travelling to a second loading tool, loading, travelling to a lime silo, receiving a dose of lime, travelling to a second dump, dumping, returning to the first loading tool; watering - travelling to a location, watering a road, watering another road, travelling, watering a plan area, traveling, watering another road, travelling to a water refill station; grading - travelling to a location, grading, travelling to anotherlocation, grading, travelling to a park up; and wheel loader - travelling to a location, loading trucks, travelling to a location, cleaning up a dump, travelling to a location, repairing a road, travelling to a location, loading trucks.

[0029] More than one BEM 100 may follow the same production circuit 204 on the worksite 200. For instance, in the example shown in FIG. 2, a first truck may be being loaded with material 206 at the loading zone 208 at the same time a previously-loaded second truck may be unloading material 206 at a delivery zone 210. Similar trucks already loaded with material 206 may be in transit from the loading zone 208 to the delivery zone 210, and may for example be located at a first position 212. Other trucks may have finished delivering loads of material 206 and be in transit from the delivery zone 210 back to the loading zone 208, and may for example be located at a second position 214.

[0030] Accordingly, BEMs 100 that are performing the same production circuit 204 may move along substantially the same route 216 through the worksite 200 as they perform and transition between different segments of the production circuit 204. Additionally, a BEM 100 may perform substantially the same operations as other BEMs 100 when the BEM 100 are at the same or similar locations along the route 216 through the worksite 200. As an example, when a production circuit 204 involves BEMs 100 (haul trucks) moving from the loading zone 208 to a delivery zone 210, each BEM 100 may be likely to perform the same or similar operations associated with dumping material 206 when they reach the delivery zone 210, even though individual BEMs 100 may arrive at the delivery zone 210 at different times. At some point in time after performing the production circuit 204, as a part of the planned tasks, the BEM 100 will need to be recharged, and may travel to a closest charging station 218 along a predetermined route 220. Additionally, or alternatively, another route for the BEM 100 to reach a second closest charging station 222 may be provided.

[0031] In some examples, the BEM 100 on the worksite 200 may communicate via a communication network 224 with a computing system 226, such as a computer, server, or other computing element in a central office 228 located away from the BEM 100. For example, the communication network 224 may be a cellular network, Wi-Fi® network, or any other type of network. In some examples, the BEM 100 may use the communication network 224 to report location data and / or other types of data to the computing system 226, such that the computingsystem 226 may track the location of the BEM 100 on the worksite 200, and the computing system 226 may communicate data and instructions to the BEM 100 via the communication network 224.

[0032] FIG. 3 is a flowchart 300 illustrating a process for optimizing energy reserve for a BEM 100. The flowchart 300 is illustrated as a logical flow graph, with reference to FIG. 2, operation of which represents a sequence of operations that can be implemented in hardware, software, or a combination thereof.

[0033] At block 302, a location of the BEM 100 allocated to the production circuit 204 may be determined. For example, the one or more processors 122 of the ECM 120 of the BEM 100 and / or the computing system 226 of the central office 228 may determine the location by utilizing global positioning system (GPS) data associated with the BEM 100. The BEM 100 may be a representative BEM instead of a particular individual BEM. At block 304, a location of a nearby charging station compatible with the BEM, such as the charging station 218 may be determined. Additionally, or alternatively, a location of another, or an alternate, nearby charging station may also be determined. The locations of the charging stations may also be obtained from a database of the computing system 226. Additionally, or alternatively, the locations of the BEM and charging stations may be determined, or obtained, by utilizing a non-GPS based process or technique, such as a landmark based location / localization (LBL) navigation and a perception based location (PBL) navigation which determine locations by observing known landmarks, and possibly including markers or targets, or a Ground Sensing Location (GSL) navigation where radar, or other detection techniques, is used to determine location based on known ground anomalies.

[0034] At block 306, a planned task energy amount associated with a travel by the BEM 100 from the current location to the charging station 218 along the predetermined route 220 may be calculated. Additionally, one or more planned tasks of the BEM 100 in executing the production circuit 204 may also be determined. As described above with reference to FIG. 2, one or more planned tasks may include one or more routine tasks of the BEM 100 associated with executing the production circuit 204 with known energy amount requirements to complete the one or more routine tasks and a number of repetitions of the one or more routine tasks to be performed by the BEM 100. Such a known set of planned task energy amounts or uses may be referred as anenergy use profile for the production circuit. For example, the computing system 226 of the central office 228 may provide an energy use profile for the production circuit to the BEM 100. The one or more planned tasks may include loading and / or unloading material, transporting the material 206 to one or more delivery zones, dumping / delivering the material at delivery zones, watering at a location, traveling to a refilling station, refilling water at traveling station, grading, traveling to another location, grading, travelling to a park up, and others like. Additionally, one or more alternative planned tasks of the BEM 100 in an alternative production circuit may be determined, and an alternate planned task energy amount associated with the one or more alternative planned tasks including a travel to the charging station 218 in the alternative production circuit may be determined. The BEM 100 may perform the one or more alternative planned tasks in the alternative production circuit in case entry criteria for the production circuit 204 are not met, for example, the BEM 100 being loaded with unexpected material but able to perform in the alternative production circuit. As described above with reference to FIG. 2, a planned task energy amount, i.e., an amount of energy required to perform each of the planned tasks, may be known, for example, from historical performance of the planned task, a heuristic algorithm for estimating the planned task energy amount, a simulation of the planned task, a stochastic modeling for the planned task, or a machine learning for the planned task.

[0035] At block 308, an unplanned energy usage associated with a plurality of unplanned events of the BEM may be determined or calculated. The plurality of unplanned events is different from the planned tasks and are not part of the planned tasks. The unplanned energy usage, therefore, is not included in, or considered by, the planned task energy amount of block 306. For example, the plurality of unplanned events for the BEM 100 may include: following behind traffic moving slower than an expected rate of an associated planned task; stopping at an intersection; reducing speed to time arrivals at a destination of an associated planned task, the destination including intersections, sources or loading zones, charging, service, and / or electronic technician (ET) stations, or sinks or deposit areas; stopping autonomously; accounting for medical emergencies such as a worksite-wide work stoppage associated with medical emergencies; accommodating a road closure, such as a closure due to maintenance, weather, flooding, etc., requiring a detour; being delayed at the destination of an associated planned task based on the destination being serviced, refueled, or otherwise maintained; queuing at thedestination of an associated planned; engaging regenerative braking of the BEM 100 for one or more unplanned stops, such as an obstacle; being prevented from completing the one or more planned tasks and completing alternative tasks that require more energy than completing the one or more planned tasks; and being disconnected from a trolley, or trolley network, before reaching a predetermined target charge of the one or more batteries while travelling connected to the trolley network. A trolley, or a trolley network, may be any type of a charging station, equipment, or network, with which a machine, such as the BEM 100, may connect and be able to charge while travelling. Designs for a trolley network may include designs employing trolley poles, bow collectors, underbody collectors, and other forms of ‘live’ electricity transfer. For example, a trolley network may include a ground-level power supply, wherein one or more contact lines may include conductive rails or tracks, and a charging apparatus of the BEM 100 may include an underbody collector configured to interact with the conductive rails or tracks. In other embodiments, the trolley network may include non-contact conductors, such as those facilitating in-road inductive charging.

[0036] Based at least in part on the planned task energy amount determined at block 306 and the unplanned energy usage determined at block 308, an energy reserve for one or more batteries 112 of the BEM 100 may be determined at block 310, where the energy reserve is an amount of energy for the BEM 100, at a given point in time and location, to be able to execute the production circuit and reach the location of the charging station 218 from the current location of the BEM 100 while accommodating at least some of the unplanned events. For example, the BEM 100 may be currently located near the charge station 218, but is scheduled to execute a production circuit that requires traveling to a worksite that is far away from the charge station 218. The energy reserve must account for some or all of the unexpected events that might occur while executing the production circuit. The BEM 100 may otherwise run out of energy before returning to the charge station 218. The energy reserve may be considered as future unplanned energy use during the execution of the production circuit. At block 312, the energy reserve and a current charge state of the batteries 112 may be transmitted to the computing system 226 in the central office 228 periodically or as needed, and may additionally, or alternatively, be transmitted to the ECM 120 of the BEM 100.

[0037] At block 314, the computing system 226 may determine, based on the current charge state of the batteries 112, whether the BEM 100 is near or below the energy reserve, and instruct, and / or cause, the BEM 100 to take an appropriate action at the appropriate time, such as executing an opportunistic charging. For example, the BEM 100 begins to approach or drops below the energy reserve, the computing system 226 of the central office 228 may start to look for opportunities to charge the batteries 112 without reducing productivity of the BEM 100, which may be referred to as an opportunistic charging. The computing system 226 may instruct, or cause, the BEM 100 to travel to the charging station 218 during a period when the BEM 100 may otherwise be idling in a queue, or move, reallocate, the BEM 100 to a different production circuit where the BEM 100 can charge on a rail or a trolley while travelling. In other cases, the computing system 226 may let the BEM 100 continue on the current assignment with the expectation that the charge state will be restored during the normal course of operations. The BEM 100 may be expected to routinely use a portion of the energy reserve while executing the production circuit because the energy reserve may be calculated to include some amount of energy for unplanned events that may occur during the execution of a production circuit without the need to divert the BEM 100. When the charge state of the batteries 112 drops to a level where there is only enough energy left for the BEM 100 to reach to the closest charging station 218, or the second closest charging station 222, the computing system 226 may instruct the BEM 100 to immediately travel to the charging station 218 or 222. This scenario would be the last resort as diverting a working machine to a charging station would ordinarily involve lost productivity.

[0038] The process described above with reference to the flowchart 300 may be repeated periodically, or as needed, as the BEM 100 executes the production circuit and moves in the worksite 200, causing changes in the charge state of the batteries 112 and the location of the BEM 100. The process may be performed by the one or more processors 122 of the ECM 120 of the BEM 100, by the computing system 226 of the central office 228, or by a combination of the one or more processors 122 and the computing system 226.

[0039] FIG. 4 is a flowchart representing an example detail process of block 308 of FIG. 3. At block 402, the plurality of unplanned events is identified, and an unplanned event (a first unplanned event) of the plurality of unplanned events is selected at block 404. An unplanned energy usage associated with the selected unplanned event is calculated at block 406. Theunplanned energy usage associated with the selected unplanned event may be calculated by using at least one of: a heuristic algorithm for estimating the unplanned energy usage associated the selected unplanned event; a simulation of the selected unplanned event for estimating the unplanned energy usage associated the selected unplanned event; a stochastic modeling for the selected unplanned event for estimating the unplanned energy usage associated the selected unplanned event, or a machine learning for estimating the selected unplanned energy usage associated the selected unplanned event. At block 408, whether all unplanned events have been evaluated for unplanned energy usage calculation is determined. If all the unplanned events have been evaluated (“YES” branch), the process proceeds to block 310. If there are one or more unplanned events left to be evaluated (“NO” branch), then a next unplanned event is selected at block 410, and the process loops back to block 406.

[0040] FIG. 5 is a flowchart representing an example detail process of block 310 of FIG. 3. At block 502, the plurality of unplanned events is ranked in order of their corresponding unplanned energy usages calculated, and a predetermined number of the highest unplanned energy usages are selected at block 504. For example, the highest two unplanned energy usages calculated at block 406 are selected.

[0041] At block 506, a corresponding weighting factor for each of unplanned events associated with the selected unplanned energy usages is determined. The weighting factor may alternatively be determined for a combined unplanned events associated with the selected predetermined number of the highest unplanned energy usages. For example, the highest two unplanned energy usages calculated at block 406 may correspond to unplanned events of stopping at an intersection and accommodating a road closure, then a first weighting factor associated with stopping at an intersection and a second weighting factor associated with accommodating a road closure may be determined. Additionally, or alternative, a single weighting factor for stopping at an intersection and accommodating a road closure may be determined. The weighting factor may range in value, for example, from 0 to 1, and indicate a likelihood of encountering the associated unplanned event, such as stopping at an intersection and accommodating a road closure. The weighting factor may, however, be greater than 1 in some cases where the risk of unplanned events occurring is greater than average for the location and production circuit. A weighting factor may be determined based at least in part on likelihoodof a corresponding unplanned event occurring while executing the production circuit, historical occurrences of the corresponding unplanned event, current and future weather conditions around the location of the BEM 100, an updated information regarding an associated route of the unplanned events such as road closures traffic conditions, and a condition of the one or more batteries of the BEM 100 including a state of charge (SoC) and a state of health (SoH) of the one or more batteries 112. The weighting factor of the unplanned event may be determined using at least one of a heuristic algorithm for determining the weighting factor of the unplanned events, a simulation for determining the weighting factor of the unplanned events, stochastic models for the unplanned events, or a machine learning for determining the weighting factor of the unplanned events. At block 508, a weighted unplanned energy usage may be determined as a sum of products of the predetermined number of highest unplanned energy usages and the corresponding weighting factors. For example, the weighted unplanned energy usage may be the sum of a first product and a second product where the first product is (the energy for stopping at an intersection) multiplied by (the first weighting factor) and the second product is (the energy for accommodating a road closure) multiplied by (the second weighting factor).

[0042] Additionally, or alternatively, a single weighting factor may be determined for a combined unplanned events associated with the selected predetermined number of the highest unplanned energy usages at block 506. For example, a sum, which is the energy for stopping at an intersection and the energy for accommodating a road closure, may be first calculated, the single weighting factor for the sum may be determined. The unplanned energy usage as a weighted unplanned energy usage may be then determined as a product of the sum and the single weighting factors at block 508.

[0043] At block 510, the energy reserve is calculated as, at this point in time and location, a total of an amount of energy for the BEM 100 to be able to execute the production circuit, the weighted unplanned energy usage, and the planned task energy amount associated with the travel by the BEM to the charging station. The process then proceeds to block 312.

[0044] FIG. 6 is a block diagram of the computing system 226 for optimizing an energy reserve of a BEM, such as the BEM 100. For the purpose of discussion, unless otherwise specified, FIG. 6 will be described below with respect to the processor 602 of the computing system 226 performing the method and steps described above with reference to FIGS. 3-5.Generally, computer-executable instructions include routines, programs, objects, components, data structures, and the like that perform particular functions or implement particular data types. The order in which the operations are described is not intended to be construed as a limitation, and any number of the described operations may be combined in any order and / or in parallel to implement the process. The computing system 226 may also embody single or multiple microprocessors, field programmable gate arrays (FPGAs), digital signal processors (DSPs), programmable logic controllers (PLCs), etc.

[0045] The computing system 226 may be hosted by a single server or distributedly hosted by a plurality of servers in a cloud environment. The computing system 226 may comprise the processor 602, a memory 604 communicatively coupled to the processor 602, and a communication module 606 communicatively coupled to the processor 602. The communication module 606 may include an interface 608, such as a user interface and input / output (I / O) module capable of receiving inputs and providing outputs. The inputs and outputs may be communicated to and from the communication module 606 via the communication network 224. As described above with reference to FIG. 2, the communication network 224 may be a cellular network, WiFi® network, or any other type of network. In some examples, the BEM 100 may use the communication network 224 to report location data and / or other types of data to the computing system 226, such that the computing system 226 may track the location of the BEM 100 on the worksite 200, and the computing system 226 may communicate data and instructions to the BEM 100 via the communication network 224.

[0046] In some examples, the processor 602 may include a central processing unit (CPU), a graphics processing unit (GPU), both CPU and GPU, or other processing units or components known in the art. Additionally, the processor 602 may possess its own local memory, which also may store program modules, program data, and / or one or more operating systems. The memory 604 may comprise computer-readable media, which may include volatile memory (e.g., RAM), non-volatile memory (e.g., ROM, flash memory, miniature hard drive, memory card, or the like), or some combination thereof. The computer-readable media may be non-transitory computer- readable media. The computer-readable media may include or be associated with the one or more of the above-noted modules, which perform various operations associated with the computing system 226. In some examples, one or more of the modules may include or be associated withcomputer-executable instructions that are stored by the computer-readable media and that are executable by one or more processors to perform such operations. For example, the memory 604 may store processor-executable instructions that, when executed by the processor 602 of the computing system 226, cause the processor 602 to perform operations for optimizing energy reserve of a battery electric machine (BEM) as described above with reference to FIGS. 3-5.

[0047] The software and or functionality of the system(s), component(s), algorithms, cloud(s), platform(s), etc., discussed above with reference to FIGs. 3-5 regarding optimizing an energy reserve of a BEM may be combined in different ways depending on design requirements, ease of construction and / or integration, cost, etc. Accordingly, while these elements have been separated for purposes of discussion, they may be combined, as appropriate, during implementation.

[0048] The computing system 226 may be configured to use artificial intelligence for maintaining synchronization between centralized (cloud-based) and distributed models. The computing system 226 may include a centralized or cloud-based computer processing system located in one or more of a back-office server or a plurality of remote servers, one or more distributed, edge-based computer processing systems separately located with each of the distributed computer processing systems communicatively connected to the centralized computer processing system.

[0049] A machine learning engine may be included in at least one of the centralized and distributed computer processing systems. The machine learning engine may train a learning system using the training data to enable the machine learning engine to safely mitigate a divergence discovered between first and second sets of output control commands using a learning function including at least one learning parameter. Training the learning system may include providing the training data as an input to the learning function. The learning function may be configured to use the at least one learning parameter to generate an output based on the input, cause the learning function to generate the output based on the input, and compare the output to one or more of the first and second sets of output control commands to determine a difference between the output and the one or more of the first and second sets of output control commands. The learning function may modify the at least one learning parameter and the outputof the learning function to decrease the difference responsive to the difference being greater than a threshold difference and under a variety of different conditions.Industrial Applicability

[0050] The example systems and methods of the present disclosure are applicable for optimizing an energy reserve of a battery electric machine (BEM), such as an automobile, a truck, an agricultural vehicle, an aircraft, a watercraft, and / or work vehicles, such as a track loader, a skid-steer loader, a grader, an on-highway truck, an off-highway truck, and / or any other machine known to a person skilled in the art. The systems and methods described herein may be used to reserve sufficient battery power for the BEM allocated to a production circuit to travel to a charging station under different unplanned events. For example, a computing system, or the BEM, determines a location of the BEM, a location of a nearest charging station compatible with the BEM, and a planned task energy amount associated with one or more planned tasks of the BEM in the production circuit including a travel by the BEM to the nearest charging station along a predetermined route. The computing system, or the BEM, calculates an unplanned energy usage associated with a plurality of unplanned events of the BEM, where the plurality of unplanned events are different from the one or more planned tasks. The computing system, or the BEM, based at least in part on the planned task energy amount and the unplanned energy usage, determines an energy reserve for one or more batteries of the BEM, where the energy reserve is an amount of energy for the BEM, at a given point in time and location, to be able to execute the production circuit and reach the location of the charging station from the location of the BEM while accommodating at least some of the unplanned events. The BEM may transmit the energy reserve and a current charge state of the batteries to the computing system, and the computing system may determine, based on the current charge state of the batteries, whether the BEM is near or below the energy reserve, and instruct the BEM to execute an appropriate action at the appropriate time, such as an opportunistic charging including charging the batteries without reducing productivity of the BEM.

[0051] Unless explicitly excluded, the use of the singular to describe a component, structure, or operation does not exclude the use of plural such components, structures, or operations or their equivalents. The use of the terms “a” and “an” and “the” and “at least one” or the term “one or more,” and similar referents in the context of describing the invention (especially in the context of the following claims) are to be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. The use of the term “at least one” followed by a list of one or more items (for example, “at least one of A and B” or one or more of A and B”) is to be construed to mean one item selected from the listed items (A or B) or any combination of two or more of the listed items (A and B; A, A and B; A, B and B), unless otherwise indicated herein or clearly contradicted by context. Similarly, as used herein, the word "or" refers to any possible permutation of a set of items. For example, the phrase "A, B, or C" refers to at least one of A, B, C, or any combination thereof, such as any of: A; B; C; A and B; A and C; B and C; A, B, and C; or multiple of any item such as A and A; B, B, and C; A, A, B, C, and C; etc.

[0052] While aspects of the present disclosure have been particularly shown and described with reference to the examples above, it will be understood by those skilled in the art that various additional embodiments may be contemplated by the modification of the disclosed devices, systems, and methods without departing from the spirit and scope of what is disclosed. Such embodiments should be understood to fall within the scope of the present disclosure as determined based upon the claims and any equivalents thereof.

Claims

ClaimsWhat is claimed is:

1. A method comprising: determining a location of a battery electric machine (BEM) allocated to a production circuit; determining a location of a charging station compatible with the BEM; determining, based at least in part on the location of the BEM and the location of the charging station, a planned task energy amount associated with one or more planned tasks of the BEM executing the production circuit; calculating an unplanned energy usage associated with a plurality of unplanned events of the BEM, the plurality of unplanned events different from the one or more planned tasks; based at least in part on the planned task energy amount and the unplanned energy usage, determining an energy reserve for one or more batteries of the BEM; determining whether a current charge state of the one or more batteries is below the energy reserve; and causing the BEM to execute an opportunistic charging.

2. The method of claim 1, wherein causing the BEM to execute the opportunistic charging includes at least one of: instructing the BEM to travel to the charging station during a period when the BEM is scheduled to idle, or instructing the BEM to move to a different production circuit where the BEM is able to charge the one or more batteries while travelling.

3. The method of claim 1 further comprising: determining an alternate planned task energy amount associated with one or more alternate planned tasks of the BEM in an alternative production circuit; anddetermining the planned task energy amount associated with travel by the BEM to the charging station from a location of the BEM in the alternative production circuit.

4. The method of claim 1, wherein the one or more planned tasks include: one or more routine tasks of the BEM associated with the production circuit having known energy amount requirements to complete the one or more routine tasks, and a number of repetitions of each routine task of the one or more routine tasks.

5. The method of claim 1, wherein the plurality of unplanned events includes at least one of: the BEM following behind traffic moving slower than an expected rate of an associated planned task, the BEM stopping at an intersection, reducing speed of the BEM to time arrivals at a destination of an associated planned task, stopping the BEM autonomously, accounting for medical emergencies, accommodating a road closure, the BEM being delayed at a destination of an associated planned task based on the destination being serviced, the BEM queuing at a destination of an associated planned task, engaging regenerative braking of the BEM for one or more unplanned stops, the BEM being prevented from completing the one or more planned tasks and completing alternative tasks that require more energy than completing the one or more planned tasks, or the BEM being disconnected from a trolley before reaching a predetermined target charge of the one or more batteries while travelling connected to the trolley.

6. The method of claim 5, wherein calculating the unplanned energy usage associated with the plurality of unplanned events includes calculating an unplanned energy usage associated with an unplanned event of the plurality of unplanned events using at least one of: a heuristic algorithm for estimating the unplanned energy usage associated the unplanned event, a simulation of the unplanned event for estimating the unplanned energy usage associated the unplanned event, a stochastic model for estimating the unplanned energy usage associated the unplanned event, or a machine learning for estimating the unplanned energy usage associated the unplanned event.

7. The method of claim 5 further comprising: ranking the plurality of unplanned events in order of corresponding unplanned energy usages; and selecting a predetermined number of unplanned events from the plurality of unplanned events based on the predetermined number of highest unplanned energy usages.

8. The method of claim 7 further comprising: determining a corresponding weighting factor for each of the predetermined number of unplanned events based at least in part on at least one of: likelihood of a corresponding unplanned event occurring, historical occurrences of the corresponding unplanned event, current and future weather conditions around the location of the BEM, an updated information regarding an associated route of the corresponding unplanned event, or a condition of the one or more batteries of the BEM; anddetermining the unplanned energy usage as a weighted unplanned energy usage, the weighted unplanned energy usage being a sum of products of the predetermined number of highest unplanned energy usages and the corresponding weighting factors.

9. The method of claim 8, wherein determining the corresponding weighting factor for each of the unplanned events includes using at least one of: a heuristic algorithm for determining the corresponding weighting factor for each of the unplanned events, a simulation for determining the corresponding weighting factor for each of the unplanned events, a stochastic model for determining the corresponding weighting factor for each of the unplanned events, or a machine learning for determining the corresponding weighting factor for each of the unplanned events.

10. The method of claim 7 further comprising: calculating a sum of the predetermined number of the highest unplanned energy usages; determining a weighting factor for unplanned events associated with the predetermined number of the highest unplanned energy usages based at least in part on at least one of: likelihood of the unplanned events occurring, historical occurrences of the unplanned events, current and future weather conditions around the location of the BEM, an updated information regarding an associated route of the unplanned events, or a condition of the one or more batteries of the BEM; and determining the unplanned energy usage as a weighted unplanned energy usage, the weighted unplanned energy usage being a product of the sum and the weighting factor.

11. The method of claim 10, wherein determining the weighting factor of the unplanned events includes using at least one of: a heuristic algorithm for determining the weighting factor of the unplanned events, a simulation for determining the weighting factor of the unplanned events, a stochastic model for determining the weighting factor of the unplanned events or a machine learning for determining the weighting factor of the unplanned events.

12. A system comprising: a processor; and a memory communicatively coupled to the processor, the memory storing thereon processor-executable instructions that, when executed by the processor, cause the processor to: determine a location of a battery electric machine (BEM) allocated to a production circuit; determine a location of a charging station compatible with the BEM; determine, based at least in part on the location of the BEM and the location of the charging station, a planned task energy amount associated with one or more planned tasks of the BEM executing the production circuit; calculate an unplanned energy usage associated with a plurality of unplanned events of the BEM; based at least in part on the planned task energy amount and the unplanned energy usage, determine an energy reserve for one or more batteries of the BEM; determine whether a current charge state of the one or more batteries is below the energy reserve; and cause the BEM to execute an opportunistic charging.

13. The system of claim 12, wherein the processor-executable instructions further cause the processor to: determine an alternate planned task energy amount associated with one or more alternate planned tasks of the BEM in an alternative production circuit; and determine the planned task energy amount associated with travel by the BEM to the charging station from a location of the BEM in the alternative production circuit.

14. The system of claim 12, wherein the plurality of unplanned events includes at least one of: the BEM following behind traffic moving slower than an expected rate of an associated planned task, the BEM stopping at an intersection, reducing speed of the BEM to time arrivals at a destination of an associated planned task, stopping the BEM autonomously, accounting for medical emergencies, accommodating a road closure, the BEM being delayed at a destination of an associated planned task based on the destination being serviced, the BEM queuing at a destination of an associated planned task, engaging regenerative braking of the BEM for one or more unplanned stops, the BEM being prevented from completing the one or more planned tasks and completing alternative tasks that require more energy than completing the one or more planned tasks, or the BEM being disconnected from a trolley before reaching a predetermined target charge of the one or more batteries while travelling connected to the trolley.

15. The system of claim 14, wherein the processor-executable instructions further cause the processor to: rank the plurality of unplanned events in order of corresponding unplanned energy usages;select a predetermined number of unplanned events from the plurality of unplanned events based on the predetermined number of highest unplanned energy usages; determine a corresponding weighting factor for each of the predetermined number of unplanned events based at least in part on at least one of: likelihood of the unplanned events occurring, historical occurrences of the unplanned events, current and future weather conditions around the location of the BEM, an updated information regarding an associated route of the unplanned events, or a condition of the one or more batteries of the BEM; and determining the unplanned energy usage as a weighted unplanned energy usage, the weighted unplanned energy usage being a sum of products of the predetermined number of highest unplanned energy usages and the corresponding weighting factors.

16. The system of claim 15, wherein the processor-executable instructions further cause the processor to calculate the unplanned energy usage associated with the plurality of unplanned events includes calculating an unplanned energy usage associated with an unplanned event of the plurality of unplanned events using at least one of: a heuristic algorithm for estimating the unplanned energy usage associated the unplanned event, a simulation of the unplanned event for estimating the unplanned energy usage associated the unplanned event, stochastic model for estimating the unplanned energy usage associated the unplanned event, or a machine learning for estimating the unplanned energy usage associated the unplanned event, and determining the corresponding weighting factor for each of the unplanned event includes using at least one of:a heuristic algorithm for determining the corresponding weighting factor of the unplanned event, a simulation for determining the corresponding weighting factor of the unplanned event, a stochastic model for determining the corresponding weighting factor of the unplanned event, or a machine learning for determining the corresponding weighting factor of the unplanned event.

17. Non-transitory computer-readable medium storing thereon processor-executable instructions that, when executed by a processor of a system, cause the processor to perform operations for optimizing energy reserve of a battery electric machine (BEM), the operations comprising: determining a location of the BEM allocated to a production circuit; determining a location of a charging station compatible with the BEM; determining, based at least in part on the location of the BEM and the location of the charging station, a planned task energy amount associated with one or more planned tasks of the BEM executing the production circuit; calculating an unplanned energy usage associated with a plurality of unplanned events of the BEM; based at least in part on the planned task energy amount and the unplanned energy usage, determining an energy reserve for one or more batteries of the BEM; determining whether a current charge state of the one or more batteries is below the energy reserve; and causing the BEM to execute an opportunistic charging.

18. The non-transitory computer-readable medium of claim 17, wherein the plurality of unplanned events includes at least one of:the BEM following behind traffic moving slower than an expected rate of an associated planned task, the BEM stopping at an intersection, reducing speed of the BEM to time arrivals at a destination of an associated planned task, stopping the BEM autonomously, accounting for medical emergencies, accommodating a road closure, the BEM being delayed at a destination of an associated planned task based on the destination being serviced, the BEM queuing at a destination of an associated planned task, engaging regenerative braking of the BEM for one or more unplanned stops, the BEM being prevented from completing the one or more planned tasks and completing alternative tasks that require more energy than completing the one or more planned tasks, or the BEM being disconnected from a trolley before reaching a predetermined target charge of the one or more batteries while travelling connected to the trolley.

19. The non-transitory computer-readable medium of claim 18, wherein the operations further comprise: ranking the plurality of unplanned events in order of corresponding unplanned energy usages; selecting a predetermined number of unplanned events from the plurality of unplanned events based on the predetermined number of highest unplanned energy usages; determining a corresponding weighting factor for each of the predetermined number of unplanned events associated based at least in part on at least one of: likelihood of the unplanned events occurring, historical occurrences of the unplanned events, current and future weather conditions around the location of the BEM,an updated information regarding an associated route of the unplanned events, or a condition of the one or more batteries of the BEM; and determining the unplanned energy usage as a weighted unplanned energy usage, the weighted unplanned energy usage being a sum of products of the predetermined number of highest unplanned energy usages and the corresponding weighting factors.

20. The non-transitory computer-readable medium of claim 19, wherein: calculating the unplanned energy usage associated with the plurality of unplanned events includes calculating an unplanned energy usage associated with an unplanned event of the plurality of unplanned events using at least one of: a heuristic algorithm for estimating the unplanned energy usage associated the unplanned event, a simulation of the unplanned event for estimating the unplanned energy usage associated the unplanned event, a stochastic model for estimating the unplanned energy usage associated the unplanned event, or a machine learning for estimating the unplanned energy usage associated the unplanned event; and determining the corresponding weighting factor for each of the unplanned event includes using at least one of: a heuristic algorithm for determining the corresponding weighting factor of the unplanned event, a simulation for determining the corresponding weighting factor of the unplanned event, a stochastic model for determining the corresponding weighting factor of the unplanned event, ora machine learning for determining the corresponding weighting factor of the unplanned event.

Images