Power consumption prediction device, working machine, power consumption prediction system, power consumption prediction method and program

Abstract

To suppress deterioration of a storage battery.SOLUTION: A power consumption prediction device comprises: a plan acquisition unit; a power consumption amount prediction unit; and an output unit. The plan acquisition unit acquires a work plan that includes work actions to performed by a working machine including a storage battery and a work time during which the work content is performed. The power consumption amount prediction unit predicts an amount of work power consumption consumed by the storage battery with the work plan on the basis of the work plan acquired by the plan acquisition unit. The output unit outputs the work power consumption amount predicted by the power consumption amount prediction unit.SELECTED DRAWING: Figure 6A

Description

[Technical Field]

[0001] The present disclosure relates to a power consumption prediction device, a work machine, a power consumption prediction system, a power consumption prediction method, and a program. [Background technology]

[0002] In recent years, work machines equipped with storage batteries and operating on the power of the storage batteries have become widespread. Storage batteries are charged periodically. Therefore, technologies have been proposed to encourage users to charge the batteries. For example, a charge control method is known in which an estimated daily power consumption is calculated based on a history of power consumption of the battery equipped in the vehicle, a charge recommendation threshold is set based on the estimated power consumption, a minimum remaining capacity, and the battery's remaining capacity, and a notification is sent to encourage charging when the remaining battery capacity falls below the charge recommendation threshold (see, for example, Patent Document 1 listed below). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7198851 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with conventional technology, it may not be possible to charge the storage battery installed in the work machine at the optimal timing with the optimal amount of power to be consumed, which may result in accelerated deterioration of the storage battery. An object of the present disclosure is to provide a power consumption prediction device, a work machine, a power consumption prediction system, a power consumption prediction method, and a program that can suppress deterioration of a storage battery provided in a work machine. [Means for solving the problem]

[0005] According to a first aspect of the present disclosure, a power consumption prediction device includes a plan acquisition unit that acquires a work plan including work content to be performed by a work machine equipped with a storage battery and work time for the work content to be performed, a power consumption prediction unit that predicts the amount of work power consumption to be consumed by the storage battery in the work plan based on the work plan acquired by the plan acquisition unit, and an output unit that outputs the amount of work power consumption predicted by the power consumption prediction unit. [Effects of the Invention]

[0006] According to the above aspect, it is possible to suppress deterioration of the storage battery provided in the work machine. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a diagram illustrating an example of a network configuration of a power consumption prediction system according to an embodiment; [Figure 2] 1 is a block diagram showing an example of the configuration of a work machine. [Figure 3] FIG. 2 is a block diagram showing the hardware configuration of a computer device provided in a power consumption prediction server, a work machine (ECU), and an administrator terminal. [Figure 4A] FIG. 2 is a diagram illustrating an example of a work plan stored in a work plan DB. [Figure 4B] FIG. 10 is a diagram illustrating an example of a power consumption list stored in a power consumption list DB. [Figure 5] FIG. 1 illustrates an example of a functional configuration of a power consumption prediction system. [Figure 6A] 10 is a flowchart illustrating a power consumption prediction method performed by the power consumption prediction server. [Figure 6B] 10 is a flowchart showing an alternative determination process performed by the power consumption prediction server. [Figure 7] 4 is a flowchart showing a charge control method performed by a work machine. [Figure 8] 10 is a flowchart showing a charging necessity process performed by a work machine. [Figure 9]4 is a flowchart showing a predicted charging time calculation process performed by a work machine. DETAILED DESCRIPTION OF THE INVENTION

[0008] <Embodiment> <Power Consumption Prediction System 1> Fig. 1 is a diagram showing an example of the network configuration of a power consumption prediction system according to an embodiment. As shown in Fig. 1, the power consumption prediction system 1 includes a power consumption prediction server 100, a plurality of work machines 110, a charger 111, and an administrator terminal 120. The power consumption prediction system 1 is installed at a work site where the work machines 110 work, such as a construction site or a quarry. The power consumption prediction system 1 predicts the power consumption of a storage battery installed in the work machine 110.

[0009] In the power consumption prediction system 1 shown in Fig. 1, the power consumption prediction server 100, a plurality of work machines 110, and an administrator terminal 120 are communicatively connected via a network 140. Note that the charger 111 may also be communicatively connected to each device via the network 140. Each device is a computer device equipped with a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), a communication unit, etc.

[0010] The power consumption prediction server 100 is an example of a power consumption prediction device. The power consumption prediction server 100 predicts power consumption according to the work content of each work machine 110. Specifically, the power consumption prediction server 100 is equipped with a work plan DB (database) 101 and a power consumption list DB 102. The work plan DB 101 stores work plans including each work content for each work machine 110. The power consumption list DB 102 stores a list of power consumption (power consumption per unit time) consumed in each work content for each work machine 110. The power consumption prediction server 100 predicts power consumption in the work plan for each work machine 110 based on the information stored in the work plan DB 101 and the power consumption list DB 102.

[0011] The work machine 110 is, for example, a hydraulic excavator, bulldozer, dump truck, wheel loader, or other type of heavy machinery. The work machine 110 is equipped with a battery 203 (FIG. 2) as a storage battery. The work machine 110 works using electricity stored in the battery 203. The work machine 110 is used in accordance with a work plan.

[0012] The charger 111 is placed at a predetermined standby location where the work machine 110 is on standby. The charger 111 is periodically connected to the battery 203 when the work machine 110 is on standby, and charges the battery 203.

[0013] The manager terminal 120 is a terminal device operated by a manager such as a site supervisor. The manager terminal 120 is a computer device such as a personal computer equipped with a display. The manager terminal 120 is placed, for example, in an office at the work site. The manager terminal 120 may also be a portable terminal device such as a smartphone or tablet terminal.

[0014] "Work Machine 110" Fig. 2 is a block diagram showing an example of the configuration of the work machine 110. As shown in Fig. 2, the work machine 110 includes a vehicle body ECU (Electronic Control Unit) 201, an on-board monitor 202, a battery 203, a DC / DC converter 204a, an inverter 204b, a work implement motor 205, and a traveling body motor 206.

[0015] The body ECU 201 controls the operation of each of the sections 202 to 207 that the work machine 110 is equipped with by reading and executing a predetermined program.

[0016] The on-board monitor 202 displays various types of information under the control of the vehicle body ECU 201. The various types of information include information relating to the state of the battery 203, such as the remaining charge level and usage status of the battery 203, and information such as the work plan for the work machine 110. The on-board monitor 202 is a touch panel display unit that receives operational input from the operator.

[0017] The battery 203 is a secondary battery. The battery 203 operates the work machine motor 205 and the traveling body motor 206 with stored electricity. The battery 203 is used within an appropriate charged amount range. For example, from the viewpoint of preventing deterioration, the battery 203 is stored so that it maintains a lower limit (for example, 20%) of remaining charge (lower limit value) even when the power is completely used up, and also maintains an upper limit (for example, 80%) of remaining charge even when the battery is fully charged.

[0018] The DC / DC converter 204a converts the direct current from the charger 111 to a desired voltage and stores the voltage in the battery 203. The DC / DC converter 204a also converts the direct current of the battery 203 to a desired voltage and supplies the voltage to the bus. The inverter 204 b converts the direct current flowing through the bus into alternating current, and drives the work machine motor 205 and the traveling body motor 206 .

[0019] The work implement motor 205 is a motor that operates the work implement portion of the work machine 110 (for example, the bucket in the case of a hydraulic excavator). The running body motor 206 is a motor that operates the running body. The running body may include tires or crawlers. The running body motor 206 is, for example, a motor that operates the tires or crawlers.

[0020] <<Functional Configuration of Each Computer Device>> 3 is a block diagram showing the hardware configuration of the computer devices of each device provided in the power consumption prediction system 1. A computer 300 is implemented in each of the power consumption prediction server 100, the work machine 110 (body ECU 201), the charger 111, and the administrator terminal 120.

[0021] The computer 300 includes a processor 301, a main memory 302, a storage 303, and an interface 304. The processor 301 reads various programs stored in the storage 303, loads them into the main memory 302, and executes processing in accordance with the programs. The processor 301 also allocates a storage area in the main memory 302 in accordance with the programs. Examples of the processor 301 include a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), and a microprocessor.

[0022] Storage 303 includes, for example, a magnetic disk, a magneto-optical disk, an optical disk, or a semiconductor memory. Storage 303 may be an internal medium directly connected to the bus of computer 300, or an external medium connected to computer 300 via interface 304 or a communication line. Furthermore, when this program is distributed to computer 300 via a communication line, computer 300 that receives the program may load the program into main memory 302 and execute the processing.

[0023] If the devices in which the computer 300 is implemented are the work machine 110 , the charger 111 , and the manager terminal 120 , the computer 300 is connected to input devices and output devices via the interface 304 . The input device includes, for example, a touch panel, operation buttons, etc. In the case of the work machine 110, the input device further includes, for example, a camera and a GNSS (Global Navigation Satellite System) unit. The output device may include, for example, a display and a speaker, and in the case of the administrator terminal 120, the output device may further include, for example, a printer.

[0024] <Work Plans Stored in the Work Plan DB 101> Next, a description will be given of the work plans stored in the work plan DB 101. The power consumption prediction server 100 includes the work plan DB 101 as an example of a unit power consumption storage unit.

[0025] Fig. 4A is a diagram showing an example of a work plan stored in the work plan DB 101. As shown in Fig. 4A, the work plan DB 101 includes the following items: "work machine ID," "model," "charger ID," "battery capacity (kWh)," "charging capacity (kW)," "work plan ID," "work content," "work start time," "work end time," and "work duration (h)." By inputting data into each item, a work plan 401 (401a, 401b, 401c) is stored as a record.

[0026] The "work machine ID" indicates identification information that identifies the work machine 110. For example, the "work machine ID" is a unique number assigned to the work machine 110 in advance, and more specifically, the vehicle number of the work machine 110. "Model" indicates the type of work machine 110 (hydraulic excavator, bulldozer, dump truck, etc.). The "charger ID" indicates identification information for identifying the charger 111. For example, the "charger ID" is a unique number assigned to the charger 111 in advance, and specifically, the model number of the charger 111. "Battery capacity (kWh)" indicates the maximum battery capacity of the battery 203 of the work machine 110. "Battery capacity" is determined in advance for each model of work machine 110. "Remaining storage capacity (kWh)" indicates the remaining battery capacity of the battery 203 of the work machine 110 in question. "Charging capacity (kW)" indicates the amount of charge per hour when the battery 203 is charged by the charger 111. The charging capacity of the battery 203 is determined in advance for each battery 203 of the work machine 110. The charging capacity of the charger 111 is determined in advance for each type of charger 111. The "charging capacity" is the lower of the charging capacity of the charger 111 and the charging capacity of the battery 203. In other words, the "charging capacity" differs depending on the combination of the charger 111 and the battery 203 of the work machine 110. The “work plan ID” indicates identification information for identifying the work plan 401 . "Work content" indicates the type of work content that the work machine 110 is performing. "Work start time" indicates the start time (date and time) of the work. "Work end time" indicates the end time (date and time) of the work. "Work time" indicates the time obtained by subtracting the work start time from the work end time.

[0027] The work plan 401 is generated by inputting various information into the manager terminal 120. For example, when generating the work plan 401, the manager determines the work to be performed and the work time for each work machine 110. The work time for each work machine 110 may be calculated based on the number of work machines 110 and the amount of work to be performed. The battery capacity and charging capacity listed in the work plan 401 shown in FIG. 4A are determined in advance according to the model of the work machine 110 and the type of charger 111. Therefore, the manager inputs a combination of the items "work machine ID," "charger ID," "work content," "work start time," and "work end time" as the work plan. In other words, when generating the work plan 401, it is not necessary to input the items "battery capacity," "charging capacity," "model," and "work time." It may also be possible to automatically obtain which charger 111 is connected to the work machine 110.

[0028] The administrator terminal 120 transmits the input items to the power consumption prediction server 100. The power consumption prediction server 100 stores the items received from the administrator terminal 120 in the work plan DB 101. The "work plan ID" may be assigned by the power consumption prediction server 100 or the administrator terminal 120 using a sequence number or the like. The "work time" is automatically calculated by the power consumption prediction server 100 or the administrator terminal 120.

[0029] <<Unit Power Consumption List Stored in Power Consumption List DB 102>> Next, the unit power consumption list stored in the power consumption list DB 102 will be described. The power consumption prediction server 100 includes the power consumption list DB 102 as an example of a unit power consumption storage unit. The unit power consumption list is the power consumed per unit period for each task. The unit power consumption list is information that is set in advance. The unit power consumption list may be updateable by an authorized operator.

[0030] Fig. 4B is a diagram showing an example of a power consumption list stored in the power consumption list DB 102. As shown in Fig. 4B, the power consumption list DB 102 includes the following items: "model," "task," and "unit power consumption (kW)." By inputting data into each item, a power consumption list 411 (411a, 411b, 411c) is stored as a record.

[0031] "Model" indicates the type of work machine 110 (hydraulic excavator, bulldozer, dump truck, etc.). "Work content" indicates the type of work content that the work machine 110 can perform. "Unit power consumption" indicates the power consumed per unit time for each type of work content.

[0032] The work plan DB 101 and the power consumption list DB 102 are not necessarily provided in the power consumption prediction server 100. They may be provided in devices other than the power consumption prediction server 100.

[0033] <Functional configuration of power consumption prediction system 1> Fig. 5 is a diagram showing an example of the functional configuration of the power consumption prediction system. As shown in Fig. 5, the power consumption prediction server 100 includes the following functional units: a plan acquisition unit 501, a unit power consumption extraction unit 502, a power consumption prediction unit 503, a transmitting / receiving unit 504, a remaining power storage amount acquisition unit 505, and a work machine identification unit 506. Each functional unit is realized by the processor 301 of the power consumption prediction server 100. In other words, each functional unit is realized by the processor 301 of the power consumption prediction server 100 executing a predetermined program stored in the storage 303.

[0034] The plan acquisition unit 501 acquires a work plan 401 from the work plan DB 101 (FIG. 4A). As shown in FIG. 4A, the work plan 401 includes the work content to be performed by the work machine 110 (work content item) and the work time during which the work content will be performed (work time item).

[0035] The unit power consumption extraction unit 502 extracts unit power consumption from the power consumption list 411 in the power consumption list DB 102 (FIG. 4B). The extracted unit power consumption is the unit power consumption according to the work content indicated in the work plan 401 acquired by the plan acquisition unit 501. For example, if the work content is "excavation" as in the work plan 401a (FIG. 4A), the unit power consumption extraction unit 502 extracts the unit power consumption of "20 kW" according to "excavation" from the power consumption list 411a (FIG. 4B).

[0036] The power consumption prediction unit 503 predicts the amount of work power consumption to be consumed by the battery 203 in the work plan 401, based on the work plan acquired by the plan acquisition unit 501. Specifically, the power consumption prediction unit 503 predicts (calculates) the amount of work power consumption by multiplying the unit power consumption extracted by the unit power consumption extraction unit 502 by the work time obtained from the work plan 401.

[0037] The transceiver unit 504 is an example of an output unit. The transceiver unit 504 outputs (transmits) the amount of power consumed for work predicted by the power consumption prediction unit 503. The output destinations of the transceiver unit 504 are, for example, the work machine 110 and the manager terminal 120. When the work machine 110 and the manager terminal 120 acquire (receive) the amount of power consumed for work output from the transceiver unit 504, they each display the amount of power consumed for work.

[0038] <<About warnings>> In this embodiment, a warning can be issued according to the remaining amount of power stored in the battery 203. Specifically, the remaining amount of power acquisition unit 505 acquires the remaining amount of power stored in the battery 203 from the work plan DB 101 (FIG. 4A). The receiver / transmitter 504 outputs warning information indicating a warning when the remaining amount of power stored is insufficient for the amount of power consumed for the work. The warning is, for example, a warning indicating that the remaining amount of power stored in the battery 203 will be insufficient for the amount of power consumed for the work.

[0039] <<About replacement vehicles>> In this embodiment, it is possible to prepare a substitute vehicle depending on the remaining amount of stored power in the battery 203. To be more specific, if the remaining amount of stored power is insufficient for the amount of power consumed during work, the work machine identifying unit 506 identifies another work machine 110. Specifically, the work machine identifying unit 506 identifies another work machine 110 that will perform the work that is lacking, based on the work plan of the other work machine 110. An example of this identification will be described later using FIG. 6B.

[0040] The receiver / transmitter unit 504 outputs information indicating the other work machine 110 (substitutable work machine 110) identified by the work machine identification unit 506. This information includes the work machine ID, the time during which the machine can be used as a substitute vehicle, and the like.

[0041] <Functional Configuration of Work Machine 110> 5, the work machine 110 (ECU 201) has the following functional units: a power consumption amount acquisition unit 521, a stored power content acquisition unit 522, a predicted charging time calculation unit 523, a time acquisition unit 524, and an instruction unit 525. Each functional unit is realized by the processor 301 of the work machine 110. In other words, the processor 301 of the ECU 201 executes a predetermined program stored in the storage 303 to realize each functional unit.

[0042] The power consumption amount acquisition unit 521 acquires the amount of power consumed by work output by the transmitting / receiving unit 504 of the power consumption prediction server 100. When the work machine 110 receives the amount of power consumed by work from the power consumption prediction server 100, it stores it in a memory unit such as the storage 303. Therefore, the power consumption amount acquisition unit 521 acquires the amount of power consumed by work stored in that memory unit. The timing when the power consumption amount acquisition unit 521 acquires the amount of power consumed by work is, for example, the timing when charging of the battery 203 can start. This timing is, for example, the timing when the work machine 110 is placed at a specified charging location. The timing when the amount of power consumed by work is transmitted to the work machine 110 is, for example, the timing when the power consumption prediction server 100 predicts the amount of power consumed by work (the timing when a work plan is made).

[0043] When the power consumption amount acquiring unit 521 acquires the work power consumption amount, the power storage content acquiring unit 522 acquires the remaining power storage amount of the battery 203. The battery 203 is equipped with a BMU (Battery Monitoring Unit). The BMU monitors the state of the battery 203. The state includes the state of charge (SOC), voltage, capacity, temperature, etc. The power storage content acquiring unit 522 acquires the remaining power storage amount from the BMU. In addition to the remaining power storage amount, the power storage content acquiring unit 522 also acquires the charging capacity of the battery 203 or the charging capacity of the charger 111. The charging capacity is assumed to be a value included in the work plan 401 in the work plan DB 101, but is not limited to this, and a value input in advance to the in-vehicle monitor 202 or the like may be acquired. In addition, if the charging capacity can be detected by the charger 111, the power consumption amount acquiring unit 521 may acquire the charging capacity from the charger 111.

[0044] The predicted charging time calculation unit 523 calculates a predicted charging time required to charge the battery 203 based on the amount of power consumed during work acquired by the power consumption acquisition unit 521 and the remaining amount of stored power and charging capacity acquired by the stored power content acquisition unit 522. Specifically, the predicted charging time calculation unit 523 calculates the required amount of charge (kWh) by subtracting the remaining amount of stored power from the amount of power consumed during work. Furthermore, the predicted charging time calculation unit 523 calculates the predicted charging time by dividing the required amount of charge (kWh) by the charging capacity (kW).

[0045] The time acquisition unit 524 acquires the work start time of the work plan 401 ( FIG. 4A ) from the power consumption prediction server 100. When the work machine 110 receives the work plan 401 from the power consumption prediction server 100, it stores it in a memory unit such as the storage 303. Therefore, the time acquisition unit 524 acquires the work start time stored in the memory unit. The timing for acquiring the work start time is, for example, the timing when charging of the battery 203 can begin. Note that the timing for transmitting the work start time to the work machine 110 is, for example, the timing when the power consumption prediction server 100 predicts the amount of power consumed by the work (the timing when the work plan is created).

[0046] The instruction unit 525 issues an instruction to start charging the battery 203. For example, if the battery 203 and the charger 111 are connected, the instruction is an instruction to start charging (an instruction to start charging automatically). Also, for example, if the battery 203 and the charger 111 are not connected, the instruction includes an instruction to prompt the connection between the battery 203 and the charger 111 and an instruction to start charging (an instruction to start charging manually).

[0047] The instruction unit 525 issues an instruction based on the predicted charging time calculated by the predicted charging time calculation unit 523. Specifically, the charging start time is a time obtained by subtracting the predicted charging time calculated by the predicted charging time calculation unit 523 from the work start time acquired by the time acquisition unit 524. The calculation of the charging start time may be performed by the predicted charging time calculation unit 523 or may be performed by the instruction unit 525.

[0048] "method" Next, a power consumption prediction method performed by the power consumption prediction server 100 according to the embodiment will be described. Fig. 6A is a flowchart showing a power consumption prediction method performed by the power consumption prediction server 100. In Fig. 6A, the power consumption prediction server 100 determines whether the work plan 401 (Fig. 4A) has been input or updated from the administrator terminal 120 (step S601).

[0049] The power consumption prediction server 100 waits until the work plan 401 is input or updated (step S601: NO). When the work plan 401 is input or updated (step S601: YES), the power consumption prediction server 100 acquires the work plan 401 input or updated by the administrator terminal 120 (step S602).

[0050] Next, the power consumption prediction server 100 extracts the task time (the value obtained by subtracting the task start time from the task end time) from the task plan 401 (step S603). Then, the power consumption prediction server 100 extracts the unit power consumption corresponding to the task plan 401 from the power consumption list 411 in the power consumption list DB 102 (FIG. 4B) (step S604). Next, the power consumption prediction server 100 calculates (predicts) the task power consumption by multiplying the task time extracted in step S603 by the unit power consumption extracted in step S604 (step S605).

[0051] Then, the power consumption prediction server 100 compares the calculated work power consumption with the remaining stored power obtained from the work plan 401 (FIG. 4A) and determines whether the remaining stored power is insufficient for the work power consumption (step S606). If the remaining stored power is not insufficient for the work power consumption (step S606: NO), the power consumption prediction server 100 proceeds to step S609.

[0052] On the other hand, if the remaining stored power is insufficient for the amount of power consumed during work (step S606: YES), the power consumption prediction server 100 outputs a warning indicating that the remaining stored power is insufficient for the amount of power consumed during work (step S607). The power consumption prediction server 100 then performs substitution determination processing (FIG. 6B) to determine whether or not there is an alternative work machine 110 that can be substituted. Next, the power consumption prediction server 100 outputs the amount of power consumed during work predicted in step S605 (step S609), and ends the series of processing steps.

[0053] <<Alternative Determination Process Performed by the Power Consumption Prediction Server 100>> 6B is a flowchart showing the substitution determination process performed by the power consumption prediction server 100. Note that the following description will be given taking the values ​​of the work plan 401b (FIG. 4A) and the values ​​of the power consumption list 411a (FIG. 4B) as examples.

[0054] In FIG. 6B, the power consumption prediction server 100 calculates the power shortage amount ("60 kWh" - "50 kWh" = "10 kWh") by subtracting the remaining power storage amount (e.g., 50 kWh) of the work plan 401 (FIG. 4A) from the work power consumption amount (60 kWh = 20 kW × 3 h) predicted in step S605 (step S611).

[0055] Then, the power consumption prediction server 100 divides the power shortage (10 kWh) by the unit power consumption (for example, 20 kW) to calculate the work time shortage ("10 kWh" / "20 kW"="0.5 h") (step S612).

[0056] Next, the power consumption prediction server 100 calculates the available work time from the start of work until charging runs out ("50 kWh" / "20 kW" = 2.5 h) by dividing the remaining amount of stored power (e.g., 50 kWh) by the unit power consumption (e.g., 20 kW) (step S613).

[0057] Then, the power consumption prediction server 100 calculates the charge exhaustion time (17:30) by adding the available work time (2.5 hours) to the work start time (for example, 15:00) (step S614).

[0058] Next, the power consumption prediction server 100 acquires the work plans 401 of the other work machines 110 (step S615). Then, the power consumption prediction server 100 references the acquired work plans 401 and determines whether there is a work machine 110 that can secure work for the missing work time (0.5 hours) from the time when the battery runs out (17:30) (step S616).

[0059] If there is a work machine 110 that can ensure work for the shortfall in work time from the charge-out time (step S616: YES), the power consumption prediction server 100 determines whether a predetermined charging time can be ensured immediately before the charge-out time (17:30) for that work machine 110 (step S617). The predetermined charging time may be a predetermined fixed time (for example, two hours), or may be a calculated charging time (the time required to charge the shortfall in power).

[0060] If the specified charging time cannot be secured (step S617: NO), or if there is no work machine 110 that can secure work for the shortfall in work time from the time when the charge runs out in step S616 (step S616: NO), the power consumption prediction server 100 outputs a message that there is no substitutable work machine 110 (step S618), and proceeds to step S609 in FIG. 6A.

[0061] On the other hand, in step S617, if the specified charging time can be secured for the work machine 110 (step S617: YES), the power consumption prediction server 100 outputs information indicating the substitutable work machine 110 (the work machine ID and information about the time period during which substitutable use is possible) (step S619). The information is output to the administrator terminal 120 or the on-board monitor 202. In other words, the information is notified to the administrator or the driver of the work machine 110. Next, the power consumption prediction server 100 outputs the amount of power shortage to the substitutable work machine 110 (step S620), and the series of processes ends.

[0062] <Charging Control Process Performed by Work Machine 110> Figure 7 is a flowchart showing the charge control process performed by the work machine 110. In Figure 7, the work machine 110 determines whether the timing has come when charging can begin (step S701). The work machine 110 waits until the timing comes when charging can begin (hereinafter referred to as "chargeable timing") (step S701: NO). The chargeable timing is, for example, the timing when the work machine 110 is placed at a specified charging location and further when a cable between the battery 203 and charger 111 is connected. Note that even if the cable between the battery 203 and charger 111 is connected, it is assumed that no electricity is flowing through it.

[0063] In step S701, when the timing becomes available for charging (step S701: YES), the work machine 110 acquires from a predetermined storage unit the amount of power consumption for work that has already been received from the power consumption prediction server 100 (step S702). Note that if another work machine 110 is used in place of the other work machine 110, in step S702 the amount of power shortage can be acquired instead of the amount of power consumption for work, and the subsequent processing can be performed.

[0064] Next, the work machine 110 executes charging necessity processing (FIG. 8) to determine whether charging is necessary (step S703). Then, the work machine 110 determines whether charging is necessary based on the results of the charging necessity processing (step S704). If charging is not necessary (step S704: NO), the work machine 110 ends the series of processes.

[0065] On the other hand, if the result of the charging necessity processing is that charging is necessary (step S704: YES), the work machine 110 executes predicted charging time calculation processing (FIG. 9) (step S705). In the predicted charging time calculation processing, the charging start time is calculated.

[0066] The work machine 110 then determines whether the current time has reached the charging start time (step S706). The work machine 110 waits until the current time reaches the charging start time (step S706: NO), and when the current time reaches the charging start time (step S706: YES), it outputs a command to start charging to the charger 111 that is already connected to the battery 203, thereby carrying out charging (step S707). Note that when charging starts, the work machine 110 may be configured to issue a notification to that effect, such as "Charging is starting," on the on-board monitor 202 or the like.

[0067] The work machine 110 then determines whether the remaining amount of stored power in the battery 203 is equal to or greater than the amount of power consumed for work (step S708). The work machine 110 returns to step S707 and continues charging until the remaining amount of stored power is equal to or greater than the amount of power consumed for work (step S708: NO). On the other hand, if the remaining amount of stored power is equal to or greater than the amount of power consumed for work (step S708: YES), the work machine 110 outputs a command to the charger 111 to end charging, thereby ending the series of processes. Note that when charging is complete, the work machine 110 may issue a notification to that effect on the on-board monitor 202, etc., such as "Charging is ending."

[0068] In step S708, charging may be terminated under conditions other than the condition that the remaining amount of stored power is equal to or greater than the amount of power consumed during work. For example, charging may be terminated when the work start time arrives. Specifically, there may be cases where the work start time is early and the charging time cannot be secured. More specifically, for example, if the charging start time is 9:00 AM, the predicted charging time is 3 hours, and the work start time is 11:00 AM, the work start time will arrive two hours after the start of charging, and it may not be possible to secure the three hours of charging time. For this reason, the work machine 110 terminates charging when the work start time arrives.

[0069] In addition, if the amount of power consumed during work is greater than the battery capacity, the work machine 110 will be unable to charge any more once the battery capacity is reached. In this case as well, the work machine 110 will end charging.

[0070] At the start and end of charging, the work machine 110 transmits information indicating this (a charging start notification and a charging completion notification) to the power consumption prediction server 100. This allows the power consumption prediction server 100 to manage whether or not each work machine 110 is currently charging. The charging start notification and charging completion notification do not necessarily have to be transmitted from the work machine 110 to the power consumption prediction server 100. These notifications may also be transmitted from the charger 111 to the power consumption prediction server 100, for example.

[0071] <<Charging Necessity Processing Performed by Work Machine 110>> Figure 8 is a flowchart showing the charging necessity processing performed by the work machine 110. In Figure 8, the work machine 110 acquires the remaining amount of stored power in the battery 203 (step S801). The work machine 110 then determines whether the remaining amount of stored power is equal to or greater than the amount of power consumed for work (step S802). If the remaining amount of stored power is equal to or greater than the amount of power consumed for work (step S802: YES), the work machine 110 determines that charging is not necessary (step S803) and ends the series of processes. On the other hand, if the remaining amount of stored power is not equal to or greater than the amount of power consumed for work (step S802: NO), the work machine 110 determines that charging is necessary (step S804) and ends the series of processes.

[0072] <<Predicted Charging Time Calculation Process Performed by Work Machine 110>> Figure 9 is a flowchart showing the predicted charge time calculation process performed by the work machine 110. In Figure 9, the work machine 110 calculates the amount of charge to be charged to the battery 203 by subtracting the remaining amount of electricity stored in the battery 203 from the amount of power consumed during work (step S901). Then, the work machine 110 acquires the charging capacity (step S902).

[0073] Next, the work machine 110 calculates the predicted charging time by dividing the charging amount (kWh) calculated in step S901 by the charging capacity (kW) acquired in step S902 (step S903).The work machine 110 then calculates the charging start time by subtracting the predicted charging time calculated in step S903 from the work start time (step S904), and ends the series of processes.

[0074] Actions and Effects As described above, according to this embodiment, the power consumption prediction server 100 predicts and outputs the amount of work power consumption to be consumed by the battery 203 in a work plan based on the work content to be performed by the work machine 110 and the work time for that work content. Therefore, the amount of power required to be consumed by the battery 203 in the work plan can be charged at the optimal timing for the work plan. Therefore, deterioration of the battery 203 can be suppressed.

[0075] In this embodiment, the power consumption prediction server 100 extracts the unit power consumption corresponding to the work content indicated in the work plan from the power consumption list DB 102, and predicts the amount of work power consumption based on the extracted unit power consumption and the work time obtained from the work plan. This makes it possible to obtain an appropriate amount of work power consumption corresponding to the work content.

[0076] Furthermore, in this embodiment, the power consumption prediction server 100 outputs a warning when the remaining power stored in the battery 203 is insufficient for the amount of power consumed during the work. This allows the work staff to know in advance that the remaining power stored in the battery 203 will be insufficient. This allows them to take action in response to the warning, thereby preventing work from being delayed.

[0077] Furthermore, in this embodiment, when the remaining power stored in the battery 203 is insufficient for the amount of power consumed during work, the power consumption prediction server 100 outputs information indicating an alternative work machine 110 that will perform the work that is insufficient, based on the work plan of the other work machine. This allows the work staff to know in advance that an alternative work machine 110 is available if the remaining power stored in the battery 203 becomes insufficient. Therefore, even if the remaining power stored in the battery 203 becomes insufficient, the work can be continued using the alternative work machine 110.

[0078] Furthermore, in this embodiment, the work machine 110 calculates the predicted charging time required to charge the battery 203 based on the amount of power consumed during work acquired from the power consumption prediction server 100, the remaining power storage capacity of the battery 203, and the charging capacity of the battery 203, and issues instructions based on this predicted charging time. This makes it possible to charge the amount of power required to be consumed by the battery 203 in the work plan at the optimal timing for the work plan. Therefore, deterioration of the battery 203 can be suppressed.

[0079] Furthermore, in this embodiment, the work machine 110 outputs a command to start charging the battery 203 when the charging start time arrives, which is based on the work start time and the calculated predicted charging time. This allows the battery 203 to be used immediately after charging is complete. Therefore, deterioration of the battery 203 can be prevented more efficiently.

[0080] <Modifications of the embodiment> Modifications of the embodiment will be described below. Note that in the following modifications, the contents described in the above embodiment will be omitted as appropriate.

[0081] Variation 1 First, Modification 1 will be described. In the above-described embodiment, an example has been described in which unit power consumption (FIG. 4B) is stored for each type of work. However, even for the same type of work, conditions (for example, soil conditions) may differ from site to site, and as a result, the amount of power consumption of the work machine 110 may differ. In Modification 1, an example will be described in which unit power consumption is stored for each type of load on the site to take such differences into consideration.

[0082] The power consumption list DB 102 according to the first modification includes a "site load" item, which is a subdivision of the "work content" item. The "site load" item stores "large," "medium," and "small" according to the magnitude of the load, and further stores a corresponding unit power consumption. This makes it possible to predict the amount of work power consumption according to the situation (soil condition), even when the same work is performed and the soil conditions vary from site to site, resulting in different unit power consumption.

[0083] It is also possible to feed back the results of work on site and re-predict the predicted power consumption. For example, the work machine 110 transmits the site load (heavy load, medium load, light load) to the power consumption prediction server 100 as the results of work on site. When the power consumption prediction server 100 receives the site load from the work machine, it stores it in the power consumption list 411. Furthermore, the power consumption prediction server 100 re-predicts the predicted power consumption based on the unit power consumption corresponding to the received site load. In this way, it is also possible to feed back the results of work on site and re-predict the predicted power consumption.

[0084] Variation 2 Next, a description will be given of Modification 2. In the above-described embodiment, an example was described in which the work machine 110 is not equipped with a generator. In Modification 2, an example will be described in which the work machine 110 is equipped with a generator (a so-called hybrid example).

[0085] In Modification 2, the generator provided on the work machine 110 is driven by the on-board engine, so that the battery 203 can be charged even during work. Therefore, in Modification 2, work can be carried out taking into consideration the amount of charge provided by the generator. From the perspective of charging efficiency, it is effective to operate the generator with the engine at a predetermined rotation speed.

[0086] For example, if the charging capacity of the generator is 10 kW and the unit power consumption for the work is 30 kW, the actual unit power consumption will be 20 kW (30 kW - 10 kW). Therefore, if the remaining charge (original charge amount) of the battery 203 is 100 kWh, it will be possible to perform work for 5 hours (100 kWh ÷ 20 kW = 5 hours) by operating the engine at a predetermined rotation speed.

[0087] If a generator is provided, the battery 203 may be charged when the remaining amount of stored power in the battery 203 falls below a predetermined value. Charging may be performed, for example, when the workload is light (below the predetermined value). For example, if the charging capacity of the generator is 10 kW and the unit power consumption in the work is 6 kW, then 4 kW (10 kW - 6 kW) of power can be stored.

[0088] Variation 3 Next, Modification 3 will be described. In Modification 3, an example of monitoring power consumption in real time will be described. In Modification 3, the power consumption prediction server 100 acquires power consumption in real time from each work machine 110. The power consumption prediction server 100 monitors the gradient of power consumption (amount of use per hour) for each work machine 110.

[0089] For example, if the workload is greater than the initial work plan, the actual power consumption may be greater than the predicted work power, resulting in a power shortage. In such a case, the power consumption prediction server 100 may warn that a power shortage will occur if the work continues as is. Furthermore, if there is an alternative work machine 110, the power consumption prediction server 100 may notify that fact.

[0090] According to the third modification, if it is determined that the amount of power used is greater than the initial work plan, a warning can be issued in real time, allowing the work staff to take action in response to the warning, thereby preventing work from being delayed.

[0091] Variation 4-1 Next, Modification 4-1 will be described. In Modification 4-1, an example will be described in which the functional units of the power consumption prediction server 100 are provided in the work machine 110. In Modification 4-1, the work machine 110 may be provided with the functional units of the plan acquisition unit 501, unit power consumption extraction unit 502, power consumption prediction unit 503, receiving / transmitting unit 504, remaining power storage amount acquisition unit 505, and work machine identification unit 506 shown in FIG. 5A.

[0092] In this way, the work power consumption amount to be consumed by the battery 203 in a work plan can be predicted using only the work machine 110, based on a work plan that includes the work content and the time when the work content will be performed.

[0093] Variation 4-2 Next, Modification 4-2 will be described. In Modification 4-2, an example will be described in which the functional units of the work machine 110 are provided in the power consumption prediction server 100. In Modification 4-2, the power consumption prediction server 100 may include the functional units of a power consumption amount acquisition unit 521, a stored power content acquisition unit 522, a predicted charging time calculation unit 523, an instruction unit 525, and a time acquisition unit 524 shown in Fig. 5A.

[0094] In this way, the power consumption prediction server 100 alone can predict the amount of work power consumed by the battery 203 in a work plan based on the work plan including the work content and the time when the work content will be performed.

[0095] Variation 5 Next, a description will be given of Modification 5. In the above-described embodiment, an example has been described in which the amount of power consumed during work is predicted based on the power consumption list 411 stored in the power consumption list DB 102 (FIG. 4B). In Modification 5, an example will be described in which the amount of power consumed during work is predicted using a trained model.

[0096] In the fifth modification, the trained model is trained using input samples and output samples. The input samples include, for example, the work content performed by the work machine 110 and the work time for performing the work content. The output samples include, for example, the amount of work power consumed by the battery 203. The trained model is, for example, a model expressed using a neural network. However, the trained model may also be, for example, a DNN (Deep Neural Network). The trained parameters include, for example, the number of layers of the neural network, the number of neurons in each layer, the connection relationships between the neurons, the connection weights (connection loads) between each neuron, and the thresholds of each neuron. The trained model includes an input layer, one or more intermediate layers (hidden layers), and an output layer. Each layer has one or more neurons. The number of intermediate layers, the number of neurons in each layer, etc. are set by the trained parameters.

[0097] The input layer receives input of the work content of the work machine 110 and the work time during which that work content is performed. The output layer outputs the probability that the work energy consumption amount (work energy consumption amount 1, work energy consumption amount 2, ..., work energy consumption amount m) will be selected. The trained model is a learning model that has been trained and generated so that when the work content and the work time during which that work content is performed are input to the input layer, the work energy consumption amount output from the output layer matches as closely as possible with the actual selection record (the selection result of the work energy consumption amount).

[0098] About generating trained models Next, generation of a trained model performed by the power consumption prediction server 100 will be described. The power consumption prediction server 100 includes a dataset acquisition unit, a model generation unit, and a model generation storage unit. Each unit is realized by the processor 301. That is, the processor 301 executes a model generation program included in a predetermined program to realize the function of each unit. The model generation storage unit is realized by the storage 303.

[0099] The dataset acquisition unit acquires a training dataset. The dataset acquisition unit may acquire the training dataset from an external device using a storage medium (such as a USB memory stick), or may acquire the training dataset from an external device via communication.

[0100] The training data set includes training samples 1 to N. Each of the training samples 1 to N includes an input sample and an output sample. The input samples are data input to the input layer when training the training model. Specifically, the input samples are upper limit powers, and are data input to the input layer when training the training model.

[0101] The output sample is data (also referred to as teacher data or correct label) that serves as the correct answer for comparison with the output value from the output layer when training the learning model. The output sample is performance information (actual work power consumption) selected according to the work content of the work machine 110 and the work time for that work content, and is teacher data (correct label) that serves as the correct answer for comparison with the output value from the output layer when training the learning model.

[0102] The data set acquisition unit may acquire the learning samples 1 to N collectively or individually. The model generation storage unit stores the learning model and parameters.

[0103] The model generation unit trains the learning model using the learning dataset acquired by the dataset acquisition unit to generate a trained model. The model generation unit stores the generated trained model in the model storage unit.

[0104] Specifically, the model generation unit inputs each input sample to the input layer, and updates the parameters of the learning model so as to reduce the difference between each output value obtained from the output layer and each output sample, thereby generating a trained model. As an example, the model generation unit may generate the trained model using backpropagation, as shown in the following (1) to (5).

[0105] (1) The model generation unit inputs the input samples of the learning dataset into the input layer and performs calculations in the forward propagation direction of the learning model to obtain output values ​​from the output layer. The output values ​​from the output layer represent the probability (likelihood) of each operating parameter being selected. (2) The model generation unit calculates the error between the output value from the output layer and the output sample for all input samples, for example, by using the backpropagation method. The output sample is performance information (actually selected work power consumption). For example, when the output sample of learning sample 1 indicates an operating parameter m, if the input sample of learning sample 1 is input to the input layer and the output value obtained from the output layer is operating parameter m, the error for learning sample 1 is zero. (3) The model generation unit determines whether the calculated error is within a predetermined value. (4) If the calculated error is within a predetermined value, the model generation unit determines that various parameters such as the connection weights between neurons (such as the connection weights between neurons and the thresholds of each neuron) have been optimized, terminates learning (training), and completes the generation of a trained model. The trained model is defined as a trained model in which the various parameters are trained parameters. (5) If the calculated error is not within a predetermined value, the model generation unit updates various parameters based on the calculated errors. Thereafter, the model generation unit inputs the input sample to the input layer again for the learning model whose various parameters have been updated, and repeatedly updates various parameters until the error is within a predetermined value.

[0106] According to the fifth modification, the power consumption prediction server 100 can use the trained model to predict and output the amount of work power consumption to be consumed by the battery 203 in a work plan based on the work content to be performed by the work machine 110 and the work time for the work content to be performed. Even in this way, the power required to be consumed by the battery 203 in the work plan can be charged at the optimal timing for the work plan. Therefore, deterioration of the battery 203 can be suppressed.

[0107] Other Embodiments Although one embodiment has been described in detail above with reference to the drawings, the specific configuration is not limited to that described above, and various design modifications and the like are possible.

[0108] In the power consumption prediction server 100 and work machine 110 according to the above-described embodiment, the programs are stored in the storage 303, but this is not limiting. For example, the programs may be distributed to the power consumption prediction server 100 and work machine 110 via a communication line. In this case, the power consumption prediction server 100 and work machine 110 that receive the programs each load the programs into the main memory 302 and execute the above-described processing.

[0109] Furthermore, each of the programs may be for realizing part of the above-described functions. For example, each of the programs may be for realizing the above-described functions in combination with other programs stored in the storage 303 or in combination with other programs installed in other devices.

[0110] Furthermore, the power consumption prediction server 100 and the work machine 110 may each be equipped with a programmable logic device (PLD) in addition to or instead of the above configuration. Examples of PLDs include programmable array logic (PAL), generic array logic (GAL), complex programmable logic device (CPLD), and field programmable gate array (FPGA). In this case, some of the functions realized by the processor 301 may be realized by the PLD.

[0111] Furthermore, the power consumption prediction server 100 and the work machine 110 may each be equipped with a plurality of processors 301, or may be configured from a plurality of computers. [Explanation of symbols]

[0112] 1...power consumption prediction system, 100...power consumption prediction server, 101...work plan DB, 102...power consumption list DB, 110...multiple work machines, 111...charger, 120...administrator terminal, 201...vehicle ECU, 202...on-board monitor, 203...battery, 501...plan acquisition unit, 502...unit power consumption extraction unit, 503...power consumption prediction unit, 504...transmission / reception unit, 505...remaining power storage amount acquisition unit, 506...work machine identification unit, 521...power consumption amount acquisition unit, 522...storage content acquisition unit, 523...predicted charging time calculation unit, 524...time acquisition unit, 525...instruction unit

Claims

1. a plan acquisition unit that acquires a work plan including work content to be performed by a work machine equipped with a storage battery and work time for the work content to be performed; a power consumption prediction unit that predicts, based on the work plan acquired by the plan acquisition unit, an amount of work power consumption to be consumed by the storage battery in the work plan; an output unit that outputs the work-related power consumption predicted by the power consumption prediction unit; A power consumption prediction device comprising:

2. a unit power consumption extraction unit that extracts unit power consumption corresponding to the work content indicated in the work plan from a unit power consumption storage unit that stores unit power consumption per unit period for each work content; the power consumption prediction unit predicts the work power consumption based on the unit power consumption extracted by the unit power consumption extraction unit and the work time obtained from the work plan. The power consumption prediction device according to claim 1 .

3. a remaining charge acquisition unit that acquires a remaining charge of the storage battery; the output unit outputs warning information indicating a warning when the remaining amount of stored power is insufficient for the amount of power consumed during the work. The power consumption prediction device according to claim 1 or 2.

4. a remaining charge acquisition unit that acquires a remaining charge of the storage battery; a work machine identifying unit that, when the remaining amount of stored power is insufficient for the amount of power consumed by work, identifies another work machine that will perform the work that is insufficient based on the work plans of the other work machines; Equipped with the output unit outputs information indicating the other work machine identified by the work machine identification unit. The power consumption prediction device according to claim 1 or 2.

5. A work machine connected to the power consumption prediction device according to claim 1 or 2 and equipped with the storage battery, a power consumption amount acquiring unit that acquires the work power consumption amount output by the output unit; a storage content acquiring unit that acquires a remaining amount of stored power of the storage battery and a charging capacity of the storage battery or a charger connected to the storage battery; a predicted charging time calculation unit that calculates a predicted charging time required to charge the storage battery based on the work-powered energy amount acquired by the power consumption amount acquisition unit, and the remaining amount of stored energy and the charging capacity acquired by the stored energy content acquisition unit; an instruction unit that issues an instruction based on the predicted charging time calculated by the predicted charging time calculation unit; A work machine comprising:

6. a time acquisition unit that acquires a work start time included in the work time; the instruction unit outputs an instruction to start charging of the storage battery when a charging start time based on the work start time acquired by the time acquisition unit and the predicted charging time calculated by the predicted charging time calculation unit arrives. The work machine according to claim 5 , comprising:

7. 3. A power consumption prediction system including the power consumption prediction device according to claim 1 or 2 and a work machine equipped with the storage battery, The work machine includes: a power consumption amount acquiring unit that acquires the work power consumption amount output by the output unit; a storage content acquiring unit that acquires a remaining amount of stored power of the storage battery and a charging capacity of the storage battery or a charger connected to the storage battery; a predicted charging time calculation unit that calculates a predicted charging time required to charge the storage battery based on the work-powered energy amount acquired by the power consumption amount acquisition unit, and the remaining amount of stored energy and the charging capacity acquired by the stored energy content acquisition unit; an instruction unit that issues an instruction based on the predicted charging time calculated by the predicted charging time calculation unit; A power consumption prediction system comprising:

8. The power consumption prediction device a plan acquisition step of acquiring a work plan including work content to be performed by a work machine equipped with a storage battery and work time for the work content to be performed; a power consumption prediction step of predicting an amount of work power consumption to be consumed by the storage battery in the work plan based on the work plan acquired in the plan acquisition step; an output step of outputting the work power consumption amount predicted in the power consumption prediction step; The power consumption prediction method includes the steps of:

9. The computer of the power consumption prediction device a plan acquisition unit that acquires a work plan including work content to be performed by a work machine equipped with a storage battery and work time for the work content to be performed; a power consumption prediction unit that predicts, based on the work plan acquired by the plan acquisition unit, an amount of work power consumption to be consumed by the storage battery in the work plan; an output unit that outputs the work-related power consumption predicted by the power consumption prediction unit; A program that functions as a

Images