Prediction system

Abstract

To provide a prediction system capable of increasing the prediction accuracy of a change amount in SOH.SOLUTION: The prediction system predicts the degradation state of a battery supplying electric power to an electric motor when a first vehicle driven by an internal combustion engine is replaced by a second vehicle driven by the electric motor and is provided with an acquisition unit for acquiring first data related to the use of the first vehicle, a generation unit for generating second data based on the first data in which second data related to a charge-discharge frequency of a battery of the second vehicle when the use of the second vehicle is the same as that of the first vehicle, and a prediction unit for predicting a degradation state of the battery based on the second data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a forecasting system. [Background technology]

[0002] There is an increasing demand to replace vehicles powered by internal combustion engines such as diesel engines with electric vehicles. The lease price and period for electric vehicles are determined based on the battery's state of health (SOH) from the start to the end of the lease. This requires precise prediction of the SOH, and currently, electricity consumption is estimated using information gathered from customers, and the SOH is predicted based on the estimated electricity consumption.

[0003] For example, Patent Document 1 describes a method of performing current control to flow current through a battery, obtaining at least the voltage value of the battery when current flows through the battery as measurement information, and estimating the SOH of the battery based on a model for estimating the deterioration state of the battery and the obtained measurement information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2013 / 145734 Summary of the Invention [Problem to be solved by the invention]

[0005] However, when estimating electricity consumption using hearing information, there is a possibility that errors or variations may occur in the estimated electricity consumption. Since the change in SOH is predicted based on such electricity consumption, there is a risk that the prediction accuracy of the change in SOH may decrease.

[0006] An object of the present disclosure is to provide a prediction system capable of improving the prediction accuracy of the amount of change in SOH. [Means for solving the problem]

[0007] In order to achieve the above object, the prediction system in the present disclosure comprises: A prediction system for predicting a deterioration state of a battery that supplies power to an electric motor when a first vehicle driven by an internal combustion engine is replaced with a second vehicle driven by an electric motor, comprising: An acquisition unit that acquires first data regarding how the first vehicle is used; a generation unit that generates second data related to a frequency of charging and discharging the battery of the second vehicle when the second vehicle is used in the same manner as the first vehicle, based on the first data; a prediction unit that predicts a deterioration state of the battery based on the second data; Equipped with. Effect of the Invention

[0008] According to the present disclosure, it is possible to improve the accuracy of predicting the amount of change in SOH. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram illustrating a functional configuration of a prediction system according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a diagram showing tools of the prediction system according to the present embodiment. [Diagram 3] FIG. 3 is a diagram showing second data relating to the frequency of charging and discharging the battery. [Figure 4] FIG. 4 is a diagram showing a degradation coefficient map in this embodiment. [Diagram 5] FIG. 5 is a diagram showing a map for linear interpolation for linearly interpolating the battery temperature and the SOC from key-off to key-on. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. FIG. 1 is a block diagram showing a schematic functional configuration of a prediction system according to an embodiment of the present disclosure. As shown in FIG. 1, a prediction system 100 according to the present embodiment has a server 1a. In FIG. 1, arrows indicate main data flows. Note that there may be data flows different from the data flows shown in FIG. 1. In FIG. 1, each functional block shows a functional configuration, not a hardware (device) configuration. Therefore, the functional blocks shown in FIG. 1 may be implemented in a single device, or may be implemented separately in multiple devices. Data exchange between the functional blocks may be performed via any means, such as a data bus or a communication network. Note that in the following description, a vehicle driven by an internal combustion engine is referred to as a "first vehicle," and a vehicle driven by an electric motor is referred to as a "second vehicle." In this embodiment, the first vehicle is described as a diesel vehicle (DIE vehicle), and the second vehicle is described as an EV (Electric Vehicle). Note that the second vehicle is equipped with a battery that supplies power to the electric motor. The first vehicle has one or more sensors (not shown) and one or more measuring instruments (not shown). The sensors and measuring instruments possessed by the first vehicle are those that have been conventionally installed in the first vehicle. The second vehicle has one or more sensors (not shown) and one or more measuring instruments (not shown). The sensors and measuring instruments possessed by the second vehicle include those that have been conventionally installed in the second vehicle and those that have been newly installed for creating various maps described below. The second vehicle that has sensors and measuring instruments is sometimes called a "monitor vehicle."

[0011] The server 1a has a control device 1. The control device 1 includes a storage unit 2 and a control unit 3. The server 1a also has a communication unit 4. The communication unit 4 transmits and receives data to and from the first vehicle. Detection data indicating the detection results detected by the sensor and measurement data indicating the measurement results measured by the measuring instrument are transmitted from the first vehicle to the communication unit 4 at predetermined time intervals. In the following description, the detection data and measurement data transmitted from the first vehicle are referred to as "management data of the first vehicle" or simply as "management data." In other words, the server 1a can be said to be a traffic management system that acquires and stores management data related to the operation of the first vehicle, which will be described later, from the first vehicle to manage the vehicle state and operation state of the first vehicle.

[0012] The management data (first data) includes data indicating the power consumption of the body mounted on the first vehicle, the power consumption of the heating device (heater for heating the cab), and the power consumption of the cooling device (electric compressor for cooling the cab).

[0013] The communication unit 4 transmits and receives data to and from the monitor vehicle. Detection data indicating the detection results detected by the sensors and measurement data indicating the measurement results measured by the measuring instruments are transmitted from the monitor vehicle to the communication unit 4 at predetermined time intervals. In the following description, the detection data and measurement data transmitted from the monitor vehicle are referred to as "performance data of the monitor vehicle" or simply "performance data." It is also possible to accumulate performance data using a mass-produced vehicle of the second vehicle, create a deterioration coefficient map based on the accumulated performance data, and predict the amount of change in SOH by referring to the created deterioration coefficient map. In this case, the mass-produced vehicle of the second vehicle functions as a monitor vehicle.

[0014] The performance data also includes data showing the power consumption of the body mounted on the second vehicle, the power consumption of the heating device (heater for heating the cab), the power consumption of the cooling device (electric compressor for cooling the cab), and the power consumption of a high-voltage heater for keeping the battery warm. Note that the body mounted on the second vehicle, the heating device, and the cooling device are each assumed to be the same as the body mounted on the first vehicle, the heating device, and the cooling device, respectively.

[0015] FIG. 2 is a diagram showing a tool of the prediction system in this embodiment. The prediction system 100 in this embodiment predicts the change in the SOH of the battery of a second vehicle (EV) when a first vehicle (DIE vehicle) is replaced with the second vehicle and the second vehicle is used in the same manner as the first vehicle. In theory, the work done by an internal combustion engine is the same even when replaced by an electric motor. Based on the above theory, the charge and discharge amount of the battery is estimated based on information on the amount of work done by the internal combustion engine.

[0016] However, the information on the workload of the internal combustion engine lacks information on the power used by the air conditioner, the power used by the body compressor, and the exhaust gas purification system. The missing information can be interpolated from management data and performance data.

[0017] In addition, in the process of transitioning from a state in which the rotation of the electric motor is maintained to a state in which the motor is decelerating, the electric motor becomes a generator and generates electric power (regenerative electric power). The regenerative electric power generated by regeneration acts as a brake on the generator. The generated regenerative electric power needs to be subtracted from the battery discharge electric power amount. The calculation of the regenerative electric power will be described later. In addition, heat generated from the internal combustion engine is used for heating the cab of the first vehicle, but heat generated from the internal combustion engine cannot be used for heating the cab of the second vehicle, and electric power supplied from the battery is used. The electric power used for heating the cab needs to be added as the battery discharge electric power amount. In addition, electric power supplied from the battery is used for cooling the electric motor mounted on the second vehicle. In addition, electric power supplied from the battery is also used for keeping the battery warm and cooling. The electric power used for cooling the electric motor, keeping the battery warm, and cooling the battery needs to be added as the battery discharge electric power amount.

[0018] As shown in FIG. 1, the amount of work done by the internal combustion engine can be obtained based on the engine speed and torque of the first vehicle.

[0019] The battery discharge power amount is calculated by subtracting regenerative power from the work of the internal combustion engine, and then adding the power used for the body compressor, the power used for the air conditioner, the power used for heating the cab, the power used to keep the battery warm and cool, and the power used to cool the electric motor, and further adding the power loss in the electric motor and the power loss in the battery. Each of the regenerative power and the power used for the body compressor can be calculated by a predetermined calculation formula based on the management data stored in the memory unit 2 and by referring to various maps stored in the memory unit 2.

[0020] (Storage unit 2) The memory unit 2 is a storage device such as a ROM (Read Only Memory) that stores the BIOS (Basic Input Output System) of the computer that realizes the control device 1, a RAM (Random Access Memory) that serves as the working area of ​​the control device 1, an HDD (Hard Disk Drive) or an SSD (Solid State Drive) that stores the OS (Operating System), application programs, various information referenced when the application programs are executed, and various maps.

[0021] (Control Unit 3) The control unit 3 is a processor such as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit) of the control device 1, and functions as an acquisition unit 30, an estimation unit 31, a generation unit 32, and a prediction unit 33 by executing programs stored in the memory unit 2.

[0022] 1 shows an example in which the control device 1 is configured as a single device. However, the control device 1 may be realized by, for example, multiple processors, memories, and other computational resources. In this case, each unit constituting the control unit 3 is realized by at least one of multiple different processors executing a program.

[0023] (Acquisition part 30) The acquisition unit 30 acquires the management data from the communication unit 4. The control unit 3 stores the management data acquired by the acquisition unit 30 (data indicating the engine speed, torque, running speed, atmospheric temperature, and operating time of the air conditioner of the first vehicle) as first data in the storage unit 2. Note that if the first data has already been stored in the storage unit 2 and is data that can be used to estimate the amount of change in the SOH of the battery, it is possible to omit acquiring the management data from the first vehicle.

[0024] (Regenerative power calculation method) Next, a specific example of a method for calculating regenerative power (kW) will be described. The estimation unit 31 calculates the regenerative energy (J) based on the traveling speed of the first vehicle (information related to braking of the first vehicle) as frequency data, and estimates the regenerative power (W=J / s) based on the regenerative energy. The regenerative energy (J) is calculated using the following formula (1). Regenerative energy = (1 / 2)*M*(v1-v2) 2 …(1) Here, M is the mass of the second vehicle, v1 is the velocity before deceleration, and v2 is the velocity after deceleration.

[0025] (Generation unit 32) The generating unit 32 calculates the work amount (kW) of the internal combustion engine by the following formula (2). Work load = 2π x torque x engine speed / 60 / 1000…(2)

[0026] (How to calculate power consumption for bodywork) Next, an example of a method for calculating the power used by the compressor for the body will be described. Here, the body is, for example, a loading platform equipped with a cooling device. The estimation unit 31 multiplies the map value of the power consumption map of the body created from the performance data of the monitor vehicle by the map value of the body on-time ratio map created from the performance data of the monitor vehicle, and further multiplies the multiplied map value by the atmospheric temperature frequency data of the first vehicle to calculate the power used by the compressor for the body. Note that the power consumption map of the body and the body on-time ratio map are provided for each type of body.

[0027] (Calculation method for power consumption for cab heating) Next, an example of a method for calculating the power used for heating the cab will be described. A heater is used for heating the cab. The estimation unit 31 multiplies a map value of a heater power consumption map created from the performance data of the monitor vehicle by a map value of a heater on time ratio map created from the performance data of the monitor vehicle, and further multiplies the multiplied map value by the atmospheric temperature frequency data of the first vehicle to calculate the power (kW) used for the heater.

[0028] (How to calculate power consumption for air conditioners) Next, an example of a method for calculating the power used by the air conditioner will be described. The estimation unit 31 calculates the power (kW) used by the air conditioner by multiplying the map value of the air conditioner power consumption map created from the performance data of the monitor vehicle by the air conditioner operation time frequency data for each atmospheric temperature.

[0029] (Calculation method for power consumption for keeping the battery warm) Next, an example of a method for calculating the power used to keep the battery warm will be described. The estimation unit 31 calculates the power consumption for keeping the battery warm (high voltage heater) by multiplying the map value of the power consumption map of the high voltage heater by the atmospheric temperature frequency data of the first vehicle.

[0030] (Calculation method for power consumption for battery cooling) Next, an example of a method for calculating the electric power used for cooling the battery will be described. The estimation unit 31 multiplies the map value of the electric power consumption map of the electric compressor by the atmospheric temperature frequency data of the first vehicle, and multiplies the multiplied value by a correction coefficient (a correction coefficient that is preset based on the average vehicle speed, vehicle type, delivery mode, etc.) to calculate the electric power used for cooling the battery.

[0031] (Calculation method of loss) Next, a method for calculating the loss will be described. When comparing the efficiency at the start of the first vehicle and the monitor vehicle, the monitor vehicle is more efficient than the first vehicle. The workload is corrected based on the difference in efficiency between the first vehicle and the monitor vehicle, and the battery discharge power amount is corrected using the corrected workload (corrected workload).

[0032] (Second data) The generating unit 32 corrects the workload of the internal combustion engine based on the regenerative power, the power consumption for the body, the power consumption for the cab heating, the power consumption for the air conditioner, the power consumption for keeping the battery warm, and the loss, and generates the second data during the discharge of the battery and the second data during the charge of the battery based on the corrected workload. The second data during the discharge of the battery is obtained by recording one count per second in a corresponding area on three axes of the remaining capacity (State Of Charge: SOC) [%] of the battery during discharge, the battery temperature [°C], and the power [kW]. The second data during the discharge of the battery is obtained by recording one count per second in a corresponding area on three axes of the SOC [%], the battery temperature [°C], and the power [kW] during charging (including regeneration).

[0033] The generation unit 32 calculates the regenerative energy (J) based on the frequency of the vehicle speed of the first vehicle (information regarding the braking of the first vehicle), calculates the regenerative power [W] based on the regenerative energy (W = J / s), and records one count per second in the corresponding area based on the calculated regenerative power.

[0034] Next, the second data regarding the frequency of charging and discharging the battery will be described with reference to FIG. 3. The second data during battery discharge and the second data during battery charging are the same in that the counts (number of seconds) are recorded on the above three axes. Below, the second data during battery discharge is shown in FIG. 3 as a representative. The battery temperature shown in FIG. 3 is divided into 21 sections every 5°C in a temperature range from less than -35°C to 60°C or more. The SOC shown in FIG. 3 is divided into 22 sections every 5% in a SOC range from less than 0% to 100% or more. The power shown in FIG. 3 is divided into 103 sections every 2kW in a power range from 0kW to 206kW. The number of sections into which the temperature range, SOC range, and power range shown in FIG. 3 are divided is an example, and the present disclosure is not limited to each number.

[0035] (Degradation factor map) Next, the deterioration coefficient map will be described. The deterioration coefficient map has a deterioration coefficient map during discharge associated with the second data during battery discharge, and a deterioration coefficient map during charging associated with the second data during battery charging. The deterioration coefficient map during discharge and the deterioration coefficient map during charging are each stored in the storage unit 2. The deterioration coefficient map during discharge is a map in which coefficients are recorded in corresponding areas on three axes of SOC [%], battery temperature [°C], and power [kW] during discharge. The deterioration coefficient map during charging is a map in which coefficients are recorded in corresponding areas on three axes of SOC [%], battery temperature [°C], and power [kW] during charging.

[0036] Next, the deterioration coefficient map will be described with reference to FIG. 4. The deterioration coefficient map during discharge and the deterioration coefficient map during charging are the same in that the coefficients are recorded on the above three axes. Below, the deterioration coefficient map during discharge is shown in FIG. 4 as a representative. The battery temperature shown in FIG. 4 is divided into 21 sections every 5°C in a temperature range from less than -35°C to 60°C or more. The SOC shown in FIG. 4 is divided into 22 sections every 5% in a SOC range from less than 0% to 100% or more. The power shown in FIG. 4 is divided into 103 sections every 2kW in a power range from 0kW to 206kW. The number of sections into which the temperature range, SOC range, and power range shown in FIG. 4 are divided is an example, and the present disclosure is not limited to the number of each, as is the number of sections into which the temperature range, SOC range, and power range in the second data are divided.

[0037] (Prediction Section 33) The prediction unit 33 predicts the amount of change in SOH (=ΔSOH) based on the second data and the degradation coefficient map. The period for predicting the amount of change in SOH is a predetermined period. The second data when predicting the amount of change in SOH is frequency data accumulated during a predetermined period. The amount of change in SOH is predicted for each of the 21 battery temperatures during discharging, and for each of the 21 battery temperatures during charging.

[0038] Specifically, the prediction unit 33 multiplies the count (number of seconds) recorded in each area in the second data for each battery temperature category during discharge by the coefficient recorded in each area in the deterioration coefficient map for each battery temperature category during discharge, which corresponds to each area in the second data. Furthermore, the prediction unit 33 tallies up the multiplied values. The tallied values ​​represent the amount of change in SOH for each battery temperature category during discharge. Furthermore, the prediction unit 33 sums up the amounts of change in SOH for each battery temperature category during discharge. The summed values ​​represent the amount of change in SOH for each battery temperature category during discharge.

[0039] Similarly, the prediction unit 33 multiplies the count (number of seconds) recorded in each area in the second data for each battery temperature category during charging by the coefficient recorded in each area in the deterioration coefficient map for each battery temperature category during charging, which corresponds to each area in the second data. Furthermore, the prediction unit 33 aggregates the multiplied values. The aggregated numerical value becomes the amount of change in SOH for each battery temperature category during charging. Furthermore, the prediction unit 33 sums up the amount of change in SOH for each battery temperature category during charging. The summed numerical value becomes the amount of change in SOH during charging.

[0040] Furthermore, the prediction unit 33 sums up the amount of change in SOH during discharging and the amount of change in SOH during charging. The sum represents the amount of change in SOH during charging and discharging of the battery in a predetermined period.

[0041] The control device 1 outputs to the display unit 5 (see FIG. 1) the amount of change in SOH that occurs when the battery is charged or discharged during a predetermined period.

[0042] The prediction system 100 in the above embodiment is a prediction system that predicts a deterioration state of a battery when a first vehicle driven by an internal combustion engine is replaced with a second vehicle driven by an electric motor and equipped with a battery that supplies power to the electric motor, and includes an acquisition unit 30 that acquires first data related to the frequency of how the first vehicle is used, a generation unit 32 that generates second data related to the frequency of charging and discharging the battery of the second vehicle when the second vehicle is used in the same manner as the first vehicle, based on the first data, a memory unit 2 that stores a deterioration coefficient map showing the relationship between the second data and the deterioration state of the battery, and a prediction unit 33 that predicts the deterioration state of the battery by referring to the deterioration coefficient map based on the generated second data.

[0043] With the above configuration, the change in SOH is predicted based on second data regarding the frequency of charging and discharging the battery of the second vehicle when the second vehicle is used in the same manner as the first vehicle, which makes it possible to improve the accuracy of predicting the change in SOH compared to a case in which electricity consumption is estimated using hearing information and the change in SOH is predicted based on the estimated electricity consumption.

[0044] In the prediction system 100 according to the above embodiment, the generation unit 32 generates second data indicating the power, remaining capacity, and temperature of the battery during discharging. This makes it possible to accurately predict the amount of change in the SOH of the battery during discharging.

[0045] In the prediction system 100 according to the above embodiment, the generation unit 32 generates second data indicating the power, remaining capacity, and temperature of the battery during charging. This makes it possible to accurately predict the amount of change in the SOH of the battery during charging.

[0046] In addition, in the prediction system 100 in the above embodiment, the frequency data generating unit calculates the workload of the internal combustion engine based on the first data, and generates the second data based on the calculated workload. This allows the workload of the internal combustion engine to be replaced with the second data, making it possible to accurately predict the amount of change in the SOH of the battery according to the workload of the internal combustion engine.

[0047] In addition, in the prediction system 100 in the above embodiment, the first vehicle is equipped with a first mounting that operates with the output of an internal combustion engine, and the second vehicle is equipped with a second mounting that operates with power from a battery, the acquisition unit 30 further acquires information indicating the workload of the internal combustion engine for operating the first mounting, and the generation unit 32 further estimates the power for operating the mounting, which is the power from the battery for operating the second mounting with the same workload as the workload of the internal combustion engine, corrects the workload of the internal combustion engine based on the estimated power for operating the mounting, and generates second data based on the corrected workload. This allows the workload of the first mounting to be replaced with the second data, making it possible to accurately predict the change in the SOH of the battery according to the workload of the first mounting.

[0048] In the prediction system 100 according to the above embodiment, the second data is frequency data for a predetermined lease period, and the first data is frequency data for a period the same length as the lease period. This makes it possible to accurately predict the amount of change in SOH during the lease period.

[0049] In the prediction system 100 according to the above embodiment, the deterioration coefficient map is a map created based on the performance data of the second vehicle. This allows the deterioration coefficient map to reflect the deterioration state of the battery mounted on the second vehicle, making it possible to more accurately predict the amount of change in SOH.

[0050] (Modification) The prediction system 100 in the above embodiment does not predict the amount of change in SOH from key-off (also called power-off or shutdown) of the second vehicle to key-on. However, the battery naturally discharges between key-off and key-on of the second vehicle. Therefore, in order to improve the prediction accuracy of the amount of change in SOH, it is necessary to predict the amount of change in SOH from key-off to key-on of the second vehicle.

[0051] The prediction system 100 in a modified example of this embodiment predicts the amount of change in SOH from key-off to key-on of the second vehicle. In this modified example, the battery temperature and SCO are recorded at key-off, and then the battery temperature and SOC are obtained at the timing when the key is turned on. Next, the battery temperature and SOC from key-off to key-on are linearly interpolated.

[0052] 5 is a diagram showing a map for linear interpolation for linearly interpolating the battery temperature and SOC from key-off to key-on. The generating unit 32 in the modified example has an interpolating unit (not shown) that refers to the map for linear interpolation based on the battery temperature and SOC at key-on and the battery temperature and SOC at key-off to interpolate the battery temperature and SOC of the second vehicle from key-off to key-on. The interpolated data of the battery temperature and SOC become second data. The predicting unit 33 in the modified example predicts the amount of change in SOH based on the data of the battery temperature and SOC from key-off to key-on of the second vehicle (second data) interpolated by the interpolating unit.

[0053] In addition, the above-mentioned embodiments are merely examples of the embodiment of the present disclosure, and the technical scope of the present disclosure should not be interpreted as being limited by them. In other words, the present disclosure can be embodied in various forms without departing from the gist or main features thereof. [Industrial Applicability]

[0054] The present disclosure is preferably used for a management device equipped with a prediction system in which it is required to improve the prediction accuracy of the amount of change in SOH. [Explanation of symbols]

[0055] 1 Control device 1a Server 2 Storage section 3. Control Unit 4. Communications Department 5 Display section 30 Acquisition Department 31 Estimation part 32 Frequency Data Generation Unit 33 Prediction Department 100 Prediction System

Claims

1. A prediction system for predicting a deterioration state of a battery that supplies power to an electric motor when a first vehicle driven by an internal combustion engine is replaced with a second vehicle driven by an electric motor, the prediction system comprising: An acquisition unit that acquires first data regarding a usage of the first vehicle; a generation unit that generates second data related to a frequency of charging and discharging the battery of the second vehicle when the second vehicle is used in the same manner as the first vehicle, based on the first data; a prediction unit that predicts a deterioration state of the battery based on the second data; Equipped with Prediction system.

2. The generating unit generates the second data indicating the power, remaining capacity, and temperature of the battery during discharging. The prediction system of claim 1 .

3. The generating unit generates the second data indicating a power, a remaining capacity, and a temperature of the battery during charging. The prediction system of claim 1 .

4. the generation unit estimates a change in remaining capacity between the first remaining capacity and the second remaining capacity based on a first remaining capacity and a first temperature of the battery when a power source of the second vehicle is turned off, and a second remaining capacity and a second temperature of the battery when a power source of the second vehicle is turned on, and estimates a change in temperature between the first temperature and the second temperature, and generates, as the second data, data indicating the estimated change in remaining capacity and data indicating the estimated change in temperature, respectively; The prediction system of claim 1 .

5. The generation unit calculates a workload of the internal combustion engine based on the first data, and generates the second data based on the calculated workload. The prediction system of claim 1 .

6. The first vehicle is equipped with a first mounting that is operated by output of the internal combustion engine, The second vehicle is equipped with a second mounting that operates using power from the battery, The acquisition unit further acquires information indicating a workload of the internal combustion engine for operating the first mounting, The generation unit further estimates the electric power for operating the mounting, which is the electric power from the battery for operating the second mounting with the same workload as the workload of the internal combustion engine, corrects the workload of the internal combustion engine based on the estimated electric power for operating the mounting, and generates the second data based on the corrected workload. The prediction system of claim 5 .

7. The second data is frequency data for a predetermined lease period, The first data is frequency data for a period of time equal to the lease period. The prediction system of claim 1 .

8. the prediction unit predicts the deterioration state of the battery based on a deterioration coefficient map in which data regarding a frequency of charging and discharging of the battery of the second vehicle and a deterioration state of the battery are previously associated with each other, and on performance data of the second vehicle. A prediction system according to any one of claims 1 to 7.

9. The deterioration coefficient map is a map created based on performance data of the second vehicle. The prediction system of claim 8.

Images