Fuel economy prediction system and fuel economy prediction method

Abstract

To provide a fuel consumption prediction system and a fuel consumption prediction method configured to reduce fuel consumption of vehicles constituting a fleet.SOLUTION: A fuel consumption prediction system predicts fuel consumption of vehicles constituting a fleet. On the basis of actual values of a driver-related explanatory variable and a vehicle-related explanatory variable, the fuel consumption prediction system sets a driver-related coefficient to be applied to the driver-related explanatory variable and a vehicle-related coefficient to be applied to the vehicle-related explanatory variable, and calculates fuel consumption as an objective variable using the driver-related explanatory variable and the vehicle-related explanatory variable. Using the driver-related coefficient and the vehicle-related coefficient, the fuel consumption prediction system re-calculates a predicted value of fuel consumption to be obtained when at least one of an attribute of the driver and an attribute of the vehicle has been changed.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure relates to a fuel efficiency prediction system and a fuel efficiency prediction method for predicting the fuel efficiency of vehicles that make up a fleet. [Background technology]

[0002] 2. Description of the Related Art Conventionally, a demand prediction system for consumables (for example, tires) for a fleet consisting of a plurality of vehicles (for example, buses and trucks) owned by a transportation company or the like is known (Patent Document 1).

[0003] The demand forecasting system described in Patent Document 1 collects the deterioration degree of consumables and predicts the type and quantity of consumables required at a vehicle maintenance factory, which can contribute to reducing fleet maintenance costs. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2016 / 071993 Summary of the Invention [Problem to be solved by the invention]

[0005] In the case of a fleet consisting of multiple vehicles, in order to achieve efficient operation, it is important to reduce not only the maintenance costs as described above, but also fuel consumption.

[0006] The following disclosure has been made in light of the above circumstances, and aims to provide a fuel efficiency prediction system and a fuel efficiency prediction method that can contribute to reducing the fuel efficiency of vehicles that make up a fleet. [Means for solving the problem]

[0007] One aspect of the present disclosure is a fuel efficiency prediction system (fleet management system 10) that predicts fuel efficiency of vehicles that constitute a fleet, and includes a driver-related variable acquisition unit (driver-related variable acquisition unit 110) that acquires a plurality of driver-related explanatory variables related to attributes of a driver who drives the vehicle, a vehicle-related variable acquisition unit (vehicle-related variable acquisition unit 120) that acquires a plurality of vehicle-related explanatory variables related to attributes of the vehicle, a coefficient setting unit (coefficient setting unit 140) that sets a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables, and a response variable calculation unit (response variable calculation unit 150) that calculates the fuel efficiency as a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables, and the response variable calculation unit recalculates a predicted value of the fuel efficiency when at least one of the attributes of the driver and the attributes of the vehicle is changed, using the driver-related coefficients and the vehicle-related coefficients.

[0008] One aspect of the present disclosure is a fuel efficiency prediction method for predicting fuel efficiency of vehicles that constitute a fleet, the method including the steps of: acquiring a plurality of driver-related explanatory variables related to attributes of a driver who drives the vehicle; acquiring a plurality of vehicle-related explanatory variables related to attributes of the vehicle; setting a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables; and calculating the fuel efficiency as a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables, wherein in the step of calculating the response variable, the driver-related coefficients and the vehicle-related coefficients are used to recalculate a predicted value of the fuel efficiency in the case where at least one of the driver's attributes and the vehicle's attributes is changed.

[0009] One aspect of the present disclosure is a tire wear prediction system (fleet management system 10) that predicts wear on tires mounted on vehicles that constitute a fleet, and includes a driver-related variable acquisition unit (driver-related variable acquisition unit 110) that acquires a plurality of driver-related explanatory variables related to the attributes of a driver who drives the vehicle, a vehicle-related variable acquisition unit (vehicle-related variable acquisition unit 120) that acquires a plurality of vehicle-related explanatory variables related to the attributes of the vehicle, a coefficient setting unit (coefficient setting unit 140) that sets a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables, and a response variable calculation unit (response variable calculation unit 150) that calculates the wear as a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables, and the response variable calculation unit recalculates the predicted value of the wear when at least one of the attributes of the driver and the attributes of the vehicle is changed using the driver-related coefficients and the vehicle-related coefficients.

[0010] One aspect of the present disclosure is a tire wear prediction method for predicting wear on tires mounted on vehicles that constitute a fleet, the method including the steps of: acquiring a plurality of driver-related explanatory variables related to attributes of a driver who drives the vehicle; a vehicle-related variable acquisition unit that acquires a plurality of vehicle-related explanatory variables related to attributes of the vehicle; setting a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables; and calculating the wear as a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables, wherein in the step of calculating the response variable, the driver-related coefficients and the vehicle-related coefficients are used to recalculate a predicted value of the wear in the case where at least one of the attributes of the driver and the attributes of the vehicle is changed. Effect of the Invention

[0011] The above-described fuel efficiency prediction system and fuel efficiency prediction method can contribute to reducing the fuel efficiency of vehicles that make up a fleet. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a schematic diagram of the overall configuration of a fleet and a fleet management system 10. [Diagram 2] FIG. 2 is a functional block diagram of the server computer 100. As shown in FIG. [Diagram 3] FIG. 3 is a diagram showing an overall schematic operation flow of the fleet management system 10. As shown in FIG. [Figure 4] FIG. 4 is a diagram showing tire positions for each type of bus. [Diagram 5] FIG. 5 is a diagram showing an example of an aggregation of fleet operation, tire, and driver characteristics. [Figure 6] FIG. 6 is a diagram showing the relationships between the variables. [Figure 7] Figure 7 is an example of a descriptive profile of representative variables (data). [Figure 8] Figure 8 is an example of a descriptive profile of representative variables (data). [Figure 9] FIG. 9 shows the results of the 3SLS model. [Figure 10] FIG. 10 illustrates an example of a simulated scenario. [Figure 11] Figure 11 shows the descriptive profile of the maintenance cost dataset. [Figure 12] FIG. 12 shows the results of the maintenance cost model. [Figure 13] FIG. 13 is a diagram showing an example of a simulation scenario using the DSS tool of the 3SLS model. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment will be described with reference to the drawings. Note that the same or similar reference numerals are used to designate the same functions or configurations, and the description thereof will be omitted as appropriate.

[0014] (1) Overall configuration of the fleet and fleet management system 1 is a schematic diagram of an entire fleet and a fleet management system 10. The fleet management system 10 manages a fleet, specifically, a plurality of vehicles.

[0015] In this embodiment, the fleet management system 10 manages a plurality of buses that make up a fleet. As shown in Fig. 1, the fleet is made up of a plurality of types of buses (vehicles).

[0016] Specifically, the fleet may include regular buses 20 , double-decker buses 30 and articulated buses 40 .

[0017] The normal bus 20 is a rigid vehicle with one floor having a low floor or a high floor. In this embodiment, the normal bus 20 has one front axle and one rear axle.

[0018] The double-decker bus 30 has a two-story structure having a first floor and a second floor. The double-decker bus 30 is also called a double-decker. In this embodiment, the double-decker bus 30 has two front wheel axles and one rear wheel axle.

[0019] The articulated bus 40 has a structure in which two vehicle bodies are connected by a joint. The articulated bus 40 is also called an articulated bus or a Bendy bus. In this embodiment, the articulated bus 40 has one front axle and one rear axle of the leading vehicle, as well as one axle of the rear vehicle.

[0020] The normal bus 20, the double-decker bus 30, and the articulated bus 40 may be provided as route buses or as charter buses (privately chartered buses).

[0021] The regular bus 20, the double-decker bus 30, and the articulated bus 40 are driven by drivers of a bus operating company that manages a fleet. Specifically, the buses are driven by a male driver 50A and a female driver 50B. The bus operating company includes a plurality of male drivers 50A and a plurality of female drivers 50B. In addition, the drivers may vary in age composition and years of driving experience.

[0022] The fleet management system 10 can provide a number of functions related to fleet management. In this embodiment, a fuel consumption prediction system that predicts the fuel consumption of vehicles (buses) that make up the fleet, and a tire wear prediction system that predicts the wear of tires attached to the vehicles (buses) that make up the fleet can be configured.

[0023] Such fuel economy prediction system and tire wear prediction system may be provided as a decision support system (DSS) to assist a fleet operating entity (such as a bus operating company) in making decisions. Such a DSS may provide some guidance regarding tire-related impacts on the fleet's fuel consumption and maintenance costs. More details on the DSS are provided below.

[0024] The fleet management system 10 may include a server computer 100, a mobile terminal 200, and a desktop terminal 300.

[0025] The server computer 100 can execute computer programs that realize the fuel consumption prediction system and the tire wear prediction system. The server computer 100 may be configured as a standalone server computer connected to a communication network, or may be configured virtually on a network cloud.

[0026] A network cloud typically includes the Internet, and includes various information services (such as weather information), storage services, and application services provided over the Internet.

[0027] The mobile terminal 200 and the desktop terminal 300 can access the server computer 100 via a communication network.

[0028] The mobile terminal 200 is typically a smartphone or a tablet terminal, but may also be a laptop personal computer (PC). The desktop terminal 300 is a relatively large PC (including a monitor) installed in the office of a business entity that operates a fleet.

[0029] The mobile terminal 200 and the desktop terminal 300 are used to input data to the server computer 100 (fuel consumption prediction system and tire wear prediction system), display and output the results of processing in the server computer 100, and the like.

[0030] The data handled by the fuel economy prediction system and the tire wear prediction system is wide-ranging, but broadly speaking, the data may be related to the vehicle (e.g., bus type), tire-related measurements (remaining tread depth, temperature, internal pressure, etc.), weather (air temperature, etc.), driving (distance, fuel consumption, etc.), driver (gender, age, years of driving experience, etc.), and road (driving route, number of traffic lights, number of stops, etc.).

[0031] In addition, some of this data may be obtained not via the mobile terminal 200 or the desktop terminal 300, but rather, for example, tire-related measurement data may be obtained via a telemetry system using a tire pressure monitoring system (TPMS) or the like, and weather data, etc. may be obtained directly by the server computer 100 via a communication network.

[0032] (2) Functional block configuration of the fleet management system Next, a description will be given of the functional block configuration of the fleet management system 10. Specifically, the functional block configurations of a fuel consumption prediction system and a tire wear prediction system realized by the server computer 100 will be described.

[0033] Fig. 2 is a functional block diagram of the server computer 100. As shown in Fig. 2, the server computer 100 includes a driver-related variable acquisition unit 110, a vehicle-related variable acquisition unit 120, a data storage unit 130, a coefficient setting unit 140, a target variable calculation unit 150, and an output unit 160.

[0034] These functional blocks are realized by executing a computer program (software) on the hardware of the server computer 100. Specifically, the server computer 100 may include, as hardware elements, a processor, a memory, an input device, a display, an external interface, etc. However, as described above, the server computer 100 (the fuel consumption prediction system and the tire wear prediction system) may be virtually configured on a network cloud.

[0035] The fuel efficiency prediction system predicts the fuel efficiency of vehicles (buses) that make up the fleet, and the tire wear prediction system predicts the wear of tires installed on the vehicles (buses) that make up the fleet.

[0036] The driver-related variable acquisition unit 110 can acquire a plurality of driver-related explanatory variables. The driver-related explanatory variables may be defined as variables related to the attributes of the driver who drives the vehicle (bus).

[0037] In this embodiment, the driver-related explanatory variables are variables related to the attributes of multiple male drivers 50A and female drivers 50B who drive the normal bus 20, the double-decker bus 30, or the articulated bus 40.

[0038] The variables may be interpreted as explanatory variables. The explanatory variables may be defined as variables that explain the objective variable, and may be called independent variables. The explanatory variables may be selected from the above-mentioned data.

[0039] The response variables may be defined as the variables one wishes to predict and may also be called the dependent variables.

[0040] The driver-related variable acquisition unit 110 can acquire at least one of the average age, gender ratio, average years of experience, and number of drivers per predetermined driving distance as the driver-related explanatory variables. The gender ratio may mean the ratio of male (or female) drivers to the total. The number of drivers per predetermined driving distance (Number of drivers per 1,000 kms) means the number of drivers in charge of each predetermined distance (e.g., 1,000 km).

[0041] The driver-related explanatory variables are not limited to these variables, and statistical data related to the attributes of the driver (for example, accident history, blood type, etc.) may be further added.

[0042] The vehicle-related variable acquisition unit 120 can acquire a plurality of vehicle-related explanatory variables related to the attributes of a vehicle (bus). The vehicle-related explanatory variables may be defined as variables related to the attributes of a vehicle (bus).

[0043] In this embodiment, the vehicle-related explanatory variables are variables related to the attributes of the normal bus 20, the double-decker bus 30 or the articulated bus 40.

[0044] Such variables may be interpreted as explanatory variables, similar to the driver-related explanatory variables.

[0045] The vehicle-related variable acquisition unit 120 can acquire the wear rate of tires mounted on a vehicle (bus) as a vehicle-related explanatory variable. The wear rate may be defined as the amount of tread wear per unit travel distance of tires mounted on each bus. Alternatively, the wear rate may be defined as the amount of tread wear per unit operating time of the bus. Moreover, the wear rate may be defined as the remaining tread depth (RTD) of the tread.

[0046] Furthermore, the vehicle-related variable acquisition unit 120 can acquire the average speed of the vehicle (bus) as the vehicle-related explanatory variable. The average speed may be defined as the average traveling speed of the bus for each travel route. Alternatively, the average speed may be defined as the average traveling speed of the bus per unit travel time.

[0047] Furthermore, the vehicle-related variable acquisition unit 120 can acquire the average temperature (average tire temperature) of the tires mounted on the vehicle (bus) as the vehicle-related explanatory variable. The average temperature may be defined as the average of temperatures measured multiple times for the tires mounted on each bus. As described above, the temperature may be measured by a TPMS sensor mounted on the inner surface of the tire or the like. The temperature may be acquired when the bus starts or finishes operation or during operation, but it is desirable to exclude times when the bus is parked and not in operation.

[0048] The data storage unit 130 stores the data (variables) acquired by the driver-related variable acquisition unit 110 and the vehicle-related variable acquisition unit 120. The data storage unit 130 also stores data that is input via the mobile terminal 200 or the desktop terminal 300 and is handled by the fuel economy prediction system and the tire wear prediction system.

[0049] The coefficient setting unit 140 sets a coefficient to be applied to the driver-related explanatory variables acquired by the driver-related variable acquisition unit 110. In addition, the coefficient setting unit 140 sets a coefficient to be applied to the vehicle-related explanatory variables acquired by the vehicle-related variable acquisition unit 120.

[0050] Specifically, the coefficient setting unit 140 sets a driver-related coefficient to be applied to the driver-related explanatory variables, and also sets a vehicle-related coefficient to be applied to the vehicle-related explanatory variables.

[0051] More specifically, the coefficient setting unit 140 can set the driver-related coefficients and the vehicle-related coefficients based on the actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables.

[0052] The actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables are numerical values ​​determined based on the past numerical values ​​of the driver-related explanatory variables acquired by the driver-related variable acquisition unit 110 and the past numerical values ​​of the vehicle-related explanatory variables acquired by the vehicle-related variable acquisition unit 120.

[0053] A driver-related coefficient can be set for each driver-related explanatory variable. A vehicle-related coefficient can be set for each vehicle-related explanatory variable. A common (identical) coefficient may be set for a portion of all explanatory variables. Such coefficients may be replaced with terms such as weighting or parameters.

[0054] In this embodiment, the driver-related coefficients and the vehicle-related coefficients can be estimated using a three-stage least squares (3SLS) model. However, the 3SLS model does not necessarily have to be used, and other SLS models may be used.

[0055] Specific examples of the driver-related explanatory variables, the vehicle-related explanatory variables, the driver-related coefficients, and the vehicle-related coefficients will be described later.

[0056] The objective variable calculation unit 150 calculates an objective variable using the driver-related explanatory variables and the vehicle-related explanatory variables.

[0057] Specifically, the objective variable calculation unit 150 can calculate fuel efficiency as an objective variable by using the driver-related explanatory variables and the vehicle-related explanatory variables. The fuel efficiency is the consumption rate (or consumption amount) of fuel that is expected to be consumed when a vehicle, specifically, a normal bus 20, a double-decker bus 30, or an articulated bus 40 travels a predetermined travel route under predetermined conditions.

[0058] More specifically, the objective variable calculation unit 150 can estimate the change in fuel efficiency when the coefficient is changed by adjusting at least one of the coefficients (driver-related coefficients or vehicle-related coefficients) of the driver-related explanatory variables and the vehicle-related explanatory variables that affect the fuel efficiency.

[0059] That is, the objective variable calculation unit 150 can set weights (parameters) for each explanatory variable based on the fuel economy as the objective variable, and the driver attributes (average age, gender ratio, average years of experience, etc.) and vehicle information (years of use, vehicle type) as explanatory variables that affect the fuel economy, based on past performance. Furthermore, the objective variable calculation unit 150 can recalculate the predicted value of the objective variable when the driver attributes and / or vehicle information are changed.

[0060] Furthermore, the objective variable calculation unit 150 can calculate tire wear as an objective variable using the driver-related explanatory variables and the vehicle-related explanatory variables. The tire wear is the amount of tread wear (or RTD) of the tires mounted on the normal bus 20, the double-decker bus 30, or the articulated bus 40. Alternatively, the tire wear here may be the wear rate, as described above.

[0061] Specifically, the objective variable calculation unit 150 can estimate the change in wear that occurs when the coefficient is changed by adjusting at least one of the coefficients (driver-related coefficients or vehicle-related coefficients) of the driver-related explanatory variables and the vehicle-related explanatory variables that affect wear.

[0062] That is, the objective variable calculation unit 150 can set weights (parameters) for each explanatory variable based on the wear rate (amount of wear per fixed mileage) as the objective variable, and the driver attributes (average age, gender ratio, average years of experience, etc.) and vehicle information (years of use, vehicle type) as explanatory variables that affect the wear rate, based on past performance. Furthermore, the objective variable calculation unit 150 can recalculate the predicted value of the objective variable when the driver attributes and / or vehicle information are changed.

[0063] In this way, the objective variable calculation section 150 can recalculate the predicted value of fuel efficiency when at least one of the driver's attributes and the vehicle's attributes is changed, using the driver-related coefficients and the vehicle-related coefficients.

[0064] Furthermore, the objective variable calculation section 150 can recalculate the predicted value of tire wear when at least one of the driver attributes and the vehicle attributes is changed, using the driver-related coefficients and the vehicle-related coefficients.

[0065] The output unit 160 can output the data (explanatory variables) acquired by the driver-related variable acquisition unit 110 and the vehicle-related variable acquisition unit 120.

[0066] In addition, the output unit 160 can output the driver-related coefficients and the vehicle-related coefficients set by the coefficient setting unit 140 .

[0067] Furthermore, the output section 160 can output the predicted values ​​of fuel efficiency and tire wear calculated by the objective variable calculation section 150.

[0068] Specifically, the output unit 160 provides a function of outputting image data to a display or the like, and transmitting data to the mobile terminal 200 or the desktop terminal 300 .

[0069] The output unit 160 may display, transmit, or output the above-mentioned data via a decision support system (DSS) platform.

[0070] (3) Operation of the Fleet Management System Next, a description will be given of the operation of the fleet management system 10. Specifically, the following will mainly describe the operation of predicting the fuel efficiency of a vehicle (bus) constituting a fleet by the fleet management system 10 (fuel efficiency prediction system) and the operation of predicting the wear of tires mounted on a vehicle (bus) constituting a fleet by the fleet management system 10 (tire wear prediction system).

[0071] (3.1) Overall operation Fig. 3 shows an overall schematic operation flow of the fleet management system 10. Specifically, the operation flow shown in Fig. 3 is common to the fuel consumption prediction system and the tire wear prediction system.

[0072] As shown in FIG. 3, the fleet management system 10 acquires driver-related explanatory variables and vehicle-related explanatory variables (S10).

[0073] Specifically, the fleet management system 10 acquires explanatory variables related to the attributes of the driver who drives the vehicle (bus), and also acquires explanatory variables related to the attributes of the vehicle (bus).

[0074] The fleet management system 10 calculates coefficients to be applied to the acquired driver-related explanatory variables and vehicle-related explanatory variables (S20). Specifically, the fleet management system 10 calculates driver-related coefficients to be applied to the driver-related explanatory variables and vehicle-related coefficients to be applied to the vehicle-related explanatory variables.

[0075] More specifically, the fleet management system 10 calculates (estimates) the driver-related coefficients and the vehicle-related coefficients using a three-stage least squares (3SLS) model, as described above.

[0076] The fleet management system 10 calculates a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables (S30).

[0077] Specifically, the fleet management system 10 can calculate fuel economy as a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables. Similarly, the fleet management system 10 can calculate tire wear as a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables.

[0078] Furthermore, the fleet management system 10 can recalculate the predicted value of fuel economy when at least one of the driver attributes and the vehicle attributes is changed using the driver-related coefficients and the vehicle-related coefficients. Similarly, the fleet management system 10 can recalculate the predicted value of tire wear when at least one of the driver attributes and the vehicle attributes is changed using the driver-related coefficients and the vehicle-related coefficients.

[0079] The fleet management system 10 outputs the result of the recalculation of the predicted fuel consumption value and / or the result of the recalculation of the predicted tire wear value (S40). Specifically, the fleet management system 10 can display the result on a display or transmit the result to the mobile terminal 200 or the desktop terminal 300.

[0080] (3.2) Collected Data In the fleet management system 10 (fuel consumption prediction system and tire wear prediction system), the following data is collected as driver-related explanatory variables and vehicle-related explanatory variables in order to calculate predicted values ​​of fuel consumption and tire wear.

[0081] (3.2.1) Vehicles (buses) As described above, the type of bus may be any of the normal bus 20, the double-decker bus 30, and the articulated bus 40. The ratio of each bus is not particularly limited, but generally, the ratio of the normal bus 20 may be high.

[0082] Fig. 4 shows tire positions for each type of bus. As shown in Fig. 4, a normal bus 20 has one front axle and one rear axle. The rear wheels of a normal bus 20 are equipped with so-called double tires, in which two tires are mounted in parallel, and six tires numbered 1 to 6 are attached.

[0083] The double-decker bus 30 has two front axles and one rear axle. The double-decker bus 30 also employs dual tires for the rear wheels, and eight tires numbered 1 to 8 are attached to the rear wheels.

[0084] The articulated bus 40 has one front axle and one rear axle for the leading vehicle, as well as one axle for the rear vehicle. The articulated bus 40 also employs double tires, and is fitted with ten tires numbered 1 to 10.

[0085] There are no particular restrictions on the number of buses and the number of tires, but in order to improve the accuracy of predicting fuel efficiency and tire wear, it is preferable that there be a certain level of population, and it is preferable that the total number of buses be approximately 30 or more and the number of tires be approximately 200 or more.

[0086] In addition, the fleet management system 10 can obtain detailed driving record data (based on a unique vehicle ID) of each bus from an external system (service) connected via a communication network.

[0087] The data may include bus seating / capacity, number of trips per day, number of passengers per trip, route traveled with associated direction per time of day. Each trip per vehicle may be given a unique driver ID associated with the driver's experience profile.

[0088] The data can provide variables at a vehicle ID level and may include number of trips, average number of passengers per trip, bus seating capacity, average speed per trip, and times of day (e.g., six trips per day).

[0089] The data may also include a service (maintenance) history for each vehicle. The service history may include the following items:

[0090] Service Group The date the service was performed Number of working hours Cost of each service Service Type - Odometer reading when the vehicle is serviced A description of each record in the service Additionally, service types and costs may be counted and tallied by the RTD for each vehicle.

[0091] A service group may include, for example, the following services:

[0092] Tire related services: tire punctures, tire wear, retreading, pressure monitoring, tire retention wheel nuts, circuit protection valves and other mechanical work Chassis related services: brakes, breakdown, electrical, engine, cooling / heating, steering, AdBlue® filters etc. · Body-related services: air conditioning, body damage, maintenance, repairs, ticket vending machines, etc. Interior related services: mirrors, glass, windows, windshields, CCTV, steam clean etc. Regular service: Regular inspection, Pre-RMS inspection, RMS inspection

[0093] (3.2.2) Remaining tread depth (RTD) The remaining tread depth (RTD) of a tire tread may vary at different tread depths at different locations on the tire (tread) surface and may vary in measurement around the circumference of the tire.

[0094] However, since the difference in the measured value does not have a large effect, it is sufficient to measure the RTD at only one point along the circumference of the tire. On the other hand, considering that the outer edge is easily worn and the inner edge sometimes wears unevenly in the tire width direction, it is desirable to measure at multiple points (e.g., 3 to 4 points). The measurement may be performed using an automatic tool or manually.

[0095] The amount of wear of the tire tread (remaining groove depth) may be defined as follows.

[0096] · TreadLoss = (tread depth on current date) - (tread depth on previous date) Tread depth may be interpreted as the depth of the main grooves formed in the tread.

[0097] Tire temperature and air pressure (internal pressure) can be measured by sensors attached to each tire associated with the bus vehicle ID and tire location (see Figure 4). The average temperature and average internal pressure can be based on measurements collected at two consecutive RTD measurement timings.

[0098] (3.2.3)Fuel consumption Fuel consumption (fuel economy) may be calculated using a weighted average by distance traveled (wL 100 km). Specifically, wL 100 km may be calculated using the "service kilometers" (business distance) for each measurement interval of the RTD.

[0099] It should be noted that fuel consumption data may be obtained, for example, on a monthly basis, and tread wear (TreadLoss) and other key variables may be aggregated over the period in which a particular TreadLoss occurred.

[0100] Service kilometers for weighting purposes may be calculated for each sub-period obtained by dividing the monthly fuel consumption data by the measurement interval of the RTD.

[0101] (3.2.4) Roads and Routes For the roads traveled by each bus along the trip route, data may include the number of traffic lights and major roundabouts. The number of traffic lights may include the number of traffic lights and mini roundabouts. Also, the intersections may include large roundabouts where the diameter of the road centreline exceeds 15 metres.

[0102] Road conditions may also be quantified based on road segment datasets, such as by length, road surface, and number of lanes for each type of road feature.

[0103] (3.2.5) Tire-related In addition to the RTDs mentioned above, tracking data (records) after tire removal or installation may also be included. For example, data about the tire may be recorded when the tire is removed or replaced. Such data may include vehicle ID (of the bus where the tire is replaced), location of the replaced tire, tire brand name, tire replacement date, retread depth, tire ID (date + vehicle ID + tire location), condition of each installed tire (new or retreaded), number of tire retreads, etc.

[0104] (3.2.6) Driver Information Profile With regard to the driver information profile, data may be included such as employee ID (driver ID), gender, date of birth, date of employment, etc. This data can be combined with customer data to obtain the driver's experience over the course of tire tread wear (depth loss) events, and associated with each vehicle and each tire.

[0105] The driving experience and driving profile calculated from this stage may also include the number of trips, service kilometers, average speed and number of passengers aggregated per RTD (time to tread depth loss for each tire).

[0106] (3.2.7) Meteorological Data Regarding weather, the weather data may include weather data for the area where the fleet operating entity (bus operator) has its base (bus parking lot). For example, the maximum temperature for each month may be included, or the average temperature for a period that corresponds to the RTD measurement interval. The data may also include the weather (sunny, cloudy, rainy, snowy).

[0107] (3.3) Data Aggregation One of the most important variables in the fleet management system 10 (fuel economy prediction system and tire wear prediction system) is the tread depth loss, measured as the change in tread depth during a period between two measurement timings on a time axis. This period may be called the tread depth measurement period (interval). The measurement period is not particularly limited, but is usually about 10 to 130 days.

[0108] During the cycle in question, there are variables that do not cause problems (or are nearly constant), such as the age of the bus, the type of bus, the brand of tyres, and the fuel consumption of the bus.

[0109] Meanwhile, variables such as average speed, route, bus patronage, weather temperature, tire temperature, air pressure (internal pressure), etc. may change during the tread depth measurement period.

[0110] All variables are preferably aggregated to represent one tread measurement period. Figure 5 shows an example of an aggregation of fleet operation, tire and driver characteristics.

[0111] As shown in Figure 5, operation / route characteristics include average speed, distance traveled (every two weeks), average maximum temperature, etc. The data is also aggregated in an appropriate manner, such as weighted average.

[0112] The tire characteristics include average temperature and average internal pressure, and the driver characteristics include average age, average years of driving experience, and the percentage of female drivers.

[0113] Note that if the route is long, its characteristics may be weighted more highly than shorter routes. The distance traveled (kms) during the tread measurement period may be in units of two weeks (14 days). For example, it would not be meaningful to directly compare the distance traveled by a bus if one measurement period is 15 days and another is 50 days.

[0114] (3.4) Speed, Temperature, Tread Depth and Fuel Consumption Model Next, the speed, temperature, tread depth and fuel consumption models will be described.

[0115] (3.4.1) Simultaneous Equation Model System The statistical method according to the present embodiment can use a jointly estimated three-stage least squares (3SLS) model (a system of equations including left-hand side (LHS) and right-hand side (RHS) endogenous variables).

[0116] As mentioned above, the tread depth loss between two measurement points is important, but the number of measurements depends on the number of consistent data points that can be collected from the same tire.

[0117] The four models relate to average speed, average tire temperature, tread depth loss, and fuel consumption. Tread depth loss itself is not very informative as it is highly dependent on the distance traveled by the vehicle during the measurement period and a change in millimeters does not have the same effect on tires with different tread depths.

[0118] Therefore, a transformed variable of tread depth is used, which represents the percentage of tread depth loss per kilometer (tread wear per km) relative to the previous tread depth. This transformation is as shown in (Equation 1).

[0119]

number

[0120] Here, the units of the variables are as follows:

[0121]

number

[0122] All the attributes included in the following equations are calculated based on the tread measurement period. For example, the mileage means the service mileage each bus has traveled since the last measurement until the current time. The equation system is as shown in (Equation 2) to (Equation 5).

[0123]

number

[0124]

number

[0125]

number

[0126]

number

[0127] Figure 6 shows the relationship between each variable. Fuel consumption is partly explained by tread depth loss per km, partly explained by tire temperature, and partly explained by average speed. Part of tire temperature is explained by average speed.

[0128] Each of these endogenous variables is influenced by a number of exogenous factors, shown as circles in Figure 6. The exogenous factors included in each model shown in Figure 6 are listed as examples, but the combinations of variables and associated interactions are diverse, as shown by the equations above.

[0129] As shown in Figure 6, when the disturbances (error terms) are contemporaneously correlated, a feasible generalized least squares (FGLS) version of the two-stage least squares estimation leads to consistent and asymptotically efficient estimates (Zellner and Theil 1962). Such an estimation procedure is called three-stage least squares (3SLS).

[0130] Zellner's 3 SLS estimators are obtained by first regressing all variables in the right-hand side of each equation on all variables in the (exogenous) instrument list and retaining the fitted values.

[0131] In that event, this first stage regression produces a perfect fit with one parameter on the variable and zero for all others, so that any variables in the equation list that also appear in the trigger variables list will be reproduced exactly.

[0132] After this estimation, the disturbance covariance matrix is ​​estimated using the original variables rather than the fitted variables. Non-iterative 3SLS is used because iterations do not provide any efficiency gains and do not produce maximum likelihood estimation results.

[0133] (3.4.2) Descriptive profile of collected data Figures 7 and 8 are examples of descriptive profiles of representative variables (data). As shown in Figures 7 and 8, in the final data example of the statistical and descriptive analysis of the 3SLS model, there are 1,749 observations, each representing one tire.

[0134] The values ​​shown in Figures 7 and 8 are averages (standard deviations), and the values ​​are shown divided by bus type (all, high-floor bus, low-floor bus, articulated bus, double-decker bus).

[0135] The variables are also divided into bus characteristics, operation / route characteristics, tire characteristics and driver characteristics.

[0136] (3.4.3) Results and interpretation of the 3SLS model As mentioned above, in this embodiment, a 3SLS model is used, and there is a possibility that each of the endogenous variables has a statistically significant effect, namely, average speed, tread depth loss, average tire temperature, and fuel consumption.

[0137] The dependent (or left-hand side) variable in (Equation 2) is average speed, which is statistically explained by several route, operation, and bus characteristics.

[0138] The dependent variable in (Equation 3) is the average tire temperature, which is statistically explained by average speed, percentage of peak kilometers, patronage, air temperature and tire position.

[0139] The dependent variable in (Equation 4) is tread depth loss, which is statistically explained by average speed, average tire temperature, front tire pressure, distance traveled (km), route characteristics, passengers and tire position.

[0140] The dependent variable in (Equation 5) is fuel consumption, which is affected in a statistically significant manner by tread depth loss, bus age, mileage, and bus type.

[0141] Figure 9 shows the results of the 3SLS model, with the coefficient parameters (Coefficient) and t-tests for each dependent variable.

[0142] The results shown in Figure 9 suggest that the average speed of the double-decker bus 30 and the low-floor regular bus 20 (Rigid) is higher than that of other types of buses (articulated bus 40 and high-floor regular bus 20).

[0143] The rear (back) tires experienced greater tread depth loss than the front (front) tires, which was expected, and the inner (inner) rear tires also experienced a greater rate of tread depth loss per 1,000 km than the outer (outer) rear tires (3.7% vs. 1.3%).

[0144] The articulated bus 40 has a significantly higher fuel consumption than other types of buses, followed by the double-decker bus 30.

[0145] Importantly, many of the statistically significant explanatory variables are contextual and represent the operating environment and are therefore not under the control of the operator (bus operator). In all four interrelated equations (Equation 2-Equation 5), the variables that are under the control of the operator (i.e., variables whose values ​​they have the ability to change) are driver (years of experience, age, number of drivers), tyre pressure, tyre temperature, bus age and bus type.

[0146] Also, in the equation for average speed (Equation 2), we can see that, all else being equal, the more miles driven per two weeks, the higher the average speed will tend to be. The more stops per kilometre, the lower the average speed will be.

[0147] Furthermore, the higher the maximum load per trip, the slower the speed (the longer the loading and unloading period). The maximum load per trip has different effects on different bus types. The low-floor normal bus 20 is most affected by the maximum load, followed by the double-decker bus 30 and the articulated bus 40.

[0148] Drivers who have been with the bus operator for a longer period of time tend to offer higher average speeds, older drivers tend to offer lower average speeds and male drivers tend to offer higher average speeds, this is mainly related to the route they drive.

[0149] Interestingly, it has been shown that the longer many drivers drive a vehicle (per 1,000km), the lower their average speed tends to be. This may be related to familiarity with the vehicle and route, whereas unfamiliarity leads to lower average speeds.

[0150] Additionally, tire temperatures may increase during peak travel times (the effects of congestion and increased braking), as well as during periods of high passenger numbers and when higher temperatures are expected.

[0151] Maximum load has a significant effect on tire temperature of articulated bus 40, followed by high floor regular bus 20 and double decker bus 30, while low floor regular bus 20 shows no statistically significant effect.

[0152] Also, higher average tire temperatures are associated with greater tread depth loss, and higher average speeds are associated with greater tread depth loss. Interestingly, the optimum inflation pressure level (reduced to 105-115 psi) appears to have a statistically significant effect on front tire tread depth loss. This suggests that the optimum level of inflation pressure does not have a statistically significant effect on rear tire tread depth loss. This may be due to the influence of other variables.

[0153] Clearly, improvements in tread depth loss can make a significant contribution to fuel savings through improved fuel consumption. Although there may be opportunities to improve tread depth loss, other variables such as average speed are usually not under the control of the bus operator, except for the driver's experience and driving ability, which varies with age.

[0154] (3.5) Maintenance costs The maintenance cost of a vehicle (bus) takes into account tire service, chassis service, body service, interior service and daily service, and includes all inventory (including the cost of tires) and labor.

[0155] Figure 11 shows the descriptive profile of the maintenance cost dataset. The total maintenance cost per kilometre includes labour and inventory costs for each item, in Australian dollars (AUD).

[0156] The tread depth loss used in the model represents an average across all vehicle tires, occurring at various cost components of the total maintenance cost, as shown in Figure 11.

[0157] Therefore, we aggregate all the costs and express them as maintenance cost per kilometer using them as the dependent variable, and the maintenance cost model is explained by other candidate operations, routes traveled, and other variables. The linear regression equation is:

[0158]

number

[0159] The results of the maintenance cost model are shown in Figure 12. The main variables related to their impact on tire performance that explain the variation in total maintenance costs are:

[0160] -Average tread depth loss for all tires on the vehicle Average tire temperature Bus age Number of drivers per vehicle route Dummy variable representing 20 high-floor regular buses It can be seen that there is a relationship between tire tread depth loss and total maintenance costs.

[0161] (3.6) Decision Support Systems (DSS) A decision support system (DSS) can provide guidance on some of the key influences, especially those related to tires, fuel consumption and maintenance costs. A DSS allows the user to change the levels of explanatory variables (within acceptable limits and within operationally realistic limits) and the DSS automatically calculates the impact on all other affected variables.

[0162] The DSS includes all of the relationships shown in Figure 6, so that, for example, if there is a change in the average age of the drivers, this will affect the average speed, which will affect the rate of tire temperature and tread depth loss, which in turn will affect fuel consumption.

[0163] Thus, a change in one explanatory variable (e.g., average speed) may affect all four endogenous dependent variables despite not being included in all four equations (e.g., average speed is not a direct explanatory variable in the fuel consumption model, but is affected by tread depth loss).

[0164] Additionally, the DSS allows for the modification of the dependent variables (i.e., average speed, average tire temperature, percent tread depth loss, and fuel consumption) by adjusting the constant coefficients (see Figure 9), assuming all other explanatory variables remain unchanged.

[0165] That is, the driver-related and vehicle-related coefficients may be adjusted in value, assuming that all other explanatory variables remain unchanged.

[0166] As mentioned above, several explanatory variables are included in the 3SLS model, not all of which are controllable by the operator. Different scenarios are simulated to reveal the impact of these variables on fuel consumption and maintenance cost savings.

[0167] The scenario was simulated by varying five explanatory variables that were considered to be under the control of the operator: the percentage of tires with optimal internal pressure levels (105-115 psi), the age of the bus, the average age of the drivers, the average number of years of driving experience of the drivers, the percentage of male drivers 50A, the number of drivers, and the number of drivers per route.

[0168] Examples of simulated scenarios are shown in Figure 10. Specifically, Figure 10 shows six different simulation scenarios and a base (current situation) and their predicted impact on four endogenous (i.e.) dependent variables (average speed, average tire temperature, percentage tread depth loss per 1,000 km, and fuel consumption).

[0169] In Scenario 1, the percentage of tires at optimal pressure levels (105-115 psi) increases from 54.17% to 90.00%. The DSS can show the fuel consumption savings (in monetary terms) for that scenario (similarly for Scenarios 2-7).

[0170] In scenario 2, the age of buses drops from 6.73 years to 5 years.

[0171] Scenario 3 maintains the improved age of buses in Scenario 2 but increases the average driver age to 55.

[0172] In scenario 4, we keep the improved explanatory variables from scenario 3 and shorten the driver experience to 3 years.

[0173] In scenario 5, the level of scenario 4 is maintained, but 50% are driven by female drivers 50B.

[0174] Scenario 6 builds on the level of scenario 5 by reducing the number of drivers per 1,000 km for each vehicle to 6 (vs. 8.61 in the base scenario).

[0175] Also, in terms of maintenance costs, any change can directly or indirectly impact maintenance costs through changes in the rate of tread depth loss and average tire temperature.

[0176] The explanatory variable bus age has a significant impact on maintenance costs, as explained in scenario 2. Reducing the bus age from 6.73 years to 5 years, as in scenario 2, can save on annual maintenance costs. All simulated scenarios show similar effects in the 3SLS model and the maintenance cost model.

[0177] Scenario 7 is a model in which both fuel and maintenance costs are significantly reduced.

[0178] FIG. 13 shows an example of a simulation scenario using the DSS tool of the 3SLS model. Specifically, FIG. 13 shows an example of a screenshot of a simulation scenario using the DSS tool of the 3SLS model.

[0179] The fuel consumption savings may be converted into monetary savings in fuel consumption. For example, if fuel prices average $1.61 (AUD) per litre and a fuel credit of $0.12003 per litre is taken into account, the annual savings would be $1.49 per litre.

[0180] Also, for example, the total annual mileage provided by the subject fleet is assumed to be a predetermined value, but the DSS tool may be used to modify the total annual mileage provided by the subject fleet.

[0181] (4) Actions and Effects According to the above-described embodiment, the following advantageous effects can be obtained. Specifically, the fleet management system 10 (fuel consumption prediction system) can set a driver-related coefficient and a vehicle-related coefficient based on the actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables. In addition, the fuel consumption prediction system (specifically, the DSS) can use the driver-related coefficient and the vehicle-related coefficient to recalculate the predicted value of fuel consumption when at least one of the driver's attributes and the vehicle's attributes is changed.

[0182] In other words, by focusing on "driver attributes" and "vehicle attributes," which are variables that the operator (bus operating company) can control, and recalculating fuel efficiency when these variables are changed, it is possible to present a method for fleet management.

[0183] In addition, the accuracy of prediction can be improved by using tire wear rate, average vehicle speed, and average tire temperature as explanatory variables for fuel economy.

[0184] In addition, the fleet management system 10 (tire wear prediction system) can use the driver-related coefficients and vehicle-related coefficients to recalculate the predicted tire wear value when at least one of the driver attributes and the vehicle (bus) attributes is changed.

[0185] In other words, by focusing on "driver attributes" and "vehicle attributes," which are variables that the operator (bus operating company) can control, and recalculating the wear rate (tread depth loss) when these variables are changed, it is possible to present a method for fleet management.

[0186] In addition, the prediction accuracy can be improved by using the average vehicle speed and the average tire temperature as explanatory variables for the wear rate.

[0187] In other words, the fuel consumption prediction system can contribute to reducing the fuel consumption of the buses that make up the fleet. Also, the tire wear prediction system can more accurately predict the wear of the tires installed on the buses that make up the fleet.

[0188] In this embodiment, the fleet management system 10 can acquire at least one of the average age, gender ratio, average years of experience, and number of drivers per predetermined mileage as the driver-related explanatory variables. Therefore, the fuel economy and tire wear can be predicted with higher accuracy by using the driver-related explanatory variables that have a large effect on the fuel economy or wear rate.

[0189] In this embodiment, the fleet management system 10 can acquire the average speed of the bus, the wear rate of the tires mounted on the bus (in the case of a fuel consumption prediction system), and the average temperature of the tires mounted on the bus as vehicle-related explanatory variables. Therefore, fuel consumption and tire wear can be predicted with higher accuracy by using vehicle-related explanatory variables that have a large effect on fuel consumption or wear rate.

[0190] (5) Other embodiments Although the embodiment has been described above, it will be apparent to those skilled in the art that the present invention is not limited to the description of the embodiment and that various modifications and improvements are possible.

[0191] For example, in the above-described embodiment, the average age of drivers, the gender ratio, the average years of experience, and the number of drivers per predetermined mileage were mainly used as the driver-related explanatory variables, but the driver-related explanatory variables are not limited to these explanatory variables, and other explanatory variables shown in FIG. 7 and FIG. 8 may be used.

[0192] In addition, in the above-described embodiment, the tire wear rate, the average vehicle speed, and the average tire temperature are used as the vehicle-related explanatory variables. However, the vehicle-related explanatory variables are not limited to these explanatory variables, and other explanatory variables shown in FIG. 7 and FIG. 8 may be used.

[0193] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described in the present disclosure. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure. [Explanation of symbols]

[0194] 10 Fleet Management Systems 20 Regular Bus 30 Double-decker bus 40 articulated bus 50A Male Driver 50B Female Driver 100 Server Computers 110 Driver related variable acquisition section 120 Vehicle related variable acquisition unit 130 Data storage unit 140 Coefficient setting section 150 Objective variable calculation unit 160 Output section 200 Mobile Devices 300 desktop terminals

Claims

1. A fuel consumption prediction system for predicting fuel consumption of vehicles that constitute a fleet, A driver-related variable acquisition unit that acquires a plurality of driver-related explanatory variables related to attributes of a driver who drives the vehicle; a vehicle-related variable acquisition unit that acquires a plurality of vehicle-related explanatory variables related to attributes of the vehicle; a coefficient setting unit that sets a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables; an objective variable calculation unit that calculates the fuel efficiency as an objective variable by using the driver-related explanatory variables and the vehicle-related explanatory variables; Equipped with the objective variable calculation unit recalculates the predicted value of the fuel efficiency when at least one of an attribute of the driver and an attribute of the vehicle is changed by using the driver-related coefficient and the vehicle-related coefficient; The driver-related variable acquisition unit acquires at least one of the average age, gender ratio, average years of experience, and number of drivers for each specified driving distance as the driver-related explanatory variables.

2. A fuel efficiency prediction system for predicting fuel efficiency of vehicles that constitute a fleet, comprising: A driver-related variable acquisition unit that acquires a plurality of driver-related explanatory variables related to attributes of a driver who drives the vehicle; a vehicle-related variable acquisition unit that acquires a plurality of vehicle-related explanatory variables related to attributes of the vehicle; a coefficient setting unit that sets a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables; an objective variable calculation unit that calculates the fuel efficiency as an objective variable by using the driver-related explanatory variables and the vehicle-related explanatory variables; Equipped with the objective variable calculation unit recalculates the predicted value of the fuel efficiency when at least one of an attribute of the driver and an attribute of the vehicle is changed by using the driver-related coefficient and the vehicle-related coefficient; The vehicle-related variable acquisition unit acquires, as the vehicle-related explanatory variable, a wear rate of tires mounted on the vehicle.

3. A fuel efficiency prediction system for predicting fuel efficiency of vehicles that constitute a fleet, comprising: A driver-related variable acquisition unit that acquires a plurality of driver-related explanatory variables related to attributes of a driver who drives the vehicle; a vehicle-related variable acquisition unit that acquires a plurality of vehicle-related explanatory variables related to attributes of the vehicle; a coefficient setting unit that sets a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables; an objective variable calculation unit that calculates the fuel efficiency as an objective variable by using the driver-related explanatory variables and the vehicle-related explanatory variables; Equipped with the objective variable calculation unit recalculates the predicted value of the fuel efficiency when at least one of an attribute of the driver and an attribute of the vehicle is changed by using the driver-related coefficient and the vehicle-related coefficient; The vehicle-related variable acquisition unit acquires an average temperature of tires mounted on the vehicle as the vehicle-related explanatory variable.

4. The fuel efficiency prediction system according to claim 1 , wherein the vehicle-related variable acquisition unit acquires an average speed of the vehicle as the vehicle-related explanatory variable.

5. A fuel consumption prediction method for predicting fuel consumption of vehicles that constitute a fleet, comprising: Obtaining a plurality of driver-related explanatory variables related to attributes of a driver who drives the vehicle; obtaining a plurality of vehicle-related explanatory variables related to attributes of the vehicle; setting a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables; calculating the fuel efficiency as a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables; In the step of calculating the objective variable, the driver-related coefficient and the vehicle-related coefficient are used to recalculate the predicted value of the fuel efficiency in a case where at least one of the driver's attribute and the vehicle's attribute is changed; In the step of acquiring the driver-related explanatory variables, at least one of the average age, gender ratio, average years of experience, and number of drivers for each predetermined driving distance is acquired as the driver-related explanatory variables.

6. A fuel efficiency prediction method for predicting fuel efficiency of vehicles that constitute a fleet, comprising: Obtaining a plurality of driver-related explanatory variables related to attributes of a driver who drives the vehicle; obtaining a plurality of vehicle-related explanatory variables related to attributes of the vehicle; setting a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables; calculating the fuel efficiency as a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables; In the step of calculating the objective variable, the driver-related coefficient and the vehicle-related coefficient are used to recalculate the predicted value of the fuel efficiency in a case where at least one of the driver's attribute and the vehicle's attribute is changed; In the step of acquiring a vehicle-related explanatory variable, a wear rate of a tire mounted on the vehicle is acquired as the vehicle-related explanatory variable.

7. A fuel efficiency prediction method for predicting fuel efficiency of vehicles that constitute a fleet, comprising: Obtaining a plurality of driver-related explanatory variables related to attributes of a driver who drives the vehicle; obtaining a plurality of vehicle-related explanatory variables related to attributes of the vehicle; setting a driver-related coefficient to be applied to the driver-related explanatory variables and a vehicle-related coefficient to be applied to the vehicle-related explanatory variables based on actual values ​​of the driver-related explanatory variables and the vehicle-related explanatory variables; calculating the fuel efficiency as a response variable using the driver-related explanatory variables and the vehicle-related explanatory variables; In the step of calculating the objective variable, the driver-related coefficient and the vehicle-related coefficient are used to recalculate the predicted value of the fuel efficiency in a case where at least one of the driver's attribute and the vehicle's attribute is changed; In the step of acquiring a vehicle-related explanatory variable, an average temperature of tires mounted on the vehicle is acquired as the vehicle-related explanatory variable.

8. A fuel efficiency prediction method described in any one of claims 5 to 7, wherein in the step of acquiring the vehicle-related explanatory variables, an average speed of the vehicle is acquired as the vehicle-related explanatory variable.

Images