Energy prediction device
The energy prediction device improves accuracy by segmenting routes and constructing tailored prediction models for each segment, addressing the challenge of mixed traffic conditions.
Patent Information
- Application Number
- JP2023078311
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-11
- Publication Date
- 2024-11-21
AI Technical Summary
Existing energy prediction systems struggle to accurately predict energy consumption in vehicles due to varying traffic conditions along a route, as they use a single prediction model for the entire route, which fails to account for the mixed traffic conditions.
An energy prediction device that divides travel routes into segments and constructs a consumption prediction model for each segment, using various data sources like weather, road conditions, and driver information to improve accuracy.
Enhances the prediction accuracy of energy consumption by adapting to varying traffic conditions, providing more precise energy consumption estimates for each segment of the journey.
Smart Images

Figure 2024162616000001_ABST
Abstract
Description
[Technical field]
[0001] The present disclosure relates to an energy prediction device. [Background technology]
[0002] There is known a technology for predicting the energy required for a vehicle to travel an arbitrary route. In the invention described in the following Patent Document 1, travel data including a plurality of feature quantities of a mobile object is acquired based on information regarding the travel status of the mobile object. A prediction unit calculates a predicted value of the amount of energy consumed by the mobile object based on the travel data and a first classification rule that associates a plurality of first conditions related to at least one of the plurality of feature quantities with a plurality of first prediction models of the amount of energy consumed. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2020-27432 A Summary of the Invention [Problem to be solved by the invention]
[0004] When a vehicle travels along a route, various traffic conditions are mixed on the route, and the degree of impact of fluctuations in traffic conditions on energy consumption is not uniform. For example, while there are routes and route sections where traffic volume increases and congestion is likely to occur when it rains, there are also routes and route sections where traffic volume does not fluctuate much even when it rains. In Patent Document 1, energy consumption is predicted using one prediction model for the entire route, so it is difficult to improve prediction accuracy for routes where various traffic conditions are mixed.
[0005] An object of the present disclosure is to provide an energy prediction device that can improve the accuracy of predicting energy consumption in a vehicle even on a route where a variety of traffic conditions are mixed. [Means for solving the problem]
[0006] The present disclosure provides an energy prediction device that includes a route setting unit (101) that divides a travel route on which a vehicle travels and sets segmented routes, and a model construction unit (102) that constructs a consumption prediction model that predicts the energy consumption of the vehicle for each segmented route. Effect of the Invention
[0007] According to the present disclosure, it is possible to provide an energy prediction device that can improve the prediction accuracy of energy consumption in a vehicle even on a route where various traffic conditions are mixed. [Brief description of the drawings]
[0008] [Figure 1] FIG. 1 is a block diagram for explaining the energy prediction device according to this embodiment. [Diagram 2] FIG. 2 is a flowchart for explaining the information processing flow by the energy prediction device shown in FIG. [Diagram 3] FIG. 3 is a diagram for explaining the setting of a district route. [Figure 4] FIG. 4 is a diagram for explaining the setting of a district route. [Diagram 5] FIG. 5 is a diagram for explaining setting of a district route. [Figure 6] FIG. 6 is a diagram for explaining setting of a district route. [Figure 7] FIG. 7 is a diagram for explaining the energy prediction. [Figure 8] FIG. 8 is a diagram for explaining the energy prediction. [Figure 9] FIG. 9 is a diagram for explaining energy prediction. [Figure 10] FIG. 10 is a diagram for explaining energy prediction. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] Hereinafter, the present embodiment will be described with reference to the accompanying drawings. In order to facilitate understanding of the description, the same components in each drawing are denoted by the same reference numerals as much as possible, and duplicated description will be omitted.
[0010] An energy prediction device 10 according to this embodiment will be described with reference to Fig. 1. The energy prediction device 10 is configured to be able to exchange information with a vehicle 30 via a network NW. The energy prediction device 10 is configured to be able to exchange information with a vehicle characteristics storage unit 201, a driving route storage unit 202, a driver information storage unit 203, an environmental information storage unit 204, and a state information storage unit 205.
[0011] The energy prediction device 10 is configured as a computer having, as hardware, a calculation unit such as a CPU (Central Processing Unit), a storage unit such as a RAM (Random Access Memory) and a ROM (Read Only Memory), and an interface unit for transmitting and receiving data.
[0012] The energy prediction device 10 includes a path setting unit 101 , a model construction unit 102 , an information acquisition unit 103 , an energy prediction unit 104 , a notification unit 105 , and a storage unit 110 .
[0013] The route setting unit 101 is a part that divides a travel route on which a vehicle travels and sets segmented routes. Setting of segmented routes will be described in detail later.
[0014] The model construction unit 102 is a part that constructs a consumption prediction model that predicts the energy consumption of the vehicle for each segment of the route. The construction of the consumption prediction model will be described in detail later.
[0015] The information acquisition unit 103 is a part that acquires state information related to energy consumption when the vehicle travels along a travel route. The state information will be described in detail later.
[0016] The energy prediction unit 104 is a part that predicts the energy consumption for each segmented route using a consumption prediction model constructed for each segmented route, and predicts the energy consumption on the travel route. In another aspect, the energy prediction unit 104 is also a part that generates a vehicle speed pattern for each segmented route based on an index value related to the vehicle speed pattern, predicts the energy consumption based on the vehicle speed pattern for each segmented route, and predicts the energy consumption on the travel route. The prediction of the energy consumption will be described in detail later.
[0017] The notification unit 105 is a part that notifies a predetermined notification destination of the energy consumption predicted by the energy prediction unit 104. The predetermined notification destination can be set arbitrarily, and may be notified to the vehicle 30 or may be passed on to another notification destination.
[0018] The storage unit 110 is a part that stores segmented routes set by the route setting unit 101. The storage unit 110 is a part that stores a consumption prediction model constructed by the model construction unit 102. The storage unit 110 is a part that stores state information acquired by the information acquisition unit 103.
[0019] The vehicle characteristic storage unit 201 is a part that stores characteristic information of all vehicles including the vehicle 30. The characteristic information includes all information necessary to predict the energy consumption of the vehicle.
[0020] The travel route storage unit 202 is a part that stores route information regarding travel routes along which vehicles in general, including the vehicle 30, are travelling or scheduled to travel. The route information is information about the travel route, and includes at least one of the following: position information about each point, information about the gradient, information about the road width, information about the speed limit, information about the curvature of the curve, information about the position of traffic lights, information about the position of bus stops, and information about the position of intersections.
[0021] The driver information storage unit 203 is a part that stores driver information related to drivers who drive all vehicles including the vehicle 30. The driver information includes driver attributes and information indicating characteristics of the driver corresponding to the attributes.
[0022] The environmental information storage unit 204 is a part that stores environmental information related to the environment in which vehicles including the vehicle 30 are traveling or scheduled to travel. The environmental information includes at least one of weather information and date and time information. The weather information includes at least one of the probability of precipitation and the amount of precipitation. The date and time information includes at least one of the time of day, day of the week, public holidays, and season.
[0023] The state information storage unit 205 is a part that stores state information related to energy consumption when the vehicle travels along a travel route. The state information includes at least one of travel state information, energy state information, and road state information. The travel state information is information that specifies a pattern in which the vehicle travels along a travel route. For example, the travel state information includes information indicating at least one of a stop frequency, a maximum speed, a steady-state speed, an average speed, an acceleration, and a deceleration.
[0024] The energy state information is information that specifies the energy required when the vehicle travels along a travel route. For example, the energy state information includes information indicating at least one of fuel efficiency, power efficiency, SOC (State of Charge), and inverter power.
[0025] The road condition information is information that specifies the road condition that is the state of the travel route and affects the energy required for the vehicle to travel. For example, the road condition information includes at least one of information indicating gradient information, information on the location of bus stops, information on the location of intersections, information on road width, information on speed limits, information on the location of traffic lights, information on curve curvature, and information on the degree of congestion.
[0026] The vehicle 30 that is the prediction target of the energy prediction device 10 is connected to a network NW, and driving data of the vehicle 30 is transmitted to the energy prediction device 10 via the network NW and stored in the holding unit 110.
[0027] The vehicle 30 includes a state detection unit 301, a vehicle speed detection unit 302, a communication unit 303, a battery ECU 304, and an inverter 305. The state detection unit 301 acquires the state of charge SOC of the battery used to run the vehicle 30 from the battery ECU. The state detection unit 301 acquires a current value from the inverter 305. The state of charge SOC and the current value are transmitted by the communication unit 303 to the energy prediction device 10. The state detection unit 301 also detects position information of the vehicle 30. The position information is transmitted by the communication unit 303 to the energy prediction device 10. The vehicle speed detection unit 302 detects the speed of the vehicle 30. The communication unit 303 transmits the vehicle speed to the energy prediction device 10. In this embodiment, the vehicle 30 is an electric vehicle, but the power source of the vehicle that is the target of prediction by the energy prediction device 10 is not limited to an electric motor that uses a battery as a power source, and all power sources can be targeted, including known gasoline engines, diesel engines, hybrids that combine an electric motor and an internal combustion engine, and electric motors that use a fuel cell as a power source.
[0028] Next, an information processing flow by the energy prediction device 10 will be described with reference to Fig. 2. In step S001, the route setting unit 101 executes a process of dividing a travel route. The travel route division process will be described with reference to Fig. 3.
[0029] As shown in FIG. 3A, the route setting unit 101 pre-divides the travel route and sets eight pre-segment routes SA1, SA2, SA3, SA4, SA5, SA6, SA7, and SA8. For convenience of illustration and explanation, the pre-segment routes SA1, SA2, SA3, SA4, SA5, SA6, SA7, and SA8 are all the same length, but pre-segment routes of different lengths may be included. The length of the pre-segment route can be set arbitrarily. In addition, the pre-segment routes SA1, SA2, SA3, SA4, SA5, SA6, SA7, and SA8 are eight pre-segment routes, which is just an example, and the number can be appropriately determined if multiple or three or more segment routes are targeted.
[0030] The route setting unit 101 judges whether adjacent pre-segment routes satisfy the joining condition. In the example of FIG. 3(A), the route setting unit 101 judges whether the pre-segment route SA1 and the pre-segment route SA2 satisfy the joining condition. The route setting unit 101 judges whether the pre-segment route SA2 and the pre-segment route SA3 satisfy the joining condition. The route setting unit 101 judges whether the pre-segment route SA3 and the pre-segment route SA4 satisfy the joining condition. The route setting unit 101 judges whether the pre-segment route SA4 and the pre-segment route SA5 satisfy the joining condition. The route setting unit 101 judges whether the pre-segment route SA5 and the pre-segment route SA6 satisfy the joining condition. The route setting unit 101 judges whether the pre-segment route SA6 and the pre-segment route SA7 satisfy the joining condition. The route setting unit 101 judges whether the pre-segment route SA7 and the pre-segment route SA8 satisfy the joining condition. The joining condition will be described in detail later.
[0031] In the example of Figure 3(A), pre-segment route SA1 and pre-segment route SA2 satisfy the joining condition. Pre-segment route SA2 and pre-segment route SA3 do not satisfy the joining condition. Pre-segment route SA3 and pre-segment route SA4 satisfy the joining condition. Pre-segment route SA4 and pre-segment route SA5 satisfy the joining condition. Pre-segment route SA5 and pre-segment route SA6 do not satisfy the joining condition. Pre-segment route SA6 and pre-segment route SA7 do not satisfy the joining condition. Pre-segment route SA7 and pre-segment route SA8 satisfy the joining condition.
[0032] When the route setting unit 101 combines the pre-segment routes in the satisfying relationship of the combining condition as described above, the result is as shown in FIG. 3(B). Specifically, the route setting unit 101 combines the pre-segment route SA1 and the pre-segment route SA2 to set the segment route SB1. The route setting unit 101 combines the pre-segment route SA1, the pre-segment route SA2, and the pre-segment route SA2 to set the segment route SB1. The route setting unit 101 combines the pre-segment route SA3, the pre-segment route SA4, and the pre-segment route SA5 to set the segment route SB2. The route setting unit 101 sets the pre-segment route SA6 to the segment route SB3 without combining it with other pre-segment routes. The route setting unit 101 combines the pre-segment route SA7 and the pre-segment route SA8 to set the segment route SB4.
[0033] The process by the route setting unit 101 to combine pre-segment routes to form a segment route may be completed by combining the pre-segment routes SA1, SA2, SA3, SA4, SA5, SA6, SA7, and SA8 shown in Figure 3(A) based on a combining condition to form the segment routes SB1, SB2, SB3, and SB4 shown in Figure 3(B).
[0034] The route setting unit 101 may regard the segment routes SB1, SB2, SB3, and SB4 shown in Fig. 3(B) as pre-segment routes, and may further perform a process of combining them. In Fig. 3(B), the segment route SB1 and segment route SB2 regarded as pre-segment routes satisfy the combining condition. The segment route SB2 and segment route SB3 regarded as pre-segment routes do not satisfy the combining condition. The segment route SB3 and segment route SB4 regarded as pre-segment routes satisfy the combining condition.
[0035] In the above-described satisfying relationship of the combining condition, when the route setting unit 101 combines the segment routes SB1, SB2, SB3, and SB4 regarded as pre-segment routes, the result becomes as shown in Fig. 3(C). Specifically, the route setting unit 101 combines the segment route SB1 as a pre-segment route with the segment route SB2 to set the segment route SC1. The route setting unit 101 combines the segment route SB3 as a pre-segment route with the segment route SB4 to set the segment route SC2.
[0036] Next, the combination condition will be described. The combination condition is determined based on state information related to energy consumption when the vehicle travels along a travel route. The state information includes at least one of driving state information, energy state information, and road state information. The combination condition is determined based on at least one of the driving state information, energy state information, and road state information.
[0037] The route setting unit 101 divides the travel route into pre-segment routes, and performs processing to combine the pre-segment routes into a segment route depending on whether adjacent pre-segment routes satisfy a combining condition. The combining condition is determined based on status information regarding energy consumption when the vehicle travels the travel route, so whether or not the adjacent pre-segment routes can be combined is determined depending on whether or not the status information of the adjacent pre-segment routes is similar enough to be combined.
[0038] For example, a case where the joining condition is determined based on the number of stops per unit distance in the same trip will be described with reference to Fig. 4. Fig. 4 plots the number of vehicle stops per unit distance in each section when traveling through Section 1 and Section 2 in the same trip. By calculating the correlation coefficient from Fig. 4, the route setting unit 101 can determine whether or not the joining condition is satisfied. Note that the joining condition can also be determined using the coefficient of a regression curve or a straight line instead of the correlation coefficient.
[0039] For example, it is possible to determine the combination condition using the correlation coefficient of the feature amount of the driving state. For example, a threshold value can be set for multiple correlation coefficients, and the combination condition can be satisfied when the correlation coefficient exceeds the threshold value. The multiple correlation coefficients may be arbitrarily weighted, and the combination condition may be determined based on the calculated value.
[0040] Another example of determining the joining condition will be described with reference to FIG. 5. The example shown in FIG. 5 is an example of determining the joining condition using cluster analysis. As shown in FIG. 5, the number of stops per unit distance is recorded in each of sections 1, 2, 3, 4, and 5 for trips 1, 2, and 3. The route setting unit 101 determines, for example, whether section 1 and section 2 belong to the same cluster using a known cluster analysis method. If the route setting unit 101 determines that section 1 and section 2 belong to the same cluster, it determines that the joining condition is satisfied, and it joins section 1 and section 2. If the route setting unit 101 determines that section 1 and section 2 do not belong to the same cluster, it determines that the joining condition is not satisfied, and it does not join section 1 and section 2. The route setting unit 101 executes the process for other sections in the same manner.
[0041] Instead of clustering using a single data as shown in FIG. 5, clustering using multiple representative indices of each section acquired by one or multiple driving may be performed. In the example shown in FIG. 6, multiple representative indices such as "number of stops," "average vehicle speed," and "average road gradient" are used. As described with reference to FIG. 5, the route setting unit 101 determines whether or not, for example, section 1 and section 2 belong to the same cluster by a known cluster analysis method. If the route setting unit 101 determines that section 1 and section 2 belong to the same cluster, the route setting unit 101 determines that the joining condition is satisfied, and joins section 1 and section 2. If the route setting unit 101 determines that section 1 and section 2 do not belong to the same cluster, the route setting unit 101 determines that the joining condition is not satisfied, and does not join section 1 and section 2. The route setting unit 101 may determine the joining condition using multiple clustering results.
[0042] 2 again, a description will be given of the information processing flow by the energy prediction device 10. When the travel route division process in step S001 is completed, the process proceeds to step S002. In step S002, the model construction unit 102 constructs a consumption prediction model.
[0043] The model construction unit 102 constructs a consumption prediction model for each segment route. In the example shown in FIG. 3(B), the model construction unit 102 constructs a consumption prediction model for each of segment routes SB1, SB2, SB3, and SB4. In the example shown in FIG. 3(C), the model construction unit 102 constructs a consumption prediction model for each of segment routes SC1 and SC2. The model construction unit 102 may construct a different consumption prediction model for each segment route, or may construct the same consumption prediction model. The model construction unit 102 constructs an appropriate consumption prediction model depending on the situation of each segment route. The model construction unit 102 stores the constructed consumption prediction model in the storage unit 110.
[0044] An example of a consumption prediction model constructed by the model construction unit 102 is a consumption prediction model that directly predicts energy consumption. The explanatory variables of this consumption prediction model use at least one of the weather information, road condition information, date and time information, and driver information acquired by the information acquisition unit 103.
[0045] The weather information includes at least one of the probability of precipitation, the amount of precipitation, and the temperature. The road condition information includes information indicating at least one of information on gradient, information on the location of bus stops, information on the location of intersections, information on road width, information on speed limits, information on the location of traffic lights, information on curve curvature, and information on the degree of congestion. The date and time information includes at least one of time, day of the week, holidays, and season. The driver information includes information indicating driver attributes and characteristics of the driver corresponding to the attributes.
[0046] The objective variable of the consumption prediction model is a variable related to energy consumption. As the variable related to energy consumption, a quantity correlated with the amount of energy consumption is used. Specifically, the variable related to energy consumption is, for example, fuel efficiency, electricity efficiency, change in SOC, change in fuel consumption, and integrated value of inverter current.
[0047] As a modeling method for the consumption prediction model, any regression method can be used, such as linear regression, multiple regression, nonlinear regression, generalized linear model, support vector regression, Gaussian process regression, ensemble method, decision tree, neural network, etc. Figure 9 shows an example using a decision tree. In the example shown in Figure 9, the objective variable is electricity consumption, and the feature quantities used are the time period and the presence or absence of precipitation.
[0048] Regarding the method of learning the consumption prediction model, for example, the influence of each objective variable can be formulated by constructing a linear polynomial such as equation (f01) by multiple regression analysis. In equation (f01), Y is a variable that correlates with energy consumption, and β n is each explanatory variable X n This represents the degree of influence. Y=β 0 +β 1 X 1 +β 2 X 3 +β 3 X 3 +β 4 X 4 +··· (f01)
[0049] Other machine learning methods may be used as a learning method for the consumption prediction model. Methods other than machine learning methods may also be used as a learning method for the consumption prediction model. For example, any formulation method such as adopting a constant value according to the information acquired by the information acquisition unit 103 may be used.
[0050] Another example of the consumption prediction model constructed by the model construction unit 102 is a consumption prediction model that predicts a vehicle speed waveform. In this case, the energy consumption can be calculated from a physical model that takes into account the vehicle weight, the energy efficiency of the drivetrain, the running resistance, and the like stored in the vehicle characteristics storage unit 201, and the predicted vehicle speed waveform.
[0051] When the model construction unit 102 predicts a vehicle speed waveform, at least one of the weather information, road condition information, date and time information, and driver information acquired by the information acquisition unit 103 is used as an explanatory variable.
[0052] The weather information includes at least one of a probability of precipitation, an amount of precipitation, and an air temperature. The road condition information includes information indicating at least one of information on gradient, information on bus stop locations, information on intersection locations, information on road width, information on speed limits, information on traffic light locations, information on curve curvature, and information on congestion level. The date and time information includes at least one of time, day of the week, holidays, and season. The driver information includes information indicating driver attributes and characteristics of the driver corresponding to the attributes.
[0053] The objective variable of the consumption prediction model may be any indicator related to vehicle speed, such as the number of stops, average vehicle speed, or steady-state vehicle speed (vehicle speed from the end of acceleration to the start of deceleration). For example, the model construction unit 102 estimates the number of stops and the steady-state vehicle speed using different prediction models. As shown in FIG. 7, the model construction unit 102 creates a trapezoidal vehicle speed pattern that reflects the estimated number of stops and steady-state vehicle speed. The model construction unit 102 sets the acceleration and deceleration based on the driver information and general vehicle characteristic information. The model construction unit 102 arbitrarily determines the interval between the stop positions so that it falls within the driving distance of one section.
[0054] As a modeling method for the consumption prediction model, any regression method can be used, such as linear regression, multiple regression, nonlinear regression, generalized linear model, support vector regression, Gaussian process regression, ensemble method, decision tree, neural network, etc. Figure 10 shows an example using a decision tree. In the example shown in Figure 10, the objective variable is the average vehicle speed, and the features used are the time period and driver information.
[0055] The model construction unit 102 may prepare a vehicle speed pattern corresponding to the average vehicle speed in advance and create a vehicle speed pattern by selecting a vehicle speed pattern that matches the average vehicle speed. For example, if the average vehicle speed is 10km / h-15km / h, the model construction unit 102 selects a vehicle speed pattern as shown in FIG. 8(A). For example, if the average vehicle speed is 15km / h-25km / h, the model construction unit 102 selects a vehicle speed pattern as shown in FIG. 8(B). For example, if the average vehicle speed is 25km / h-35km / h, the model construction unit 102 selects a vehicle speed pattern as shown in FIG. 8(C). The model construction unit 102 may determine the vehicle speed pattern based on a plurality of vehicle speed index values, such as the number of stops and the average vehicle speed.
[0056] The model construction unit 102 may prepare a plurality of vehicle speed patterns and directly estimate which vehicle speed pattern to adopt from explanatory variables, which are feature quantities, using a classification model. When the model construction unit 102 adopts the classification model, at least one of the weather information, road condition information, date and time information, and driver information acquired by the information acquisition unit 103 is used as the explanatory variable.
[0057] The weather information includes at least one of a probability of precipitation, an amount of precipitation, and an air temperature. The road condition information includes information indicating at least one of information on gradient, information on bus stop locations, information on intersection locations, information on road width, information on speed limits, information on traffic light locations, information on curve curvature, and information on congestion level. The date and time information includes at least one of time, day of the week, holidays, and season. The driver information includes information indicating driver attributes and characteristics of the driver corresponding to the attributes.
[0058] The objective variable of the consumption prediction model is the classification of vehicle speed patterns such as suburban pattern, urban pattern, traffic jam pattern, etc. The modeling methods used for the consumption prediction model include support vector machines, logistic regression, k-nearest neighbor method, neural network, naive Bayes classification, discriminant analysis, and decision tree.
[0059] When the process of step S002 is completed, the process proceeds to step S003. In step S003, the energy prediction unit 104 judges whether or not to directly predict the energy consumption. If the energy consumption is to be directly predicted (step S003: YES), the process proceeds to step S004. If the energy consumption is not to be directly predicted (step S003: NO), the process proceeds to step S005.
[0060] In step S004, the energy prediction unit 104 predicts energy. The energy prediction unit 104 predicts energy consumption for each segmented route using a consumption prediction model (see formula f01) set for each segmented route. The energy prediction unit 104 can convert the objective variable into energy consumption using any formula or map. The energy prediction unit 104 adds up the energy consumption predicted for each segmented route and predicts the energy consumption for the entire travel route.
[0061] In step S005, the energy prediction unit 104 estimates a vehicle speed pattern. The energy prediction unit 104 estimates the vehicle speed pattern using the vehicle speed pattern created by the model construction unit 102 in step S002. If there is no particular additional processing, the energy prediction unit 104 uses the vehicle speed pattern created by the model construction unit 102.
[0062] When the process of step S005 ends, the process proceeds to step S006. In step S006, the energy prediction unit 104 predicts the energy consumption for each segmented route using the vehicle speed pattern V. The energy prediction unit 104 predicts the total energy consumption using, for example, the following formula (f02). Total energy consumption = Driving energy + Air conditioning energy + Other energy (f02)
[0063] The driving energy can be calculated by converting the driving resistance obtained by the following equation (f03) into energy. Rolling resistance = acceleration resistance + air resistance + rolling resistance + gradient resistance (f03)
[0064] Acceleration resistance, air resistance, gradient resistance, and rolling resistance can be calculated as follows: Acceleration resistance: Ma Air resistance: 0.5ρλAV 2 Gradient resistance: Mg sinθ Rolling resistance: μMg M: Vehicle weight A: Front projected area λ: Air resistance coefficient μ: rolling resistance coefficient θ: Road gradient V:Vehicle speed a: acceleration ρ: air density g:Gravity acceleration
[0065] For vehicles with a regenerative function such as electric vehicles and hybrid vehicles, the regenerative energy can be determined so as to correlate with the magnitude of the negative running resistance caused by deceleration. For other energies such as air conditioning energy and auxiliary equipment, a predetermined value may be used, or a value according to the weather or season, such as temperature, may be used.
[0066] [Note] Notes 1 to 7 below can be combined in any way as long as there is no technical contradiction.
[0067] [Appendix 1] The energy prediction device 10 includes: A route setting unit 101 that divides a travel route on which a vehicle travels and sets segmented routes; A model construction unit 102 constructs a consumption prediction model that predicts the energy consumption of a vehicle for each segment of a route; Equipped with.
[0068] According to supplementary note 1, a consumption prediction model is constructed for each segment of a travel route, so that a consumption prediction model that is more suited to the segment of a travel route can be constructed.
[0069] [Appendix 2] The energy prediction device 10 further includes an information acquisition unit 103 that acquires state information related to energy consumption when the vehicle travels along the travel route. The energy prediction device 10 according to claim 1, wherein the route setting unit 101 divides the travel route based on the similarity of the state information and sets segmented routes.
[0070] According to Supplementary Note 2, since the segment route is set based on the similarity of the state information, for example, in a section of the driving route where the state information is not similar and various conditions are mixed, the segment route can be set finely, and the accuracy of the consumption prediction model can be improved. Also, for example, if there are consecutive sections in the driving route where the state information is similar, it is possible to set the segment route longer, which allows the consumption prediction model to be standardized and reduces the calculation load.
[0071] [Appendix 3] The energy prediction device 10 described in Appendix 2, in which the route setting unit 101 pre-divides the driving route to set multiple pre-segment routes, determines a joining condition based on the similarity of state information in each pre-segment route, and sets a segment route by performing a process of joining pre-segment routes that satisfy the joining condition.
[0072] According to Supplementary Note 3, since the combining process is performed by determining the combining condition based on the similarity of the pre-segment routes, it becomes easy to set a segment route that reflects the similarity. Since it is only necessary to go through the process of combining the pre-segment routes that satisfy the combining condition, the segment route in which the pre-segment routes are combined can be regarded as a pre-segment route again to determine the combining condition.
[0073] [Appendix 4] The status information includes at least one of driving status information that specifies the driving status of the vehicle traveling along the driving route, energy status information that specifies the energy required for the vehicle to travel along the driving route, and road status information that specifies the road status of the driving route that affects the energy required for the vehicle to travel. The energy prediction device 10 according to any one of appendices 1 to 3, wherein the route setting unit 101 sets the segment route based on the similarity of at least one piece of information among the driving state information, the energy state information, and the road state information.
[0074] According to Supplementary Note 4, the segment route is set based on the similarity of at least one of the driving state information, the energy state information, and the road state information, so that the segment route can be set to reflect multiple aspects of the driving route.
[0075] [Appendix 5] The energy prediction device 10 according to any one of Appendices 1 to 4, wherein the model construction unit 102 constructs a consumption prediction model as a learning model using explanatory variables and dependent variables, the explanatory variables being at least one of weather information, road conditions, time information, and driver information, and the dependent variables being at least one of an index value related to a vehicle speed pattern and an index value related to energy consumption.
[0076] [Appendix 6] The energy prediction device 10 according to any one of appendices 1 to 5, further comprising an energy prediction unit 104 that predicts the energy consumption for each segment of the route using a consumption prediction model constructed for each segment of the route, and predicts the energy consumption on the travel route.
[0077] [Appendix 7] The energy prediction device 10 according to any one of appendices 1 to 5, further comprising an energy prediction unit 104 that, when the objective variable is an index value related to a vehicle speed pattern, predicts energy consumption based on a vehicle speed pattern generated for each segmented route based on the index value related to the vehicle speed pattern, and predicts energy consumption on the travel route.
[0078] The control unit and the method described in the present disclosure may be realized by a dedicated computer provided by configuring a processor and a memory programmed to execute one or more functions embodied in a computer program. Alternatively, the control unit and the method described in the present disclosure may be realized by a dedicated computer provided by configuring a processor with one or more dedicated hardware logic circuits. Alternatively, the control unit and the method described in the present disclosure may be realized by one or more dedicated computers configured by a combination of a processor and a memory programmed to execute one or more functions and a processor configured with one or more hardware logic circuits. In addition, the computer program may be stored in a computer-readable non-transitory tangible recording medium as instructions executed by a computer.
[0079] The present embodiment has been described above with reference to specific examples. However, the present disclosure is not limited to these specific examples. Any design modifications made by a person skilled in the art to these specific examples are also included within the scope of the present disclosure as long as they have the features of the present disclosure. The elements of each of the above-mentioned specific examples and their arrangements, conditions, shapes, etc. are not limited to those exemplified and can be changed as appropriate. The combination of each of the elements of each of the above-mentioned specific examples can be changed as appropriate as long as no technical contradiction occurs. [Explanation of symbols]
[0080] 10: Energy forecasting device 101: Route setting section 102: Model Construction Department 103: Information acquisition department 104: Energy Prediction Department
Claims
1. A route setting unit (101) for dividing a travel route on which a vehicle travels and setting segmented routes; A model construction unit (102) that constructs a consumption prediction model that predicts the energy consumption of a vehicle for each segment of the route; An energy prediction device comprising:
2. Furthermore, An information acquisition unit (103) that acquires status information regarding energy consumption when the vehicle travels along the travel route, The energy prediction device according to claim 1 , wherein the route setting unit divides the travel route and sets segment routes based on the similarity of the state information.
3. The energy prediction device of claim 2, wherein the route setting unit pre-divides the driving route to set a plurality of pre-division routes, determines a joining condition based on the similarity of the state information in each of the pre-division routes, and sets the division route by performing a process of joining the pre-division routes that satisfy the joining condition.
4. the state information includes at least one of driving state information that specifies a driving state in which the vehicle travels along the driving route, energy state information that specifies an energy required for the vehicle to travel along the driving route, and road state information that specifies a road state that is a state of the driving route and affects the energy required for the vehicle to travel, The path setting unit is The energy prediction device according to claim 1 , wherein the segmented route is set based on a similarity of at least one of the driving state information, the energy state information, and the road state information.
5. The model construction unit constructs the consumption prediction model as a learning model using explanatory variables and objective variables, The explanatory variable is at least one of weather information, road conditions, time information, and driver information; The energy prediction device according to claim 1 , wherein the response variable is at least one of an index value related to a vehicle speed pattern and an index value related to energy consumption.
6. Furthermore, 2. The energy prediction device according to claim 1, further comprising an energy prediction unit (104) that predicts energy consumption for each of the segmented routes by using the consumption prediction model constructed for each of the segmented routes, and predicts energy consumption on the travel route.
7. Furthermore, 2. The energy prediction device according to claim 1, further comprising an energy prediction unit that, when the objective variable is an index value related to the vehicle speed pattern, predicts energy consumption based on the vehicle speed pattern generated for each of the segmented routes based on the index value related to the vehicle speed pattern, and predicts energy consumption on the travel route.
Citation Information
Patent Citations
Energy management device, model management method, and computer program
JP2020027432A
Cited By
Energy consumption prediction method and energy consumption prediction device
WO2026203112A1
