Energy consumption optimization method and electronic equipment for new energy vehicle fleet

Abstract

The present invention relates to the technical field of new energy vehicles, and specifically discloses a method and electronic device for optimizing energy consumption of a new energy vehicle fleet, the method comprising: collecting environmental factors associated with the driving of the vehicle fleet and constructing a condition matrix, and calculating a comprehensive score of the condition matrix; dividing the roads passed by the vehicle fleet into sections based on road characteristics, and defining the influence coefficients of different sections; combining the above condition matrix with road characteristics to design a comprehensive energy consumption model for the sections; obtaining and analyzing the past energy consumption information of the vehicle fleet, and optimizing the above model. The method and electronic device for optimizing energy consumption of a new energy vehicle fleet of an embodiment of the present invention, by real-time judging the driving behavior on the corresponding section, reminds the driver to optimize if it does not meet the optimal driving standard, thereby providing the driver with specific and real-time driving behavior guidance, which helps to improve the overall driving efficiency and energy consumption performance of the vehicle fleet, thereby further reducing operating costs.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicles, and in particular to a method for optimizing energy consumption of a new energy vehicle fleet and an electronic device. Background Art

[0002] New energy logistics vehicles can not only significantly reduce carbon emissions, but also have obvious advantages over traditional fuel vehicles in terms of refueling prices. It is expected that the new energy logistics vehicle market will continue to grow rapidly in the next few years. However, due to the limitations of new energy endurance and refueling, new energy logistics heavy truck fleets are mainly used in fixed route application scenarios, especially in specific environments such as mining areas and ports.

[0003] The energy consumption management methods for new energy fleets currently on the market mainly count the overall energy consumption of the fleet. Although this can be managed in a refined manner, it is difficult to provide effective optimization suggestions to drivers. Single-vehicle energy consumption optimization technologies such as predictive cruise control require high-precision maps, which are expensive, and the update of maps in specific areas is delayed, making it difficult to solve current problems. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the purpose of the present invention is to propose a new energy fleet energy consumption optimization method and an electronic device to optimize the driving behavior of the fleet driver and reduce the energy consumption of the fleet.

[0005] To achieve the above-mentioned purpose, a first embodiment of the present invention proposes a method for optimizing energy consumption of a new energy vehicle fleet, the method comprising:

[0006] Collect environmental factors related to fleet driving and construct a condition matrix, and calculate the comprehensive score of the condition matrix;

[0007] Divide the roads that the convoy passes through into sections based on road characteristics and define the influence coefficients of different sections;

[0008] Combining the above condition matrix with road characteristics, a comprehensive energy consumption model of the road section is designed;

[0009] Obtain and analyze the fleet’s past energy consumption information to optimize the above model;

[0010] Taking road sections as units, driving behavior is evaluated in combination with the optimized comprehensive energy consumption model of road sections;

[0011] The fleet system judges the driving behavior on the corresponding road section in real time. If it does not meet the optimal driving standards, it will send instructions to the driver to remind the driver to optimize.

[0012] In some embodiments of the present invention, the condition matrix includes four dimensions: weather, temperature, time period, and load; , , , Respectively represent different categories of weather, temperature, time period, and load; each category corresponds to a different weight and energy consumption score, among which;

[0013] i∈{1,2,..., }; j∈{1,2,..., }; g∈{1,2,..., };q∈{1,2,..., }.

[0014] In some embodiments of the present invention, the weights of different categories under the above four dimensions and the energy consumption scores are defined according to specific application scenarios, and a comprehensive score of the condition matrix is ​​obtained, wherein the comprehensive score can be calculated by the following formula:

[0015] in, is the comprehensive score; i, j, g, q are the number of categories under the corresponding dimension respectively; , , , are the weights of the corresponding categories respectively; , , , They are the energy consumption scores of the corresponding categories; is an indicator function, when 1 if the value is 0, otherwise it is 0.

[0016] In some embodiments of the present invention, the specific steps of dividing the road passed by the convoy into sections based on road characteristics and defining the influence coefficients of different sections are:

[0017] Use K-means algorithm to cluster roads into K clusters ;

[0018] Road segments r with the same road characteristics are assigned to a cluster , where m∈{1,2,...,K};

[0019] Define an influence coefficient , Represents the corresponding cluster Specific impact of road section r on energy consumption.

[0020] In some embodiments of the present invention, the road section comprehensive energy consumption model can be expressed by the following formula:

[0021]

[0022] in, Indicates driving data related to vehicle energy consumption; , , It is a weight set based on historical data or expert experience to balance the impact of environmental factors, road characteristics and driving data on energy consumption.

[0023] In some embodiments of the present invention, the step of obtaining and analyzing the past energy consumption information of the fleet and optimizing the comprehensive energy consumption model of the road section includes:

[0024] The first step is to obtain the energy consumption data of the vehicles in the fleet passing through each road section from the fleet system;

[0025] The second step is to pre-process the collected energy consumption data;

[0026] The third step is to input the pre-processed energy consumption data into the above-mentioned comprehensive energy consumption model of the road section to obtain the energy consumption prediction results of each road section under different environmental factors;

[0027] The fourth step is to compare the model prediction results with the actual energy consumption data;

[0028] The fifth step is to adjust the relevant parameters in the model according to the comparison results to optimize the above model.

[0029] In some embodiments of the present invention, the step of evaluating the driving behavior includes:

[0030] Taking road sections as units, the number of trips of vehicles that the fleet has driven on the road section in the past is sorted according to energy consumption. The vehicle trips with lower energy consumption are ranked higher.

[0031] The top 10% of vehicle trips in terms of energy consumption on the road section under the corresponding environmental factors are selected, and the driving data of the corresponding vehicle trips are extracted and input into the optimized comprehensive energy consumption model of the road section. The association rule learning algorithm Apriori is used to find driving behaviors associated with low energy consumption.

[0032] The energy consumption prediction results obtained from the comprehensive energy consumption model of the road section are compared with the optimal energy consumption data of low-energy vehicle trips under the same road section and the same environmental factors to form the optimal driving standard for the corresponding road section and the corresponding environmental factors. Based on this standard, driving behavior is divided into good driving behavior and bad driving behavior.

[0033] In some embodiments of the present invention, for the vehicle trip with the lowest energy consumption performance, when the low-energy consumption vehicle trip involves multiple different environmental factors;

[0034] Calculate the ratio of the distance traveled under each condition to the total distance of the entire trip, and select the environmental factor with the highest ratio.

[0035] In some embodiments of the present invention, the specific steps of the fleet system determining the driving behavior on the corresponding road section in real time include:

[0036] When the convoy drives to the corresponding road section, it determines whether the driving behavior of the vehicles in the current convoy meets the optimal driving standard under the same environmental factors;

[0037] If the driving behavior meets or exceeds the current optimal driving standard, the fleet system will record the corresponding driving behavior and replace the stored optimal driving standard after iterative updates;

[0038] If it does not meet the requirements, the fleet system will push the optimal driving standard instructions to the vehicle computer or mobile phone APP, reminding the corresponding vehicle driver to take corresponding actions according to the instructions.

[0039] To achieve the above-mentioned purpose, a second aspect of the present invention proposes an electronic device, including a memory, a processor and a computer program stored on the memory. When the computer program is executed by the processor, the above-mentioned new energy vehicle fleet energy consumption optimization method is implemented.

[0040] Beneficial effects of the embodiments of the present invention:

[0041] The energy consumption optimization method and electronic device of the new energy vehicle fleet of the embodiment of the present invention can provide specific and real-time driving behavior guidance to the driver by judging the driving behavior on the corresponding road section in real time, and reminding the driver to optimize if it does not meet the optimal driving standard, thereby helping to improve the overall driving efficiency and energy consumption performance of the fleet, thereby further reducing operating costs. Moreover, this method does not need to rely on high-precision maps, but builds and optimizes the energy consumption model based on the actual conditions and road characteristics of the fleet's driving. It is low-cost, has strong adaptability and flexibility, and can adapt to changes in different regions and road conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of a method for optimizing energy consumption of a new energy vehicle fleet according to an embodiment of the present invention;

[0043] Figure 2 It is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0045] The following describes the energy consumption optimization method and electronic device for a new energy vehicle fleet according to an embodiment of the present invention with reference to the accompanying drawings.

[0046] Figure 1 It is a flow chart of a method for optimizing energy consumption of a new energy vehicle fleet according to an embodiment of the present invention.

[0047] like Figure 1 As shown in the figure, the energy consumption optimization methods of new energy vehicle fleets include:

[0048] S1. Collect environmental factors related to fleet driving and construct a condition matrix, and calculate the comprehensive score of the condition matrix.

[0049] It should be noted that there are many types of environmental factors associated with fleet driving, including: wind speed, humidity, traffic conditions, driver fatigue, weather, temperature, time period and load, etc. In this embodiment, the four most important dimensions of weather, temperature, time period and load are locked in as environmental factors to construct a conditional matrix.

[0050] S2. Divide the roads that the convoy passes through into sections based on road characteristics, and define the influence coefficients of different sections.

[0051] As an example, the above-mentioned road characteristics include characteristic data such as road slope, curvature, road surface type, traffic flow, number of forks, etc., which can be obtained through a GIS system, a traffic monitoring center or a vehicle-mounted sensor.

[0052] S3. Combining the above condition matrix with road characteristics, design a comprehensive energy consumption model for the road section.

[0053] It is worth noting that the comprehensive energy consumption model of road sections includes condition matrix, road characteristics and driving data. The condition matrix provides external environmental factors that affect the energy consumption of the fleet, while the road section division based on road characteristics focuses on the specific road conditions during vehicle driving. Driving data includes driving settings related to vehicle energy consumption, such as initial velocity, acceleration, gear selection, etc. The three together constitute a complete set of factors that affect the energy consumption of new energy fleets.

[0054] S4. Obtain and analyze the past energy consumption information of the fleet to optimize the above model. The past energy consumption information provides energy consumption data in actual operation, which can be used to verify the accuracy and reliability of the model prediction.

[0055] By comparing the model prediction results with the actual energy consumption data, deviations or deficiencies in the model can be discovered, so that calibration and optimization can be performed. And by introducing more actual data, the model can learn more energy consumption characteristics and patterns, thereby improving its generalization ability. This means that when the model faces new road sections and conditions, it can make more accurate energy consumption predictions and optimization suggestions.

[0056] As an example, the specific steps of obtaining and analyzing the past energy consumption information of the fleet and optimizing the comprehensive energy consumption model of the road section include:

[0057] S41. Obtain energy consumption data of vehicles in the fleet passing through various road sections from the fleet system, including location, speed, mileage, SOC status, current, voltage, load, weather, temperature, time period, etc.;

[0058] S42, preprocessing the collected energy consumption data;

[0059] S43, inputting the pre-processed energy consumption data into the above-mentioned road section comprehensive energy consumption model to obtain energy consumption prediction results of each road section under different environmental factors;

[0060] S44, comparing the model prediction results with the actual energy consumption data to evaluate the accuracy and reliability of the model;

[0061] S45. According to the comparison results, relevant parameters in the model, such as weights, scores, etc., are adjusted to optimize the above model so that the model prediction results are closer to the actual energy consumption data;

[0062] S5. Evaluate driving behavior based on road sections and the optimized comprehensive energy consumption model of road sections.

[0063] As an example, the specific steps of evaluating driving behavior include:

[0064] S51, taking a road section as a unit, sorting the trips of vehicles of the fleet that have traveled on the road section in the past according to energy consumption, and the trips of vehicles with lower energy consumption are ranked higher;

[0065] It should be noted that for abnormally high or low energy consumption data, data cleaning and verification are required to avoid interference from erroneous data. In addition, other indicators related to energy consumption (such as driving time, mileage, etc.) can also be considered for comprehensive ranking to more comprehensively reflect the pros and cons of driving behavior.

[0066] S52, selecting the top 10% of vehicle trips in energy consumption on the road section under corresponding environmental factors, extracting the driving data of the corresponding vehicle trips and inputting them into the optimized comprehensive energy consumption model of the road section, and using the association rule learning algorithm Apriori to find driving behaviors associated with low energy consumption. The association rule learning algorithm Apriori is a classic data mining algorithm used to find interesting associations or correlations between items in a transaction data set;

[0067] S53. Comparing the energy consumption prediction results obtained from the comprehensive energy consumption model of the road section with the optimal energy consumption data of the low-energy vehicle trips under the same road section and the same environmental factors can determine whether the driver's driving behavior is efficient and energy-saving, and form the optimal driving standard for the corresponding road section and the corresponding environmental factors. Based on this standard, the driving behavior is divided into good driving behavior and bad driving behavior.

[0068] S6. The fleet system determines the driving behavior on the corresponding road section in real time. If it does not meet the optimal driving standards, it will issue instructions to the driver to remind the driver to optimize.

[0069] This new energy fleet energy consumption optimization method judges the driving behavior on the corresponding road section in real time, and reminds the driver to optimize if it does not meet the optimal driving standard, thereby providing the driver with specific and real-time driving behavior guidance, which helps to improve the overall driving efficiency and energy consumption performance of the fleet, thereby further reducing operating costs. In addition, this method does not need to rely on high-precision maps, but builds and optimizes the energy consumption model based on the actual conditions and road characteristics of the fleet. It is low-cost, has strong adaptability and flexibility, and can adapt to changes in different regions and road conditions.

[0070] In some embodiments of the present invention, the condition matrix includes four dimensions: weather, temperature, time period, and load. Since different dimensions can be subdivided into multiple categories, different categories have different effects on the driving of the fleet. , , , They represent different categories of weather, temperature, time period, and load respectively; and each category corresponds to a different weight and energy consumption score, among which;

[0071] i∈{1,2,..., }; j∈{1,2,..., }; g∈{1,2,..., };q∈{1,2,..., }.

[0072] As an example, weather can be divided into five categories, including sunny, cloudy, rainy, foggy, and snowy;

[0073] Temperature can be divided into three categories, including suitable temperature, high temperature and low temperature;

[0074] The time periods can be divided into four categories, including early morning, morning, afternoon, and night;

[0075] Load can be divided into two categories, including empty and fully loaded.

[0076] As another example, when actually setting the conditional matrix, it is also necessary to set weights and energy consumption scores for different categories in the above different dimensions;

[0077] The weight setting depends on the specific application scenario and data analysis:

[0078] ① If the fleet operates mainly in high and low temperature environments, and these conditions have a significant impact on energy consumption, then the weight of temperature needs to be set higher;

[0079] ② If the fleet mainly travels in environments prone to extreme weather, and the weather has a great impact on energy consumption, the weight of the weather should be increased accordingly.

[0080] The energy consumption score can be set according to the actual situation, with different scoring values ​​for different categories under different dimensions, as shown in the following table:

[0081]

[0082] In the above ratings, the impact of weather on the driving of the fleet is taken into account, and there are five levels from the best to the worst. According to the impact of temperature on vehicle energy consumption, the temperature can be divided into three categories: suitable temperature, such as 15-25°C, is scored as 3; high temperature, such as >30°C, is scored as 2; low temperature, such as <5°C, is scored as 3. This setting is because new energy vehicles have a greater impact on energy consumption when driving in a low temperature environment. Taking into account the different lighting conditions in different time periods, the time periods are divided into four levels. Finally, the load is divided into two categories according to the actual load: empty, scored 2; fully loaded, scored 1.

[0083] In some embodiments of the present invention, the weights and energy consumption scores of different categories under the above four dimensions are defined according to specific application scenarios, and the comprehensive score of the condition matrix is ​​calculated according to the weights and energy consumption scores. The comprehensive score reflects the comprehensive evaluation result of the energy consumption of the new energy vehicle fleet under the current conditions. The higher the score, the lower the energy consumption of the vehicle under the conditions. The comprehensive score can be calculated by the following formula:

[0084]

[0085] in, is the comprehensive score; i, j, g, q are the number of categories under the corresponding dimension respectively; , , , are the weights of the corresponding categories respectively; , , , They are the energy consumption scores of the corresponding categories; is an indicator function, when 1 if the value is 0, otherwise it is 0.

[0086] It should be noted that in this new energy fleet energy consumption optimization method, the above indicator function can be used to determine whether the weather or time period under a certain road section meets the pre-set standards, and adjust the score accordingly. If the external conditions meet the standards, the indicator function returns true (or 1), otherwise it returns false (or 0). In this way, the score can be dynamically adjusted according to the return value of the indicator function, so as to more accurately evaluate the pros and cons of driving behavior.

[0087] In some embodiments of the present invention, the specific steps of dividing the road that the convoy passes through into sections based on road characteristics and defining the influence coefficients of different sections are:

[0088] S21. Use K-means algorithm to cluster roads into K clusters ;

[0089] S22, road segments r with the same road characteristics are assigned to a cluster , where m∈{1,2,...,K};

[0090] S23. Define an influence coefficient , Represents the corresponding cluster Specific impact of road section r on energy consumption.

[0091] In some embodiments of the present invention, the comprehensive energy consumption model of a road section can be expressed by the following formula:

[0092]

[0093] in, Indicates driving data related to vehicle energy consumption; , , It is a weight set based on historical data or expert experience to balance the impact of environmental factors, road characteristics and driving data on energy consumption.

[0094] The above step S42 is further refined, and the steps of pre-processing the collected past energy consumption data of the fleet include:

[0095] S421. Clean the collected data to remove duplicate, abnormal and erroneous data;

[0096] S422. Standardize the data to eliminate the influence of dimensions and units, so that different data are comparable;

[0097] S423. Classify and organize the data according to road sections and environmental factors to facilitate subsequent analysis.

[0098] The above step S52 is further refined, and the steps of using the association rule learning algorithm Apriori to discover driving behaviors associated with low energy consumption include:

[0099] S521, taking the driving data and energy consumption data of the vehicle trip as items in the transaction database, each vehicle trip can be regarded as a transaction, including a set of driving behavior and energy consumption items;

[0100] S522, using the Apriori algorithm to mine frequent item sets. In driving behavior analysis, frequent item sets represent common driving behavior patterns.

[0101] S523. Generate association rules based on frequent item sets. Association rules represent the correlation between items, that is, if a certain item (or item set) appears, the probability that another item (or item set) may also appear. In driving behavior analysis, association rules can reveal which driving behaviors are associated with low energy consumption;

[0102] S524. Filter out those rules with high confidence and support to ensure their reliability and effectiveness in practical applications. At the same time, the rules need to be verified to ensure their applicability in different environments and conditions.

[0103] By applying the Apriori algorithm, we can mine driving behavior patterns associated with low energy consumption from a large amount of driving data, thereby providing drivers with specific optimization suggestions and guidance. For example, on a uniform speed section, determine the best gear and speed range; on a non-uniform speed section, clarify the acceleration and deceleration range and the appropriate gear. These driving behaviors are conducive to reducing vehicle energy consumption; while sudden acceleration, frequent braking, and speeding, these driving behaviors may lead to increased vehicle energy consumption. These suggestions can help drivers better control the vehicle in actual driving, reduce energy consumption, and improve overall operational efficiency.

[0104] As an example, for some vehicle trips with the lowest energy consumption performance, when the low-energy vehicle trip involves multiple different environmental factors, such as the vehicle trip may pass through different weather areas, it is necessary to calculate the proportion of the distance traveled in each weather area to the total distance of the entire trip. This ratio reflects the time or distance the vehicle travels under different weather conditions, thereby helping to determine which weather condition has a greater impact on energy consumption. The weather condition with the highest proportion is selected, which is most likely to have a decisive impact on low-energy driving behavior, and should therefore be given priority in subsequent energy consumption optimization strategies.

[0105] This new energy fleet energy consumption optimization method not only considers the general influence of external environmental factors and road characteristics when optimizing energy consumption, but also goes deep into the details of specific trips to identify those specific conditions that play a key role in low-energy consumption performance, thereby more accurately guiding the driver to adopt the optimal driving behavior under different conditions, thereby achieving further reduction in energy consumption.

[0106] To further refine the above step S6, the specific steps for the fleet system to judge the driving behavior on the corresponding road section in real time include:

[0107] S61, the convoy drives to the corresponding road section, and under the same environmental factors, determines whether the driving behavior of the vehicles in the current convoy meets the optimal driving standard;

[0108] S62: If the driving behavior meets or exceeds the current optimal driving standard, the fleet system will record the corresponding driving behavior and replace the stored optimal driving standard after iterative update;

[0109] S63. If it does not meet the requirements, the fleet system will push the optimal driving standard instructions to the vehicle computer or mobile phone APP, reminding the corresponding vehicle driver to take corresponding actions according to the instructions to ensure that the driver's driving behavior reaches the optimal state, thereby having a practical and feasible execution effect and effectively improving the energy consumption of the fleet.

[0110] It should be noted that the comprehensive energy consumption model of the road section in this embodiment processes the collected data at a fixed time period in a certain period (such as one week). After the processing is completed, it is iteratively updated. The update content includes: if the energy-saving driving behavior under the same environmental factors on the same road section is better than the stored data, it is directly replaced; and for the update of the road section, since the change of the road section is a low-frequency event, especially in specific environments such as mining areas and ports, it is only re-divided when the road changes.

[0111] As an example, this embodiment can also introduce a driver feedback and reward mechanism. A driver feedback mechanism for the road section is established to collect the driver's opinions and suggestions on the road section energy consumption, driving difficulty, etc., and the model is further optimized and adjusted based on the driver's feedback. At the same time, a driving reward mechanism is established to reward drivers with good performance. The reward mechanism encourages drivers to adopt energy-saving driving behaviors and improve the overall energy consumption level of the fleet.

[0112] Through the above steps, we can make full use of the energy consumption information of the fleet passing through the corresponding road section in the past, optimize the comprehensive energy consumption model of the road section, improve the accuracy and reliability of the model, and provide strong support for driving behavior optimization.

[0113] Corresponding to the above method, the present invention also provides an electronic device.

[0114] like Figure 2 The figure shows a schematic diagram of the structure of an electronic device in the present invention, where the electronic device 200 includes: a processor 201 and a memory 203. The processor 201 and the memory 203 are connected, such as through a bus 202. Optionally, the electronic device 200 may further include a transceiver 204. It should be noted that in actual applications, the transceiver 204 is not limited to one, and the structure of the electronic device 200 does not constitute a limitation on the embodiments of the present invention.

[0115] The processor 201 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. The processor 201 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0116] The bus 202 may include a path to transmit information between the above components. The bus 202 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 202 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0117] The memory 203 is used to store a computer program corresponding to the new energy vehicle fleet energy consumption optimization method of the above embodiment of the present invention, and the computer program is controlled and executed by the processor 201. The processor 201 is used to execute the computer program stored in the memory 203 to implement the content shown in the above method embodiment.

[0118] The electronic device 200 includes, but is not limited to, mobile terminals such as laptop computers, PADs (tablet computers), and fixed terminals such as desktop computers. Figure 2 The electronic device 200 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0119] The electronic device 200 of the embodiment of the present invention can judge the driving behavior on the corresponding road section in real time, and remind the driver to optimize if it does not meet the optimal driving standard, thereby providing the driver with specific and real-time driving behavior guidance, which helps to improve the overall driving efficiency and energy consumption performance of the fleet, thereby further reducing operating costs. Moreover, this method does not need to rely on high-precision maps, but builds and optimizes the energy consumption model based on the actual conditions and road characteristics of the fleet's driving. It has low cost, strong adaptability and flexibility, and can adapt to changes in different regions and road conditions.

[0120] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0121] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0122] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0123] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0124] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for optimizing energy consumption of a new energy vehicle fleet, characterized in that: The method comprises: Collect environmental factors related to fleet driving and construct a condition matrix, and calculate the comprehensive score of the condition matrix; The condition matrix includes four dimensions: weather, temperature, time period, and load; , , , Respectively represent different categories of weather, temperature, time period, and load; each category corresponds to a different weight and energy consumption score, among which; i∈{1,2,..., };j∈{1,2,..., };g∈{1,2,..., };q∈{1,2,..., }; Define the weights and energy consumption scores of different categories under the above four dimensions according to the specific application scenarios, and obtain the comprehensive score of the condition matrix. The comprehensive score can be calculated by the following formula: in, is the comprehensive score; i, j, g, q are the number of categories under the corresponding dimension respectively; , , , are the weights of the corresponding categories respectively; , , , They are the energy consumption scores of the corresponding categories; is an indicator function, when 1 when it is, otherwise 0; Divide the roads that the convoy passes through into sections based on road characteristics and define the influence coefficients of different sections; Combining the above condition matrix with road characteristics, a comprehensive energy consumption model of the road section is designed; Obtain and analyze the fleet’s past energy consumption information to optimize the above model; Taking road sections as units, driving behavior is evaluated in combination with the optimized comprehensive energy consumption model of road sections; The steps in assessing driving behavior include: Taking road sections as units, the number of trips of vehicles that the fleet has driven on the road section in the past is sorted according to energy consumption. The vehicle trips with lower energy consumption are ranked higher. The top 10% of vehicle trips in terms of energy consumption on the road section under the corresponding environmental factors are selected, and the driving data of the corresponding vehicle trips are extracted and input into the optimized comprehensive energy consumption model of the road section. The association rule learning algorithm Apriori is used to find driving behaviors associated with low energy consumption. The energy consumption prediction results obtained by the comprehensive energy consumption model of the road section are compared with the optimal energy consumption data of the low-energy consumption vehicle trips under the same road section and the same environmental factors, so as to form the optimal driving standard under the corresponding road section and the corresponding environmental factors, and the driving behavior is divided into good driving behavior and bad driving behavior according to the standard; For the vehicle trip with the lowest energy consumption performance, when the low-energy consumption vehicle trip involves multiple different environmental factors, calculate the proportion of the distance traveled under each condition to the total distance of the entire trip, and select the environmental factor with the highest proportion; The fleet system judges the driving behavior on the corresponding road section in real time. If it does not meet the optimal driving standards, it will send instructions to the driver to remind the driver to optimize.

2. The method for optimizing energy consumption of a new energy vehicle fleet according to claim 1, characterized in that: The specific steps of dividing the road that the convoy passes through into sections based on road characteristics and defining the influence coefficients of different sections are as follows: Use K-means algorithm to cluster roads into K clusters ; Road segments r with the same road characteristics are assigned to a cluster , where m∈{1,2,...,K}; Define an influence coefficient , Represents the corresponding cluster Specific impact of road section r on energy consumption.

3. The method for optimizing energy consumption of a new energy vehicle fleet according to claim 2, characterized in that: The comprehensive energy consumption model of the road section can be expressed by the following formula: in, Indicates driving data related to vehicle energy consumption; , , It is a weight set based on historical data or expert experience to balance the impact of environmental factors, road characteristics and driving data on energy consumption.

4. The method for optimizing energy consumption of a new energy vehicle fleet according to claim 1, characterized in that: The steps of obtaining and analyzing the past energy consumption information of the fleet and optimizing the comprehensive energy consumption model of the road section include: The first step is to obtain the energy consumption data of the vehicles in the fleet passing through each road section from the fleet system; The second step is to pre-process the collected energy consumption data; The third step is to input the pre-processed energy consumption data into the above-mentioned comprehensive energy consumption model of the road section to obtain the energy consumption prediction results of each road section under different environmental factors; The fourth step is to compare the model prediction results with the actual energy consumption data; The fifth step is to adjust the relevant parameters in the model according to the comparison results to optimize the above model.

5. The method for optimizing energy consumption of a new energy vehicle fleet according to claim 1, characterized in that: The specific steps of the fleet system for real-time judging the driving behavior on the corresponding road section include: When the convoy drives to the corresponding road section, it determines whether the driving behavior of the vehicles in the current convoy meets the optimal driving standard under the same environmental factors; If the driving behavior meets or exceeds the current optimal driving standard, the fleet system will record the corresponding driving behavior and replace the stored optimal driving standard after iterative updates; If it does not meet the requirements, the fleet system will push the optimal driving standard instructions to the vehicle computer or mobile phone APP, reminding the corresponding vehicle driver to take corresponding actions according to the instructions.

6. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory. When the computer program is executed by the processor, the method for optimizing energy consumption of a new energy vehicle fleet as described in any one of claims 1 to 5 is implemented.

Images