Vehicle energy-saving prediction method, system and device based on vehicle networking data analysis

Abstract

The present invention provides a vehicle energy-saving prediction method, system and device based on vehicle network data analysis, the system comprising a data acquisition module, a data preprocessing module, a driving behavior diagnosis module and an energy-saving prediction module; the method comprising the following steps: S1: collecting vehicle operation data; S2: preprocessing the collected vehicle operation data; S3: detecting and evaluating the preprocessed vehicle operation data to determine whether there is bad driving behavior; S4: calculating the energy consumption saving amount when the bad driving behavior is corrected to an energy-saving operation state; S5: outputting an energy-saving warning; the method of the present invention improves the accuracy of driving behavior diagnosis; at the same time, the driver receives the output actual value of the energy consumption saving amount and the energy-saving warning, and takes the actual value of the energy consumption saving amount as a driving guide, which is conducive to promoting the driver to change his driving habits, concentrate on driving, actively learn, and reduce fuel expenditure.

Description

Technical Field

[0001] The present invention relates to the field of energy-saving technology, and in particular to a vehicle energy-saving prediction method, system and device based on vehicle networking data analysis. Background Art

[0002] In the automotive industry, energy conservation and emission reduction is a topic that continues to be explored in depth. There are many ways to save energy in vehicles, which are mainly achieved through continuous upgrades in vehicle design, manufacturing and use. Among them, vehicle design and manufacturing include lightweight, low rolling resistance, low wind resistance, high-efficiency engines, high-efficiency transmission systems, and improved production consistency; vehicle use and maintenance include improved driving habits, reasonable and standardized maintenance, and improved management level.

[0003] However, the energy consumption performance of the same vehicle under the same usage scenario often varies greatly when driven by different drivers, which is mainly caused by the driver's driving habits or driving intentions. To solve this problem, existing OEMs and research institutions have conducted a lot of research on driving behavior and launched various driving guidance products to score and evaluate drivers of different driving levels. However, there are still the following disadvantages:

[0004] 1. Although the existing technology can score and evaluate drivers of different driving levels, the effect of use is often limited, and the accuracy of driving behavior diagnosis is not high, which affects the evaluation results and is not conducive to promoting drivers to change their driving habits;

[0005] 2. It cannot provide power guidance to the driver, and it is difficult to attract the driver to change the driving habits formed over the years. Summary of the invention

[0006] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a vehicle energy-saving prediction method, system and device based on vehicle networking data analysis.

[0007] To achieve the above object, the present invention adopts the following technical solutions:

[0008] The vehicle energy-saving prediction system based on Internet of Vehicles data analysis includes a data acquisition module, a data preprocessing module, a driving behavior diagnosis module and an energy-saving prediction module;

[0009] The data collection module is used to continuously collect vehicle operation data in units of trips or days, and the collected vehicle operation data includes collection time point, vehicle operation speed, vehicle operation speed, vehicle acceleration, gear position, engine torque, throttle opening, brake, water temperature, fuel consumption, altitude, etc.;

[0010] The data preprocessing module is used to preprocess the collected vehicle operation data and remove abnormal data;

[0011] The driving behavior diagnosis module is used to monitor and evaluate bad driving behavior;

[0012] The energy-saving prediction module is used to predict and evaluate the energy consumption savings.

[0013] Specifically, the vehicle energy saving prediction method based on vehicle networking data analysis includes the following steps:

[0014] S1: Collect vehicle operation data;

[0015] The data collection module continuously collects vehicle operation data based on the trip or day according to actual needs through the big data cluster server. The collection frequency is 1HZ, that is, a set of vehicle operation data is collected every second;

[0016] The collected vehicle operation data includes time point, vehicle operation speed, vehicle operation speed, vehicle acceleration, gear position, engine torque, throttle opening, brake, water temperature, fuel consumption, altitude, etc.

[0017] S2: pre-processing the collected vehicle operation data;

[0018] The data preprocessing module cleans the collected vehicle operation data and identifies and removes abnormal data.

[0019] S3: Detect and evaluate the pre-processed vehicle operation data to determine whether there is any bad driving behavior;

[0020] The driving behavior diagnosis module detects and evaluates the pre-processed vehicle operation data to determine whether the driver has bad driving behavior, which includes over-economic speed behavior, over-economic speed behavior, unreasonable gear shifting behavior, improper braking behavior, and unreasonable idling behavior;

[0021] The following sub-steps are included:

[0022] S31: Determine whether the driver has exceeded the economic speed limit;

[0023] Engineers analyze the actual vehicle power train and specific customer vehicle usage data, and obtain the corresponding wheel radius r, rear axle speed ratio i0, and gearbox speed ratio ig from the vehicle usage data;

[0024] Calculate the maximum and minimum speeds of the vehicle according to the following formula;

[0025] V = 0.377*speed n*wheel radius r / rear axle speed ratio i0 / gearbox speed ratio ig;

[0026] Among them, V is the vehicle speed, and the speed n is obtained by the data acquisition module. During the driving process of the same vehicle, the speed n, the rear axle speed ratio i0, and the gearbox speed ratio ig are variables. According to the specific values ​​of the variables, the maximum speed and the minimum speed of the vehicle are calculated by the above formula;

[0027] Engineers determine the super-economic speed threshold V1 based on the calculated maximum and minimum speeds of the vehicle and the actual vehicle speed limit, and set the super-economic speed behavior standard: the continuous driving time is greater than T1 under the conditions that the vehicle running speed is greater than V1 and the accelerator pedal position is greater than A1; A1 and T1 are preset values;

[0028] The collected vehicle operation data is compared with the set super-economic speed behavior standard. If the vehicle operation data includes driving data that meets the super-economic speed behavior standard, the driver has super-economic speed behavior;

[0029] Collecting driving data that meets the super-economic speed behavior standard, including super-economic speed behavior mileage, super-economic speed behavior fuel consumption Y11, super-economic speed behavior average speed V11, etc.;

[0030] S32: determining whether the driver has exceeded the economic speed limit;

[0031] Engineers analyze the actual economic speed of the vehicle engine and determine the super-economic speed threshold R2 based on the specific road slope conditions, and set the super-economic speed behavior standard: the continuous driving time is greater than T2 under the conditions that the vehicle running speed is greater than R2, the vehicle running speed is greater than V2, and the engine torque is greater than N2; V2, N2, and T2 are preset values;

[0032] Compare the collected vehicle operation data with the set super-economic speed behavior standard. If the vehicle operation data includes driving data that meets the super-economic speed behavior standard, the driver has super-economic speed behavior.

[0033] Counting driving data that meets the super-economic speed behavior standard, including the driving mileage of super-economic speed behavior, the driving fuel consumption Y21 of super-economic speed behavior, the average speed R21 of super-economic speed behavior, etc.;

[0034] S33: Determine whether the driver has unreasonable gear shifting behavior;

[0035] Engineers analyzed the actual vehicle gear shifting data and combined it with the specific gear shifting logic of the vehicle transmission to set the unreasonable gear shifting behavior standard: the vehicle running speed is greater than V3, and the driving time from the current gear to the gear one gear higher and then switching back to the current gear is less than T3; V3 and T3 are preset values;

[0036] The collected vehicle operation data is compared with the set unreasonable shifting behavior standard. If the driving data in the vehicle operation data meets the unreasonable shifting behavior standard, the driver has unreasonable shifting behavior;

[0037] Counting driving data that meets the unreasonable shifting behavior standard, including the average vehicle speed V31 of the unreasonable shifting behavior, the number of shifts F31 of the unreasonable shifting behavior, etc.; wherein V31 and F31 are preset values;

[0038] S34: Determine whether the driver has improper braking behavior;

[0039] Engineers analyze the actual braking force of the driver when the vehicle is running and combine the specific logical relationship between braking and acceleration to set the standard for improper braking behavior: the vehicle speed is greater than V4, and the driving time from no braking to the deceleration greater than S4 when braking is less than T4; V4, S4, and T4 are preset values;

[0040] The collected vehicle operation data is compared with the set improper braking behavior standard. If the driving data in the vehicle operation data meets the improper braking behavior standard, the driver has improper braking behavior; wherein the deceleration in the vehicle operation data is converted from the collected acceleration;

[0041] Counting driving data that meets the improper braking behavior standard, including the average vehicle speed V41 of the improper braking behavior and the number of braking times F41 of the improper braking behavior;

[0042] S35: Determine whether the driver has unreasonable idling behavior;

[0043] Engineers set unreasonable idling behavior standards by analyzing the actual vehicle operating status: the continuous driving time is greater than T5 under the conditions that the vehicle operating speed is less than V5, the vehicle operating speed is within the range [R51, R52], the throttle opening is less than A5, and the water temperature is greater than P5; V5, R51, R52, A5, P5, and T5 are preset values;

[0044] Compare the collected vehicle operation data with the set unreasonable idling behavior standard. If the vehicle operation data contains driving data that meets the unreasonable idling behavior standard, the driver has unreasonable idling behavior.

[0045] The driving data that meets the unreasonable idling behavior standards are counted, including the fuel consumption Y51 of the unreasonable idling behavior, the total mileage M51, etc.

[0046] S4: Calculate the energy saving amount of correcting the bad driving behavior to an energy-saving operation state;

[0047] The energy-saving prediction module evaluates the energy savings of correcting the bad driving behavior to an energy-saving operating state, including the following sub-steps:

[0048] S41: Calculate the energy saving amount of controlling the ultra-economical vehicle speed behavior to a reasonable vehicle speed range;

[0049] Control the super-economical speed behavior within a reasonable speed range, and estimate the energy saving E1 through the dynamics and energy consumption calculation model;

[0050] The energy saving amount E1=variable A11*(average vehicle speed V11 of super-economic vehicle speed behavior-super-economic vehicle speed threshold V1)*traveling fuel consumption Y11 of super-economic vehicle speed behavior;

[0051] Among them, variable A11 is obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles;

[0052] S42: Calculate the energy saving amount of controlling the ultra-economic speed behavior to a reasonable speed range;

[0053] Control the super-economic speed behavior within a reasonable speed range, and estimate the energy saving E2 through the dynamics and energy consumption calculation model;

[0054] The energy saving amount E2 = variable A21*(average speed R21 of super-economic speed behavior-super-economic speed threshold R2)*traveling fuel consumption Y21 of super-economic speed behavior;

[0055] Among them, variable A21 is obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles;

[0056] S43: Calculating the energy saving amount of controlling the unreasonable gear shifting behavior to a reasonable gear shifting range;

[0057] Control unreasonable shifting behavior to a reasonable shifting range, and estimate the energy saving E3 through dynamics and energy consumption calculation models;

[0058] The energy saving amount E3=(variable A31*average vehicle speed V31 of unreasonable gear shifting behavior-variable A32) / 100*number of gear shifting times F31 of unreasonable gear shifting behavior;

[0059] Among them, variables A31 and A32 are obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles;

[0060] S44: Calculate the energy saving amount by controlling the improper braking behavior to a reasonable braking range;

[0061] Control improper braking behavior within a reasonable braking range and estimate energy savings E4 through dynamics and energy consumption calculation models;

[0062] The energy saving amount E4=(variable A41*average vehicle speed V41 of improper braking behavior-variable A42) / 100*number of braking times F41 of improper braking behavior;

[0063] Among them, variables A41 and A42 are obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles;

[0064] S45: Calculating the energy saving amount of controlling the unreasonable idling behavior to a reasonable idling behavior range;

[0065] Control unreasonable idling behavior to the range of reasonable idling behavior, and estimate the energy saving E5 based on seasonal climate changes and the standard idling level of similar vehicles;

[0066] The energy saving amount E5=(fuel consumption of unreasonable idling behavior Y51-total mileage M51 / seasonal climate change parameter A51), wherein the seasonal climate change parameter A51 is obtained by calculating a large amount of data through simulating user data of the Internet of Vehicles.

[0067] S5: Output energy-saving warning;

[0068] The engineer sets five energy saving thresholds and a total energy saving threshold in advance, and compares the five actual energy saving values ​​calculated in step S4 with the set energy saving thresholds. If any actual energy saving value exceeds or does not reach the set energy saving threshold, it is determined whether the energy saving threshold needs to be adjusted according to the actual situation, and finally outputs the actual energy saving value and issues an energy-saving warning.

[0069] Calculate the sum of the actual values ​​of the five energy savings, compare it with the set total energy savings threshold, determine whether the total energy savings threshold needs to be adjusted based on the actual situation, and finally output the sum of the actual energy savings and issue an energy-saving warning;

[0070] The driver receives energy-saving warnings and adjusts his driving behavior.

[0071] The threshold is continuously adjusted and updated through the collected data to make the threshold more reasonable and meet actual needs.

[0072] The present invention also proposes a vehicle energy-saving prediction device based on vehicle network data analysis, comprising: a memory and one or more processors; the memory stores executable instructions, and the one or more processors communicate with the memory to execute the executable instructions to complete the above-mentioned solution.

[0073] Compared with the prior art, the present invention has the following beneficial effects:

[0074] The method of the present invention collects vehicle operation data, compares the vehicle operation data with the bad driving behavior standard, determines whether the driver corresponding to the vehicle operation data has bad driving behavior, calculates the energy saving amount when the bad driving behavior is corrected to the energy-saving operation state, compares the energy saving amount with the set energy saving amount threshold, outputs the energy saving amount and performs energy-saving warning. The method of the present invention improves the accuracy of driving behavior diagnosis, avoids the problems in the prior art that the accuracy of driving behavior diagnosis is not high, the evaluation results are affected, and it is not conducive to promoting the driver to change his driving habits;

[0075] At the same time, the driver receives the actual value of energy savings and energy-saving warnings, and uses the actual value of energy savings as a driving guide, which helps promote the driver to change his driving habits, concentrate on driving, actively learn, and reduce fuel expenditure. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 This is a flow chart of the steps of the vehicle energy saving prediction method based on vehicle networking data analysis of the present invention;

[0077] Figure 2 This is a module flow chart of the vehicle energy-saving prediction system based on vehicle networking data analysis of the present invention. DETAILED DESCRIPTION

[0078] In order to provide a further understanding of the purpose, structure, features, and functions of the present invention, the following detailed description is given in conjunction with the embodiments.

[0079] like Figure 1 and Figure 2 As shown, the vehicle energy-saving prediction system based on vehicle networking data analysis includes a data acquisition module, a data preprocessing module, a driving behavior diagnosis module and an energy-saving prediction module;

[0080] The data collection module is used to continuously collect vehicle operation data in units of trips or days, and the collected vehicle operation data includes collection time point, vehicle operation speed, vehicle operation speed, vehicle acceleration, gear position, engine torque, throttle opening, brake, water temperature, fuel consumption, altitude, etc.;

[0081] The data preprocessing module is used to preprocess the collected vehicle operation data and remove abnormal data;

[0082] The driving behavior diagnosis module is used to monitor and evaluate bad driving behavior;

[0083] The energy-saving prediction module is used to predict and evaluate the energy consumption savings.

[0084] Specifically, the vehicle energy saving prediction method based on vehicle networking data analysis includes the following steps:

[0085] S1: Collect vehicle operation data;

[0086] The data collection module continuously collects vehicle operation data based on the trip or day according to actual needs through the big data cluster server. The collection frequency is 1HZ, that is, a set of vehicle operation data is collected every second;

[0087] The collected vehicle operation data includes time point, vehicle operation speed, vehicle operation speed, vehicle acceleration, gear position, engine torque, throttle opening, brake, water temperature, fuel consumption, altitude, etc.

[0088] S2: pre-processing the collected vehicle operation data;

[0089] The data preprocessing module cleans the collected vehicle operation data and identifies and removes abnormal data.

[0090] S3: Detect and evaluate the pre-processed vehicle operation data to determine whether there is any bad driving behavior;

[0091] The driving behavior diagnosis module detects and evaluates the pre-processed vehicle operation data to determine whether the driver has bad driving behavior, which includes over-economic speed behavior, over-economic speed behavior, unreasonable gear shifting behavior, improper braking behavior, and unreasonable idling behavior;

[0092] The following sub-steps are included:

[0093] S31: Determine whether the driver has exceeded the economic speed limit;

[0094] Engineers analyze the actual vehicle power train and specific customer vehicle usage data, and obtain the corresponding wheel radius r, rear axle speed ratio i0, and gearbox speed ratio ig from the vehicle usage data;

[0095] Calculate the maximum and minimum speeds of the vehicle according to the following formula;

[0096] V = 0.377*speed n*wheel radius r / rear axle speed ratio i0 / gearbox speed ratio ig;

[0097] Among them, V is the vehicle speed, and the speed n is obtained by the data acquisition module. During the driving process of the same vehicle, the speed n, the rear axle speed ratio i0, and the gearbox speed ratio ig are variables. According to the specific values ​​of the variables, the maximum speed and the minimum speed of the vehicle are calculated by the above formula;

[0098] Engineers determine the super-economic speed threshold V1 based on the calculated maximum and minimum speeds of the vehicle and the actual vehicle speed limit, and set the super-economic speed behavior standard: the continuous driving time is greater than T1 under the conditions that the vehicle running speed is greater than V1 and the accelerator pedal position is greater than A1; A1 and T1 are preset values;

[0099] The collected vehicle operation data is compared with the set super-economic speed behavior standard. If the vehicle operation data includes driving data that meets the super-economic speed behavior standard, the driver has super-economic speed behavior;

[0100] Collecting driving data that meets the super-economic speed behavior standard, including super-economic speed behavior mileage, super-economic speed behavior fuel consumption Y11, super-economic speed behavior average speed V11, etc.;

[0101] S32: determining whether the driver has exceeded the economic speed limit;

[0102] Engineers analyze the actual economic speed of the vehicle engine and determine the super-economic speed threshold R2 based on the specific road slope conditions, and set the super-economic speed behavior standard: the continuous driving time is greater than T2 under the conditions that the vehicle running speed is greater than R2, the vehicle running speed is greater than V2, and the engine torque is greater than N2; V2, N2, and T2 are preset values;

[0103] Compare the collected vehicle operation data with the set super-economic speed behavior standard. If the vehicle operation data includes driving data that meets the super-economic speed behavior standard, the driver has super-economic speed behavior.

[0104] Counting driving data that meets the super-economic speed behavior standard, including the driving mileage of super-economic speed behavior, the driving fuel consumption Y21 of super-economic speed behavior, the average speed R21 of super-economic speed behavior, etc.;

[0105] S33: Determine whether the driver has unreasonable gear shifting behavior;

[0106] Engineers analyzed the actual vehicle gear shifting data and combined it with the specific gear shifting logic of the vehicle transmission to set the unreasonable gear shifting behavior standard: the vehicle running speed is greater than V3, and the driving time from the current gear to the gear one gear higher and then switching back to the current gear is less than T3; V3 and T3 are preset values;

[0107] The collected vehicle operation data is compared with the set unreasonable shifting behavior standard. If the driving data in the vehicle operation data meets the unreasonable shifting behavior standard, the driver has unreasonable shifting behavior;

[0108] Counting driving data that meets the unreasonable shifting behavior standard, including the average vehicle speed V31 of the unreasonable shifting behavior, the number of shifts F31 of the unreasonable shifting behavior, etc.; wherein V31 and F31 are preset values;

[0109] S34: Determine whether the driver has improper braking behavior;

[0110] Engineers analyze the actual braking force of the driver when the vehicle is running and combine the specific logical relationship between braking and acceleration to set the standard for improper braking behavior: the vehicle speed is greater than V4, and the driving time from no braking to the deceleration greater than S4 when braking is less than T4; V4, S4, and T4 are preset values;

[0111] The collected vehicle operation data is compared with the set improper braking behavior standard. If the driving data in the vehicle operation data meets the improper braking behavior standard, the driver has improper braking behavior; wherein the deceleration in the vehicle operation data is converted from the collected acceleration;

[0112] Counting driving data that meets the improper braking behavior standard, including the average vehicle speed V41 of the improper braking behavior and the number of braking times F41 of the improper braking behavior;

[0113] S35: Determine whether the driver has unreasonable idling behavior;

[0114] Engineers set unreasonable idling behavior standards by analyzing the actual vehicle operating status: the continuous driving time is greater than T5 under the conditions that the vehicle operating speed is less than V5, the vehicle operating speed is within the range [R51, R52], the throttle opening is less than A5, and the water temperature is greater than P5; V5, R51, R52, A5, P5, and T5 are preset values;

[0115] Compare the collected vehicle operation data with the set unreasonable idling behavior standard. If the vehicle operation data contains driving data that meets the unreasonable idling behavior standard, the driver has unreasonable idling behavior.

[0116] The driving data that meets the unreasonable idling behavior standards are counted, including the fuel consumption Y51 of the unreasonable idling behavior, the total mileage M51, etc.

[0117] S4: Calculate the energy saving amount of correcting the bad driving behavior to an energy-saving operation state;

[0118] The energy-saving prediction module evaluates the energy savings of correcting the bad driving behavior to an energy-saving operating state, including the following sub-steps:

[0119] S41: Calculate the energy saving amount of controlling the ultra-economical vehicle speed behavior to a reasonable vehicle speed range;

[0120] Control the super-economical speed behavior within a reasonable speed range, and estimate the energy saving E1 through the dynamics and energy consumption calculation model;

[0121] The energy saving amount E1=variable A11*(average vehicle speed V11 of super-economic vehicle speed behavior-super-economic vehicle speed threshold V1)*traveling fuel consumption Y11 of super-economic vehicle speed behavior;

[0122] Among them, variable A11 is obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles;

[0123] S42: Calculate the energy saving amount of controlling the ultra-economic speed behavior to a reasonable speed range;

[0124] Control the super-economic speed behavior within a reasonable speed range, and estimate the energy saving E2 through the dynamics and energy consumption calculation model;

[0125] The energy saving amount E2 = variable A21*(average speed R21 of super-economic speed behavior-super-economic speed threshold R2)*traveling fuel consumption Y21 of super-economic speed behavior;

[0126] Among them, variable A21 is obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles;

[0127] S43: Calculating the energy saving amount of controlling the unreasonable gear shifting behavior to a reasonable gear shifting range;

[0128] Control unreasonable shifting behavior to a reasonable shifting range, and estimate the energy saving E3 through dynamics and energy consumption calculation models;

[0129] The energy saving amount E3=(variable A31*average vehicle speed V31 of unreasonable gear shifting behavior-variable A32) / 100*number of gear shifting times F31 of unreasonable gear shifting behavior;

[0130] Among them, variables A31 and A32 are obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles;

[0131] S44: Calculate the energy saving amount by controlling the improper braking behavior to a reasonable braking range;

[0132] Control improper braking behavior within a reasonable braking range and estimate energy savings E4 through dynamics and energy consumption calculation models;

[0133] The energy saving amount E4=(variable A41*average vehicle speed V41 of improper braking behavior-variable A42) / 100*number of braking times F41 of improper braking behavior;

[0134] Among them, variables A41 and A42 are obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles;

[0135] S45: Calculating the energy saving amount of controlling the unreasonable idling behavior to a reasonable idling behavior range;

[0136] Control unreasonable idling behavior to the range of reasonable idling behavior, and estimate the energy saving E5 based on seasonal climate changes and the standard idling level of similar vehicles;

[0137] The energy saving amount E5=(fuel consumption of unreasonable idling behavior Y51-total mileage M51 / seasonal climate change parameter A51), wherein the seasonal climate change parameter A51 is obtained by calculating a large amount of data through simulating user data of the Internet of Vehicles.

[0138] S5: Output energy-saving warning;

[0139] The engineer sets five energy saving thresholds and a total energy saving threshold in advance, and compares the five actual energy saving values ​​calculated in step S4 with the set energy saving thresholds. If any actual energy saving value exceeds or does not reach the set energy saving threshold, it is determined whether the energy saving threshold needs to be adjusted according to the actual situation, and finally outputs the actual energy saving value and issues an energy-saving warning.

[0140] Calculate the sum of the actual values ​​of the five energy savings, compare it with the set total energy savings threshold, determine whether the total energy savings threshold needs to be adjusted based on the actual situation, and finally output the sum of the actual energy savings and issue an energy-saving warning;

[0141] The driver receives energy-saving warnings and adjusts his driving behavior.

[0142] The present invention also proposes a vehicle energy-saving prediction device based on vehicle network data analysis, comprising: a memory and one or more processors; the memory stores executable instructions, and the one or more processors communicate with the memory to execute the executable instructions to complete the above-mentioned solution.

[0143] The present invention provides a vehicle energy-saving prediction method, system and device based on vehicle network data analysis, which can diagnose bad driving behavior based on vehicle operation data (bad driving behavior is determined based on the characteristics of the vehicle power configuration system and the energy-saving diagnosis verification of a large number of vehicles on the market), estimate its energy saving amount, and positively guide drivers or managers to drive or manage vehicles reasonably to save energy, reduce costs and improve economic benefits through the energy saving amount.

[0144] The present invention can also set energy-saving improvement goals and management directions for managers, and even optimize decisions; provide data support from the dimension of standardizing driver operations, as well as a basis for energy-saving improvement decisions.

[0145] The present invention has been described by the above-mentioned relevant embodiments, however, the above-mentioned embodiments are only examples for implementing the present invention. It must be pointed out that the disclosed embodiments do not limit the scope of the present invention. On the contrary, changes and modifications made without departing from the spirit and scope of the present invention are all within the scope of patent protection of the present invention.

Claims

1. A vehicle energy-saving prediction method based on Internet of Vehicles data analysis, Features: The following steps are involved: S1: Collect vehicle operation data; The data collection module continuously collects vehicle operation data based on the trip or day according to actual needs through the big data cluster server. The collection frequency is 1HZ, that is, a set of vehicle operation data is collected every second; S2: pre-processing the collected vehicle operation data; The data preprocessing module cleans the collected vehicle operation data, identifies and removes abnormal data; S3: Detect and evaluate the pre-processed vehicle operation data to determine whether there is any bad driving behavior; The driving behavior diagnosis module detects and evaluates the pre-processed vehicle operation data to determine whether the driver has bad driving behavior, which includes over-economic speed behavior, over-economic speed behavior, unreasonable gear shifting behavior, improper braking behavior, and unreasonable idling behavior; The following sub-steps are included: S31: Determine whether the driver has exceeded the economic speed limit; Engineers determine the super-economic speed threshold V1 based on the vehicle's maximum and minimum speeds and the actual vehicle speed limit, and set the super-economic speed behavior standard: the vehicle's running speed is greater than V1 and the accelerator pedal position is greater than A1, and the continuous driving time is greater than T1; A1 and T1 are preset values; The collected vehicle operation data is compared with the set super-economic speed behavior standard. If the vehicle operation data includes driving data that meets the super-economic speed behavior standard, the driver has super-economic speed behavior; Counting driving data that meets the super-economic speed behavior standard, including the driving mileage of the super-economic speed behavior, the driving fuel consumption Y11 of the super-economic speed behavior, and the average speed V11 of the super-economic speed behavior; S32: determining whether the driver has exceeded the economic speed limit; Engineers analyze the actual economic speed of the vehicle engine and determine the super-economic speed threshold R2 based on the specific road slope conditions, and set the super-economic speed behavior standard: the continuous driving time is greater than T2 under the conditions that the vehicle running speed is greater than R2, the vehicle running speed is greater than V2, and the engine torque is greater than N2; V2, N2, and T2 are preset values; Compare the collected vehicle operation data with the set super-economic speed behavior standard. If the vehicle operation data includes driving data that meets the super-economic speed behavior standard, the driver has super-economic speed behavior. Counting driving data that meets the super-economic speed behavior standard, including driving mileage of super-economic speed behavior, driving fuel consumption Y21 of super-economic speed behavior, and average speed R21 of super-economic speed behavior; S33: Determine whether the driver has unreasonable gear shifting behavior; Engineers analyzed the actual vehicle gear shifting data and combined it with the specific gear shifting logic of the vehicle transmission to set the unreasonable gear shifting behavior standard: the vehicle running speed is greater than V3, and the driving time from the current gear to the gear one gear higher and then switching back to the current gear is less than T3; V3 and T3 are preset values; The collected vehicle operation data is compared with the set unreasonable shifting behavior standard. If the driving data in the vehicle operation data meets the unreasonable shifting behavior standard, the driver has unreasonable shifting behavior; Counting driving data that meets the unreasonable shifting behavior standard, including the average vehicle speed V31 of the unreasonable shifting behavior and the number of shifts F31 of the unreasonable shifting behavior; wherein V31 and F31 are preset values; S34: Determine whether the driver has improper braking behavior; Engineers analyze the actual braking force of the driver when the vehicle is running and combine the specific logical relationship between braking and acceleration to set the standard for improper braking behavior: the vehicle speed is greater than V4, and the driving time from no braking to the deceleration greater than S4 when braking is less than T4; V4, S4, and T4 are preset values; The collected vehicle operation data is compared with the set improper braking behavior standard. If the driving data in the vehicle operation data meets the improper braking behavior standard, the driver has improper braking behavior; wherein the deceleration in the vehicle operation data is converted from the collected acceleration; Counting driving data that meets the improper braking behavior standard, including the average vehicle speed V41 of the improper braking behavior and the number of braking times F41 of the improper braking behavior; S35: Determine whether the driver has unreasonable idling behavior; Engineers set unreasonable idling behavior standards by analyzing the actual vehicle operating status: the continuous driving time is greater than T5 under the conditions that the vehicle operating speed is less than V5, the vehicle operating speed is within the range [R51, R52], the throttle opening is less than A5, and the water temperature is greater than P5; V5, R51, R52, A5, P5, and T5 are preset values; Compare the collected vehicle operation data with the set unreasonable idling behavior standard. If the vehicle operation data contains driving data that meets the unreasonable idling behavior standard, the driver has unreasonable idling behavior. Collect driving data that meets the unreasonable idling behavior standards, including the fuel consumption Y51 and total mileage M51 of unreasonable idling behavior; S4: Calculate the energy saving amount of correcting the bad driving behavior to an energy-saving operation state; The energy saving prediction module evaluates the energy saving amount of correcting the bad driving behavior to the energy-saving operation state, including the following sub-steps: S41: Calculate the energy saving amount of controlling the ultra-economical vehicle speed behavior to a reasonable vehicle speed range; Control the super-economical speed behavior within a reasonable speed range, and estimate the energy saving E1 through the dynamics and energy consumption calculation model; The energy saving amount E1=variable A11*(average vehicle speed V11 of super-economic vehicle speed behavior-super-economic vehicle speed threshold V1)*traveling fuel consumption Y11 of super-economic vehicle speed behavior; Among them, variable A11 is obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles; S42: Calculate the energy saving amount of controlling the ultra-economic speed behavior to a reasonable speed range; Control the super-economic speed behavior within a reasonable speed range, and estimate the energy saving E2 through the dynamics and energy consumption calculation model; The energy saving amount E2 = variable A21*(average speed R21 of super-economic speed behavior-super-economic speed threshold R2)*traveling fuel consumption Y21 of super-economic speed behavior; Among them, variable A21 is obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles; S43: Calculating the energy saving amount of controlling the unreasonable gear shifting behavior to a reasonable gear shifting range; Control unreasonable shifting behavior to a reasonable shifting range, and estimate the energy saving E3 through dynamics and energy consumption calculation models; The energy saving amount E3=(variable A31*average vehicle speed V31 of unreasonable gear shifting behavior-variable A32) / 100*number of gear shifting times F31 of unreasonable gear shifting behavior; Among them, variables A31 and A32 are obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles; S44: Calculate the energy saving amount by controlling the improper braking behavior to a reasonable braking range; Control improper braking behavior within a reasonable braking range and estimate energy savings E4 through dynamics and energy consumption calculation models; The energy saving amount E4=(variable A41*average vehicle speed V41 of improper braking behavior-variable A42) / 100*number of braking times F41 of improper braking behavior; Among them, variables A41 and A42 are obtained by calculating a large amount of data through simulated user data of the Internet of Vehicles; S45: Calculating the energy saving amount of controlling the unreasonable idling behavior to a reasonable idling behavior range; Control unreasonable idling behavior to the range of reasonable idling behavior, and estimate the energy saving E5 based on seasonal climate changes and the standard idling level of similar vehicles; The energy saving amount E5=(fuel consumption of unreasonable idling behavior Y51-total mileage M51 / seasonal climate change parameter A51), wherein the seasonal climate change parameter A51 is obtained by calculating a large amount of data through the Internet of Vehicles simulation user data; S5: Output energy-saving warning.

2. The vehicle energy saving prediction method based on vehicle networking data analysis as claimed in claim 1, Features: In step S5, The engineer sets five energy saving thresholds and a total energy saving threshold in advance, and compares the five actual energy saving values ​​calculated in step S4 with the set energy saving thresholds. If any actual energy saving value exceeds or does not reach the set energy saving threshold, it is determined whether the energy saving threshold needs to be adjusted according to the actual situation, and finally outputs the actual energy saving value and issues an energy-saving warning. Calculate the sum of the actual values ​​of the five energy savings, compare it with the set total energy savings threshold, determine whether the total energy savings threshold needs to be adjusted based on the actual situation, and finally output the sum of the actual energy savings and issue an energy-saving warning; The driver receives energy-saving warnings and adjusts his driving behavior.

3. The vehicle energy saving prediction method based on vehicle networking data analysis as claimed in claim 2, Features: In step S31, the engineer analyzes the actual vehicle power train and the specific vehicle usage data of the customer, and obtains the wheel radius r, rear axle speed ratio i0, and gearbox speed ratio ig corresponding to the vehicle from the vehicle usage data; Calculate the maximum and minimum speeds of the vehicle according to the following formula; V = 0.377*speed n*wheel radius r / rear axle speed ratio i0 / gearbox speed ratio ig; Among them, V is the vehicle speed, and the speed n is obtained by the data acquisition module. During the driving process of the same vehicle, the speed n, rear axle speed ratio i0, and gearbox speed ratio ig are variables. According to the specific values ​​of the variables, the maximum speed and minimum speed of the vehicle are calculated by the above formula.

4. A vehicle energy-saving prediction system based on vehicle networking data analysis, used to implement the vehicle energy-saving prediction method based on vehicle networking data analysis according to any one of claims 1 to 3, Features: It includes data acquisition module, data preprocessing module, driving behavior diagnosis module and energy-saving prediction module; The data collection module is used to continuously collect vehicle operation data in units of trips or days; The data preprocessing module is used to preprocess the collected vehicle operation data and remove abnormal data; The driving behavior diagnosis module is used to monitor and evaluate bad driving behavior; The energy-saving prediction module is used to predict and evaluate the energy consumption savings.

5. A vehicle energy-saving prediction device based on vehicle networking data analysis, used to implement the vehicle energy-saving prediction method based on vehicle networking data analysis according to any one of claims 1 to 3, Features: It includes a memory and a processor; the memory stores executable instructions, and the processor communicates with the memory to execute the executable instructions to complete vehicle energy saving prediction through Internet of Vehicles data analysis.

Images