Vehicle fuel economy evaluation method based on data analysis

A fuel economy and data analysis technology, applied in the field of vehicle-machine systems, can solve the problems of parameters and other parameters and weight influences, lack of long-term dynamic improvement capabilities, and poor pertinence, so as to improve calculation and operation efficiency and enhance learning The effect of the mechanism

Pending Publication Date: 2022-02-15
ZHEJIANG UFO AUTOMOBILE MFG CO LTD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] 1. The relevant technologies currently on the market lack economical long-term dynamic improvement capabilities. Although there are long-term and short-term memory neural networks on the market, which can analyze and learn based on updated data to obtain more fuel-saving suggestions, this method has a large time span. In the case of deep layers, the amount of calculation is large and time-consuming, which is not economical
[0009] 2. Affected by artificial preset road environment parameters and other parameters and weights
[0010] 3. Suggestions on driving behavior are general and not very specific

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vehicle fuel economy evaluation method based on data analysis
  • Vehicle fuel economy evaluation method based on data analysis
  • Vehicle fuel economy evaluation method based on data analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] Step S1: Data processing, analyzing the original message data sent by the vehicle terminal to obtain the driving time, vehicle VIN code, load, engine speed, engine fuel flow, instantaneous fuel consumption, vehicle speed, percentage of net engine output torque, and accelerator pedal opening , clutch status and brake status data;

[0086] Step S2: If it is judged that it is a training mode, then step S3, step S4 and step S5 are executed in sequence;

[0087] Step S3: Construct a training data set and store it in a configuration file;

[0088] Step S4: Fill the training data into the fuel economy model based on the KNN model;

[0089] Step S5: Deploy the model.

[0090] In the step S3, the training data set is constructed and stored in the configuration file. In order to reduce the amount of data used as the training data set and optimize the efficiency of the model, the travel data is cut between small areas and the average value of the interval is calculated. The spec...

Embodiment 2

[0097] Step S1: Data processing, analyzing the original message data sent by the vehicle terminal to obtain the driving time, vehicle VIN code, load, engine speed, engine fuel flow, instantaneous fuel consumption, vehicle speed, percentage of net engine output torque, and accelerator pedal opening , clutch status and brake status data;

[0098] Step S2: If it is judged that it is not the training mode, execute step S6;

[0099] Step S6: Calculation of the actual fuel index of the trip;

[0100] Step S7: Fuel model, output fuel consumption prediction results and driving conditions;

[0101] Step S8: judge whether it is an economical trip according to the fuel consumption prediction result output in step S7, if yes, execute step S9; if not, execute step S10 and end;

[0102] Step S9: Carry out incremental learning;

[0103] Step S10: the non-incremental learning ends.

[0104] In the step S6, the calculation of the actual fuel index of the itinerary is based on the processed...

Embodiment 3

[0120] The fuel model outputs the driving conditions, the specific steps are as follows:

[0121] Extraction of driving conditions: Based on the original message data sent by the vehicle terminal analyzed in step S1, according to the acceleration, accelerator opening, brake clutch status, minimum duration of the working condition, maximum interval of the same working condition, gear position, engine Speed, to identify the working condition of the travel data.

[0122] The driving conditions identified by this method include:

[0123] Acceleration, deceleration, rapid acceleration, rapid deceleration, constant speed, start, stop, small throttle, medium throttle, large throttle, full throttle, idle speed, coasting, shifting, stepping on the brake, stepping on the clutch, near the external characteristic curve, low speed full throttle, High gear at low vehicle speed, low gear at high vehicle speed, skip shifting, rapid acceleration at start.

[0124] Step S11: Make a driving be...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a vehicle fuel economy evaluation method based on data analysis. The method predicts fuel consumption, analyzes driving behaviors and improves suggestion output through data processing and a fuel model with a reinforcement learning mechanism. Along with continuous reinforcement learning and long-term dynamic improvement of the model, the prediction of economic fuel consumption is more and more accurate, and the method provides help for the driver to carry out economic driving in cooperation with specific and visual driving behavior suggestions.

Description

technical field [0001] The invention belongs to the technical field of vehicle-machine systems, in particular, the invention relates to a method for evaluating vehicle fuel economy based on data analysis. Background technique [0002] Automobile fuel economy refers to the ability of an automobile to consume as little fuel as possible for economical driving under the premise of ensuring power performance. Since the fuel cost of a car is an important part of the cost of car transportation, improving fuel economy is the key to saving car transportation costs. [0003] At the same time, the annual growth of car ownership, the increasing shortage of petroleum energy and the increasingly stringent environmental protection regulations also require improved fuel economy. Therefore, how to improve fuel economy and make use of it has become a major issue of common concern to the whole society. [0004] In addition to the car's own structure, including the engine structure, curb weig...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G07C5/08G07C5/00B60R16/023G06Q10/04G06N20/00G06F16/2458G06F16/215
CPCG07C5/0808G07C5/0841G07C5/008B60R16/0232B60R16/0236G06Q10/04G06N20/00G06F16/2462G06F16/2477G06F16/215Y02T10/84B60W40/09G06N20/10G06N3/08B60W50/14B60W2050/0088B60W50/0098G06F18/24G06N5/04B60W2756/00G06V10/72B60W40/105B60W40/107B60W40/13B60W2510/10B60W2530/18
Inventor 姜文娟徐礼成崔震王惠艺曹贵宝卢东涛张明华
Owner ZHEJIANG UFO AUTOMOBILE MFG CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap