CN112950811A - New energy automobile region operation risk assessment and early warning system integrating whole automobile safety - Google Patents
New energy automobile region operation risk assessment and early warning system integrating whole automobile safety Download PDFInfo
- Publication number
- CN112950811A CN112950811A CN202110144514.4A CN202110144514A CN112950811A CN 112950811 A CN112950811 A CN 112950811A CN 202110144514 A CN202110144514 A CN 202110144514A CN 112950811 A CN112950811 A CN 112950811A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- early warning
- state
- risk
- new energy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Medical Informatics (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
Abstract
The invention discloses a new energy automobile regional operation risk assessment and early warning system fusing whole automobile safety states, which is characterized in that the new energy automobile has various whole automobile safety risks such as battery thermal runaway, power loss and the like, and the whole automobile safety states and intra-domain weather state information of a self automobile and other automobiles in a domain are fused into the existing automobile operation risk early warning method, so that accurate assessment and early warning of the operation risk of the new energy automobile under the complex road traffic condition can be realized. Processing and analyzing driving data acquired by each vehicle-mounted sensor in real time to complete sensing of the whole vehicle safety state of each vehicle, and outputting a vehicle battery thermal runaway risk state and a power loss risk state; the extraction of the safety states of the self vehicle and other vehicles in the domain, the perception of the motion state and the weather state in the domain are realized; the safety state, the motion state and the intra-domain weather state of the own vehicle and other vehicles in the domain are fused, and risk assessment and early warning are carried out on the whole process real-time operation of the new energy vehicle on the basis of the operation risk early warning model and strategy.
Description
Technical Field
The invention belongs to the field of new energy automobile operation safety, and particularly relates to a new energy automobile regional operation risk assessment and early warning system integrating the whole automobile safety state.
Background
The new energy automobile has the advantages that the new energy automobile has safety risks such as battery thermal runaway and power loss due to related systems and parts such as a power battery, a driving motor and an electric control system which are special for the new energy automobile. If the new energy automobile has thermal runaway of the battery and power loss during operation, the new energy automobile may collide with the adjacent vehicles in the area, and even further thermal runaway of the power batteries of other vehicles in the area and vehicle fire may be caused after the collision. Therefore, under the running condition that the urban traffic structure and the traffic environment are complex, the driving risk modes of the new energy automobile are also diverse and complex. At present, the new energy automobile operation risk early warning method based on the internet of vehicles does not consider the own special safety risk of the whole automobile. Therefore, a terminal network cloud integrated new energy automobile regional operation risk assessment and early warning method integrating the safety state of the own automobile and the whole automobile of other automobiles and the intra-regional weather state needs to be established.
Disclosure of Invention
Aiming at the defects or improvement requirements of the prior art, the invention provides a new energy automobile regional operation risk assessment and early warning system fusing the whole automobile safety state, and aims to enable a risk early warning system of a new energy automobile cloud supervision platform to fuse real-time sensed whole automobile safety state information of vehicles in a domain and weather state information in the domain so as to realize accurate assessment and early warning of regional operation risks of the new energy automobile.
In order to achieve the purpose, the invention provides a new energy automobile regional operation risk assessment and early warning system integrating the safety state of the whole automobile, which comprises: the system comprises a vehicle safety state sensing and identifying module, an end network cloud integrated traffic system element sensing module and a regional operation risk assessment and early warning module;
the whole vehicle safety state perception and identification module is used for collecting driving data in real time through various sensors of the new energy vehicle, receiving and processing driving data information based on the built cloud platform, conducting whole vehicle safety state perception and identification of coupling of driving working conditions and working states of key parts by utilizing an artificial neural network algorithm, and accurately outputting a power battery thermal runaway risk state and a whole vehicle power loss risk state;
the end network cloud integrated traffic system element sensing module is used for sensing the motion states of the self vehicle and other vehicles in the area in real time, extracting the safety state information of the self vehicle and other vehicles in the area in real time and sensing and identifying the weather state in the driving area;
the regional operation risk assessment and early warning module is used for fusing multi-source output of the end network cloud integrated traffic system element sensing module through the cloud platform, performing risk assessment and early warning on the whole process real-time operation of the new energy automobile, and then feeding early warning information back to the new energy automobile terminal.
In some optional embodiments, the vehicle safety state sensing and identifying module includes:
the system comprises a new energy automobile driving data acquisition, uploading and preprocessing unit, a cloud platform and a data processing unit, wherein the new energy automobile driving data acquisition, uploading and preprocessing unit is used for acquiring real-time driving data of a new energy automobile through various sensors which are arranged on the new energy automobile driving data acquisition unit and the cloud platform;
the system comprises a finished automobile safety state sensing characteristic index extraction unit, a cloud platform and a control unit, wherein the finished automobile safety state sensing characteristic index extraction unit is used for extracting characteristic parameters required to be input by finished automobile safety state sensing identification through the cloud platform, and the characteristic parameters comprise driving condition characteristic parameters, batteries, motors and electric control characteristic parameters;
and the whole vehicle safety state perception and identification unit is used for carrying out whole vehicle safety state perception and identification of coupling of the running condition and the working state of key parts through the cloud platform based on the trained artificial neural network model, and outputting a battery thermal runaway risk state and a whole vehicle power loss risk state.
In some optional embodiments, the end-network cloud-integrated traffic system element awareness module includes:
the vehicle state sensing unit is used for extracting the sensed whole vehicle safety state of the vehicle from the output of the whole vehicle safety state sensing and identifying module, and extracting acceleration, speed and position data from vehicle running data preprocessed by the cloud platform so as to sense the motion state of the vehicle in real time;
the intra-domain other vehicle state sensing unit is used for extracting the sensed whole vehicle safety state of other vehicles from the output of the whole vehicle safety state sensing and identifying module, and extracting speed and acceleration data of other vehicles from the driving data of other vehicles preprocessed by the cloud platform so as to sense the motion state of other vehicles in real time;
and the weather state sensing unit is used for realizing the real-time acquisition and identification of weather state information through a weather monitor, and uploading the identified weather state data to the cloud end platform.
In some optional embodiments, the regional operational risk assessment and pre-warning module comprises:
the multi-source data fusion unit is used for fusing the output of the element sensing module of the end network cloud integrated traffic system based on a plurality of data processing methods;
and the operation risk assessment and early warning unit is used for realizing the real-time operation risk assessment and early warning of the new energy automobile in the whole process based on the established operation risk early warning model and the established strategy rule base.
In some optional embodiments, the vehicle safety state sensing and identifying unit is configured to input driving condition characteristic parameters and battery thermal runaway characteristic parameters into a battery thermal runaway prediction model based on an artificial neural network, perform joint analysis on a predicted value obtained by calculation and a classified battery thermal runaway risk level threshold, and output a real-time battery thermal runaway risk state; and inputting the driving condition characteristic parameters and the power loss characteristic parameters into a power loss prediction model based on an artificial neural network, outputting predicted values after calculation, further performing joint analysis on the predicted values and the divided power loss risk grades, and finally outputting a real-time power loss risk state of the whole vehicle.
In some optional embodiments, the operating risk pre-warning model comprises: after the safety braking distance model, the corrected safety braking distance model, the longitudinal distance monitoring model and the lateral distance monitoring model are researched and judged by the whole vehicle safety risk scene, regional operation risk early warning is carried out by one or more models under the applicable scene conditions.
In some optional embodiments, the safe braking distance model is:
wherein v is1And v2Respectively the initial speeds of the self vehicle and the front vehicle; a is1And a2The maximum acceleration of the bicycle and the front bicycle respectively; d is the minimum acceptable distance between the two vehicles when the two vehicles are static after emergency braking is carried out on the self vehicle and the front vehicle; t is tdThe time required for a driver to take action from the discovery of an emergency is called driver delay time; t is tsThe time for the vehicle brake system to increase from the completion of the brake actuation by the driver to the maximum brake deceleration, referred to as the system delay time;
the corrected safe braking distance model is obtained by multiplying a correction coefficient which is larger than 1 on the basis of the early warning threshold value of the safe braking distance model so as to improve the early warning threshold value, wherein the coefficient is larger when the early warning level of the power loss is higher;
the longitudinal distance monitoring model is as follows: when the real-time distance between the current vehicle and the previous vehicle exceeds a specific value, outputting operation early warning information, wherein the higher the early warning level of the thermal runaway of the battery of the previous vehicle is, the larger the safety distance threshold value is;
the lateral distance monitoring model is used for outputting early warning information after the transverse distance between the self vehicle and the lateral vehicle exceeds a specific value, and the higher the early warning level of the thermal runaway of the battery of the lateral vehicle is, the larger the safety distance threshold value is.
The invention integrates the whole vehicle safety state perception into the operation risk assessment and early warning of the new energy vehicle, has comprehensive consideration factors, can solve the key problems existing in the operation risk assessment of the new energy vehicle under the complex traffic environment condition, and has the following advantages compared with the prior art: (1) the running data of the new energy automobile collected in real time is deeply processed and analyzed on the basis of the cloud platform, so that the safety state of the whole automobile can be sensed in real time, and the risk of the whole automobile end can be accurately evaluated; (2) the operation risk assessment and early warning method integrates real-time sensed safety state information of the whole new energy automobile, safety state information of other automobiles in the area and weather state information in the area, safety risks of the new energy automobile are taken into consideration, safety risks of multiple automobiles in the area are taken into consideration, and safety risk assessment and early warning of the whole automobile end of the new energy automobile are taken into consideration.
Drawings
Fig. 1 is a schematic diagram of a system for evaluating and warning regional operation risks of a new energy vehicle integrating a safety state of the whole vehicle according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for implementing a vehicle safety status sensing and identifying module according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for implementing a regional operation risk assessment and early warning module according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Fig. 1 is a schematic diagram of a system for assessing and warning regional operation risk of a new energy vehicle integrating a safety state of the entire vehicle, provided by an embodiment of the present invention, where the system includes: the system comprises a vehicle safety state sensing and identifying module A, an end network cloud integrated traffic system element sensing module B and a regional operation risk assessment and early warning module C;
the whole vehicle safety state sensing and identifying module is used for collecting driving data in real time through various sensors of the new energy vehicle, receiving and processing driving data information based on the built cloud platform, sensing and identifying the whole vehicle safety state coupling driving working conditions and the working state of key parts by utilizing an artificial neural network, and accurately outputting a power battery thermal runaway risk state and a whole vehicle power loss risk state;
the end network cloud integrated traffic system element sensing module is used for sensing the motion states (speed, acceleration and position) of the self vehicle and other vehicles in the domain in real time; extracting safety state information (battery thermal runaway risk state and whole vehicle power loss risk state) of the self vehicle and other vehicles in the domain in real time; sensing and identifying weather states (such as precipitation, snowfall, fog, haze and the like) in a driving area;
the regional operation risk assessment and early warning module is used for fusing multi-source output of the end network cloud integrated traffic system element sensing module by using a data fusion method through the cloud platform, performing risk assessment and early warning on the whole process real-time operation of the new energy automobile, and further feeding early warning information back to the new energy automobile terminal.
The specific process of the vehicle safety state sensing and identifying module is shown in fig. 2, and is mainly used for executing the following operations:
step A1: acquiring, uploading and preprocessing driving data of the new energy automobile: the new energy automobile terminal collects and uploads automobile data to the cloud platform in real time, and the cloud platform receives the data and then preprocesses the data to remove abnormal values and filter noise in the data;
in the embodiment of the invention, the driving data acquired and uploaded by the new energy automobile in real time comprises two types: according to the specification of GB/T32960.3-2016 technical Specification of electric vehicle remote service and management System (part 3: communication protocol and data Format), the new energy vehicle is provided with T-BOX to collect and upload data in real time, and the data types mainly comprise vehicle data, driving motor data, fuel cell data, engine data, vehicle position data, extreme value data, alarm data, voltage data of a rechargeable energy storage device and temperature data of the rechargeable energy storage device; the other type is driving condition data such as acceleration data acquired by an additionally arranged acceleration sensor and a three-axis gyroscope in real time.
At present, the uploading frequency of T-BOX data of a new energy automobile is 1 time/10 s, the requirement of real-time perception and identification of the safety state of the whole automobile coupled with the driving working condition and key parts cannot be met, and the accuracy and the real-time performance of regional operation risk assessment and early warning cannot be guaranteed. Therefore, the embodiment of the invention provides the requirements for acquiring and uploading the driving data of the new energy automobile in real time: (1) the data acquisition frequency is 200 ms/time, namely 0.2 s/time; (2) the positioning precision of the vehicle is less than or equal to 10 cm; (3) the communication time delay is less than or equal to 20 ms. In order to realize the practical application of the invention, an end network cloud integrated intelligent terminal facing the operation risk identification can be developed, and the terminal acquires and uploads data to a cloud platform in real time according to the precision and frequency requirements.
Step A2: extracting characteristic indexes of vehicle safety state perception: the whole vehicle safety state of the new energy vehicle in the embodiment of the invention mainly refers to a power battery thermal runaway risk state and a whole vehicle power loss risk state;
after the cloud platform finishes data cleaning, characteristic parameters required to be input for sensing and identifying the safety state of the whole vehicle are extracted, and the characteristic parameters are mainly classified into three types: characterizing characteristic parameters of driving conditions, including vehicle speed parameters, acceleration and brake pedal parameters and the like; battery characteristic parameters related to the battery thermal runaway risk comprise voltage parameters, temperature parameters, internal resistance parameters and the like; and thirdly, characteristic parameters of batteries, motors and electric controls related to the risk of power loss of the whole vehicle comprise battery pack voltage, monomer voltage, battery pack temperature, motor temperature, input voltage of a motor controller, DC-DC state, insulation resistance and the like. The characteristic parameters are determined through the verification of an established battery thermal runaway prediction model and a power loss prediction model. The battery thermal runaway prediction model and the power loss prediction model are established based on a long-time memory neural network, and the establishing process mainly comprises the following steps: the method comprises the steps of mining massive historical operation big data, extracting battery characteristic parameters related to battery thermal runaway risks and characteristic parameters related to vehicle power loss risks, finally determining characteristic indexes of two types of risk assessment based on a principal component analysis method, taking the characteristic indexes and driving condition characteristic parameters determined by the same method as input of a long-time and short-time memory neural network, and establishing a prediction model after the network is subjected to multiple parameter optimization, training and verification.
Step A3: and (3) sensing and identifying the safety state of the whole vehicle: inputting the characteristic parameters extracted in the step A2 into a corresponding risk prediction model to realize the whole vehicle safety state perception and identification of the coupling driving working condition and the key component working state, and the specific method is as follows: firstly, inputting driving condition characteristic parameters and battery thermal runaway related characteristic parameters into a battery thermal runaway prediction model based on an artificial neural network, outputting a predicted value after calculation, further carrying out joint analysis on the predicted value and divided battery thermal runaway risk grades, and finally outputting a real-time battery thermal runaway risk state; secondly, inputting the characteristic parameters of the driving conditions and the characteristic parameters related to the power loss into a power loss prediction model based on an artificial neural network, outputting a predicted value after calculation, further performing joint analysis on the predicted value and the divided power loss risk level, and finally outputting a real-time power loss risk state of the whole vehicle.
The divided battery thermal runaway risk grade and power loss risk grade are realized by mining and analyzing massive historical operation big data in the early stage, and the realization method comprises the following steps: and respectively carrying out K-means cluster analysis on the determined characteristic indexes associated with the thermal runaway risk of the battery and the characteristic indexes associated with the power loss risk, setting an initial cluster center, distributing all points to corresponding classes according to discrimination conditions in a distribution step, calculating a new cluster center in an updating step, judging whether convergence exists, finishing clustering and the like, finally respectively marking out 4 states of safety, low, medium and high risks of the thermal runaway and the power loss of the battery, and determining corresponding risk grade thresholds.
The end network cloud integrated traffic system element sensing module can be realized in the following modes:
step B1: extracting safety state of the self vehicle and sensing motion state: directly extracting the sensed safety state of the whole vehicle from the output of the module A; and (3) extracting acceleration, speed and position data from the vehicle running data preprocessed by the cloud platform so as to sense the motion state of the vehicle in real time.
Step B2: extracting safety states of other vehicles in the domain and sensing motion states: based on the real-time self-vehicle position data in the step B1, the system can automatically search and lock other vehicles in the driving domain according to the set range, once the objects of the other vehicles are determined, the speed and acceleration data of the vehicle can be extracted and called to realize the real-time perception of the motion state of the vehicle, and meanwhile, the system can extract the whole vehicle safety state of the vehicle from the output of the module A;
step B3: intra-domain weather status perception: the traffic weather video monitor along the road can realize real-time acquisition and identification of weather information based on computer vision and a deep learning algorithm, and software and hardware of the traffic weather video monitor comprise a video acquisition module, a control processing module, an identification software module and the like, wherein the identification software module is used for identifying various traffic weather states and parameters such as cloudy days, sunny days, rainfall, snowfall intensity, visibility, fog, icy roads and the like by sensing after carrying out data processing, feature extraction and neural network classification on acquired weather video data, and then the sensed and identified weather states are uploaded to a cloud-end platform in real time.
The specific flow of the above-mentioned regional operation risk assessment and early warning module is shown in fig. 3, and can be implemented by the following means:
step C1: multi-source data fusion: processing the safety state of the self vehicle and the whole vehicle of other vehicles, the motion state of the self vehicle and other vehicles and the weather state data output by the end network cloud integrated traffic system element sensing module, and further completing the feature information extraction and the feature level hierarchical fusion, wherein the main contents of the step are as follows:
(1) processing the vehicle position information by using a Kalman filtering algorithm to obtain more accurate and reliable vehicle position data, and further establishing a rectangular coordinate system taking a self-parking position as an origin and a vehicle advancing direction as a positive direction of a longitudinal axis so as to obtain real-time longitudinal distance and lateral distance between vehicles in a domain;
(2) and processing weather state information: weather state information such as rainfall, rainfall intensity, snowfall depth, air temperature, fog, haze, wind and sand and the like are fused, and two characteristic parameter values of visibility and road surface adhesion coefficient are calibrated comprehensively;
(3) and (3) data synchronization processing: and (3) utilizing an interpolation method to continuously convert the discrete data and ensuring the synchronization of characteristic data such as vehicle distance, vehicle speed, vehicle acceleration, vehicle safety state, visibility, road adhesion coefficient and the like.
Step C2: and (3) operation risk assessment and early warning: the method comprises the steps that multi-source data are input into an operation risk early warning model and an early warning strategy rule base through feature level hierarchical fusion, classified and hierarchical early warning information is output, then a cloud platform transmits the early warning information to a new energy automobile end network cloud integrated intelligent terminal in real time, and after a vehicle driver receives the early warning information, safety accidents are avoided through certain driving operation.
The new energy automobile risk early warning model and the early warning strategy are key for realizing accurate early warning of automobile running risks, and the new energy automobile risk early warning model and the early warning strategy need to consider the safety state of the whole automobile, namely the battery thermal runaway risk state and the power loss risk state of the automobile and other automobiles need to be fused into the existing regional running risk assessment and early warning model. When the new energy automobile runs in a certain traffic environment, the power loss risk value, the battery thermal runaway risk value and the spatial position distribution of the automobile and other automobiles are all variables, so that the new energy automobile can face various running risk scene combinations on the regional running level. Under different risk scenes, different new energy vehicles risk early warning models and early warning strategies are adopted to realize accurate early warning. Therefore, a new energy automobile operation risk early warning model and a strategy rule base are required to be established. And fusing the multi-source data into an input rule base, and calculating and outputting early warning information by using a corresponding algorithm model after scene study and judgment.
In the embodiment of the invention, the established new energy automobile risk early warning model and the early warning strategy rule base mainly comprise 4 early warning models and applicable risk scene conditions, wherein the 4 early warning models are as follows:
(1) safe Braking Distance Model (SBDM): the basis is the distance required by the vehicle to safely stop in the braking process, and the calculation formula is as follows:
wherein v is1And v2Respectively the initial speeds of the self vehicle and the front vehicle; a is1And a2The maximum acceleration of the bicycle and the front bicycle respectively; d is the minimum acceptable distance between the two vehicles when the two vehicles are static after emergency braking is carried out on the self vehicle and the front vehicle; t is tdThe time required for a driver to take action from the discovery of an emergency is called driver delay time; t is tsThe time for the vehicle brake system to increase from the completion of the braking action by the driver to the maximum brake deceleration is referred to as the system delay time.
When the real-time vehicle distance D is smaller than DwarThe system generates early warning information. The safety braking distance model may comprehensively consider a plurality of factors, such as a braking implementation process, a driver reaction time, road adhesion coefficients under different weather conditions, and the like (it should be noted that visibility under different weather conditions also affects the driver reaction time). In the actual early warning application, the maximum acceleration of the self vehicle and the front vehicle is always set to be a, wherein a is mu g, mu is a road surface adhesion coefficient, and g is a gravity acceleration.
(2) Modified Safety Braking Distance Model (Correction Model of Safety Braking Distance, CMSBD): on the basis of the early warning threshold value of the safe distance model, a correction coefficient larger than 1 is multiplied to improve the early warning threshold value, and the coefficient is larger when the early warning level of the power loss is higher (the risk value is higher).
(3) Longitudinal Distance Monitoring Model (LDMM): and when the real-time distance between the self vehicle and the front vehicle exceeds a specific value, outputting operation early warning information. The higher the early warning level of the thermal runaway of the battery of the front vehicle is, the larger the safety distance threshold value is.
(4) Lateral Distance Monitoring Model (transient Distance Monitoring Model, TDMM): and when the transverse distance between the self vehicle and the side vehicle exceeds a specific value, outputting early warning information. The higher the battery thermal runaway early warning level of the side vehicle is, the larger the safety distance threshold value is.
The early warning grades of the 4 models are set to be two levels, and the grading early warning threshold value is comprehensively calibrated by combining a vehicle thermal runaway risk value and a power loss risk value. The risk early warning model and the strategy rule base of the new energy automobile formed by the 4 early warning models and the applicable risk scenes are shown in table 1:
TABLE 1 New energy automobile risk early warning model and strategy rule base
To be noted with respect to the above table: firstly, when a battery thermal runaway early warning occurs in a current vehicle, a driver is reminded to keep a certain safety distance from the previous vehicle in principle, and the vehicle spontaneous combustion caused by the thermal runaway and even explosion accidents can endanger surrounding vehicles, so that early warning is carried out based on a Longitudinal Distance Monitoring Model (LDMM), but the model cannot carry out collision early warning, and the early warning time of the model can be later than the early warning time of a Safety Braking Distance Model (SBDM), so that the two models are combined for risk early warning; secondly, when the front vehicle has thermal runaway and power loss early warning at the same time, the LDMM and CMSBD are adopted to carry out combined early warning in the same way; when the lateral vehicle has thermal runaway early warning, performing lateral distance monitoring early warning based on TDMM, and performing forward collision early warning based on SBDM; aiming at the problem of collision between two vehicles in the cut-in and lane change scenes, a conventional direction bounding box (OBB) detection algorithm based on a separation axis theorem can be adopted for early warning, the safety state of the whole vehicle does not need to be considered, and therefore the problem is not listed in a table; and fifthly, early warning of power loss, early warning of battery thermal runaway and early warning of regional operation, wherein the three kinds of early warning information are output to the self-vehicle in a classified mode, and in addition, the early warning information of thermal runaway and power loss of the adjacent vehicles in the area and the position information of the dangerous vehicle relative to the self-vehicle are also fed back to the self-vehicle.
It should be noted that, according to the implementation requirement, each step/component described in the present application can be divided into more steps/components, and two or more steps/components or partial operations of the steps/components can be combined into new steps/components to achieve the purpose of the present invention.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (7)
1. The utility model provides a fuse regional operation risk assessment of new energy automobile and early warning system of whole car safe state which characterized in that includes: the system comprises a vehicle safety state sensing and identifying module, an end network cloud integrated traffic system element sensing module and a regional operation risk assessment and early warning module;
the whole vehicle safety state perception and identification module is used for collecting driving data in real time through various sensors of the new energy vehicle, receiving and processing driving data information based on the built cloud platform, conducting whole vehicle safety state perception and identification of coupling of driving working conditions and working states of key parts by utilizing an artificial neural network algorithm, and accurately outputting a power battery thermal runaway risk state and a whole vehicle power loss risk state;
the end network cloud integrated traffic system element sensing module is used for sensing the motion states of the self vehicle and other vehicles in the area in real time, extracting the safety state information of the self vehicle and other vehicles in the area in real time and sensing and identifying the weather state in the driving area;
the regional operation risk assessment and early warning module is used for fusing multi-source output of the end network cloud integrated traffic system element sensing module through the cloud platform, performing risk assessment and early warning on the whole process real-time operation of the new energy automobile, and then feeding early warning information back to the new energy automobile terminal.
2. The system of claim 1, wherein the vehicle safety status awareness identification module comprises:
the system comprises a new energy automobile driving data acquisition, uploading and preprocessing unit, a cloud platform and a data processing unit, wherein the new energy automobile driving data acquisition, uploading and preprocessing unit is used for acquiring real-time driving data of a new energy automobile through various sensors which are arranged on the new energy automobile driving data acquisition unit and the cloud platform;
the system comprises a finished automobile safety state sensing characteristic index extraction unit, a cloud platform and a control unit, wherein the finished automobile safety state sensing characteristic index extraction unit is used for extracting characteristic parameters required to be input by finished automobile safety state sensing identification through the cloud platform, and the characteristic parameters comprise driving condition characteristic parameters, batteries, motors and electric control characteristic parameters;
and the whole vehicle safety state perception and identification unit is used for carrying out whole vehicle safety state perception and identification of coupling of the running condition and the working state of key parts through the cloud platform based on the trained artificial neural network model, and outputting a battery thermal runaway risk state and a whole vehicle power loss risk state.
3. The system of claim 2, wherein the end-to-end network cloud-integrated traffic system element awareness module comprises:
the vehicle state sensing unit is used for extracting the sensed whole vehicle safety state of the self vehicle from the output of the whole vehicle safety state sensing and identifying module, and extracting acceleration, speed and position data from the vehicle running data preprocessed by the cloud platform so as to sense the motion state of the self vehicle in real time;
the intra-domain other vehicle state sensing unit is used for extracting the sensed whole vehicle safety state of other vehicles from the output of the whole vehicle safety state sensing and identifying module, and extracting speed and acceleration data of other vehicles from the driving data of other vehicles preprocessed by the cloud platform so as to sense the motion state of other vehicles in real time;
and the weather state sensing unit is used for realizing the real-time acquisition and identification of weather state information through a weather monitor, and uploading the identified weather state data to the cloud end platform.
4. The system of claim 3, wherein the regional operational risk assessment and warning module comprises:
the multi-source data fusion unit is used for fusing the output of the element sensing module of the end network cloud integrated traffic system based on a plurality of data processing methods;
and the operation risk assessment and early warning unit is used for realizing the real-time operation risk assessment and early warning of the new energy automobile in the whole process based on the established operation risk early warning model and the established strategy rule base.
5. The system according to claim 2, wherein the vehicle safety state sensing and identifying unit is configured to input driving condition characteristic parameters and battery thermal runaway characteristic parameters into a battery thermal runaway prediction model based on an artificial neural network, and further perform joint analysis on a predicted value obtained by calculation and a classified battery thermal runaway risk level threshold, and output a real-time battery thermal runaway risk state; and inputting the driving condition characteristic parameters and the power loss characteristic parameters into a power loss prediction model based on an artificial neural network, outputting predicted values after calculation, further performing joint analysis on the predicted values and the divided power loss risk grades, and finally outputting a real-time power loss risk state of the whole vehicle.
6. The system of claim 4, wherein the operational risk pre-warning model comprises: after the safety braking distance model, the corrected safety braking distance model, the longitudinal distance monitoring model and the lateral distance monitoring model are researched and judged by the whole vehicle safety risk scene, regional operation risk early warning is carried out by one or more models under the applicable scene conditions.
7. The system of claim 6, wherein the safe braking distance model is:
wherein v is1And v2Respectively the initial speeds of the self vehicle and the front vehicle; a is1And a2The maximum acceleration of the bicycle and the front bicycle respectively; d is the minimum acceptable distance between the two vehicles when the two vehicles are static after emergency braking is carried out on the self vehicle and the front vehicle; t is tdThe time required for a driver to take action from the discovery of an emergency is called driver delay time; t is tsThe time for the vehicle brake system to increase from the completion of the brake actuation by the driver to the maximum brake deceleration, referred to as the system delay time;
the corrected safe braking distance model is obtained by multiplying a correction coefficient which is larger than 1 on the basis of the early warning threshold value of the safe braking distance model so as to improve the early warning threshold value, wherein the coefficient is larger when the early warning level of the power loss is higher;
the longitudinal distance monitoring model is as follows: when the real-time distance between the current vehicle and the previous vehicle exceeds a specific value, outputting operation early warning information, wherein the higher the early warning level of the thermal runaway of the battery of the previous vehicle is, the larger the safety distance threshold value is;
the lateral distance monitoring model is used for outputting early warning information after the transverse distance between the self vehicle and the lateral vehicle exceeds a specific value, and the higher the early warning level of the thermal runaway of the battery of the lateral vehicle is, the larger the safety distance threshold value is.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110144514.4A CN112950811B (en) | 2021-02-02 | 2021-02-02 | New energy automobile region operation risk assessment and early warning system integrating whole automobile safety |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110144514.4A CN112950811B (en) | 2021-02-02 | 2021-02-02 | New energy automobile region operation risk assessment and early warning system integrating whole automobile safety |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112950811A true CN112950811A (en) | 2021-06-11 |
| CN112950811B CN112950811B (en) | 2022-12-13 |
Family
ID=76241713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110144514.4A Active CN112950811B (en) | 2021-02-02 | 2021-02-02 | New energy automobile region operation risk assessment and early warning system integrating whole automobile safety |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112950811B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113642893A (en) * | 2021-08-16 | 2021-11-12 | 公安部交通管理科学研究所 | New energy automobile operation risk assessment method |
| CN113808403A (en) * | 2021-09-26 | 2021-12-17 | 公安部交通管理科学研究所 | New energy automobile operation risk studying and judging method fusing traffic management big data |
| CN114781256A (en) * | 2022-04-18 | 2022-07-22 | 北京航空航天大学 | Power battery thermal runaway risk assessment method based on cloud lifelong learning |
| CN114987208A (en) * | 2022-06-07 | 2022-09-02 | 武汉理工大学 | Electric vehicle power loss risk early warning system and method |
| CN114997748A (en) * | 2022-08-01 | 2022-09-02 | 中通客车股份有限公司 | New energy automobile operation safety risk prediction method and system based on model fusion |
| CN117268793A (en) * | 2023-10-25 | 2023-12-22 | 长安大学 | Rapid detection and evaluation method and system for electric automobile operation safety rack |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070112475A1 (en) * | 2005-11-17 | 2007-05-17 | Motility Systems, Inc. | Power management systems and devices |
| JP2018020775A (en) * | 2017-09-01 | 2018-02-08 | 日立オートモティブシステムズ株式会社 | Vehicle motion control system |
| US20180164825A1 (en) * | 2016-12-09 | 2018-06-14 | Zendrive, Inc. | Method and system for risk modeling in autonomous vehicles |
| CN109738815A (en) * | 2017-10-30 | 2019-05-10 | 现代自动车株式会社 | Cloud Server, vehicle and method for controlling a vehicle |
| CN110164181A (en) * | 2018-02-13 | 2019-08-23 | 阿里巴巴集团控股有限公司 | A kind of car accident detection, method for early warning, equipment and system |
| CN110414831A (en) * | 2019-07-24 | 2019-11-05 | 清华大学 | People's bus or train route coupling methods of risk assessment and device based on driver's Cognitive Perspective |
| CN110491154A (en) * | 2019-07-23 | 2019-11-22 | 同济大学 | Suggestion speed formulating method based on security risk and distance |
| CN110861531A (en) * | 2019-11-27 | 2020-03-06 | 四川野马汽车股份有限公司 | Power battery failure early warning system and method |
| CN112015843A (en) * | 2020-09-02 | 2020-12-01 | 中国科学技术大学 | Driving risk situation assessment method and system based on multi-vehicle intention interaction result |
| CN112215497A (en) * | 2020-10-14 | 2021-01-12 | 公安部交通管理科学研究所 | Pure electric vehicle operation risk early warning method |
-
2021
- 2021-02-02 CN CN202110144514.4A patent/CN112950811B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070112475A1 (en) * | 2005-11-17 | 2007-05-17 | Motility Systems, Inc. | Power management systems and devices |
| US20180164825A1 (en) * | 2016-12-09 | 2018-06-14 | Zendrive, Inc. | Method and system for risk modeling in autonomous vehicles |
| JP2018020775A (en) * | 2017-09-01 | 2018-02-08 | 日立オートモティブシステムズ株式会社 | Vehicle motion control system |
| CN109738815A (en) * | 2017-10-30 | 2019-05-10 | 现代自动车株式会社 | Cloud Server, vehicle and method for controlling a vehicle |
| CN110164181A (en) * | 2018-02-13 | 2019-08-23 | 阿里巴巴集团控股有限公司 | A kind of car accident detection, method for early warning, equipment and system |
| CN110491154A (en) * | 2019-07-23 | 2019-11-22 | 同济大学 | Suggestion speed formulating method based on security risk and distance |
| CN110414831A (en) * | 2019-07-24 | 2019-11-05 | 清华大学 | People's bus or train route coupling methods of risk assessment and device based on driver's Cognitive Perspective |
| CN110861531A (en) * | 2019-11-27 | 2020-03-06 | 四川野马汽车股份有限公司 | Power battery failure early warning system and method |
| CN112015843A (en) * | 2020-09-02 | 2020-12-01 | 中国科学技术大学 | Driving risk situation assessment method and system based on multi-vehicle intention interaction result |
| CN112215497A (en) * | 2020-10-14 | 2021-01-12 | 公安部交通管理科学研究所 | Pure electric vehicle operation risk early warning method |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113642893A (en) * | 2021-08-16 | 2021-11-12 | 公安部交通管理科学研究所 | New energy automobile operation risk assessment method |
| CN113808403A (en) * | 2021-09-26 | 2021-12-17 | 公安部交通管理科学研究所 | New energy automobile operation risk studying and judging method fusing traffic management big data |
| CN113808403B (en) * | 2021-09-26 | 2022-04-29 | 公安部交通管理科学研究所 | New energy automobile operation risk studying and judging method fusing traffic management big data |
| CN114781256A (en) * | 2022-04-18 | 2022-07-22 | 北京航空航天大学 | Power battery thermal runaway risk assessment method based on cloud lifelong learning |
| CN114781256B (en) * | 2022-04-18 | 2024-06-14 | 北京航空航天大学 | Power battery thermal runaway risk assessment method based on cloud lifetime learning |
| CN114987208A (en) * | 2022-06-07 | 2022-09-02 | 武汉理工大学 | Electric vehicle power loss risk early warning system and method |
| CN114997748A (en) * | 2022-08-01 | 2022-09-02 | 中通客车股份有限公司 | New energy automobile operation safety risk prediction method and system based on model fusion |
| CN117268793A (en) * | 2023-10-25 | 2023-12-22 | 长安大学 | Rapid detection and evaluation method and system for electric automobile operation safety rack |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112950811B (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112950811B (en) | New energy automobile region operation risk assessment and early warning system integrating whole automobile safety | |
| EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
| CN110155046B (en) | Automatic emergency braking hierarchical control method and system | |
| CN111599181B (en) | Typical natural driving scene recognition and extraction method for intelligent driving system test | |
| CN111583693B (en) | Intelligent traffic cooperative operation system for urban road and intelligent vehicle control method | |
| CN113487874B (en) | System and method for collecting, identifying and classifying following behavior scene data | |
| CN108765942B (en) | Intelligent networking automobile curve danger early warning system and method | |
| CN112654549A (en) | Method and device for controlling vehicle driving mode switching | |
| CN106601000B (en) | new energy automobile electric control system and method | |
| CN108961473A (en) | A kind of vehicle-state assessment method for early warning based on intelligent network connection automobile control centre | |
| CN109544725B (en) | Event-driven-based automatic driving accident intelligent processing method | |
| CN111231971A (en) | Automobile safety performance analysis and evaluation method and system based on big data | |
| CN114056346B (en) | Automatic driving control method and device | |
| CN111619482A (en) | Vehicle driving data acquisition and processing system and method | |
| CN112258850A (en) | Edge side multi-sensor data fusion system of vehicle-road cooperative system | |
| CN117409583A (en) | Vehicle state evaluation and early warning method based on intelligent network-connected automobile control center | |
| CN113570747A (en) | Driving safety monitoring system and method based on big data analysis | |
| CN111858719A (en) | Specific condition early warning method and system based on vehicle accident data mining analysis | |
| CN113335293B (en) | Highway road surface detection system of drive-by-wire chassis | |
| CN113885045A (en) | Method and device for detecting lane line | |
| CN111105616B (en) | Road surface information acquisition system | |
| CN116753938A (en) | Vehicle test scene generation method, device, storage medium and equipment | |
| Song et al. | State-of-the-art and development trends of energy management strategies for intelligent and connected new energy vehicles: a review | |
| US12014552B2 (en) | Intelligent vehicle systems and control logic for incident prediction and assistance in off-road driving situations | |
| CN114579088A (en) | Unmanned algorithm development method based on data mining and test closed loop |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |