WO2022213596A1 - 基于大数据的新能源汽车超载检测方法 - Google Patents

基于大数据的新能源汽车超载检测方法 Download PDF

Info

Publication number
WO2022213596A1
WO2022213596A1 PCT/CN2021/129476 CN2021129476W WO2022213596A1 WO 2022213596 A1 WO2022213596 A1 WO 2022213596A1 CN 2021129476 W CN2021129476 W CN 2021129476W WO 2022213596 A1 WO2022213596 A1 WO 2022213596A1
Authority
WO
WIPO (PCT)
Prior art keywords
target vehicle
overloaded
average speed
vehicle
probability
Prior art date
Application number
PCT/CN2021/129476
Other languages
English (en)
French (fr)
Inventor
王震坡
刘鹏
张普琛
张照生
武烨
曲昌辉
Original Assignee
北京理工大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京理工大学 filed Critical 北京理工大学
Publication of WO2022213596A1 publication Critical patent/WO2022213596A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/18Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/15Correlation function computation including computation of convolution operations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40Business processes related to the transportation industry

Definitions

  • the invention belongs to the technical field of new energy vehicle big data, and in particular relates to a method for detecting vehicle overloading by using the big data of new energy vehicles.
  • the traffic management department and its related departments spend a lot of human, material and financial resources.
  • the detection methods for overloading of traditional fuel vehicles or new energy vehicles mainly include: setting over-limit stations to carry out Detection, adding acceleration sensors to vehicles for detection, and routine inspection of vehicles overloaded by traffic control department staff are still limited to single-vehicle detection, and there are serious defects in real-time and detection efficiency, which consumes manpower. , material and financial costs are extremely high.
  • the present invention aims to solve the technical problem of low overload detection efficiency and high cost in the prior art, and provides a new energy vehicle based on big data by utilizing the advantages of new energy vehicles, big data, Internet of Vehicles and other technologies.
  • the overload detection method specifically includes the following steps:
  • step (2) is specifically as follows: obtaining the voltage and current data in the driving condition data corresponding to a plurality of consecutive segments, and calculating the total energy E consumed by a certain vehicle type on the road section by the following formula:
  • n is the number of times to collect segments
  • U k is the voltage of the kth sampling, in V
  • I k is the current of the kth sampling, in A
  • ⁇ t is the time interval between two adjacent samplings, in s
  • the unit of E is J.
  • n 1 is the total number of vehicles of the same type as the target vehicle that have been checked on the same road segment
  • n 2 is the total number of overloaded and speeding vehicles of the same type that have been checked
  • step (6) Repeat step (5) for other vehicles of the same model, and obtain the probability density function of the total average speed of the model on the road section by statistics;
  • step (6) is specifically as follows: obtaining the average speed v k corresponding to a plurality of consecutive segments, and calculating the total average speed v of a specific vehicle model on the road section by the following formula:
  • n 1 is the total number of vehicles of the same type as the target vehicle that have been checked on the same road section
  • n 3 is the total number of vehicles of the same type that have been checked that are overloaded but not speeding
  • the above method provided by the present invention can determine whether the target new energy vehicle is overloaded by calculating the overload energy consumption probability of similar models on the same road section, and comparing it with the processed traffic control historical data, which overcomes the complicated and complex problems in the prior art.
  • the single-time inspection method of single vehicle fully utilizes the advantages of new energy vehicles and big data platforms, which significantly improves the efficiency of overload inspection and reduces costs.
  • the overloading is divided into different situations of overloading and overspeeding and overloading without overspeeding, so as to effectively find the overloaded target vehicle in the state of low speed and low energy consumption, and avoid the omission of inspection results or the overspeeding of the target. Misidentification as overload ensures the accuracy of this method.
  • those skilled in the art can flexibly choose whether to adjust the accuracy of the result in combination with the subsequent detection process of the average speed.
  • FIG. 1 is a schematic flowchart of the method provided by the present invention.
  • the method for detecting overload of new energy vehicles based on big data specifically includes the following steps:
  • step (2) is specifically as follows: acquiring voltage and current data in the driving condition data corresponding to a plurality of continuous segments, and calculating the consumption of a certain vehicle type on the road section by the following formula Total energy E:
  • n is the number of times to collect segments
  • U k is the voltage of the kth sampling, in V
  • I k is the current of the kth sampling, in A
  • ⁇ t is the time interval between two adjacent samplings, in s
  • the unit of E is J.
  • the specific calculation method for determining the probability threshold of overload energy according to the historical statistical data of the traffic control department is as follows:
  • n 1 is the total number of vehicles of the same type as the target vehicle that have been checked on the same road segment
  • n 2 is the total number of overloaded and speeding vehicles of the same type that have been checked
  • the probability of the total energy of the target vehicle can be obtained. Compare the probability P(E test ) of the total energy consumed by the target vehicle when driving on the road section with the P 1 , and if P(E test )>P 1 , it is confirmed that overloading occurs.
  • the target vehicle When the target vehicle is in a low speed state, it may not be possible to correctly judge whether it is overloaded based on the energy probability alone because the energy consumed at this time is less. Since overloaded vehicles are less harmful at low speed, the continuous inspection can be terminated after the above-mentioned steps to realize the inspection of the more dangerous situation of overloading and overspeeding, which is sufficient to solve the technical problem proposed by the present invention.
  • the following steps (5)-(6) can be performed synchronously when performing the steps (1)-(3):
  • step (6) Repeat step (5) for other vehicles of the same model, and obtain the probability density function of the total average speed of the model on the road section by statistics;
  • the probability density function f v (x) of the overall average velocity by formula The probability that the overall average speed of the target vehicle can be obtained.
  • 50% ⁇ P(E test ) ⁇ P 1 because the energy consumption is still high, the probability density function of the total average speed is used to calculate the average speed probability of the target vehicle, and the average speed probability of the target vehicle is calculated according to the historical statistical data of the traffic control department.
  • the determined overspeed probability thresholds are compared to determine whether the target vehicle is overloaded.
  • step (6) the average speed v k corresponding to a plurality of consecutive segments is obtained, and the total average speed v of a vehicle of a certain type on the road section is calculated by the following formula:
  • the specific calculation method for determining the speeding probability threshold according to the historical statistical data of the traffic control department is as follows:
  • n 1 is the total number of vehicles of the same type as the target vehicle that have been checked on the same road section
  • n 3 is the total number of vehicles of the same type that have been checked that are overloaded but not speeding

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Algebra (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Operations Research (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)

Abstract

基于大数据的新能源汽车超载检测方法,通过计算同类车型在相同路段上的超载能耗概率,并与经处理的交管历史数据比较即可确定目标新能源汽车是否发生超载情况,克服了现有技术中繁复的单车单次的车辆检查方式,充分地发挥了新能源车辆以及大数据平台的优势,显著提高了超载检查的效率并降低了成本。结合对目标车辆平均速度概率的计算,将超载区分为超载且超速与超载不超速的不同情况,从而能够有效发现低速低耗能状态的超载目标车辆,避免了检查结果的遗漏或者将仅超速的目标误识别为超载,保证了该方法的精确性。本领域技术人员根据该方法所提供的教导,可以较为灵活地选择是否结合后续对平均速度的检测过程来调整结果的精确度。

Description

基于大数据的新能源汽车超载检测方法 技术领域
本发明属于新能源汽车大数据技术领域,具体涉及利用新能源汽车的大数据对车辆超载情况进行检测的方法。
背景技术
由于路况的不断改善和新能源汽车各项性能的提升,新能源汽车的超载问题也日趋严重。超载问题不仅仅会对公共道路造成破坏,还会对人员的生命财产安全造成伤害。超载问题已经成为导致交通事故的主要原因之一。
为了解决汽车超载问题,交通管理部门及其相关部门耗费大量的人力物力财力,然而在目前条件下,无论是对于传统燃油车辆亦或是新能源汽车超载的检测方法主要包括:设置超限站进行检测,给车辆加装加速度传感器进行检测以及交管部门工作人员进行车辆超载例行检查等方法,都仍然局限于单车单次的检测,在实时性和检测效率方面均存在严重缺陷,所耗费的人力、物力、财力成本极高。
发明内容
有鉴于此,本发明旨在解决现有技术中超载检测效率低下成本过高的技术问题,利用新能源汽车与大数据、车联网等技术的优势,提供了一种基于大数据的新能源汽车超载检测方法,具体包括以下步骤:
(1)对某新能源汽车车型在某一特定路段上行驶的多个连续片段所对应的行驶工况数据进行采集;
(2)利用所采集的每个片段所对应的行驶工况数据,计算出目标车辆在每个所述片段上消耗的能量;基于每个片段上消耗的能量,得到目标车辆在该路段上消耗的总能量;
(3)对同一车型其他车辆重复执行步骤(1)-(2),并统计得到该车型在该路段所消耗总能量的概率密度函数;
(4)基于所述总能量的概率密度函数计算得到该车型的待测目标车辆当前在该路段行驶时消耗的总能量的概率,并与根据交管部门的历史统计数据所确定的超载能量概率阈值比较,从而确定目标车辆是否发生超载。
进一步地,步骤(2)具体为:获取多个连续片段所对应的行驶工况数据中的电压与电流数据,通过以下公式计算某特定车型在该路段上消耗的总能量E:
Figure PCTCN2021129476-appb-000001
其中,n为采集片段的次数;U k为第k次采样的电压,单位为V;I k为第k次采样的电流,单位为A;Δt为相邻两次采样的时间间隔,单位为s;E的单位为J。
进一步地,根据交管部门的历史统计数据确定超载能量概率阈值的具体计算方法为:
Figure PCTCN2021129476-appb-000002
其中,n 1为同路段上已经检查过的与目标车辆同类型的车辆总数;n 2为已经检查过的同类车辆超载且超速的总数;
比较目标车辆在该路段行驶时消耗的总能量的概率P(E )与所述P 1,如果P(E )>P 1则确认发生超载。
进一步地,在执行所述步骤(1)-(3)后,还执行以下步骤(5)-(6):
(5)利用所采集的每个片段所对应的行驶工况数据,计算出目标车辆在每个所述片段上平均速度;基于每个片段上的平均速度,得到目标车辆在该路段上总平均速度;
(6)对同一车型其他车辆重复执行步骤(5),并统计得到该车型在该路段上总平均速度的概率密度函数;
当50%<P(E )<P 1时,则利用所述总平均速度的概率密度函数计算目标车辆平均速度的概率,并与根据交管部门的历史统计数据所确定的速度概率阈值比较,从而确定目标车辆是否发生超载。
进一步地,步骤(6)具体为:获取多个连续片段所对应的平均速度v k,通过以下公式计算某特定车型在该路段上的总平均速度v:
Figure PCTCN2021129476-appb-000003
进一步地,根据交管部门的历史统计数据确定超速概率阈值的具体计算方法为:
Figure PCTCN2021129476-appb-000004
其中,n 1为同路段上已经检查过的与目标车辆同类型的车辆总数;n 3为已经检查过的同类车辆超载但未超速的总数;
比较目标车辆在该路段行驶时总平均速度的概率P(v )与所述P 2,如果P(v )<P 2则确认发生超载,否则没有发生超载。
上述本发明所提供的方法,通过计算同类车型在相同路段上的超载能耗概率,并与经处理的交管历史数据比较即可确定目标新能源汽车是否发生超载情况,克服了现有技术中繁复的单车单次的检查方式,充分地发挥了新能源车辆以及大数据平台的优势,显著提高了超载检查的效率并降低了成本。结合对目标车辆超速概率的计算,将超载区分为超载且超速与超载不超速的不同情况,从而能够有效发现低速低耗能状态的超载目标车辆,避免了检查结果的遗漏或者将仅超速的目标误识别为超载,保证了本方法的精确性。本领域技术人员根据本发明所提供的 教导,可以较为灵活地选择是否结合后续对平均速度的检测过程来调整结果的精确度。
附图说明
图1为本发明所提供方法的流程示意图。
具体实施方式
下面将结合附图对本发明的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
本发明所提供的基于大数据的新能源汽车超载检测方法,具体包括以下步骤:
(1)对某新能源汽车车型在某一特定路段上行驶的多个连续片段所对应的行驶工况数据进行采集;
(2)利用所采集的每个片段所对应的行驶工况数据,计算出目标车辆在每个所述片段上消耗的能量;基于每个片段上消耗的能量,得到目标车辆在该路段上消耗的总能量;
(3)对同一车型其他车辆重复执行步骤(1)-(2),并统计得到该车型在该路段所消耗总能量的概率密度函数;
(4)基于所述总能量的概率密度函数计算得到该车型的待测目标车辆当前在该路段行驶时消耗的总能量的概率,并与根据交管部门的历史统计数据所确定的超载能量概率阈值比较,从而确定目标车辆是否发生超载。
在本发明的一个优选实施方式中,步骤(2)具体为:获取多个连续片段所对应的行驶工况数据中的电压与电流数据,通过以下公式计算某特定车型车辆在该路段上消耗的总能量E:
Figure PCTCN2021129476-appb-000005
其中,n为采集片段的次数;U k为第k次采样的电压,单位为V;I k为第k次采样的电流,单位为A;Δt为相邻两次采样的时间间隔,单位为s;E的单位为J。
根据交管部门的历史统计数据确定超载能量概率阈值的具体计算方法为:
Figure PCTCN2021129476-appb-000006
其中,n 1为同路段上已经检查过的与目标车辆同类型的车辆总数;n 2为已经检查过的同类车辆超载且超速的总数;
利用总能量的概率密度函数f E(x)通过公式
Figure PCTCN2021129476-appb-000007
即可得到目标车辆总能量的概率。比较目标车辆在该路段行驶时消耗的总能量的概率P(E )与所 述P 1,如果P(E )>P 1则确认发生超载。
当目标车辆处于低速状态,由于此时消耗的能量较少,仅根据能量概率可能无法正确判断其是否超载。由于低速时超载车辆的危害性较小,因此可以在上述步骤实现对超载且超速这种更具危险性的情况检查后终止继续检查,此时已足以解决本发明所提出的技术问题。而对于需要更全面地检查超载的场景,则可在执行所述步骤(1)-(3)时同步执行以下步骤(5)-(6):
(5)利用所采集的每个片段所对应的行驶工况数据,计算出目标车辆在每个所述片段上平均速度;基于每个片段上的平均速度,得到目标车辆在该路段上总平均速度;
(6)对同一车型其他车辆重复执行步骤(5),并统计得到该车型在该路段上总平均速度的概率密度函数;
利用总平均速度的概率密度函数f v(x)通过公式
Figure PCTCN2021129476-appb-000008
可得到目标车辆总平均速度的概率。当50%<P(E )<P 1时,由于消耗的能量仍然较高,故利用所述总平均速度的概率密度函数计算目标车辆的平均速度概率,并与根据交管部门的历史统计数据所确定的超速概率阈值比较,从而确定目标车辆是否发生超载。
在步骤(6)中,获取多个连续片段所对应的平均速度v k,通过以下公式计算某特定车型车辆在该路段上的总平均速度v:
Figure PCTCN2021129476-appb-000009
根据交管部门的历史统计数据确定超速概率阈值的具体计算方法为:
Figure PCTCN2021129476-appb-000010
其中,n 1为同路段上已经检查过的与目标车辆同类型的车辆总数;n 3为已经检查过的同类车辆超载但未超速的总数;
比较目标车辆在该路段行驶时总平均速度的概率P(v )与所述P 2,如果P(v )<P 2则说明目标车辆在速度较低的状态下仍然消耗了较高的能量,因此可以确认发生超载,否则可以确认没有发生超载。
应理解,本发明实施例中各步骤的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本发明实施例的实施过程构成任何限定。
尽管已经示出和描述了本发明的实施例,对于本领域的普通技术人员而言,可以理解在不脱离本发明的原理和精神的情况下可以对这些实施例进行多种变化、修改、替换和变型,本发明的范围由所附权利要求及其等同物限定。

Claims (6)

  1. 基于大数据的新能源汽车超载检测方法,其特征在于:具体包括以下步骤:
    (1)对某一特定的新能源汽车车型在某一特定路段上行驶的多个连续片段所对应的行驶工况数据进行采集;
    (2)利用所采集的每个片段所对应的行驶工况数据,计算出目标车辆在每个所属片段上消耗的能量;基于每个片段上消耗的能量,得到目标车辆在该路段上消耗的总能量;
    (3)对同一车型其他车辆重复执行步骤(1)-(2),并统计得到该车型在该路段所消耗总能量的概率密度函数;
    (4)基于所述总能量的概率密度函数计算得到该车型的待测目标车辆当前在该路段行驶时消耗的总能量的概率,并与根据交管部门的历史统计数据所确定的超载能量概率阈值比较,从而确定目标车辆是否发生超载。
  2. 如权利要求1所述的方法,其特征在于:步骤(2)具体为:获取多个连续片段所对应的行驶工况数据中的电压与电流数据,通过以下公式计算某特定车型目标车辆在该路段上消耗的总能量E:
    Figure PCTCN2021129476-appb-100001
    其中,n为采集片段的次数;U k为第k次采样的电压,单位为V;I k为第k次采样的电流,单位为A;Δt为相邻两次采样的时间间隔,单位为s;E的单位为J。
  3. 如权利要求1所述的方法,其特征在于:根据交管部门的历史统计数据确定超载能量概率阈值的具体计算方法为:
    Figure PCTCN2021129476-appb-100002
    其中,n 1为同路段上已经检查过的与目标车辆同类型的车辆总数;n 2为已经检查过的同类车辆超载且超速的总数;
    比较目标车辆在该路段行驶时消耗的总能量的概率P(E )与所述P 1,如果P(E )>P 1则确认发生超载。
  4. 如权利要求3所述的方法,其特征在于:在执行所述步骤(1)-(3)后,还执行以下步骤(5)-(6):
    (5)利用所采集的每个片段所对应的行驶工况数据,计算出目标车辆在每个所述片段上平均速度;基于每个片段上的平均速度,得到目标车辆在该路段上总平均速度;
    (6)对同一车型其他车辆重复执行步骤(5),并统计得到该车型在该路段上总平均速度的概率密度函数;
    当50%<P(E )<P 1时,则利用所述总平均速度的概率密度函数计算目标车辆平均速度的概率,并与根据交管部门的历史统计数据所确定的速度概率阈值比较,从而确定目标车辆是否发生超载。
  5. 如权利要求4所述的方法,其特征在于:步骤(6)具体为:获取多个连续片段所对应的平均速度v k,通过以下公式计算某特定车型在该路段上的总平均速度v:
    Figure PCTCN2021129476-appb-100003
  6. 如权利要求5所述的方法,其特征在于:根据交管部门的历史统计数据确定速度概率阈值的具体计算方法为:
    Figure PCTCN2021129476-appb-100004
    其中,n 1为同路段上已经检查过的与目标车辆同类型的车辆总数;n 3为已经检查过的同类车辆超载但未超速的总数;
    比较目标车辆在该路段行驶时总平均速度的概率P(v )与所述P 2,如果P(v )<P 2则确认发生超载,否则没有发生超载。
PCT/CN2021/129476 2021-04-07 2021-11-09 基于大数据的新能源汽车超载检测方法 WO2022213596A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110372170.2 2021-04-07
CN202110372170.2A CN113158141B (zh) 2021-04-07 2021-04-07 基于大数据的新能源汽车超载检测方法

Publications (1)

Publication Number Publication Date
WO2022213596A1 true WO2022213596A1 (zh) 2022-10-13

Family

ID=76888559

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/129476 WO2022213596A1 (zh) 2021-04-07 2021-11-09 基于大数据的新能源汽车超载检测方法

Country Status (2)

Country Link
CN (1) CN113158141B (zh)
WO (1) WO2022213596A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116152757A (zh) * 2023-04-18 2023-05-23 深圳亿维锐创科技股份有限公司 一种基于多点位的称重数据分析方法及相关装置

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113158141B (zh) * 2021-04-07 2023-02-28 北京理工大学 基于大数据的新能源汽车超载检测方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170309093A1 (en) * 2014-11-11 2017-10-26 Chunkui FENG Vehicle operation monitoring, overseeing, data processing and overload monitoring method and system
CN108860011A (zh) * 2018-04-17 2018-11-23 北京理工大学 一种车辆超载识别方法及系统
CN111762096A (zh) * 2020-06-27 2020-10-13 王亚鹏 一种基于人工智能的新能源汽车安全预警方法及系统
CN113158141A (zh) * 2021-04-07 2021-07-23 北京理工大学 基于大数据的新能源汽车超载检测方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101887639A (zh) * 2010-06-25 2010-11-17 苏州位置科技有限公司 基于can总线的车辆超载检测系统和检测方法
CN111027146B (zh) * 2019-12-30 2023-11-24 行蜂科技(深圳)有限责任公司 一种车辆载荷动态实时计算方法
CN111833604B (zh) * 2020-07-10 2021-10-29 北京交通大学 基于驾驶行为特征提取的车辆载重状态识别方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170309093A1 (en) * 2014-11-11 2017-10-26 Chunkui FENG Vehicle operation monitoring, overseeing, data processing and overload monitoring method and system
CN108860011A (zh) * 2018-04-17 2018-11-23 北京理工大学 一种车辆超载识别方法及系统
CN111762096A (zh) * 2020-06-27 2020-10-13 王亚鹏 一种基于人工智能的新能源汽车安全预警方法及系统
CN113158141A (zh) * 2021-04-07 2021-07-23 北京理工大学 基于大数据的新能源汽车超载检测方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116152757A (zh) * 2023-04-18 2023-05-23 深圳亿维锐创科技股份有限公司 一种基于多点位的称重数据分析方法及相关装置
CN116152757B (zh) * 2023-04-18 2023-07-07 深圳亿维锐创科技股份有限公司 一种基于多点位的称重数据分析方法及相关装置

Also Published As

Publication number Publication date
CN113158141A (zh) 2021-07-23
CN113158141B (zh) 2023-02-28

Similar Documents

Publication Publication Date Title
WO2022213596A1 (zh) 基于大数据的新能源汽车超载检测方法
CN109191830B (zh) 一种基于视频图像处理的道路拥堵检测方法
CN104408925B (zh) 基于陈列雷达的交叉口运行状态评价方法
CN109142524A (zh) 一种轨道损伤检测方法、装置及设备
CN102881162B (zh) 大规模交通信息的数据处理及融合方法
CN104464307B (zh) 一种基于视频的隧道交通拥堵事件自动检测方法
CN111505010A (zh) 一种基于云平台的桥梁安全检测系统
CN116644373B (zh) 基于人工智能的汽车流量数据分析管理系统
CN104809878A (zh) 利用公交车gps数据检测城市道路交通异常状态的方法
CN104392610A (zh) 基于分布式视频的高速路交通事件影响范围动态监控方法
CN112347943A (zh) 一种基于YOLOV4的anchor优化安全帽检测方法
CN106227859A (zh) 从gps数据中识别交通工具的方法
CN108009574B (zh) 一种轨道扣件检测方法
CN102042986A (zh) 基于图像和fpga的汽车尾气自动监测
CN101075377A (zh) 基于偏最小二乘原理的高速公路交通事件自动检测方法
CN111598424A (zh) 一种基于重型柴油车远程监控数据的排放计算方法
CN109003442B (zh) 一种道路延误时间计算及交通拥堵情况确定方法、系统
CN104123840B (zh) 基于视频检测技术的车流密度定性判别方法
CN106910334B (zh) 一种基于大数据预测路段状况的方法及装置
CN113052196A (zh) 一种基于贪心算法的汽车工况构建方法
CN110060370B (zh) 车辆急加速急减速次数等效统计方法
CN112948965A (zh) 一种基于机器学习和统计验证的汽车行驶工况的构建方法
CN109344903A (zh) 基于车载感知数据的城市道路路面故障实时检测方法
CN110047167B (zh) 车辆急转弯次数等效统计方法
CN103778782A (zh) 一种基于半监督机器学习的交通状态划分方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21935814

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21935814

Country of ref document: EP

Kind code of ref document: A1