WO2020187113A1 - Method for predicting emission amount of single vehicle - Google Patents
Method for predicting emission amount of single vehicle Download PDFInfo
- Publication number
- WO2020187113A1 WO2020187113A1 PCT/CN2020/078891 CN2020078891W WO2020187113A1 WO 2020187113 A1 WO2020187113 A1 WO 2020187113A1 CN 2020078891 W CN2020078891 W CN 2020078891W WO 2020187113 A1 WO2020187113 A1 WO 2020187113A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- model
- emission
- emissions
- single vehicle
- predicting
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 230000001133 acceleration Effects 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 5
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 7
- 239000013598 vector Substances 0.000 abstract description 4
- 238000012216 screening Methods 0.000 abstract 1
- 238000012360 testing method Methods 0.000 description 6
- BUCXEFZXWKUCCY-UHFFFAOYSA-N 4-methyl-3-(2-phenylethyl)-1,2,4-oxadiazol-5-one Chemical compound O1C(=O)N(C)C(CCC=2C=CC=CC=2)=N1 BUCXEFZXWKUCCY-UHFFFAOYSA-N 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000002229 photoelectron microspectroscopy Methods 0.000 description 3
- 239000000446 fuel Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G06Q50/40—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Definitions
- the invention belongs to the field of transportation, in particular to a method for predicting the emission of a single vehicle.
- AVL-Cruise simulation software
- MOVES models such as MOVES.
- the user uses the VSPbin distribution to establish an effective correlation between vehicle specific power, vehicle operating speed, and transient pollutant emission rate. Based on a large amount of emission data, considering the driving characteristic data and adjustment factors of the fleet, it can determine or Estimate current and future vehicle activity levels, technical conditions, and overall emission levels under management factors.
- emissions are also affected by operating conditions. Traditional modeling methods are complicated and cannot truly reflect the actual emissions of vehicles.
- the present invention proposes a method for predicting the emissions of a single vehicle, and the technical solutions adopted are as follows:
- a method for predicting the emissions of a single vehicle The emissions of a single vehicle are composed of two parts: the idle emission and the cumulative emission of the sports segment.
- the emission of each sports segment is predicted by the RVM model.
- the idle emission is the idle duration and the idle emission rate The product of.
- the input of the model is part of the feature value of the motion segment, and the type of the feature value as the model input is determined through the mutual information value of each feature value in the motion segment and the emission amount.
- the parameters of the kernel function are determined by the leapfrog algorithm.
- the input when predicting the emission of a moving segment through the RVM model, the input includes the duration of the moving segment, the relative positive acceleration and the average velocity.
- the beneficial effect of the present invention is that the emission prediction method proposed by the present invention is used to predict the emission of a single vehicle, and can describe the relationship between the vehicle operating speed and the emission level in the current state.
- the emission level is unknown. Only by investing in low-cost collection of a small amount of random driving data as input to the model, the model can directly output the emission results, which is simple and easy to implement.
- Figure 1 is a flowchart of the establishment and prediction of a single vehicle emission model
- Figure 2 is a histogram of mutual information values between eigenvalues and emissions.
- the emission of the motion segment is predicted by the RVM (Relevance Vector Machine) model, where the steps of establishing the RVM model include:
- Select 300 sets of PEMS test data of heavy trucks, including vehicle speed, NOx emissions, etc., and divide each set of test data into idle speed segments and motion segments;
- the duration, average speed, maximum speed and emissions are directly obtained through raw data.
- ⁇ i is the acceleration corresponding to the acceleration point
- ⁇ is the average acceleration during the acceleration period
- i is the sampling time
- vi is the speed of the vehicle in the i-th second
- T is the total duration of the motion segment
- the acceleration (deceleration/constant speed) ratio is the ratio of the duration of all acceleration (deceleration/constant speed) conditions of the motion segment to the total duration of the motion segment.
- MI(t,C) H(t)+H(C)-H(t,C)
- t is a characteristic value of the moving segment
- C is the total emission of the short stroke of the moving segment
- MI(t, C) is the mutual information value of the two
- H(t) is the entropy of the characteristic value t
- H( C) is the entropy of emissions C
- H(t, C) is the joint entropy of t and C.
- the selected three key characteristic values are the duration of the motion segment, the relative positive acceleration, and the average velocity.
- the kernel function calculation process when the kernel function calculation process is optimized by the leapfrog algorithm, it includes:
- One w i corresponds to a training sample
- L is the number of training samples
- C is the set upper limit.
- the kernel function may be a common kernel function such as a polynomial kernel function, an RBF kernel function, or a Sigmoid kernel function.
- the original data of the vehicle is divided into the idle segment and the motion segment, the total duration of the idle segment is obtained, and the total duration is multiplied by the idle emission rate to obtain the idle emission K 1 .
- the key feature values in the motion segment after normalization, are input into the RVM model to obtain the emissions corresponding to the motion segment, and the emissions of all motion segments are accumulated to obtain the sum of the motion emissions K 2 , K 1 , and K 2 That is the single vehicle emissions.
Abstract
A method for predicting emission amount of a single vehicle. A relevance vector machine model is established by using actual working condition features of a vehicle and corresponding emission data; a mutual information algorithm is introduced when the model is established, implementing screening of key features; and a frog leaping algorithm is introduced so as to optimize the calculation process of kernel function parameters of a relevance vector machine. By using the model, for a vehicle with an unknown emission level, only a small amount of random driving data needs to be acquired at low cost to serve as model input, and thus the model can directly output an emission result. The model is simple, convenient, and easy to implement.
Description
本发明属于交通运输领域，尤其是一种用于预测单车排放量的方法。The invention belongs to the field of transportation, in particular to a method for predicting the emission of a single vehicle.
目前，对于油耗预测，各大车企及发动机企业都有成型的模拟软件(如AVL-Cruise)，可以准确的预测车辆实际运行中的油耗。对于宏观车队排放预测而言，有MOVES等成型的模型。使用者利用VSPbin分布建立了机动车比功率、车辆运行工况速度、污染物瞬态排放速率之间的有效关联，以大量排放数据为基础，考虑车队的行驶特征数据和调整因子，能够确定或估算当前以及未来车辆活动水平和技术条件、管理因素下的整体排放水平。但对于单车车辆排放预测而言，由于排放除受机内净化技术和后处理装置的影响外，还受运行工况的影响。传统的建模方法复杂，且不能真实地反映车辆的实际排放情况。At present, for fuel consumption prediction, major car companies and engine companies have formed simulation software (such as AVL-Cruise) that can accurately predict fuel consumption in actual vehicle operation. For macro fleet emission forecasts, there are models such as MOVES. The user uses the VSPbin distribution to establish an effective correlation between vehicle specific power, vehicle operating speed, and transient pollutant emission rate. Based on a large amount of emission data, considering the driving characteristic data and adjustment factors of the fleet, it can determine or Estimate current and future vehicle activity levels, technical conditions, and overall emission levels under management factors. However, for single-vehicle vehicle emission forecasts, in addition to the impact of in-flight purification technology and after-treatment devices, emissions are also affected by operating conditions. Traditional modeling methods are complicated and cannot truly reflect the actual emissions of vehicles.
发明内容Summary of the invention
本发明提出一种用于预测单车排放量的方法，采用的技术方案如下：The present invention proposes a method for predicting the emissions of a single vehicle, and the technical solutions adopted are as follows:
一种用于预测单车排放量的方法，单车排放量由怠速排放量和运动片段排放累加量两部分组成，每段运动片段排放量通过RVM模型预测得到，怠速排放量为怠速时长与怠速排放率的乘积。A method for predicting the emissions of a single vehicle. The emissions of a single vehicle are composed of two parts: the idle emission and the cumulative emission of the sports segment. The emission of each sports segment is predicted by the RVM model. The idle emission is the idle duration and the idle emission rate The product of.
进一步的，训练RVM模型时，模型的输入为运动片段的部分特征值，通过运动片段中各特征值与排放量的互信息值，确定作为模型输入的特征值的种类。Further, when training the RVM model, the input of the model is part of the feature value of the motion segment, and the type of the feature value as the model input is determined through the mutual information value of each feature value in the motion segment and the emission amount.
进一步的，训练RVM模型时，通过蛙跳算法确定核函数的参数。Further, when training the RVM model, the parameters of the kernel function are determined by the leapfrog algorithm.
进一步的，通过RVM模型预测运动片段排放量时，输入包括运动片段时长、相对正加速度和平均速度。Further, when predicting the emission of a moving segment through the RVM model, the input includes the duration of the moving segment, the relative positive acceleration and the average velocity.
与现有技术相比，本发明的有益效果在于：本发明提出的排放预测方法用于对单车排放进行预测，能够很好的描述车辆运行速度与当前状态的排放水平的关系，对于排放水平未知的车辆，只需通过投入低成本采集少量随机行驶数据，以此作为模型输入，模型便能直接输出排放结果，简便易行。Compared with the prior art, the beneficial effect of the present invention is that the emission prediction method proposed by the present invention is used to predict the emission of a single vehicle, and can describe the relationship between the vehicle operating speed and the emission level in the current state. The emission level is unknown. Only by investing in low-cost collection of a small amount of random driving data as input to the model, the model can directly output the emission results, which is simple and easy to implement.
图1是单车排放模型建立与预测流程图；Figure 1 is a flowchart of the establishment and prediction of a single vehicle emission model;
图2是特征值与排放量的互信息值直方图。Figure 2 is a histogram of mutual information values between eigenvalues and emissions.
本实施例中，通过RVM(相关向量机)模型预测运动片段的排放量，其中RVM模型建立的步骤包括：In this embodiment, the emission of the motion segment is predicted by the RVM (Relevance Vector Machine) model, where the steps of establishing the RVM model include:
S1.选取300组重型货车的PEMS试验数据，包括车速、NOx排放等，并将每组试验数据划分为怠速片段和运动片段；S1. Select 300 sets of PEMS test data of heavy trucks, including vehicle speed, NOx emissions, etc., and divide each set of test data into idle speed segments and motion segments;
S2.通过试验数据中所有怠速片段总时长和总排量的比值，计算出怠速排放率；S2. Calculate the idling emission rate based on the ratio of the total duration of all idling segments to the total displacement in the test data;
S3.计算每组试验数据中各运动片段的特征值，包括时长(t
1)，平均速度(t
2)，最大速度(t
3)，加速段平均加速度(t
4)，减速段平均减速度(t
5)，加速比例(t
6)，减速比例(t
7)，匀速比例(t
8)，相对正加速度(t
9)，最大加速度(t
10)，并记录每个运动片段对应的排放量C。
S3. Calculate the characteristic value of each motion segment in each set of test data, including duration (t 1 ), average speed (t 2 ), maximum speed (t 3 ), average acceleration during acceleration (t 4 ), average deceleration during deceleration (t 5 ), acceleration ratio (t 6 ), deceleration ratio (t 7 ), constant speed ratio (t 8 ), relative positive acceleration (t 9 ), maximum acceleration (t 10 ), and record the emission corresponding to each motion segment量 C.
本实施例中，时长，平均速度，最大速度和排放量通过原始数据直接获取。In this embodiment, the duration, average speed, maximum speed and emissions are directly obtained through raw data.
加速段平均加速度的计算公式为：The calculation formula of the average acceleration in the acceleration stage is:
其中α
i为加速点对应的加速度，α为加速段平均加速度，i为采样时刻，vi为车辆在第i秒的速度，T为运动片段工况总时长，减速段平均减速度与加速段平均加速度的计算方法相似，在此不再赘述。
Among them, α i is the acceleration corresponding to the acceleration point, α is the average acceleration during the acceleration period, i is the sampling time, vi is the speed of the vehicle in the i-th second, T is the total duration of the motion segment, the average deceleration during the deceleration period and the average acceleration during the acceleration period The calculation method of acceleration is similar, so I won't repeat it here.
加速(减速/匀速)比例为运动片段所有加速(减速/匀速)工况时长占运动片段工况总时长的比例。The acceleration (deceleration/constant speed) ratio is the ratio of the duration of all acceleration (deceleration/constant speed) conditions of the motion segment to the total duration of the motion segment.
相对正加速度的计算公式为：The calculation formula of relative positive acceleration is:
其中vi为车辆在第i秒的速度，T为运动片段工况总时长，
为加速度大于0m/s
2的加速度值，x为车辆运动片段运行里程。
Where vi is the speed of the vehicle in the i second, and T is the total duration of the motion segment, Is the acceleration value with acceleration greater than 0m/s 2 and x is the mileage of the vehicle motion segment.
本实施例中，其中5个运动片段的特征值如下表所示：In this embodiment, the feature values of 5 motion segments are shown in the following table:
表1Table 1
表2Table 2
S4.利用互信息算法，求取每个运动片段中，10项特征值与排放量的互信息值MI，统计所有运动片段中互信息值最大的特征值，选取其中出现频率最大的三个特征值作为关键特征值。互信息值的计算公式为：S4. Use the mutual information algorithm to obtain the mutual information value MI of 10 feature values and emissions in each motion segment, count the eigenvalues with the largest mutual information value in all motion segments, and select the three most frequently occurring features The value is used as the key characteristic value. The calculation formula of mutual information value is:
MI(t,C)＝H(t)+H(C)-H(t,C)MI(t,C)=H(t)+H(C)-H(t,C)
式中，t为运动片段某一特征值，C为运动片段短行程的总排放量，MI(t,C)为两者的互信息值，H(t)为特征值t的熵，H(C)为排放量C的熵，H(t,C)为t和C的联合熵。In the formula, t is a characteristic value of the moving segment, C is the total emission of the short stroke of the moving segment, MI(t, C) is the mutual information value of the two, H(t) is the entropy of the characteristic value t, H( C) is the entropy of emissions C, and H(t, C) is the joint entropy of t and C.
本实施例中，选取的三个关键特征值为运动片段的时长、相对正加速度和平均速度。In this embodiment, the selected three key characteristic values are the duration of the motion segment, the relative positive acceleration, and the average velocity.
S5.对关键特征值进行归一化处理，以去除各特征的单位和数量级。S5. Normalize the key feature values to remove the unit and magnitude of each feature.
S6.选择200组PEMS试验数据中，进行归一化处理后的、每个运动片段对应的关键特征值作为输入值，每个运动片段对应的排放量作为输出值，训练并建立RVM模型，训练时通过蛙跳算法对核函数参数的计算过程进行优化。S6. Select 200 sets of PEMS test data, the key feature value corresponding to each motion segment after normalization processing is used as the input value, and the emission volume corresponding to each motion segment is used as the output value, train and establish the RVM model, train The calculation process of the kernel function parameters is optimized by the leapfrog algorithm.
本实施例中，通过蛙跳算法对核函数计算过程进行优化时，包括：In this embodiment, when the kernel function calculation process is optimized by the leapfrog algorithm, it includes:
S601.首先初始化总种群，具体为随机产生P个L维的向量，其分量w
i为区间[0,C]中 的随机数，并设定总种群迭代次数为g′，子种群个数为Q，子种群迭代次数为g。
S601. First initialize the total population, specifically, randomly generate P L-dimensional vectors, whose components w i are random numbers in the interval [0, C], and set the iteration number of the total population as g′, and the number of sub-populations as Q, the number of iterations of the subpopulation is g.
其中一个w
i对应一个训练样本，L为训练样本的数量，C为设定的上限值。
One w i corresponds to a training sample, L is the number of training samples, and C is the set upper limit.
S602.计算每个分量w
i的适应度值，若违反约束条约
(约束条约中y
i为w
i对应的期望值)，则定义该分量的适应度值为一个无穷大正数，否则保持适应度值不变，并划分子种群。
S602. Calculate the fitness value of each component w i , if the binding treaty is violated (In the constraint treaty, y i is the expected value corresponding to w i ), the fitness value of this component is defined as an infinite positive number, otherwise the fitness value is kept unchanged and the subpopulations are divided.
S603.针对每个子种群，利用蛙跳算法中对最差分量的更新公式寻找子种群中的最优分量，然后混合所有子种群生成新的总种群，并返回S602，如此反复直到满足总种群的迭代次数，并返回适应度最好的分量w
g。
S603. For each sub-population, use the update formula of the least difference component in the leapfrog algorithm to find the optimal component in the sub-population, then mix all the sub-populations to generate a new total population, and return to S602, and repeat until the total population is satisfied The number of iterations, and returns the best fitness component w g .
S604.计算w
g中的非零解，该解即为核函数对应的参数。
S604. Calculate the non-zero solution in w g , and the solution is the parameter corresponding to the kernel function.
本实施例中，核函数可以为多项式核函数、RBF核函数或者Sigmoid核函数等常见的核函数。In this embodiment, the kernel function may be a common kernel function such as a polynomial kernel function, an RBF kernel function, or a Sigmoid kernel function.
S7.选择另外100组PEMS试验数据中，进行归一化处理后的每个运动片段对应的关键特征值作为输入值，将输出的排放量和实际排放量进行对比，以验证建立的RVM模型。S7. Select the key feature value corresponding to each motion segment after normalization in another 100 sets of PEMS test data as the input value, and compare the output emissions with the actual emissions to verify the established RVM model.
本实施例中，预测单车排放量时，将车辆原始数据划分为怠速片段和运动片段，求取怠速片段的总时长，用总时长乘以怠速排放率得到怠速排放量K
1，求取每个运动片段中的关键特征值，归一化后，输入到RVM模型中求取该运动片段对应的排放量，累加所有运动片段的排放量，得到运动排放量K
2，K
1、K
2的和即为单车排放量。
In this embodiment, when predicting the emissions of a single vehicle, the original data of the vehicle is divided into the idle segment and the motion segment, the total duration of the idle segment is obtained, and the total duration is multiplied by the idle emission rate to obtain the idle emission K 1 . The key feature values in the motion segment, after normalization, are input into the RVM model to obtain the emissions corresponding to the motion segment, and the emissions of all motion segments are accumulated to obtain the sum of the motion emissions K 2 , K 1 , and K 2 That is the single vehicle emissions.
以上所述仅为本发明创造的较佳实施例而已，并不用以限制本发明创造，凡在本发明创造的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明创造的保护范围之内。The above are only the preferred embodiments created by the present invention and are not intended to limit the creation of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in Within the scope of protection created by the present invention.
Claims (4)
- 一种用于预测单车排放量的方法，其特征在于，单车排放量由怠速排放量和运动片段排放累加量两部分组成，每段运动片段排放量通过RVM模型预测得到，怠速排放量为怠速时长与怠速排放率的乘积。A method for predicting the emissions of a single vehicle, which is characterized in that the emissions of a single vehicle are composed of two parts: the emissions at idle speed and the cumulative emissions of the sport segments. The emissions of each sport segment are predicted by the RVM model, and the idle emissions are the idle duration. The product of the idling emission rate.
- 如权利要求1所述一种用于预测单车排放量的方法，其特征在于，训练RVM模型时，模型的输入为运动片段的部分特征值，通过运动片段中各特征值与排放量的互信息值，确定作为模型输入的特征值的种类。The method for predicting the emission of a single vehicle according to claim 1, wherein when training the RVM model, the input of the model is part of the feature values of the motion segment, and the mutual information between each feature value and the emission volume in the motion segment Value, which determines the type of feature value that is input to the model.
- 如权利要求2所述一种用于预测单车排放量的方法，其特征在于，训练RVM模型时，通过蛙跳算法确定核函数的参数。The method for predicting the emissions of a single vehicle according to claim 2, wherein when the RVM model is trained, the parameters of the kernel function are determined by the leapfrog algorithm.
- 如权利要求2所述一种用于预测单车排放量的方法，其特征在于，通过RVM模型预测运动片段排放量时，输入包括运动片段时长、相对正加速度和平均速度。The method for predicting the emission of a single vehicle according to claim 2, wherein when the emission of a moving segment is predicted by the RVM model, the input includes the duration of the moving segment, the relative positive acceleration and the average speed.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910199075.XA CN109948237B (en) | 2019-03-15 | 2019-03-15 | Method for predicting emission of bicycle |
| CN201910199075.X | 2019-03-15 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020187113A1 true WO2020187113A1 (en) | 2020-09-24 |
Family
ID=67010114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/078891 WO2020187113A1 (en) | 2019-03-15 | 2020-03-12 | Method for predicting emission amount of single vehicle |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN109948237B (en) |
| LU (1) | LU102193B1 (en) |
| WO (1) | WO2020187113A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529104A (en) * | 2020-12-23 | 2021-03-19 | 东软睿驰汽车技术（沈阳）有限公司 | Vehicle fault prediction model generation method, fault prediction method and device |
| CN113806675A (en) * | 2021-08-06 | 2021-12-17 | 中汽研汽车检验中心（天津）有限公司 | NOx emission and oil consumption characteristic analysis method |
| CN114821854A (en) * | 2022-03-28 | 2022-07-29 | 中汽研汽车检验中心（天津）有限公司 | Method for evaluating influence of working condition switching on vehicle oil consumption |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948237B (en) * | 2019-03-15 | 2023-06-02 | 中国汽车技术研究中心有限公司 | Method for predicting emission of bicycle |
| CN113781771B (en) * | 2021-08-17 | 2022-10-28 | 四川省生态环境科学研究院 | Online operation method of IVE model |
| CN114991922B (en) * | 2022-05-30 | 2024-01-23 | 中国汽车工程研究院股份有限公司 | Real-time early warning method for exceeding of NOx emission of vehicle |
| CN117074046B (en) * | 2023-10-12 | 2024-01-02 | 中汽研汽车检验中心(昆明)有限公司 | Automobile laboratory emission test method and device in plateau environment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150317844A1 (en) * | 2014-05-02 | 2015-11-05 | Kookmin University Industry-Academic Cooperation Foundation | Method of processing and analysing vehicle driving big data and system thereof |
| CN106845371A (en) * | 2016-12-31 | 2017-06-13 | 中国科学技术大学 | A kind of city road network automotive emission remote sensing monitoring system |
| CN107368913A (en) * | 2017-06-15 | 2017-11-21 | 中国汽车技术研究中心 | A kind of oil consumption Forecasting Methodology based on least square method supporting vector machine |
| CN107545122A (en) * | 2017-09-27 | 2018-01-05 | 重庆长安汽车股份有限公司 | A kind of simulation system of the vehicle gaseous effluent based on neutral net |
| CN107886188A (en) * | 2017-10-18 | 2018-04-06 | 东南大学 | Liquefied natural gas public transport exhaust emissions Forecasting Methodology |
| CN108629450A (en) * | 2018-04-26 | 2018-10-09 | 东南大学 | A kind of liquefied natural gas bus exhaust emissions prediction technique |
| CN109948237A (en) * | 2019-03-15 | 2019-06-28 | 中国汽车技术研究中心有限公司 | A method of for predicting bicycle discharge amount |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4318299B2 (en) * | 2004-03-31 | 2009-08-19 | 株式会社山武 | Method and apparatus for creating prediction model for fuel consumption or CO2 emissions |
| JP4853969B2 (en) * | 2006-11-28 | 2012-01-11 | 範幸 杉本 | Carbon dioxide display device for automobile with evaluation device |
| US8896682B2 (en) * | 2008-12-19 | 2014-11-25 | The Johns Hopkins University | System and method for automated detection of age related macular degeneration and other retinal abnormalities |
| CN101519073A (en) * | 2009-04-07 | 2009-09-02 | 北京大学 | Method for forecasting running load of hybrid electric vehicle |
| FR2984557B1 (en) * | 2011-12-20 | 2014-07-25 | IFP Energies Nouvelles | SYSTEM AND METHOD FOR PREDICTING EMISSIONS OF POLLUTANTS OF A VEHICLE WITH SIMULTANEOUS CALCULATIONS OF CHEMICAL KINETICS AND EMISSIONS |
| US20130274952A1 (en) * | 2012-04-16 | 2013-10-17 | Feisel Weslati | Predictive powertrain control using driving history |
| CN104680232A (en) * | 2014-10-28 | 2015-06-03 | 芜湖杰诺瑞汽车电器系统有限公司 | RVM (Relevance Vector Machine)-based engine failure detecting method |
| CN105966195B (en) * | 2016-05-31 | 2018-09-25 | 中国汽车技术研究中心 | A kind of air quality in vehicle intelligent management system and its application method |
| CN106446398B (en) * | 2016-09-20 | 2019-08-20 | 中山大学 | Light-duty vehicle rate of discharge calculation method based on traffic circulation data and deterioration rate |
| JP7162814B2 (en) * | 2017-07-31 | 2022-10-31 | 本田技研工業株式会社 | Control device |
| CN108596104B (en) * | 2018-04-26 | 2021-01-05 | 安徽大学 | Wheat powdery mildew remote sensing monitoring method with disease characteristic preprocessing function |
| CN108717165A (en) * | 2018-05-28 | 2018-10-30 | 桂林电子科技大学 | Lithium ion battery SOC on-line prediction methods based on data-driven method |
| CN108846526A (en) * | 2018-08-08 | 2018-11-20 | 华北电力大学 | A kind of CO2 emissions prediction technique |
| CN109443779A (en) * | 2018-11-07 | 2019-03-08 | 中国汽车技术研究中心有限公司 | A kind of dynamic diagnosis extracts diesel vehicle actual motion NOXThe method and apparatus of maximum discharge bad working environments |
-
2019
- 2019-03-15 CN CN201910199075.XA patent/CN109948237B/en active Active
-
2020
- 2020-03-12 WO PCT/CN2020/078891 patent/WO2020187113A1/en active Application Filing
- 2020-03-12 LU LU102193A patent/LU102193B1/en active IP Right Grant
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150317844A1 (en) * | 2014-05-02 | 2015-11-05 | Kookmin University Industry-Academic Cooperation Foundation | Method of processing and analysing vehicle driving big data and system thereof |
| CN106845371A (en) * | 2016-12-31 | 2017-06-13 | 中国科学技术大学 | A kind of city road network automotive emission remote sensing monitoring system |
| CN107368913A (en) * | 2017-06-15 | 2017-11-21 | 中国汽车技术研究中心 | A kind of oil consumption Forecasting Methodology based on least square method supporting vector machine |
| CN107545122A (en) * | 2017-09-27 | 2018-01-05 | 重庆长安汽车股份有限公司 | A kind of simulation system of the vehicle gaseous effluent based on neutral net |
| CN107886188A (en) * | 2017-10-18 | 2018-04-06 | 东南大学 | Liquefied natural gas public transport exhaust emissions Forecasting Methodology |
| CN108629450A (en) * | 2018-04-26 | 2018-10-09 | 东南大学 | A kind of liquefied natural gas bus exhaust emissions prediction technique |
| CN109948237A (en) * | 2019-03-15 | 2019-06-28 | 中国汽车技术研究中心有限公司 | A method of for predicting bicycle discharge amount |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529104A (en) * | 2020-12-23 | 2021-03-19 | 东软睿驰汽车技术（沈阳）有限公司 | Vehicle fault prediction model generation method, fault prediction method and device |
| CN113806675A (en) * | 2021-08-06 | 2021-12-17 | 中汽研汽车检验中心（天津）有限公司 | NOx emission and oil consumption characteristic analysis method |
| CN113806675B (en) * | 2021-08-06 | 2023-06-23 | 中汽研汽车检验中心（天津）有限公司 | NOx emission and oil consumption characteristic analysis method |
| CN114821854A (en) * | 2022-03-28 | 2022-07-29 | 中汽研汽车检验中心（天津）有限公司 | Method for evaluating influence of working condition switching on vehicle oil consumption |
| CN114821854B (en) * | 2022-03-28 | 2023-06-09 | 中汽研汽车检验中心（天津）有限公司 | Method for evaluating influence of working condition switching on vehicle fuel consumption |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109948237B (en) | 2023-06-02 |
| CN109948237A (en) | 2019-06-28 |
| LU102193B1 (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020187113A1 (en) | Method for predicting emission amount of single vehicle | |
| Yuhui et al. | Development of a representative driving cycle for urban buses based on the K-means cluster method | |
| KR102233589B1 (en) | Modeling method and device for evaluation model | |
| Huang et al. | An intelligent multifeature statistical approach for the discrimination of driving conditions of a hybrid electric vehicle | |
| CN106427589A (en) | Electric car driving range estimation method based on prediction of working condition and fuzzy energy consumption | |
| CN105868787A (en) | Electric car driving range evaluation method based on working condition identification and fuzzy energy consumption | |
| CN105469611B (en) | A kind of short-term traffic flow forecasting model method | |
| CN109145982A (en) | The personal identification method and device of driver, storage medium, terminal | |
| CN108986457B (en) | ETC lane layout scheme evaluation method based on traffic conflict analysis | |
| CN102063375A (en) | Software reliability assessment method and device based on hybrid testing | |
| CN108629450A (en) | A kind of liquefied natural gas bus exhaust emissions prediction technique | |
| CN101964061B (en) | Binary kernel function support vector machine-based vehicle type recognition method | |
| Shi et al. | Applying a WNN-HMM based driver model in human driver simulation: Method and test | |
| CN115759322A (en) | Urban rail transit passenger flow prediction and influence analysis method | |
| CN112003312A (en) | Private electric vehicle participation power grid regulation and control capability assessment method based on trip chain and participation willingness | |
| CN106569981A (en) | Statistic parameter determination method and system applicable to large-scale data set | |
| CN115841712A (en) | Driving data processing method, device and equipment based on V2X technology | |
| Xing et al. | Driving cycle recognition for hybrid electric vehicle | |
| CN109614967A (en) | A kind of detection method of license plate based on negative sample data value resampling | |
| CN108805458A (en) | A kind of enterprise technology Competitiveness Assessment method and device | |
| Genadot | Averaging for some simple constrained Markov processes | |
| Zhang et al. | Using the amce algorithm to high-efficiently develop vehicle driving cycles with road grade | |
| CN110852378A (en) | Road condition kinematics segment extraction method based on navigation system | |
| Weber et al. | Data-driven bev modeling for realistic consumption calculation in traffic simulation | |
| Zhong et al. | Estimating Remaining Driving Range of Electric Vehicles Using BPNN Based on Real-world Data |
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: 20773870 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: 20773870 Country of ref document: EP Kind code of ref document: A1 |