WO2010041382A1 - 車両の故障診断のための基準値の生成 - Google Patents
車両の故障診断のための基準値の生成 Download PDFInfo
- Publication number
- WO2010041382A1 WO2010041382A1 PCT/JP2009/004818 JP2009004818W WO2010041382A1 WO 2010041382 A1 WO2010041382 A1 WO 2010041382A1 JP 2009004818 W JP2009004818 W JP 2009004818W WO 2010041382 A1 WO2010041382 A1 WO 2010041382A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- reference value
- numerical
- vector
- data
- clusters
- Prior art date
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
- G07C5/0808—Diagnosing performance data
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
-
- 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
- G07C5/085—Registering performance data using electronic data carriers
Definitions
- the present invention collects data stored in a storage device of an electronic control unit (ECU, Electronic Control Unit) of each vehicle during driving of the vehicle, and generates normal value data of various driving parameters serving as a basis for fault diagnosis About doing.
- ECU Electronice Control Unit
- a diagnostic device is known as a tool for diagnosing a failure of a vehicle such as an automobile.
- the expert system includes a rule-based inference method that searches and registers human experience knowledge in a database, and a model base that learns the behavior of the system during normal operation or failure, and searches for the cause of failure through simulation.
- the former method is simple in structure and can be expected to have relatively high reliability, but it is difficult to make knowledge into rules, and it is necessary to add or modify rules every time a change is made to the target system.
- the failure site can be estimated even if the operating staff does not have sufficient experience and knowledge, and a certain degree of versatility can be expected for changing the target system.
- a method of comparing normal data with failure data under the same operating environment conditions is one of the most effective means of finding the cause of the malfunction.
- Patent Document 1 Japanese Patent Application Laid-Open No. 62-261938 includes knowledge data storage means for storing accurate information about the relationship between failure symptoms and causes corresponding thereto, and rare case storage means for storing uncertain information. A diagnostic device is described.
- Patent Document 2 analyzes design data and past defect data and inputs them into a relational database as a positive inference method EMEA, and creates a modified EMEA to create an event sequence diagram. Then, it is described that a fault search tree is created and used for rule-based reference, and expert know-how is digitized to create a rule base.
- the accumulation of driving data performed in a normal vehicle is limited to the data at the time of occurrence of a failure that is recorded as diagnostic information in the ECU when the failure occurs.
- the data recorded / accumulated as data at the time of failure occurrence in this way is a collection of various operation parameters, but some parameters related to failure become abnormal values, but many other Most of the parameters are normal values.
- the present invention provides an apparatus for generating data during normal operation using traveling data stored in a normal vehicle that is traveling in a city or the like on a daily basis. Objective.
- the present invention is based on time-series ECU data for a plurality of operation parameters at the time of occurrence of a failure stored in a storage device of an electronic control unit (ECU) of the vehicle at the time of occurrence of the failure of the vehicle.
- a reference value generation device for failure diagnosis that performs failure diagnosis of the vehicle in comparison with a value.
- the reference value generating device includes a storage device that sequentially stores and stores the time-series ECU data obtained from a large number of vehicles, and a means for generating a numerical vector of the time-series ECU data stored in the storage device. Prepare.
- the numerical vectors are clustered to be classified into a plurality of clusters according to characteristics, and in each of the plurality of clusters, a range of values having a high appearance frequency is obtained for each parameter of the operation, and the frequency A range of values having a high appearance frequency obtained by the calculation means is stored as a normal value range of the operation parameter, and the normal value range is set as a reference value for fault diagnosis.
- the means for generating the numerical vector divides the time-series ECU data into a plurality of time zones, and generates the numerical vector for each time zone.
- the numerical vectors for each time zone are clustered.
- FIG. 1 shows a data collection device 14 included in an electronic control system for an automobile which is a premise of the present invention.
- the in-vehicle network 11 is a network for performing communication between a plurality of electronic control units (ECUs) mounted on the vehicle.
- the network is divided into two systems of F system and B system, but a network of one system may be used.
- the F-system network is a network for communicating among a plurality of ECUs of a so-called control system such as an ECU that performs engine fuel injection control, ignition timing control, an ECU that controls transmissions, an ECU that controls brakes, etc. It is.
- the B system network is a network for communicating among a plurality of ECUs of a so-called body electrical system such as an ECU for controlling a power window and a door lock, an ECU for controlling a light, and an ECU for controlling electrical components such as an air conditioner.
- the ECU is basically a computer and includes a microprocessor and a communication module.
- the F system network sends to the data collection device 14 control system data such as vehicle speed data 11A, engine water temperature data 11B, engine speed data 11C, and a fault code 11E indicating a fault detected by the ECU.
- the network of the B system sends data from the ECU of the body electrical system such as data 11F indicating the state of an accessory (ACC) such as an air conditioner, and a failure code 11G indicating a failure detected by the ECU to the data collection device 14.
- ACC an accessory
- 11G failure code
- the data collection device 14 is itself an ECU.
- the data collection device 14 is controlled by a controller 14H whose main element is a microprocessor.
- the receiving unit 14A sequentially receives the latest data indicating the state of the vehicle from the in-vehicle network 11, and the controller 14H sequentially stores the data in the vehicle state data memory 14B sequentially.
- the vehicle state data memory 14B is a random access memory (RAM), which stores the latest data of a predetermined time width such as 20 seconds, and is a first-in first-out (FIFO) shift register type. For example, it is rewritten with new data every 0.2 seconds.
- RAM random access memory
- Non-volatile memory 14D is configured by a rewritable ROM such as a backup memory or an EEPROM that retains memory by receiving a supply of a maintenance current from the battery even when the power is turned off.
- a rewritable ROM such as a backup memory or an EEPROM that retains memory by receiving a supply of a maintenance current from the battery even when the power is turned off.
- the controller 14H receives the trouble code (DTC, “Diagnosis“ Trouble Code ”)
- the controller 14H reads the data for 15 seconds before the trouble code is generated from the vehicle state data memory 14B and stores it in the nonvolatile memory 14D.
- This data is called onboard snapshot (OBS). This process is executed every time a fault code is generated, and the nonvolatile memory 14D stores a plurality of OBSs corresponding to the plurality of fault codes.
- OBS onboard snapshot
- the service staff connects the connection terminal of the failure diagnostic machine 16 to the output terminal of the ECU, reads the data stored in the nonvolatile memory 14D to the diagnostic machine, Perform fault diagnosis using a diagnostic machine.
- the data stored in the read nonvolatile memory 14D is stored in the data storage device 20 as travel data to which the present invention is applied.
- a reference data creation device 30 is provided in association with the data storage device 20.
- the data stored in the nonvolatile memory 14D can be sent from the in-vehicle communication device to the data storage device 20 without waiting for the vehicle to be brought to the service store.
- Table 1 shows an example of the OBS stored in the nonvolatile memory 14D in response to the occurrence of one fault code.
- R engine speed
- V vehicle speed
- T engine cooling water temperature
- the output value of the air-fuel ratio sensor the output value of the O2 sensor
- data on a large number of parameters such as an air-fuel ratio is included in the OBS.
- the time is shown by a minus sign when the occurrence time of the defect code is set to 0 seconds as a reference, and the time goes back by 0.2 seconds.
- the number of sample cars is 13000, and OBS data is obtained as described above from a general user's car that is actually traveling in the market.
- the normal value range to be extracted is considered to exist for each “certain state (under certain operating conditions)”. Therefore, if the OBS data in the approximated state is collected as a cluster (group) and an appropriate value range is extracted for each cluster, a normal value range for each “certain state” can be extracted.
- the OBS data approximated using a clustering method is classified as a cluster (set).
- a range of appropriate values of parameters is extracted for each cluster, and this is used as a reference value for reference during failure diagnosis.
- Clustering is a data analysis method for grouping data without external criteria.
- a method called K-means method is used. The idea is to plot the data in a dimensional space corresponding to the number of parameters and classify the data according to the distance.
- the reference data creation device 30 collects OBS from, for example, 13,000 vehicles for one vehicle type (in the case of 1 / vehicle).
- the collected OBS data is clustered to “20” with the feature quantities of the three parameters “engine speed: R”, “vehicle speed: V”, and “cooling water temperature: T”. (Primary clustering)
- “20” clusters extracted by the primary clustering are further clustered to “30” with all parameters to extract “600” clusters, that is, operating conditions. (Secondary clustering)
- the primary clustering is a rough clustering performed with three parameters of “engine speed: R”, “vehicle speed: V”, and “cooling water temperature: T”, which are considered to be particularly dependent among the operation parameters related to the occurrence of the malfunction.
- R engine speed
- V vehicle speed
- T cooling water temperature
- a numerical vector of operation parameter feature values is generated (31).
- the average value, the maximum value, the minimum value, and the average value of the slope are used as feature amounts in this example.
- select features suitable for vehicle driving parameter analysis can do.
- the parameters of the OBS data obtained from n units are represented by Rn, Vn, Tn, the average values are represented by Rn av , Vn av , Tn av , and the maximum values are represented by Rn mx , Vn mx , Tn It is represented by mx , the minimum value is represented by Rn mn , Vn mn , Tn mn, and the average value of the inclination is represented by Rn in , Vn in , Tn in .
- the slope here is an important feature that also serves as an indicator of whether the vehicle is accelerating, decelerating, or cruise driving (constant speed driving), and is a parameter value with respect to time (h).
- This value is obtained by differentiating the amount of change in f (x) and is expressed by the following equation. In the digital calculation, it can be obtained by calculating the difference of the parameter value f (x).
- the parameter Rk has an average value Rn av-1 , a maximum value Rn mx-1 , and a minimum value Rn mn-1 in this time zone. , And the average value Rn in-1 of the slope.
- an average value Vn av ⁇ 1 , a maximum value Vn mx ⁇ 1 , a minimum value Vn mn ⁇ 1 , and an average value Vn in ⁇ 1 of the slope are generated for the parameter V, and Tn av ⁇ 1 , Tn for the parameter T mx-1 , Tn mn-1 , and Tn in-1 are generated.
- Second time zone (-11.8 to -9.0 seconds), Third time zone (-8.8 to -6.0 seconds), Fourth time zone (-5.8 to -3.0 seconds) and Fifth time zone (-2.8 Similarly, the feature amounts shown in Table 2 are calculated for ( ⁇ 0 seconds).
- numerical vectors in the above five time zones of the three parameters (Rn, Vn, Tn) of “engine speed: R”, “vehicle speed: V”, and “cooling water temperature: T” are obtained by primary clustering. For example, it is classified into 20 primary clusters Dj (33). As an initial condition, a core vector that becomes the center of 20 primary clusters is determined at random. The initial value of the core vector can be determined according to an empirical rule from a limited number of experimental data.
- the core vector that is the center of the j-th cluster is defined as (R av-cj , R mx-cj , R mn-cj , R in-cj , V av-cj , V mx- , where j is an integer from 1 to 20.
- the Manhattan distance D1nj with each core vector of the clusters Dj is calculated by the following equation.
- D1nj
- the numerical vector of the second time zone of the OBS data obtained from n cars is classified into 20 primary clusters Dj.
- the numerical vectors in the third time zone are classified into 20 primary clusters Dj
- the numerical vectors in the fourth time zone and the fifth time zones are classified into 20 primary clusters Dj.
- the average value of the numerical vector to which it belongs is calculated, and this average value is used as the core vector of each cluster.
- the above clustering is executed again.
- a third clustering is further performed using the updated core vector. This repetition is executed until the core vector converges or until the preset number of trials is completed.
- the convergence method may vary depending on the default core vector, for example, 10 different initial settings are prepared at random, and clustering is repeated using each initial setting. Can be adopted. Thus, a final core vector (center of gravity) is obtained for each of the 20 primary clusters Dj.
- the clustering of 20 primary clusters is executed using this final core vector to complete the primary clustering of 65000 data (13000 units ⁇ 5 units / unit).
- the primary clustering is performed using the operation parameter having the highest importance, and the numerical vectors having the highest degree of approximation are grouped. Therefore, all the data is first grouped according to the difference in the operation state having a high importance. Will be. Therefore, each group, that is, a cluster is formed corresponding to the case of an operation state where the difference is relatively large.
- the process proceeds to secondary clustering (35).
- clustering in each of the 20 primary clusters Dj, clustering is further performed on the OBS numerical vectors of all the parameters included in the cluster (the numerical vector of FIG. 3 expanded to all the parameters), and each 1 The next cluster is classified into 30 secondary clusters. That is, each of the 20 primary clusters corresponding to different operating states is subdivided into 30 secondary clusters.
- each primary cluster is secondarily clustered to form 30 secondary clusters, 600 (20 ⁇ 30) secondary clusters are obtained as a whole.
- Each OBS numerical vector (65000 pieces of data in the embodiment) belongs to one of these 600 secondary clusters.
- the initial values of the core vectors of 30 secondary clusters used for secondary clustering can be determined randomly in the same way as in primary clustering. This initial value can also be determined according to empirical rules in light of past data.
- This core vector is updated by the same method as the primary clustering to obtain a final core vector, and final clustering is performed using 30 final core vectors, so that 600 secondary clusters are obtained. It is formed.
- a 20-division histogram is created from the 600 secondary cluster data obtained in this way, with the horizontal axis representing the parameter value and the vertical axis representing the number of data for each parameter (FIG. 4).
- A) Exclude classes whose vertical axis values are less than or equal to a predetermined value (for example, a% of the total) (Fig. 4 (B)), group the remaining classes together, and the number of data belonging to the group is b Group them so that they are at least% (Fig. 4 (C)).
- This process is executed for each cluster, that is, for 600 secondary clusters individually.
- the values of a% and b% are adjusted according to the clustering parameter residual that is a measure of the dispersion of OBS data in the secondary cluster.
- the parameter residual is a value obtained by evaluating how far each parameter value of the numerical vector is away from the core vector that is the center of gravity of the cluster to which the numerical vector belongs.
- the difference from the center of gravity of the cluster to which it belongs is taken, and the residual is expressed by its root mean square (square root of sum of squares). Simple differences have a plus or minus sign, so we use the root mean square to see the magnitude of the difference.
- a histogram for each column (parameter) in FIG. 3 is created for all numeric vectors in a certain cluster. For example, it is assumed that a histogram as shown in Table 2 is obtained for one feature amount of a certain operation parameter. If this cluster contains 100 numeric vectors, the total number of counts is 100.
- the process proceeds to the reference value setting step 39, and the column in the remaining group, that is, the range of the feature value of the operation parameter is set as the normal value range.
- the normal value ranges are combined into a reference value range used for fault diagnosis.
- the range of the reference value is 0.0 to ⁇ 0.7.
- the diagnosis target ECU data of the faulty vehicle is read by a diagnostic machine, and the normal value data (600 driving status data as different driving situations) is read. Search the most similar driving situation data from. Next, by comparing the normal value data of the search result with the ECU data to be diagnosed, it is determined which of the operating parameters is deviated from the reference value (normal value range) under the same operating conditions. Based on this determination, it is possible to search for a defective part.
- the feature amount of each driving parameter of the ECU data is calculated, and normal value data similar to this ECU data is calculated.
- the target normal value data can be selected by performing an approximate search from among the 600 normal value data.
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
Description
D1nj=|Rnav-1-Rav-cj|+|Rnmx-1-Rmx-cj|+|Rnmn-1-Rmn-cj|+| Rnin-1-Rin-cj|
+|Vnav-1-Vav-cj|+|Vnmx-1-Vmx-cj|+|Vnmn-1-Vmn-cj|+|Vnin-1-Vin-cj|
+|Tnav-1-Tav-cj|+|Tnmx-1-Tmx-cj|+|Tnmn-1-Tmn-cj|+|Tnin-1-Tin-cj| (1)
D2nj=|Rnav-2-Rav-cj|+|Rnmx-2-Rmx-cj|+|Rnmn-2-Rmn-cj|+|Rnin-2-Rin-cj|
+|Vnav-2-Vav-cj|+|Vnmx-2-Vmx-cj|+|Vnmn-2-Vmn-cj|+|Vnin-2-Vin-cj|
+|Tnav-2-Tav-cj|+|Tnmx-2-Tmx-cj|+|Tnmn-2-Tmn-cj|+|Tnin-2-Tin-cj| (2)
16 診断機
20 データ蓄積装置
30 基準データ生成装置
Claims (16)
- 車両の不具合発生時に該車両の電子制御装置(ECU)の記憶装置に保存された不具合発生時の複数の運転パラメータについての時系列ECUデータを、基準値と比較して該車両の故障診断を行う故障診断用の基準値生成装置であって、
多数の車両から得られる前記時系列ECUデータを逐次蓄積して保存する蓄積装置と、
前記蓄積装置に蓄積された時系列ECUデータの数値ベクトルを生成する手段と、
前記数値ベクトルをクラスタリングして、特徴に応じた複数のクラスタに分類するクラスタリング手段と、
前記複数のクラスタのそれぞれにおいて、それぞれの運転パラメータごとに該パラメータの値について出現頻度の高い値の範囲を求める、頻度算出手段と、
前記頻度算出手段で得られた、出現頻度の高い値の範囲を前記運転パラメータの正常値の範囲として保存する手段と、
を備え、前記正常値の範囲を故障診用の基準値とする、基準値生成装置。 - 前記時系列ECUデータは、車両の不具合発生前の所定の時間における、エンジン回転数、車両の速度および冷却水温の少なくとも一つを含む複数の運転パラメータに関するデータである、請求項1に記載の基準値生成装置。
- 前記数値ベクトルを生成する手段は、前記時系列ECUデータをレコードごとに複数の時間帯に分割して、時間帯ごとに前記運転パラメータの特徴量を算出して、該特徴量の数値ベクトルを生成する、請求項2に記載の基準値生成装置。
- 前記クラスタリング手段は、異なる初期値をもつ第1の複数のコアベクトルを中心として、前記時間帯ごとの数値ベクトルと該複数のコアベクトルとの近似度を算出して、各数値ベクトルを最も近似度の高いコアベクトルを中心とするクラスタに所属させ、前記第1の複数のクラスタを生成する、請求項3に記載の基準値生成装置。
- a)前記クラスタごとに、所属する複数の数値ベクトルの前記特徴量ごとの平均をとり、該平均で該クラスタの中心である前記コアベクトルの数値を置換し、
b)こうして得られたコアベクトルを用いて、再度前記時間帯ごとの数値ベクトルと複数のコアベクトルとの近似度を算出し、各数値ベクトルを最も近似度の高いコアベクトルを中心とするクラスタに所属させる、
請求項4に記載の基準値生成装置。 - c)前記コアベクトルの中心が収束するまで、または予め定めた試行回数を終了するまで、前記a)およびb)の処理を繰り返す、請求項5に記載の基準値生成装置。
- 前記第1の複数のクラスタに数値ベクトルを所属させる処理は、所定の一つまたは複数の運転パラメータについて実行し、こうして得られた前記第1の複数のクラスタに所属する数値ベクトルに関し、より多数の運転パラメータについて前記第1の複数のクラスタごとに第2の複数の数のクラスタに2次クラスタリングする、請求項6に記載の基準値生成装置。
- 前記2次クラスタリングで得られたクラスタごとに、所属する数値ベクトルについて前記運転パラメータごとの出現頻度を算出し、該出現頻度の高い数値範囲をそれぞれの運転パラメータの基準値とする、請求項7に記載の基準値生成装置。
- 車両の不具合発生時に該車両の電子制御装置(ECU)の記憶装置に保存された不具合発生時の複数の運転パラメータについての時系列ECUデータを、基準値と比較して該車両の故障診断を行う故障診断用の基準値を生成する方法であって、
多数の車両から得られる前記時系列ECUデータを逐次蓄積して保存し、
前記保存された時系列ECUデータの数値ベクトルを生成し、
前記数値ベクトルをクラスタリングして、特徴に応じた複数のクラスタに分類し、
前記複数のクラスタのそれぞれにおいて、それぞれの運転パラメータごとに該パラメータの値について出現頻度の高い値の範囲を求め、
前記頻度算出手段で得られた、出現頻度の高い値の範囲を前記運転パラメータの正常値の範囲として保存し、
前記正常値の範囲を故障診用の基準値とする、基準値の生成方法。 - 前記時系列ECUデータは、車両の不具合発生前の所定の時間における、エンジン回転数、車両の速度および冷却水温の少なくとも一つを含む複数の運転パラメータに関するデータである、請求項9に記載の基準値の生成方法。
- 前記数値ベクトルの生成は、前記時系列ECUデータをレコードごとに複数の時間帯に分割して、時間帯ごとに前記運転パラメータの特徴量を算出して、該特徴量の数値ベクトルを生成することにより行われる、請求項10に記載の基準値の生成方法。
- 前記クラスタリングは、異なる初期値をもつ第1の複数のコアベクトルを中心として、前記時間帯ごとの数値ベクトルと該複数のコアベクトルとの近似度を算出して、各数値ベクトルを最も近似度の高いコアベクトルを中心とするクラスタに所属させ、前記第1の複数のクラスタを生成する、請求項11に記載の基準値の生成方法。
- a)前記クラスタごとに、所属する複数の数値ベクトルの前記特徴量ごとの平均をとり、該平均で該クラスタの中心である前記コアベクトルの数値を置換し、
b)こうして得られたコアベクトルを用いて、再度前記時間帯ごとの数値ベクトルと複数のコアベクトルとの近似度を算出し、各数値ベクトルを最も近似度の高いコアベクトルを中心とするクラスタに所属させる、
請求項12に記載の基準値の生成方法。 - c)前記コアベクトルの中心が収束するまで、または予め定めた試行回数を終了するまで、前記a)およびb)の処理を繰り返す、請求項13に記載の基準値の生成方法。
- 前記第1の複数のクラスタに数値ベクトルを所属させる処理は、所定の一つまたは複数の運転パラメータについて実行し、こうして得られた前記第1の複数のクラスタに所属する数値ベクトルに関し、より多数の運転パラメータについて前記第1の複数のクラスタごとに第2の複数の数のクラスタに2次クラスタリングする、請求項14に記載の基準値の生成方法。
- 前記2次クラスタリングで得られたクラスタごとに、所属する数値ベクトルについて前記運転パラメータごとの出現頻度を算出し、該出現頻度の高い数値範囲をそれぞれの運転パラメータの基準値とする、請求項15に記載の基準値の生成方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/123,354 US9043079B2 (en) | 2008-10-10 | 2009-09-24 | Generation of reference value for vehicle failure diagnosis |
CN200980140012.1A CN102177049B (zh) | 2008-10-10 | 2009-09-24 | 用于车辆故障诊断的基准值的生成 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2008264593A JP4414470B1 (ja) | 2008-10-10 | 2008-10-10 | 車両の故障診断のための基準値の生成 |
JP2008-264593 | 2008-10-10 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2010041382A1 true WO2010041382A1 (ja) | 2010-04-15 |
Family
ID=41739287
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2009/004818 WO2010041382A1 (ja) | 2008-10-10 | 2009-09-24 | 車両の故障診断のための基準値の生成 |
Country Status (4)
Country | Link |
---|---|
US (1) | US9043079B2 (ja) |
JP (1) | JP4414470B1 (ja) |
CN (1) | CN102177049B (ja) |
WO (1) | WO2010041382A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10089670B2 (en) | 2011-01-20 | 2018-10-02 | Paccar Inc | System and method for analyzing a powertrain configuration |
WO2019142484A1 (ja) * | 2018-01-16 | 2019-07-25 | 株式会社日立製作所 | 故障診断支援装置 |
Families Citing this family (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4414470B1 (ja) * | 2008-10-10 | 2010-02-10 | 本田技研工業株式会社 | 車両の故障診断のための基準値の生成 |
JP5161829B2 (ja) * | 2009-04-06 | 2013-03-13 | 本田技研工業株式会社 | 故障再現を支援する診断装置および故障再現データの出力方法 |
JP5263315B2 (ja) * | 2011-02-14 | 2013-08-14 | 株式会社デンソー | 車両挙動データ記憶装置 |
JP5810877B2 (ja) * | 2011-12-08 | 2015-11-11 | 株式会社豊田中央研究所 | 異常診断システム及び異常診断方法 |
US8880277B2 (en) * | 2012-02-29 | 2014-11-04 | GM Global Technology Operations LLC | Methods and systems for diagnosing a vehicle |
US9780967B2 (en) | 2013-03-14 | 2017-10-03 | Telogis, Inc. | System for performing vehicle diagnostic and prognostic analysis |
WO2014159127A1 (en) * | 2013-03-14 | 2014-10-02 | Telogis Inc. | System and method for crowdsourcing vehicle-related analytics |
JP6003810B2 (ja) * | 2013-06-04 | 2016-10-05 | 株式会社デンソー | 車両用基準値生成装置 |
JP6135545B2 (ja) * | 2014-02-24 | 2017-05-31 | 株式会社デンソー | 補正値生成装置、故障診断装置、補正値生成プログラム、および故障診断プログラム |
JP6486640B2 (ja) * | 2014-10-09 | 2019-03-20 | 株式会社日立製作所 | 運転特性診断装置、運転特性診断システム、運転特性診断方法、情報出力装置、情報出力方法 |
JP6816379B2 (ja) | 2016-04-14 | 2021-01-20 | 富士ゼロックス株式会社 | 衝突回避システム、情報処理装置、衝突回避プログラム及び情報処理プログラム |
JP2017191555A (ja) | 2016-04-15 | 2017-10-19 | 富士ゼロックス株式会社 | 移動体制御装置及び移動体制御プログラム |
US9846979B1 (en) * | 2016-06-16 | 2017-12-19 | Moj.Io Inc. | Analyzing telematics data within heterogeneous vehicle populations |
JP6908405B2 (ja) * | 2017-03-29 | 2021-07-28 | 本田技研工業株式会社 | 小型船舶の故障予測システム |
CN107273930A (zh) * | 2017-06-14 | 2017-10-20 | 成都四方伟业软件股份有限公司 | 一种动态流式数据的聚类方法 |
US11972178B2 (en) * | 2018-02-27 | 2024-04-30 | Falkonry Inc. | System and method for explanation of condition predictions in complex systems |
JP6978975B2 (ja) * | 2018-04-13 | 2021-12-08 | 本田技研工業株式会社 | 情報出力装置及び情報出力方法 |
WO2019205017A1 (zh) | 2018-04-25 | 2019-10-31 | 深圳市元征软件开发有限公司 | 车辆诊断方法、系统、设备及计算机可读存储介质 |
US11461674B2 (en) | 2018-05-01 | 2022-10-04 | Kyndryl, Inc. | Vehicle recommendations based on driving habits |
JP7134903B2 (ja) * | 2019-03-05 | 2022-09-12 | 株式会社日立製作所 | 不具合再現支援システム、不具合再現支援方法 |
JP7304198B2 (ja) | 2019-04-26 | 2023-07-06 | 日立建機株式会社 | インジェクタ診断装置及びインジェクタ診断方法 |
WO2021010143A1 (ja) * | 2019-07-12 | 2021-01-21 | パナソニックIpマネジメント株式会社 | 車載セキュアストレージシステム |
JP6717419B1 (ja) * | 2019-10-11 | 2020-07-01 | トヨタ自動車株式会社 | 車両用故障原因特定装置 |
JP7134159B2 (ja) * | 2019-12-17 | 2022-09-09 | 本田技研工業株式会社 | 車両データ分類方法及び車両データ分類装置 |
JP7411473B2 (ja) * | 2020-03-27 | 2024-01-11 | 三菱重工業株式会社 | 妥当性確認方法、妥当性確認システム及びプログラム |
JP7217767B2 (ja) * | 2021-03-19 | 2023-02-03 | 本田技研工業株式会社 | 更新管理サーバ、更新管理方法、及びプログラム |
JP7214780B2 (ja) | 2021-04-06 | 2023-01-30 | 日立建機株式会社 | 性能診断装置、性能診断方法 |
US11407667B1 (en) | 2021-06-06 | 2022-08-09 | Christopher R. Moylan | Systems and methods for removal of carbon dioxide from seawater |
US11685673B2 (en) | 2021-06-06 | 2023-06-27 | Christopher R. Moylan | Systems and methods for removal of carbon dioxide from seawater |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005117756A (ja) * | 2003-10-06 | 2005-04-28 | Nissan Motor Co Ltd | 直流電圧検出回路の故障診断装置およびモータ制御システム |
JP2007281959A (ja) * | 2006-04-07 | 2007-10-25 | Fuji Xerox Co Ltd | 故障診断システム及び故障診断方法 |
Family Cites Families (44)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6735506B2 (en) * | 1992-05-05 | 2004-05-11 | Automotive Technologies International, Inc. | Telematics system |
JPS62261938A (ja) | 1986-05-08 | 1987-11-14 | Nissan Motor Co Ltd | 故障診断装置 |
JP2754721B2 (ja) * | 1989-05-11 | 1998-05-20 | 日産自動車株式会社 | 車両のフェイルセーフ装置 |
US7006881B1 (en) * | 1991-12-23 | 2006-02-28 | Steven Hoffberg | Media recording device with remote graphic user interface |
JPH0695881A (ja) | 1992-09-16 | 1994-04-08 | Kawasaki Heavy Ind Ltd | 機械装置類故障診断エキスパートデータ用ルールベース作成システム |
US7765039B1 (en) * | 1994-02-15 | 2010-07-27 | Hagenbuch Leroy G | Apparatus for tracking and recording vital signs and task-related information of a vehicle to identify operating patterns |
US5629869A (en) * | 1994-04-11 | 1997-05-13 | Abb Power T&D Company | Intelligent circuit breaker providing synchronous switching and condition monitoring |
JP3456058B2 (ja) * | 1995-02-10 | 2003-10-14 | 株式会社デンソー | 触媒の劣化検出装置及び排気浄化装置の異常検出装置 |
US8140358B1 (en) * | 1996-01-29 | 2012-03-20 | Progressive Casualty Insurance Company | Vehicle monitoring system |
JP3333378B2 (ja) * | 1996-02-05 | 2002-10-15 | 本田技研工業株式会社 | 車両診断方法および装置 |
JP3897135B2 (ja) * | 1997-03-10 | 2007-03-22 | 本田技研工業株式会社 | 車両診断方法および装置 |
JPH10253505A (ja) * | 1997-03-10 | 1998-09-25 | Honda Motor Co Ltd | 車両診断方法および装置 |
US6076504A (en) * | 1998-03-02 | 2000-06-20 | Cummins Engine Company, Inc. | Apparatus for diagnosing failures and fault conditions in a fuel system of an internal combustion engine |
US6053147A (en) * | 1998-03-02 | 2000-04-25 | Cummins Engine Company, Inc. | Apparatus and method for diagnosing erratic pressure sensor operation in a fuel system of an internal combustion engine |
US6484109B1 (en) * | 1998-05-20 | 2002-11-19 | Dli Engineering Coporation | Diagnostic vibration data collector and analyzer |
US8364136B2 (en) * | 1999-02-01 | 2013-01-29 | Steven M Hoffberg | Mobile system, a method of operating mobile system and a non-transitory computer readable medium for a programmable control of a mobile system |
US20110208567A9 (en) * | 1999-08-23 | 2011-08-25 | Roddy Nicholas E | System and method for managing a fleet of remote assets |
US20020059075A1 (en) * | 2000-05-01 | 2002-05-16 | Schick Louis A. | Method and system for managing a land-based vehicle |
US6691023B2 (en) * | 2000-05-26 | 2004-02-10 | Yamaha Marine Kabushiki Kaisha | Diagnostic system for engine |
AU2002213706A1 (en) * | 2000-10-26 | 2002-05-06 | Triant Technologies Inc. | Method for estimating and reducing uncertainties in process measurements |
JP2003084998A (ja) * | 2001-09-12 | 2003-03-20 | Denso Corp | 故障診断システム及び電子制御装置 |
US6581371B1 (en) * | 2002-02-20 | 2003-06-24 | Ford Global Technologies, Inc. | Engine catalyst monitor |
US20040003401A1 (en) * | 2002-06-27 | 2004-01-01 | Koninklijke Philips Electronics N.V. | Method and apparatus for using cluster compactness as a measure for generation of additional clusters for stereotyping programs |
US7042663B2 (en) * | 2002-10-03 | 2006-05-09 | Hitachi Global Storage Technologies Netherlands B.V. | Magnetic disk protection mechanism, computer system comprising protection mechanism, protection method for magnetic disk, and program for protection method |
DE10397025B3 (de) * | 2002-10-25 | 2021-10-21 | Denso Corporation | Variable Ventilzeitabstimmungssteuerungsvorrichtung einer Brennkraftmaschine |
JP4333331B2 (ja) * | 2002-12-20 | 2009-09-16 | セイコーエプソン株式会社 | 故障予測システム及び故障予測プログラム並びに故障予測方法 |
JP2004227439A (ja) * | 2003-01-27 | 2004-08-12 | Nissan Motor Co Ltd | 車両用故障診断システムおよび装置 |
US7072797B2 (en) * | 2003-08-29 | 2006-07-04 | Honeywell International, Inc. | Trending system and method using monotonic regression |
US7383238B1 (en) * | 2004-02-24 | 2008-06-03 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Inductive monitoring system constructed from nominal system data and its use in real-time system monitoring |
US7124019B2 (en) * | 2004-08-06 | 2006-10-17 | Ford Global Technologies, Llc | Powertrain control module spark duration diagnostic system |
FR2880167B1 (fr) * | 2004-12-23 | 2009-05-08 | Celec Conception Electronique | Procede de detection de presence et de mouvement pour des automatismes de porte et automatismes de porte mettant en oeuvre un tel procede |
JP4606965B2 (ja) * | 2005-03-07 | 2011-01-05 | 本田技研工業株式会社 | 内燃機関の排気浄化装置 |
US7826945B2 (en) * | 2005-07-01 | 2010-11-02 | You Zhang | Automobile speech-recognition interface |
JP4262260B2 (ja) * | 2006-05-12 | 2009-05-13 | 株式会社日立製作所 | 内燃機関の診断装置 |
JPWO2008038741A1 (ja) * | 2006-09-28 | 2010-01-28 | 富士通テン株式会社 | 車載機、頻度収集装置、及び、頻度収集方法 |
JP4899791B2 (ja) * | 2006-10-30 | 2012-03-21 | 株式会社デンソー | 燃料噴射制御装置及び燃料供給系の診断方法 |
JP5058575B2 (ja) * | 2006-12-12 | 2012-10-24 | キヤノン株式会社 | 画像処理装置及びその制御方法、プログラム |
US7788017B2 (en) * | 2006-12-27 | 2010-08-31 | Denso Corporation | Engine control, fuel property detection and determination apparatus, and method for the same |
JP4770742B2 (ja) * | 2007-01-17 | 2011-09-14 | 株式会社デンソー | エンジンの燃料噴射制御装置及び燃焼装置 |
JP2008285075A (ja) * | 2007-05-18 | 2008-11-27 | Toyota Motor Corp | 車両および車両の故障診断方法 |
US20090138153A1 (en) * | 2007-11-26 | 2009-05-28 | Honeywell International, Inc. | Advanced algorithm framework |
US20090216584A1 (en) * | 2008-02-27 | 2009-08-27 | Fountain Gregory J | Repair diagnostics based on replacement parts inventory |
JP4414470B1 (ja) * | 2008-10-10 | 2010-02-10 | 本田技研工業株式会社 | 車両の故障診断のための基準値の生成 |
EP2350443B1 (en) * | 2008-10-31 | 2018-10-17 | Filter Sensing Technologies, Inc. | After-treatment method and system having a filter load monitoring system |
-
2008
- 2008-10-10 JP JP2008264593A patent/JP4414470B1/ja not_active Expired - Fee Related
-
2009
- 2009-09-24 US US13/123,354 patent/US9043079B2/en active Active
- 2009-09-24 WO PCT/JP2009/004818 patent/WO2010041382A1/ja active Application Filing
- 2009-09-24 CN CN200980140012.1A patent/CN102177049B/zh not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005117756A (ja) * | 2003-10-06 | 2005-04-28 | Nissan Motor Co Ltd | 直流電圧検出回路の故障診断装置およびモータ制御システム |
JP2007281959A (ja) * | 2006-04-07 | 2007-10-25 | Fuji Xerox Co Ltd | 故障診断システム及び故障診断方法 |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10089670B2 (en) | 2011-01-20 | 2018-10-02 | Paccar Inc | System and method for analyzing a powertrain configuration |
US10096052B2 (en) | 2011-01-20 | 2018-10-09 | Paccar Inc | System and method for analyzing a powertrain configuration |
WO2019142484A1 (ja) * | 2018-01-16 | 2019-07-25 | 株式会社日立製作所 | 故障診断支援装置 |
JP2019123351A (ja) * | 2018-01-16 | 2019-07-25 | 株式会社日立製作所 | 故障診断支援装置 |
US11769355B2 (en) | 2018-01-16 | 2023-09-26 | Hitachi, Ltd. | Fault diagnosis support device |
Also Published As
Publication number | Publication date |
---|---|
CN102177049B (zh) | 2014-11-05 |
JP2010089760A (ja) | 2010-04-22 |
CN102177049A (zh) | 2011-09-07 |
US9043079B2 (en) | 2015-05-26 |
US20110196572A1 (en) | 2011-08-11 |
JP4414470B1 (ja) | 2010-02-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4414470B1 (ja) | 車両の故障診断のための基準値の生成 | |
JP4928532B2 (ja) | 車両の故障診断装置 | |
JP5161829B2 (ja) | 故障再現を支援する診断装置および故障再現データの出力方法 | |
US20230169804A1 (en) | Telematically monitoring a condition of an operational vehicle component | |
DE102020103768B4 (de) | Überwachung und Diagnose von Fahrzeugsystemproblemen mit Maschinenlern-Klassifikatoren | |
CN102375452B (zh) | 改善故障代码设定和隔离故障的事件驱动的数据挖掘方法 | |
EP2678832B1 (en) | Diagnostic baselining | |
EP3776494A1 (en) | Predictive vehicle diagnostics method | |
Murphey et al. | Automotive fault diagnosis-part II: a distributed agent diagnostic system | |
KR102215107B1 (ko) | 주행 데이터 기반 차량 상태 예측 시스템 및 방법 | |
KR102141988B1 (ko) | 자율주행 대중버스에 대한 실시간 버스 신뢰성 통합지표 모니터링 시스템 및 방법 | |
US20230063601A1 (en) | Methods and systems for anomaly detection of a vehicle | |
EP4167040A1 (en) | Fault model editor and diagnostic tool | |
CN114239734B (zh) | 一种分布式车载健康管理系统 | |
CN105335599B (zh) | 一种汽车故障诊断率的检测方法及系统 | |
CN113173104A (zh) | 一种新能源车辆动力电池预警方法及系统 | |
DE102022120962A1 (de) | Batteriefehlererkennung | |
CN115113601A (zh) | 车辆管理装置、车辆管理方法和计算机可读存储介质 | |
US20210192872A1 (en) | Model diagnosis device and model diagnosis system | |
CN112329341B (zh) | 一种基于ar和随机森林模型的故障诊断系统及方法 | |
Suda et al. | Automated diagnosis of engine misfire faults using combination classifiers | |
EP4316918A1 (en) | Vehicle abnormality detection device and vehicle abnormality detection method | |
EP2787205B1 (en) | System for estimating a vehicle fuel consumption | |
US20240338980A1 (en) | Dtc rulebook generation system and method | |
CN117520953A (zh) | 怠速异常识别及模型训练方法、装置、车辆及介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 200980140012.1 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 09818922 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13123354 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 09818922 Country of ref document: EP Kind code of ref document: A1 |