DE102013007007A1 - Pattern and significance detection in databases with genetic algorithms - Google Patents

Pattern and significance detection in databases with genetic algorithms

Info

Publication number
DE102013007007A1
DE102013007007A1 DE102013007007.4A DE102013007007A DE102013007007A1 DE 102013007007 A1 DE102013007007 A1 DE 102013007007A1 DE 102013007007 A DE102013007007 A DE 102013007007A DE 102013007007 A1 DE102013007007 A1 DE 102013007007A1
Authority
DE
Germany
Prior art keywords
data
vehicle
algorithm
method according
patterns
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.)
Pending
Application number
DE102013007007.4A
Other languages
German (de)
Inventor
Florian Netter
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Audi AG
Original Assignee
Audi AG
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 Audi AG filed Critical Audi AG
Priority to DE102013007007.4A priority Critical patent/DE102013007007A1/en
Publication of DE102013007007A1 publication Critical patent/DE102013007007A1/en
Application status is Pending legal-status Critical

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0205Diagnosing or detecting failures; Failure detection models
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0062Adapting control system settings
    • B60W2050/0075Automatic parameter input, automatic initialising or calibrating means
    • B60W2050/0077Automatic parameter input, automatic initialising or calibrating means involving external transmission of data to or from the vehicle
    • B60W2050/0079Automatic parameter input, automatic initialising or calibrating means involving external transmission of data to or from the vehicle using telemetry
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0062Adapting control system settings
    • B60W2050/0075Automatic parameter input, automatic initialising or calibrating means
    • B60W2050/0089Historical data record of previous events
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0205Diagnosing or detecting failures; Failure detection models
    • B60W2050/0215Sensor drifts or sensor failures

Abstract

The invention relates to a method for identifying as yet undefined patterns and / or significant relationships and / or significant differences of technical processes in an operation of at least one vehicle, wherein data and / or data sets are detected and provided by a vehicle sensor system of a respective vehicle and based on an algorithm is carried out on the acquired data and / or data sets and / or on already existing off-vehicle data and / or on already calculated data, which comprises at least the operations mutation and recombination of defined or randomly selected attributes of the data or data sets, the operations mutation and Recombination according to predetermined or random criteria and wherein an evaluation of significances and selection of data or data sets is performed by means of a fitness function, about which prognoses and diagnoses of current and / or future Er events of the at least one vehicle or its components calculated and, if appropriate, appropriate countermeasures are taken before they occur. Furthermore, the invention comprises a corresponding system.

Description

  • The present invention relates generally to a method and related system for improving vehicle diagnostic and prediction algorithms, and more particularly to a method for identifying patterns and / or significant differences and / or significant relationships in data relevant to vehicle operation / or records, by using so-called genetic algorithms.
  • Vehicle diagnostic and forecasting calculations are crucial in optimizing durability and vehicle service intervals. Usually, this method is based on experience and lengthy tests. Such tests are carried out under different outdoor conditions and with changing components.
  • Furthermore, often only those information which is directly associated with an error or problem or identified as belonging to a person skilled in the art or a system as problem generation is included in a vehicle analysis.
  • In the US 2012/0158212 A1 An intelligent data processing unit is disclosed based on a data service for vehicle-based systems, which comprises a static storage unit, a dynamic storage unit and a computing element for executing necessary processes, and an analysis unit for analyzing static and dynamic data, wherein dynamic data is understood to mean time characteristics of driving maneuvers are. In this case, the vehicle-based system can be provided with a large number of data services by the intelligent data processing unit. Furthermore, the provided data services can be personalized based on analysis processes of the analysis unit.
  • Furthermore, in the DE 10 2006 017 824 A1 a method or system for constructing a diagnostic function for mapping a symptom of an error in a mechatronic system, in particular a vehicle, to the error that caused the symptom. It is an object of the method or system to find a machine learning approach that learns as well as possible a classification function based on simulations of a vehicle function in order to use this machine learning approach for diagnostic purposes in the vehicle.
  • In the DE 102 35 525 A1 discloses a method that discloses generation of models based on data from multiple vehicles, which in turn have been analyzed using data mining and machine learning technologies. It is further disclosed that the generated models are aligned with vehicle sensor data and diagnostic data to provide for continued analysis of the vehicle for repair, maintenance and diagnostics.
  • In the EP 2 159 122 A2 discloses a method or system, which has the task to allow an influence of conditions and environmental influences that are not measurable from a particular vehicle out. For this purpose, a secure wireless connection is disclosed, which transmits vehicle-specific, sensor-acquired data to a central system, where they are compared with stored in a database reference data. Furthermore, depending on the evaluation result control or control signals for Fahrzeugkomponeten, z. B. the brake system generated.
  • In the DE 10 2009 054 900 A1 discloses an apparatus and method for determining controller parameters. The device has a user interface, with which target variables can be selected, and a memory unit, in which at least one set of optimal parameters is stored, wherein there is an association between the target variables to be selected and the at least one set of optimal parameters.
  • Against this background, a method and a corresponding system for identifying as yet unspecified patterns and / or significant relationships and / or significant differences of technical processes in an operation of at least one vehicle with the features of the independent claims are presented. Further embodiments can be found in the respective subclaims.
  • In this case, according to the invention, based on data or data sets, for example, are detected and provided by a vehicle sensor system of a respective vehicle and / or execute an algorithm based on already existing relevant data or data records, in particular also from external data sources, which at least the operations Mutation and recombination of defined or randomly selected attributes of the data and / or datasets, whereby the mutation and recombination operations proceed according to fixed or random criteria and wherein an evaluation of significances and a selection of data or datasets (mutations) via a fitness function (selection) is to run to calculate forecasts and diagnoses of current and / or future events of the at least one vehicle or its components and possibly take appropriate countermeasures before they occur.
  • In the context of the method according to the invention or of the corresponding system, external data are to be understood as meaning data which are not recorded directly in the respective vehicle itself.
  • An interpretation of large data and / or datasets is usually only to be done under very high manual effort. In order to avoid this expense, the method according to the invention provides a machine approach which is optimized to recognize patterns that have not yet been determined or whose occurrence is not yet known.
  • According to the invention, a method is provided which uses an algorithm that is based on the basic principles of biological evolution. In so-called genetic algorithms, the genus of which includes the algorithm used in the method according to the invention, patterns and / or significant relationships and / or significant differences are found by the following steps: Analogous to DNA in biological evolution are fixed or randomly selected attributes of the acquired data and / or records mutated and recombined. Both mutation and recombination proceed according to fixed or random criteria. Through a fitness function in which identified significances are evaluated, appropriate mutations can be selected, which is known as the process of selection.
  • The evaluation of the significances by the fitness function is based on an assignment of a fitness value to a respective mutation, the fitness value indicating to what extent the respective mutation is suitable for a description of the respective pattern. The fitness function compares different mutations and finally selects them through a selection process. An example of an absolute fitness score would be "the smaller the better," and relative associations with pre-defined benchmarks may be used. Depending on the fitness value, it is decided which data or data sets influence how strongly the respective calculations.
  • By using the presented genetic algorithms, it is possible to predict how the datasets or their attributes may evolve, and whether significant patterns may occur in the future in connection with other data and / or datasets. This forecast makes it possible to identify new connections within the respective data, to derive new concrete patterns and proactive measures, and thus to initiate appropriate measures at an early stage against any unwanted patterns in the respective data.
  • As already explained, very large data sets can also be analyzed for patterns and / or significant relationships and / or significant differences by the method according to the invention. This also means that any patterns and / or relationships and / or differences that are of relevance to a vehicle diagnosis can be identified. By means of prior knowledge about, for example, wear of components, their respective lifetimes can be determined and accurately predicted in conjunction with prior knowledge of cofactors. A metal component, for example, has rusted after an average of ten years and must be replaced. However, if the vehicle is used in desert regions, the life of the metal component is extended due to the changed environmental conditions. By using the method according to the invention, it is possible, for example, to uncover this relationship by an analysis of a vibration behavior of the metal component detected by suitable sensors and to react proactively to a wear effect which may be identified by a characteristic pattern, ie to possibly disturb any disturbances.
  • In a further embodiment of the method according to the invention, it is provided that the algorithm is used to generate a prognosis about a possible occurrence of significant patterns in conjunction with other data and / or data records.
  • By using the method according to the invention, it is possible to include additional data sets in the forecast underlying calculations or selectively exclude data and / or records and using the calculated prognosis, a future behavior of those vehicle components, with the respective data and / or the respective data set or to consider effects of additional inserted or removed components. Furthermore, by using the method according to the invention by which patterns and / or significant differences and / or significant correlations have already been identified in first data and / or a first data record, it is possible to check in at least one further data record whether the identified patterns and / or or significant differences and / or significant relationships are also relevant. In this case, the at least one further data set can consist of data from the respective vehicle sensor system and / or from already calculated data and / or from external data, such as, for example, the traffic infrastructure or also to a physiological state of a driver.
  • Calculated data in the context of the method according to the invention or of the corresponding system are to be understood as data which has already been subjected to a calculation method and / or a calculation step and / or a mathematical preprocessing.
  • Due to additionally inserted or removed data records, the effect of individual components on future (driving) performance of future vehicles can thus be extrapolated. This process can counteract expensive mistakes and contribute to a sustainable and durable construction.
  • Furthermore, the inserted or removed data sets may also be used to predict a behavior of the driver and / or a particular environment. A possible application of a prediction of a driver behavior on the basis of driver-specific data would be, for example, a warning of the driver on the basis of a prediction of tiredness and an associated traffic hazard, which occurs, for example, as a function of an analysis of steering movements and traffic control conditions. In this case, the driver could be warned, for example, that his current behavior requires a rest period in the near future.
  • In a further refinement of the method according to the invention, it is provided that data and data records are exchanged between the respective vehicle and at least one further data source, such as a vehicle fleet or a server, via a so-called car-to-X interface and thereby for analysis by means of genetic algorithms be made accessible.
  • By networking the vehicle with external data sources by means of the aforementioned car-to-X interface, it is possible to provide the respective vehicle with external information and thereby preventively act against potentially harmful events. By means of external information, for example, accident focuses can be identified and / or predicted and / or exchanged between different vehicles, for example a vehicle fleet, wherein an exchange with another vehicle is possible regardless of a possible affiliation to a vehicle fleet.
  • It is further provided that the external information can also be obtained via the Internet or another data network by means of the Car-to-X interface. The car-to-X interface can be realized, for example, as a wireless connection in the form of an LTE or UMTS or WLAN connection, wherein the wireless connection may need to be adapted to future developments.
  • Furthermore, it is also possible by means of the aforementioned car-to-X interface to detect potentially advantageous events, such as, for example, a possible saving of fuel prematurely and thereby optimally use.
  • In a further embodiment of the method according to the invention, it is provided that the algorithm is used to identify not yet known connections within the data and / or the data records.
  • Using the method according to the invention, it is possible to determine characteristic parameters or patterns from a large number of independent and / or dependent information, on the basis of which a prognosis of a development of the processes underlying the respective data and / or data sets can be calculated.
  • In a further embodiment of the method according to the invention, it is provided that the algorithm is used to generate a prognosis about a temporal development of the data and / or the data record.
  • Insights into the longevity of components of a vehicle are of great interest, especially in vehicle construction. Although individual samples can give a clue to this, the findings obtained in this way are only conditionally transferable to other vehicles in series production.
  • By using the method according to the invention, it is possible to fuse data from different individual samples and to look at it together or to calculate a prognosis based on the data of the entire data set.
  • This prognosis can be modified by a larger number of cases, ie several vehicles as well as by repeated measures at different times on a same case study. Findings about the longevity of a component of a vehicle can be refined in particular by combining it with data of other components and / or cofactors. For example, a tire wear on a vehicle is not only dependent on the nature of the tire itself, but also on the performance of the vehicle or the driving style of the driver. The method according to the invention is optimized to identify these relationships and to include them in any prognosis. Therefore, it can also be provided that data of the driver or user of the respective vehicle are included in the underlying calculations. There If the calculations for the prognosis are automated and do not have to be done manually by complex covariance analyzes or the like, very large datasets called "big data" can be combined.
  • Furthermore, it is provided that even preprocessed data, which, for example, come from another vehicle, can be included in the respective prognosis.
  • In a further embodiment of the method according to the invention, it is provided that the data and / or data records comprise all the properties and / or operating data of a vehicle or of components of a vehicle.
  • Due to the provided possibility of the method according to the invention also to examine large data records on their effects with each other, it is provided in particular in the context of vehicle construction that all properties and / or operating data of a vehicle or components of a vehicle, d. H. expressly those factors which influence individual components, such as the outside temperature or the driver, are used as the basis for the formation of a data set or data set.
  • In a further refinement of the method according to the invention, it is provided that results obtained by the algorithm are analyzed by methods of data mining, whereby the patterns which are thereby recognized automatically and not yet known are evaluated and identified.
  • Data Mining aims to detect and extract patterns from data and / or datasets. For this purpose, however, it must be determined what is to be sought. Therefore, possible pattern generators should be known. Only then can an algorithm based on data mining be defined with regard to cluster analysis or classification of the data. In order to automate this step of specifying the pattern to be searched, the proposed method according to the invention should be used. By combining data mining and pattern analysis based on the method according to the invention, there is a possibility to identify a problem by means of a suitable data record and to identify or predict this in data of a respective vehicle. It is also possible to merge data from several data sets.
  • Using data mining, it is conceivable to gain knowledge in two directions: In a positive direction, components and cofactors are identified which, for example, are particularly durable or promote a longevity of components, such as, for example, a particularly good engine oil; In the negative direction, components and cofactors can be identified which, for example, reduce the longevity or the performance of components to a particular extent, such as, for example, high air humidity.
  • The method according to the invention uses already existing knowledge in the form of, for example, sensory data of the respective vehicle and / or other vehicles and generates a prognosis about a future behavior of an entire system, which serves as the basis for the respective data and / or data sets or individual components thereof serves. Moreover, it is possible with the aid of the method according to the invention to include also data from external data sources, such as, for example, a weather forecast in the analysis.
  • In a further refinement of the method according to the invention, it is provided that data and / or data sets which are not derived from the vehicle sensor system of the respective vehicle but are nevertheless of relevance for a functionality of the respective vehicle are analyzed by means of the algorithm.
  • As already explained, with increasing complexity of a system, in particular of a vehicle, factors for its performance or longevity play a role that are not directly associated with the respective vehicle. These factors can be factors such as weather conditions, nature of a particular roadway, but also a respective condition of the driver, etc. External factors contribute significantly to a meaningful prognosis about a behavior of the respective vehicle or its components and are therefore intended as a source of information.
  • Furthermore, the present invention relates to a system for identifying patterns and / or significant relationships and / or significant differences in data and / or datasets of at least one vehicle. The system according to the invention serves, in particular, to carry out the method according to the invention.
  • According to a possible embodiment of the system according to the invention, it is provided that in order to carry out a method for identifying patterns and / or significant relationships and / or significant differences in data and / or data sets of at least one vehicle, necessary calculations must be performed in at least one computing element is to be arranged inside or outside of a respective vehicle, wherein a result of the calculations is to be displayed on a display medium. In According to an embodiment of the system according to the invention, the system comprises both the at least one arithmetic unit and the display medium in operative contact with the arithmetic unit. However, it is also conceivable that the display medium is indeed in operative contact with the arithmetic unit, ie in a communicative connection, but not part of the system according to the invention.
  • It is further provided that the system according to the invention can be operated both in a vehicle and at a fixed location, for example a server. The system according to the invention receives the data and / or data records necessary for the respective calculations either directly through interfaces with a respective vehicle sensor system, for example through a CAN bus, in particular through wireless interfaces of the respective vehicle sensors or the vehicle, or via a serial interface.
  • The data acquired by the interface with the respective vehicle sensor system are archived by the system according to the invention and evaluated by means of the genetic algorithm.
  • Furthermore, it is provided that data already recorded in stored form by suitable storage media, such as USB drives, CDs, DVDs, hard disks and the like, are transferred to the system according to the invention and are thereby fed to an evaluation or analysis.
  • In a further embodiment of the system, it is provided that the sensors provided for detecting the data are part of the system according to the invention.
  • As already mentioned above, the system according to the invention, in one possible embodiment for displaying results of the necessary calculations, comprises a display medium, which can consist of any technically suitable device for displaying results of mathematical calculations. In particular, these are LCD, LED or TFT displays, monitors of all kinds, and mechanical means for displaying numbers.
  • It is understood that the features mentioned above and those yet to be explained below can be used not only in the particular combination indicated, but also in other combinations or in isolation, without departing from the scope of the present invention.
  • The invention is illustrated schematically with reference to an embodiment in the drawing and will be described schematically and in detail with reference to the drawing.
  • 1 shows a schematic representation of a flowchart of an embodiment of the method according to the invention.
  • In one embodiment, for optimizing the longevity of an engine on a racing car, an embodiment of the method according to the invention, as in FIG 1 shown used. To do so, as in step 1 shown, all available data from race cars, which use the type of motor to be optimized, collected, collected and provided as a record for further processing.
  • Thereby, the data set is analyzed for characteristic patterns and / or significant relationships and / or significant differences by means of the genetic algorithm, as in step 2 shown. By means of this method step, for example, a significant relationship is identified between a rapid change of high and low speeds and engine damage at outside temperatures of more than 35 ° C., as in step 3 shown.
  • By means of a classifier, this relationship is now searched in the respective race car, as in step 4 and determines its probability of occurrence. If the probability of occurrence exceeds a certain limit, for example 85%, appropriate countermeasures can be used to initiate countermeasures, as in step 5 shown. This can be, for example, an immediate shutdown of the engine or activation of a speed limit. This means that the technical staff without their own prior knowledge is able to recognize future problems and to make appropriate countermeasures.
  • QUOTES INCLUDE IN THE DESCRIPTION
  • This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.
  • Cited patent literature
    • US 2012/0158212 A1 [0004]
    • DE 102006017824 A1 [0005]
    • DE 10235525 A1 [0006]
    • EP 2159122 A2 [0007]
    • DE 102009054900 A1 [0008]

Claims (8)

  1. Method for identifying yet undefined patterns and / or significant relationships and / or significant differences of technical processes in an operation of at least one vehicle, wherein data and / or data sets are detected and provided by a vehicle sensor system of a respective vehicle and based on the acquired data and an algorithm comprising at least the operations of mutation and recombination of specified or randomly selected attributes of the data or datasets, the mutation and recombination operations according to a set or at least one of data sets and data sets and / or on already existing off-vehicle data and / or already calculated data run random criteria and wherein an evaluation of significances and selection of data or records is performed by means of a fitness function, about which forecasts and diagnoses of current and / or future events of at least one the vehicle or its components and, if appropriate, appropriate countermeasures are taken before they occur.
  2. The method of claim 1, wherein the algorithm is used to generate a prognosis about a possible occurrence of significant patterns in connection with other data and / or data sets than the in-vehicle data.
  3. Method according to Claim 1 or 2, in which the algorithm is used to identify not yet known connections within the data and / or the data records.
  4. Method according to one of the preceding claims, wherein the algorithm is used to generate a prognosis about a temporal evolution of the data and / or the at least one data set.
  5. Method according to one of the preceding claims, in which the data and / or the at least one data record comprise all the properties and / or operating data of a vehicle or of components of a vehicle.
  6. Method according to one of the preceding claims, wherein the results obtained by the algorithm are analyzed by methods of data mining, whereby the automatically recognized, not yet known patterns are evaluated and identified.
  7. A system for carrying out a method for identifying patterns and / or significant relationships and / or significant differences in data and / or datasets of at least one vehicle comprising at least one computing element that is configured to perform necessary calculations to perform the method and is to be arranged inside or outside of a respective vehicle, wherein a result of the calculations is to be displayed on a communicating with the at least one computing element display medium, the result can be made available on demand via an interface of the system further data processing equipment.
  8. The system according to claim 7, wherein the result of the calculations is to be provided to further data processing devices selected from the following list of further data processing devices for display on a display medium and / or for further calculations: vehicles, servers, computers, smartphones and data networks.
DE102013007007.4A 2013-04-23 2013-04-23 Pattern and significance detection in databases with genetic algorithms Pending DE102013007007A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
DE102013007007.4A DE102013007007A1 (en) 2013-04-23 2013-04-23 Pattern and significance detection in databases with genetic algorithms

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE102013007007.4A DE102013007007A1 (en) 2013-04-23 2013-04-23 Pattern and significance detection in databases with genetic algorithms

Publications (1)

Publication Number Publication Date
DE102013007007A1 true DE102013007007A1 (en) 2014-10-23

Family

ID=51628752

Family Applications (1)

Application Number Title Priority Date Filing Date
DE102013007007.4A Pending DE102013007007A1 (en) 2013-04-23 2013-04-23 Pattern and significance detection in databases with genetic algorithms

Country Status (1)

Country Link
DE (1) DE102013007007A1 (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10235525A1 (en) 2001-09-10 2003-04-10 Daimler Chrysler Ag Monitoring of the state of a motor vehicle using machine learning and data mining technology to generate component models that are then used to monitor components, predict failure, etc., such analysis being useful for repair, etc.
DE102006017824A1 (en) 2006-04-13 2007-10-18 Dspace Digital Signal Processing And Control Engineering Gmbh Diagnostic function building method for vehicle, involves acquiring classification function from collected simulation results to assign error symptoms, and determining symptom vectors by compiling results of error and non-error simulations
US20080004764A1 (en) * 2006-06-30 2008-01-03 Manokar Chinnadurai Diagnostics data collection and analysis method and apparatus to diagnose vehicle component failures
US7333960B2 (en) * 2003-08-01 2008-02-19 Icosystem Corporation Methods and systems for applying genetic operators to determine system conditions
EP2159122A2 (en) 2008-06-05 2010-03-03 Efkon Germany GmbH Method and system for simultaneous vehicle and driving profile monitoring
US20100114806A1 (en) * 2008-10-17 2010-05-06 Lockheed Martin Corporation Condition-Based Monitoring System For Machinery And Associated Methods
DE102009054900A1 (en) 2009-12-17 2011-06-22 Robert Bosch GmbH, 70469 Device for determining control device parameters
US20120158212A1 (en) 2009-12-31 2012-06-21 Shanghai Pateo Internet Technology Service Co., Ltd. Intelligent data center based on service platform for vehicle-mounted devices

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10235525A1 (en) 2001-09-10 2003-04-10 Daimler Chrysler Ag Monitoring of the state of a motor vehicle using machine learning and data mining technology to generate component models that are then used to monitor components, predict failure, etc., such analysis being useful for repair, etc.
US7333960B2 (en) * 2003-08-01 2008-02-19 Icosystem Corporation Methods and systems for applying genetic operators to determine system conditions
DE102006017824A1 (en) 2006-04-13 2007-10-18 Dspace Digital Signal Processing And Control Engineering Gmbh Diagnostic function building method for vehicle, involves acquiring classification function from collected simulation results to assign error symptoms, and determining symptom vectors by compiling results of error and non-error simulations
US20080004764A1 (en) * 2006-06-30 2008-01-03 Manokar Chinnadurai Diagnostics data collection and analysis method and apparatus to diagnose vehicle component failures
EP2159122A2 (en) 2008-06-05 2010-03-03 Efkon Germany GmbH Method and system for simultaneous vehicle and driving profile monitoring
US20100114806A1 (en) * 2008-10-17 2010-05-06 Lockheed Martin Corporation Condition-Based Monitoring System For Machinery And Associated Methods
DE102009054900A1 (en) 2009-12-17 2011-06-22 Robert Bosch GmbH, 70469 Device for determining control device parameters
US20120158212A1 (en) 2009-12-31 2012-06-21 Shanghai Pateo Internet Technology Service Co., Ltd. Intelligent data center based on service platform for vehicle-mounted devices

Similar Documents

Publication Publication Date Title
Tsui et al. Prognostics and health management: A review on data driven approaches
CN102062619B (en) For being come method system and the device of Analysis of Complex system by Forecast reasoning
US7395188B1 (en) System and method for equipment life estimation
Cerrada et al. A review on data-driven fault severity assessment in rolling bearings
Sugumaran et al. Feature selection using decision tree and classification through proximal support vector machine for fault diagnostics of roller bearing
CN103493019B (en) Many Agents cooperation vehicle breakdown diagnostic system and the method being associated
Zheng et al. A rolling bearing fault diagnosis method based on multi-scale fuzzy entropy and variable predictive model-based class discrimination
US8630962B2 (en) Error detection method and its system for early detection of errors in a planar or facilities
Sugumaran et al. Effect of number of features on classification of roller bearing faults using SVM and PSVM
US10078871B2 (en) Systems and methods to identify and profile a vehicle operator
Constantinescu et al. Driving style analysis using data mining techniques
JP4453764B2 (en) Vehicle diagnostic device, vehicle diagnostic system, and diagnostic method
JP5301310B2 (en) Anomaly detection method and anomaly detection system
JP5530020B1 (en) Abnormality diagnosis system and abnormality diagnosis method
US20140074345A1 (en) Systems, Apparatuses, Methods, Circuits and Associated Computer Executable Code for Monitoring and Assessing Vehicle Health
CN1981297B (en) Data compression apparatus and method, apparatus and method of data analysis, and data management system
EP1857964A2 (en) Inspection apparatus
EP2064106A1 (en) Diagnostic system and method for monitoring a rail system
CN1834607A (en) Inspection method and inspection apparatus
Purarjomandlangrudi et al. A data mining approach for fault diagnosis: An application of anomaly detection algorithm
JP4928532B2 (en) Vehicle fault diagnosis device
Murphey et al. Automotive fault diagnosis-part II: a distributed agent diagnostic system
Dozza What factors influence drivers’ response time for evasive maneuvers in real traffic?
WO2012074823A1 (en) Machine anomaly detection and diagnosis incorporating operational data
CN104044413B (en) That predicts is monitored based on equal tire health

Legal Events

Date Code Title Description
R012 Request for examination validly filed
R079 Amendment of ipc main class

Free format text: PREVIOUS MAIN CLASS: G01M0099000000

Ipc: G01M0017000000

R016 Response to examination communication
R016 Response to examination communication