DE10320809A1 - Car motion recognition and monitoring procedure processes data from acceleration, speed, force and body noise sensors using pattern recognition based on state vectors - Google Patents

Car motion recognition and monitoring procedure processes data from acceleration, speed, force and body noise sensors using pattern recognition based on state vectors

Info

Publication number
DE10320809A1
DE10320809A1 DE2003120809 DE10320809A DE10320809A1 DE 10320809 A1 DE10320809 A1 DE 10320809A1 DE 2003120809 DE2003120809 DE 2003120809 DE 10320809 A DE10320809 A DE 10320809A DE 10320809 A1 DE10320809 A1 DE 10320809A1
Authority
DE
Germany
Prior art keywords
characterized
measured values
sensors
estimation
chassis
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.)
Withdrawn
Application number
DE2003120809
Other languages
German (de)
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.)
Conti Temic Microelectronic GmbH
Original Assignee
Conti Temic Microelectronic GmbH
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 Conti Temic Microelectronic GmbH filed Critical Conti Temic Microelectronic GmbH
Priority to DE2003120809 priority Critical patent/DE10320809A1/en
Publication of DE10320809A1 publication Critical patent/DE10320809A1/en
Application status is Withdrawn legal-status Critical

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60GVEHICLE SUSPENSION ARRANGEMENTS
    • B60G17/00Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load
    • B60G17/015Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load the regulating means comprising electric or electronic elements
    • B60G17/018Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load the regulating means comprising electric or electronic elements characterised by the use of a specific signal treatment or control method
    • B60G17/0185Resilient suspensions having means for adjusting the spring or vibration-damper characteristics, for regulating the distance between a supporting surface and a sprung part of vehicle or for locking suspension during use to meet varying vehicular or surface conditions, e.g. due to speed or load the regulating means comprising electric or electronic elements characterised by the use of a specific signal treatment or control method for failure detection
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60GVEHICLE SUSPENSION ARRANGEMENTS
    • B60G2600/00Indexing codes relating to particular elements, systems or processes used on suspension systems or suspension control systems
    • B60G2600/08Failure or malfunction detecting means
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60GVEHICLE SUSPENSION ARRANGEMENTS
    • B60G2600/00Indexing codes relating to particular elements, systems or processes used on suspension systems or suspension control systems
    • B60G2600/18Automatic control means
    • B60G2600/187Digital Controller Details and Signal Treatment
    • B60G2600/1875Other parameter or state estimation methods not involving the mathematical modelling of the vehicle
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60GVEHICLE SUSPENSION ARRANGEMENTS
    • B60G2600/00Indexing codes relating to particular elements, systems or processes used on suspension systems or suspension control systems
    • B60G2600/18Automatic control means
    • B60G2600/187Digital Controller Details and Signal Treatment
    • B60G2600/1878Neural Networks
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60GVEHICLE SUSPENSION ARRANGEMENTS
    • B60G2600/00Indexing codes relating to particular elements, systems or processes used on suspension systems or suspension control systems
    • B60G2600/18Automatic control means
    • B60G2600/187Digital Controller Details and Signal Treatment
    • B60G2600/1879Fuzzy Logic Control
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60GVEHICLE SUSPENSION ARRANGEMENTS
    • B60G2800/00Indexing codes relating to the type of movement or to the condition of the vehicle and to the end result to be achieved by the control action
    • B60G2800/80Detection or control after a system or component failure
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60GVEHICLE SUSPENSION ARRANGEMENTS
    • B60G2800/00Indexing codes relating to the type of movement or to the condition of the vehicle and to the end result to be achieved by the control action
    • B60G2800/80Detection or control after a system or component failure
    • B60G2800/802Diagnostics

Abstract

A method for recognizing and monitoring the movement of a vehicle is presented, in which a plurality of sensors for detecting measured values of accelerations, speeds, distances, forces or noises on the chassis and on the body are attached to the vehicle, and the measured values recorded by the sensors with a Pattern recognition methods, in particular with a method known from language processing, can be processed.

Description

  • The The invention relates to a method for detection and monitoring the movement in vehicles, according to the generic term of claim 1.
  • The So far, chassis condition is different from different Sensors measured, which the different parameters on different Type capture. One will be measurands when driving, the other metrics will be determined when the vehicle is stationary. So is the tire pressure of a tire is detected by a pressure sensor that detects the Measures tire pressure. There are also measurement methods for test benches check the condition of the tires and / or the dampers when the vehicle is at a standstill. Also are simple monitoring and control algorithms for damper adjustment known as the sky hook damper. The condition of the road and thus the bumps in the road can be ultrasound be measured. Various methods are also known for weather conditions to capture.
  • The methods known in connection with chassis diagnostics and controller optimization are based on modeling the chassis using differential equations and embedding them in condition observers. These methods require considerable computational and metrological effort to assess the condition of the entire vehicle, so that these methods have only been used in practice for reduced requirements. The following references and patents are listed as examples: DE3608420C2 . DE4218087A1 . DE4019501A1 . DE3883212T2 . DE19909157A1 . DE4213221A1 . DE4235809C1 . DE19543137A1 . DE4440413A1 . DE4431794A1 . DE4435448A1 ,
  • In the publication: "Dynamics of Motor Vehicles" by Manfred Mitschke are in the third edition in volume B vibrations of motor vehicles described and analyzed that a four-wheel motor vehicle generates, which about an uneven road surface and represents a vibration system. Here it is shown what influence the various parameters have on the vibration system Have motor vehicle. In this book, the parameters (e.g .: Tire pressure, wheel suspension, damper Bumps, motor excitation, motor speed) presented that the Affect the vibration system. There are oscillation equations dependent on set up by these parameters. As a solution or solutions to these vibration equations receives one accelerations, relative distances and forces, which are then used for assessment the chassis behavior and thus to determine comfort and Serve driving safety.
  • adversely in these known methods for determining the chassis condition are the high costs of directly sensing the measurement parameters caused. Another disadvantage arises from the partial very time-consuming and costly calculation of complicated vibration systems and the big one Amounts of data within shortest Time to be processed. Another unfavorable Circumstance is that no multiple use of the sensor signals possible is.
  • In the DE 4218087 A1 discloses a method for controlling the damping of the chassis of a motor vehicle and / or for diagnosing the chassis. Here, process variables which are related to a vertical movement of the vehicle are fed to a mathematical model which represents the relationship between the vertical acceleration of a wheel or a structure of the vehicle on the one hand and other process variables and parameters on the other hand. The parameters of the model are estimated using a parameter estimation method known per se and used to generate a manipulated variable for setting the damping and / or as diagnostic data.
  • adversely here is also the complex calculation. Be first several equations established the physical relationships between describe the measured values and the parameters. These equations contain several unknown parameters. Because the number of equations not enough to calculate every unknown parameter exactly, becomes a parameter estimation method used. The elaborately estimated Parameters in turn then serve to calculate the physical Process variables that to control or diagnose the chassis.
  • It is in the EP 0554131 A1 Method for sensing the tire condition using a sensor attached to the tire is known. The sensors record the speed of rotation of each tire. Another sensor detects the speed or acceleration of the vehicle. By comparing these values with each other, conclusions can be drawn about the tire pressure.
  • adversely in addition to the disadvantages mentioned above, this is very many sensors are needed to recognize a state.
  • The The object of the invention is the chassis state in particular Tire pressure, wheel and tire condition, damper condition and damper settings, the road or rail quality and the body's own movement fast, reliable and inexpensive to monitor. Another object of the invention is optimization the setting parameters of the damping system in the field of road, To achieve rail and aircraft.
  • The The object is achieved by the features in claim 1 solved. Here are sensors to record accelerations, speeds, distances and / or forces attached to the chassis and body. The evaluation of the Sensor signals are generated using a parameter estimation process. The parameters obtained from this are evaluated with the help of methods for pattern recognition, the fuzzi techniques and / or neural networks that is the causes, the movements on the chassis are not recorded effect and over Vibration equations are calculated using the movements of the vehicle then the result obtained is used to assess the chassis condition. The chassis condition is made up of the individual, different measured values Vectors formed. These vectors, which are not just individual measured values themselves, but also reflect the relation of several measured values to each other, can then compared with stored vectors or vector fields to which a vehicle state is assigned.
  • The The advantage of the invention is that compared to previous ones Very small amount of data, very reliable statements about the process Chassis condition can be made because of the different constellations of the measured values to each other also have meaningfulness about the state of the vehicle. Also The data processing for previous methods is very low because no complicated calculations are required, only result vectors be compared with each other. The evaluation is very quick, so that at disorders early can be intervened in the system e.g. prevent major damage. It is also an inexpensive one Multiple use of the sensors used is an advantage, resulting in a increase security, early detection of dangerous conditions (e.g. the aging or pressure loss in the tires) and an improvement comfort is achieved. This also creates opportunities for Detection of the road condition as an input signal for intelligent braking algorithms.
  • The The method presented here now takes a completely different approach: The sensor signals are without any direct reference to mathematical or processed physical models with the methods of speech recognition and the comparison of the quantized states leads to the state of the Road condition and the overall chassis as well as individual Components closed.
  • In As is known, sensors are located at suitable points in the vehicle attached, which directly or indirectly capture the required measurement parameters. In the area of the wheel hub, subframe or damper dome attached sensors primarily detect the excitation that is generated from the road surface, over tires and spring / shock absorber act on the body. Acceleration sensors are preferred here Use, but also sensors for speed, structure-borne noise, Pressure, force, stroke, travel or angle applicable. The number and spatial Distribution depends depending on the requirements. The minimum equipment is one sensor per vehicle, the maximum equipment one sensor per measurement variable per wheel. In addition can at least one sensor on the chassis for detecting the excitation, which is transmitted via the Impact chassis on the body, be attached. With help motion sensors, such as acceleration (preferably), Speed, pressure, distance, stroke, angle, position, yaw rate, pitching movement or rolling motion, can be a measure of the payload from the movement of the chassis or the adjustment of the dampers be won. With the help of acoustic sensors, such as Microphone or structure-borne sound sensor, vibrations of the chassis caused by brakes, mechanical bearings, Tire profile, stone chips or splashing water, recorded. Triggered with the brake application can thereby critical states of the Brake (wear, Rubbing, squeaking) are determined and evaluated. An acoustic Sensor, on or near attached to the wheel arch can be critical using speech analysis Recognize road surface conditions such as roll split or water film. About the spatial Arrangement of the sensor or sensors can amplify or measure certain parameters attenuated be recorded.
  • These measuring principles are known and described in the specialist literature. In conventional practice, one or more sensors are assigned to each measurement task. The algorithms, based on digital filters, statistical procedures and / or rms value calculations are tailored to the measurement task.
  • The new approach is based on multiple use of the sensors the methods of speech recognition. This results in the same Safety and comfort requirements are an essential cost, Space, u. Weight advantage. The technical effort for speech recognition remains within reasonable limits.
  • The Use of speech recognition methods for the assessment of the chassis and the carriageway is based on the idea that during the Driving operation time u. quasi-steady-state states on the sensor outputs to adjust. The sequence of quasi-stationary driving conditions causes Sectional signal signatures on the sensors, comparable to the sequence of sounds within a word, where a sound each such a quasi-stationary driving state equivalent.
  • So the driving noises differ dependent whether you are on cobblestone with summer or winter tires or tarred road. These four different sounds can four different class names (= sounds) can be assigned. The number of different class names are application specific set. According to claim the output signals of the sensors are processed using speech recognition methods, as they are applied to a microphone signal in a known manner, processed.
  • A general description of speech recognition can be found in the literature at:
    Schukat-Talamazzini: Automatic speech recognition, Vieweg Verlag 1995
    Quartieri, Thomas: Speech Signal Processing, Prentice Hall 2001.
    Zell, A .: Simulation of Neural Networks, Addison Verlag 1994.
  • The transfer of these procedures into the proposed application of the evaluation of the chassis and the condition of the road takes place in these three layers:
    Layers 1 and 2 are sensor-specific, layer 3 represents the overall context with regard to the vehicle.
  • The Sensors are preferably used as sensors for the measured variables: acceleration, structure-borne noise, Speed, force, pressure, stroke, path, angle, distance, pitch movement or rolling motion used.
  • For the extraction of characteristics the methods of linear prediction analysis, Cepstrum Analysis, Short Time Fourier Analysis, Filter Bank Analysis, Sinusoidal Analysis or Frequency Domain Pitch Estimation used.
  • The Illustration of the estimation vectors to defined class names is preferably carried out using a method of neural networks, fuzzy logic, assignment tables, linear Discriminant analysis or hidden Markov models.
  • The Sampling of the measured values is preferably carried out in a time-equidistant manner as well as away equidistant.
  • The supervision and recognition using a classifier is preferably carried out based on the processes of neural networks, fuzzy logic, assignment tables, Linear discriminant analysis or hidden Markov models, which the overall rating from the comparison of the class names for each measuring channel performs.
  • For the generation of characteristics an orthogonal estimation method is preferably used.
  • The estimate vectors are preferably using AR-Lattice- (autoregressive), ARMA-Lattice- (autoregressive moving average) or joint lattice / ladder method.
  • The Sensor signals, the estimation vectors, the class names and / or the overall rating via bus coupling are preferred forwarded to other diagnostic, reporting or control systems or generated in at least one of these systems and a specified one there Action started.
  • A value for
    • - the condition of the road and / or
    • - the tire condition and / or
    • - the damper condition and / or
    • - the brake condition and / or
    • - determines the load.
  • Preferably driving on the verge is also recognized.
  • The Invention can for Road vehicles, Rail vehicles and aircraft are used.
  • Out the comparison of the estimation vectors can preferably also on the functionality of individual sensors getting closed.
  • moreover the results are preferably saved and from the temporal Comparison of the state of aging assessed.
  • The Invention is intended to be based on exemplary embodiments and the figures are shown.
  • 1 shows the model for the detection and monitoring of movements on vehicles. In this exemplary embodiment, it is a vehicle with four wheels, four dampers, a chassis and five sensors, which generally measure accelerations. However, speed, distance, length, force or noise sensors can also be used. Essentially two transmission systems are shown in the upper part of the figure. One transmission system is the unit of road and wheel. The other transmission system is represented by dampers and chassis. Both transmission systems are interconnected. Four suspension sensors - one on each subframe - are arranged between the transmission systems roadway / wheel and damper / chassis. The fifth sensor, the chassis sensor, is located on the chassis. The transmission systems change a signal WR present at the input of the transmission systems, the white noise. In the first step of the method, measurement signals are recorded at suitable points, which were selected on the basis of empirical values.
  • The The second stage of this model illustration shows five inputs for the sensor signals. Be here the measurement results of the four chassis sensors and the chassis sensor fed into the prefilter.
  • To the values are added to the pre-filter together with the white noise one or more estimation methods fed.
  • Everyone Sensor delivers series of measurements. Measurement series are understood here a number of measurement results obtained during a period be included. From the measurement series of a sensor become by an orthogonal estimation method computes the components of vectors. Obtained for each chassis sensor three estimation vectors and for the chassis sensor results in two estimation vectors.
  • Fundamental for the embodiment is that the dynamic behavior of the mechanical elements with sufficient accuracy thanks to a sectionally linear transmission system can be modeled. In speech recognition, orthogonal estimation methods used.
  • These properties can also be used to describe a driving state of a vehicle. Depending on the structure of the transmission system, the AR (autoregressive, ARMA (autoregressive moving average) or joint ladder method can be selected. These estimation methods form at least two vectors from a measurement series of a sensor, the number of elements of which depends on the order of the system, which Again, changes in the state of the system depend: In the application example, the chassis sensor is a series of measurements consisting of the time-dependent measured values: m 1 (t 1 ), m 2 (t 2 ), m 3 (t 3 ), ... m n (t n If no changes occur during the journey, the following applies in the steady state: m 1 (t 1 ) = m 2 (t 2 ) = m 3 (t 3 ) = ... = m n (t n ) The values may differ more or less depending on the event. Two vectors K → c and K → d are calculated from this number of measured values, these vectors each having μ elements with:
    Figure 00100001
  • The Number of μ Elements is dependent from the change of the measured values above the time.
  • The values of k c1 ... k and k d1 ... k dμ depend on the one hand on the individual measured values and on the relation of the measured values to one another. For example:
    Figure 00110001
  • It With this procedure, new series of measurements with the current Measured values formed and new vectors calculated from them.
  • In the exemplary embodiment, two vectors are then formed from the measured values of the chassis sensor using the AR estimation method, as described above, and from the measured value series:
    Figure 00110002
    of the chassis sensors F1, F2, F3, F4 and the chassis sensor, three estimate vectors K → f , K → b , K → g are formed per chassis sensor according to the joint ladder estimation method
    Figure 00110003
    Figure 00120001
  • In total, 14 vectors are obtained in the application example:
    Figure 00120002
  • This Vectors are now compared to one another and one others with stored values, element by element and afterwards they are classified. For The classification is necessary for the most diverse Driving situations and conditions, that are reflected in vectors and there in particular in the elements, Values, ranges of values, and possibly relations of the elements of different vectors with each other, stored in a memory are.
  • To The results of a classification are fed to the classification. The Map in turn influences the prefilter.
  • It the estimation vectors are converted into physical ones Sizes. Functions result from the conversion. From the joint ladder estimate one Suspension sensor results in a function H (z) = B (z) / A (z).
  • Out the AR estimate of the chassis sensor results in a function after the conversion H (z) = 1 / E (z). The physical values then result, the then in the third stage of the control loops, diagnostic systems model or driver information systems are fed to an unwanted Influencing driving conditions, recognizing errors early or at least Report bugs.
  • 2 describes the course of the estimation. In the system illustration, the white noise is fed into the function 1 / A (z). The chassis sensor detects what this function or the transmission system does with the white noise. On the one hand, this series of measured values reaches a prefilter, and on the other hand it is fed into a further transmission system or function B (z). The chassis sensor detects what the second transmission system does with the white noise. These series of measured values go into two different pre-filters, if necessary. In this example, three calculation strings are formed, which result from two different series of measurements. Two of the calculation strings are linked to each other and influence each other by using the value or vector from one strand as the basis for calculating the value or vector in the other strand.
  • Either in one as well as in the other independent calculation string after the pre-filter two processes set in motion. A first value arrives at point T and then in a first circle. This branches between T and the first circle to a second circle. The first value also goes directly to the second Circle and previously branches back to the first circle.
  • In 3 a diagnostic table is shown. If you want to detect a fault on the wheel at the front right on the chassis sensor F1, you have to, for example, an element, k F1 / f2 of the corresponding vector
    Figure 00130001
    compare with the corresponding elements k F2 / f2 k F3 / f2 k F4 / f2, which were recorded by the other chassis sensors F2, F3, F4. If k F1 / f2 ≠ k F2 / f2 = k F3 / f2 = k F4 / f2, it can be concluded from this that there is a different condition on the wheel, for example a too low lutt pressure.
  • 4 outlines a modified evaluation.
  • 5 illustrates the two-stage basic principle of parameter estimation and pattern recognition, as it is ultimately used in speech processing, applied here to the analysis of the vehicle and road condition.
  • The transfer of a pattern recognition method, as has been used up to now in speech recognition, into the proposed application of the assessment of the chassis and the condition of the road takes place in these three layers and is in 6 visualized.
  • layer 1 and 2 are sensor-specific, layer 3 provides the overall context in terms of of the vehicle.
  • layer 1 is used to generate features. The measurement signals are time and / or path equidistant sampled and processed separately. For feature generation are optionally based on these samples without claim to completeness the well-known methods: Linear Prediction Analysis (LPC), Cepstrum Analysis, Short Time Fourier Analysis, Filter Bank Analysis, Sinusoidal Analysis, frequency domain pitch estimation, combinations of these or further developments applied. Processes are advantageous the to orthogonal estimation vectors to lead.
  • The LPC method estimates the coefficients of the equivalent transfer function. The order of the transfer function is determined by the underlying physical model. Ladder / lattice processes are preferably used here. There are different approaches for modeling the transfer function using LPC:
    The AR (autoregressive) lattice method is used when a pulse train or white noise has to be used as the input signal of the transmission system to be modeled. Because of the generality of the approach, this method can be applied to any sensor output. The estimation vector describes the coefficients of the approximated AR model.
  • ARMA (autoregressive moving average) -Lattice methods require two measurement signals as input and output of a transfer function can be interpreted. The estimate vector describes the coefficients of the ARMA transfer function between these two measurement channels.
  • Joint-Ladder / Lattice process can be used advantageously if the signal on channel 1 is used AR Lattice estimate and the transmission link can be simulated between channel 1 and channel 2 using an MA model. exemplary can the signal of the chassis sensor on channel 1 and the signal of the Chassis sensors can be connected to channel 2. In this case describes the AR estimate vector the entire transmission path Road surface and tires, the MA estimation vector the transmission link Spring / damper.
  • filter Bank Analysis determines the effective values of the output signals of a Series of band passes with certain passband areas adapted to the application. Cepstrum analysis and the different Fourier analysis methods determine the weighted spectral components in the recorded Sensor signal.
  • The Samples as well as the estimation vectors can if necessary to superordinate Control loops are forwarded.
  • The Arithmetic operations usually result in an infinite number of different estimation vectors. That is why in the further configuration in the second layer with the help of the classification methods known from speech recognition the infinite number of solutions mapped to a finite number of class names. In speech recognition this corresponds to the assignment to sounds. The most famous classification methods are not exhaustive: Neural networks, fuzzy logic, linear discriminant analysis, allocation tables or Hidden Markov models. The number of class names ("lute") is determined by the desired Classification depth determined. This in turn is determined by the downstream diagnostic and Control systems. Stand with it these systems both the estimate vectors as well as the quantized class names, which are tabular controller parameters be assigned. The classification takes place as part of a learning process, whereby Both simulation methods and driver testing are used.
  • In In the further development, these class names become the individual Pass sensors to the third layer. The mutual comparison of the class names takes place in this layer. Here too come the classification procedures for speech recognition for use (without claim to completeness): neural networks, Fuzzy logic, linear discriminant analysis, assignment tables or Hidden Markov models.
  • For example, if all sensors attached to the chassis report the same status (= same class name, "= loud"), this information about the road surface and tires can be passed on to the higher-level control system as a current estimate. The class name of a wheel sensor signal differs significantly from the class name of the other wheel sensor signals can be concluded that there is a defect on the single wheel (unbalance, carcass tear, insufficient tire pressure, different tire profile, etc.) A distinction between the condition of the road surface and the tire is the fact that the class names obtained from the path-equidistant scanning are independent of the wheel speed for the tire properties. This makes it possible, for example, to clearly differentiate between tire imbalance and a wavy road surface. In the latter, the class names change depending on the vehicle speed, in the former there is essentially no influence. Another criterion relates to the rate at which class names change: sizes that depend on the road surface or tire pressure can change very briefly. Wear-dependent variables, such as tire tread depth, or damping coefficient usually change very slowly. Trend tracking of class names or estimation vectors is required here.
  • Vary the class names in pairs (left vehicle half: VL and HL against right Half of the vehicle: VR and HR), can change lanes or drive on of the edge strip are closed, being from the different Class names can be concluded, which side of the vehicle the road has left.
  • In Connection with a soft set damper can result from your own movement of the vehicle chassis, recorded via a suitable chassis sensor on the vehicle's payload getting closed.
  • to Avoiding evaluation errors, it is advantageous to use the excitation frequency of the undercarriage.
  • acoustic Sensors attached to the chassis or chassis are special Suitable for signal analysis using speech recognition. Herewith can the profile properties of the tires, which influence the braking process, recorded, bearing damage detected due to the characteristic spectral components and damage to the Brake can be recognized.

Claims (8)

  1. Method for detecting and monitoring the movement of a vehicle on which a plurality of sensors for recording measured values of accelerations, speeds, distances, forces or noises are attached to the chassis and body, characterized in that the measured values recorded by the sensors are processed using a pattern recognition method ,
  2. A method according to claim 1, characterized in that the measured values recorded by the sensors with a from the Speech processing known pattern recognition processes edited become.
  3. A method according to claim 1 or 2, characterized in that that the measured values recorded by the sensors using an estimation method are edited, whereby - of one sensor each recorded several measured values over time become and then - out the measured values of a sensor, numerical values are calculated, which form the components of different estimation vectors and - the estimation vectors with other vectors stored in a storage unit are and which are each assigned a defined driving state, compared and classified.
  4. Method according to one of the preceding claims, characterized characterized in that the components of an estimation vector with an orthogonal Estimation methods, especially the ladder or lattice method.
  5. Method according to one of the preceding claims, characterized characterized in that the components of an estimation vector with autoregressive, Moving average or joint ladder methods can be estimated.
  6. Method according to one of the preceding claims, characterized characterized that the measured values for calculating the components an estimation vector at defined intervals be repeated.
  7. Method according to one of the preceding claims, characterized characterized that the measured values for calculating the components an estimation vector after putting it back defined distances can be repeated.
  8. Structure for a method according to one of the preceding claims, characterized in that at least one sensor is arranged on each subframe and on the chassis, the measurements of which are used to calculate the components of the vector.
DE2003120809 2003-05-08 2003-05-08 Car motion recognition and monitoring procedure processes data from acceleration, speed, force and body noise sensors using pattern recognition based on state vectors Withdrawn DE10320809A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
DE2003120809 DE10320809A1 (en) 2003-05-08 2003-05-08 Car motion recognition and monitoring procedure processes data from acceleration, speed, force and body noise sensors using pattern recognition based on state vectors

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE2003120809 DE10320809A1 (en) 2003-05-08 2003-05-08 Car motion recognition and monitoring procedure processes data from acceleration, speed, force and body noise sensors using pattern recognition based on state vectors
PCT/DE2004/000976 WO2004101300A1 (en) 2003-05-08 2004-05-10 Method for detection and monitoring of the movements of vehicles

Publications (1)

Publication Number Publication Date
DE10320809A1 true DE10320809A1 (en) 2004-11-25

Family

ID=33394374

Family Applications (1)

Application Number Title Priority Date Filing Date
DE2003120809 Withdrawn DE10320809A1 (en) 2003-05-08 2003-05-08 Car motion recognition and monitoring procedure processes data from acceleration, speed, force and body noise sensors using pattern recognition based on state vectors

Country Status (2)

Country Link
DE (1) DE10320809A1 (en)
WO (1) WO2004101300A1 (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102004049380A1 (en) * 2004-10-09 2006-04-13 Conti Temic Microelectronic Gmbh Vehicle sensor has processing characteristic for electrical signals produced through sensing of different oscillations and which can be adjusted automatically in dependence upon control signal
EP1703471A1 (en) * 2005-03-14 2006-09-20 Harman Becker Automotive Systems GmbH Automatic recognition of vehicle operation noises
DE102005048141A1 (en) * 2005-10-07 2007-04-12 Zf Friedrichshafen Ag Product e.g. motor vehicle, evaluating method for use in automobile industry, involves performing fine analysis on partial data, and evaluating product based on quantifiable evaluation criterion and characteristic data or pattern
DE102005053223A1 (en) * 2005-11-08 2007-05-10 Bayerische Motoren Werke Ag Chassis diagnosis system for e.g. truck, has chassis components whose vibrations characteristics are evaluated, where variations between actual- and reference-vibrations characteristics are stored as error codes and are read during overhaul
EP1785290A1 (en) * 2005-11-09 2007-05-16 Mando Corporation Method for measuring vertical accelaration and velocity of semi-active suspension system
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
DE102006000915B4 (en) * 2005-01-07 2008-04-17 General Motors Corp., Detroit Method for modeling vehicle parameter cycles
US7627408B2 (en) 2005-11-02 2009-12-01 Mando Corporation Method for measuring vertical acceleration and velocity of semi-active suspension system
EP2537723A3 (en) * 2011-06-24 2013-01-02 Kabushiki Kaisha Bridgestone Method and apparatus for determining road surface condition
DE102014011162A1 (en) 2014-07-25 2016-01-28 Audi Ag Method for operating an active chassis
DE102015203026A1 (en) * 2015-02-19 2016-08-25 Bayerische Motoren Werke Aktiengesellschaft Motor vehicle with ballast detection device and method for detecting ballast
DE102018203560A1 (en) * 2018-03-08 2019-09-12 Bayerische Motoren Werke Aktiengesellschaft Method and control unit for detecting a lane boundary

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3700409A1 (en) * 1986-01-10 1987-07-16 Nissan Motor hybrid fahrzeugbewegungsabschaetzsystem
EP0554131A1 (en) * 1992-01-31 1993-08-04 Honda Giken Kogyo Kabushiki Kaisha System and method for determining a reduction in the pneumatic tire pressure
DE4218087A1 (en) * 1992-06-01 1993-12-02 Isermann Rolf Prof Dr Ing Dr H Controlling vibration damping of car chassis or body - using mathematical model with linear relationship between vertical chassis acceleration and its displacement and velocity
DE4340746A1 (en) * 1992-11-30 1994-06-01 Toyota Chuo Kenkyusho Aichi Kk Dynamic system error diagnostic appts., e.g. for motor vehicle - determines integrated disturbance vector, consisting of sum of external and internal vectors of dynamic system, based on internal state vector of dynamic system, and cross-correlates with internal state vector
DE69028872T2 (en) * 1989-05-18 1997-02-20 Ford Werke Ag Process and apparatus for diagnosis of the electronic control system of a motor vehicle with the aid of pattern recognition
DE19827271A1 (en) * 1998-06-19 1999-12-23 Andreas Mueller Sensor supported ON LINE determination system with evaluation of wheel and track related data during train travel
DE19911848A1 (en) * 1999-03-17 2000-09-21 Robert Kuehn Railway rolling stock operational safety data monitoring method, involves using slave computer with software for controlling operation of master computer and at least one slave computer in train unit
DE4133237C2 (en) * 1991-10-05 2001-10-11 Bosch Gmbh Robert System for chassis control
DE10062606A1 (en) * 2000-12-12 2002-06-13 Daimler Chrysler Ag Monitoring of the mechanical state of electric motor vehicles to detect damage or incorrect operation of the motor or drive mechanism based on statistical analysis of measured motor operating values, e.g. supply voltage
DE10064754A1 (en) * 2000-12-22 2002-07-04 Daimler Chrysler Ag Method and arrangement for determining a noise signal of a noise source
DE10161283A1 (en) * 2000-12-12 2002-08-01 Deutsche Bahn Ag Method for permanently monitoring the condition of railway wagon wheel bearings at fixed time intervals involves using transducers to record characteristics or each wheel bearing
DE10161655A1 (en) * 2000-12-14 2003-01-16 Siemens Corp Res Inc X-ray maintenance method for medical field, involves deriving pattern classifier using linear discriminant which separates two sets of vectors, for monitoring persistence of event occurrence in X-ray device
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.
DE10215464A1 (en) * 2002-03-28 2003-10-16 Volkswagen Ag Determining method for an assessed value of a flotation angle in motor vehicles to be measured indirectly uses a non-linear differential equation to describe the flotation angle
DE10319493A1 (en) * 2002-05-16 2003-11-27 Ford Global Tech Inc Remote diagnosis and forecasting methods for complex systems

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06104455B2 (en) 1985-03-15 1994-12-21 日産自動車株式会社 Vehicle motion state estimation apparatus
DE3642590C2 (en) * 1985-12-12 1990-02-22 Bayerische Motoren Werke Ag, 8000 Muenchen, De
JPH0818484B2 (en) * 1988-01-25 1996-02-28 日産自動車株式会社 Suspension and steering force control device
US5041976A (en) * 1989-05-18 1991-08-20 Ford Motor Company Diagnostic system using pattern recognition for electronic automotive control systems
DE4019501A1 (en) 1989-09-30 1991-04-11 Lehn F Heinrich Method and apparatus for schwingungsueberwachung of wheel systems of motor vehicles during driving operation
DE4014876A1 (en) * 1990-05-09 1991-11-14 Bayerische Motoren Werke Ag Method and device for determining and / or supervise the states, a technical component of an automotive vehicle
DE4213221C2 (en) 1992-04-22 2001-05-17 Porsche Ag A method for detecting the wetting of a road surface
DE4235809C2 (en) 1992-10-23 1997-07-24 Telefunken Microelectron Sensor system in motor vehicles for detecting moisture on the roadway
DE4431794A1 (en) 1994-09-06 1996-03-07 Langlechner Richard Gmbh Method and apparatus for determining the characteristics of the built in an automobile shock absorber
DE4440413A1 (en) 1994-11-11 1996-05-15 Fichtel & Sachs Ag Monitoring system for determining efficiency of esp. motor vehicle shock absorber
DE19543137A1 (en) 1995-11-18 1997-05-22 Porsche Ag Sensor with vibrational body for determining wet or broken roadway for vehicle
DE19723037A1 (en) * 1996-06-07 1997-12-18 Volkswagen Ag Tyre pressure monitor based on stub axle vibration
DE19730414A1 (en) * 1997-07-16 1999-01-21 Opel Adam Ag Method to judge condition of roadway in advance
DE19803386A1 (en) * 1998-01-29 1999-08-05 Daimler Chrysler Ag Device for monitoring the air pressure of a vehicle tire
DE19909157A1 (en) 1999-03-02 2000-09-21 Daimler Chrysler Ag Distributed Fahrzeuginformationsverarbeitungs- and vehicle control system
DE10044128A1 (en) * 2000-09-06 2002-05-29 Continental Ag Chassis for vehicles and method for detecting pressure changes to vehicle tires
DE10145433C2 (en) * 2000-09-15 2003-11-27 Db Reise & Touristik Ag Method and device for fault monitoring of components of rail vehicles

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3700409A1 (en) * 1986-01-10 1987-07-16 Nissan Motor hybrid fahrzeugbewegungsabschaetzsystem
DE69028872T2 (en) * 1989-05-18 1997-02-20 Ford Werke Ag Process and apparatus for diagnosis of the electronic control system of a motor vehicle with the aid of pattern recognition
DE4133237C2 (en) * 1991-10-05 2001-10-11 Bosch Gmbh Robert System for chassis control
EP0554131A1 (en) * 1992-01-31 1993-08-04 Honda Giken Kogyo Kabushiki Kaisha System and method for determining a reduction in the pneumatic tire pressure
DE4218087A1 (en) * 1992-06-01 1993-12-02 Isermann Rolf Prof Dr Ing Dr H Controlling vibration damping of car chassis or body - using mathematical model with linear relationship between vertical chassis acceleration and its displacement and velocity
DE4340746A1 (en) * 1992-11-30 1994-06-01 Toyota Chuo Kenkyusho Aichi Kk Dynamic system error diagnostic appts., e.g. for motor vehicle - determines integrated disturbance vector, consisting of sum of external and internal vectors of dynamic system, based on internal state vector of dynamic system, and cross-correlates with internal state vector
DE19827271A1 (en) * 1998-06-19 1999-12-23 Andreas Mueller Sensor supported ON LINE determination system with evaluation of wheel and track related data during train travel
DE19911848A1 (en) * 1999-03-17 2000-09-21 Robert Kuehn Railway rolling stock operational safety data monitoring method, involves using slave computer with software for controlling operation of master computer and at least one slave computer in train unit
DE10062606A1 (en) * 2000-12-12 2002-06-13 Daimler Chrysler Ag Monitoring of the mechanical state of electric motor vehicles to detect damage or incorrect operation of the motor or drive mechanism based on statistical analysis of measured motor operating values, e.g. supply voltage
DE10161283A1 (en) * 2000-12-12 2002-08-01 Deutsche Bahn Ag Method for permanently monitoring the condition of railway wagon wheel bearings at fixed time intervals involves using transducers to record characteristics or each wheel bearing
DE10161655A1 (en) * 2000-12-14 2003-01-16 Siemens Corp Res Inc X-ray maintenance method for medical field, involves deriving pattern classifier using linear discriminant which separates two sets of vectors, for monitoring persistence of event occurrence in X-ray device
DE10064754A1 (en) * 2000-12-22 2002-07-04 Daimler Chrysler Ag Method and arrangement for determining a noise signal of a noise source
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.
DE10215464A1 (en) * 2002-03-28 2003-10-16 Volkswagen Ag Determining method for an assessed value of a flotation angle in motor vehicles to be measured indirectly uses a non-linear differential equation to describe the flotation angle
DE10319493A1 (en) * 2002-05-16 2003-11-27 Ford Global Tech Inc Remote diagnosis and forecasting methods for complex systems

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102004049380B4 (en) * 2004-10-09 2017-02-02 Conti Temic Microelectronic Gmbh Vehicle sensor
DE102004049380A1 (en) * 2004-10-09 2006-04-13 Conti Temic Microelectronic Gmbh Vehicle sensor has processing characteristic for electrical signals produced through sensing of different oscillations and which can be adjusted automatically in dependence upon control signal
DE102006000915B4 (en) * 2005-01-07 2008-04-17 General Motors Corp., Detroit Method for modeling vehicle parameter cycles
EP1703471A1 (en) * 2005-03-14 2006-09-20 Harman Becker Automotive Systems GmbH Automatic recognition of vehicle operation noises
DE102005048141A1 (en) * 2005-10-07 2007-04-12 Zf Friedrichshafen Ag Product e.g. motor vehicle, evaluating method for use in automobile industry, involves performing fine analysis on partial data, and evaluating product based on quantifiable evaluation criterion and characteristic data or pattern
US7627408B2 (en) 2005-11-02 2009-12-01 Mando Corporation Method for measuring vertical acceleration and velocity of semi-active suspension system
DE102005053223A1 (en) * 2005-11-08 2007-05-10 Bayerische Motoren Werke Ag Chassis diagnosis system for e.g. truck, has chassis components whose vibrations characteristics are evaluated, where variations between actual- and reference-vibrations characteristics are stored as error codes and are read during overhaul
EP1785290A1 (en) * 2005-11-09 2007-05-16 Mando Corporation Method for measuring vertical accelaration and velocity of semi-active suspension system
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
DE102006017824B4 (en) * 2006-04-13 2018-10-11 Dspace Digital Signal Processing And Control Engineering Gmbh Method for constructing a diagnostic function
US7991583B2 (en) 2006-04-13 2011-08-02 Dspace Digital Signal Processing And Control Engineering Gmbh Diagnosis in automotive applications
EP2537723A3 (en) * 2011-06-24 2013-01-02 Kabushiki Kaisha Bridgestone Method and apparatus for determining road surface condition
DE102014011162A1 (en) 2014-07-25 2016-01-28 Audi Ag Method for operating an active chassis
DE102014011162B4 (en) * 2014-07-25 2017-12-21 Audi Ag Method for operating an active chassis
US9868333B2 (en) 2014-07-25 2018-01-16 Audi Ag Method of operating an active suspension
DE102015203026A1 (en) * 2015-02-19 2016-08-25 Bayerische Motoren Werke Aktiengesellschaft Motor vehicle with ballast detection device and method for detecting ballast
DE102018203560A1 (en) * 2018-03-08 2019-09-12 Bayerische Motoren Werke Aktiengesellschaft Method and control unit for detecting a lane boundary

Also Published As

Publication number Publication date
WO2004101300A1 (en) 2004-11-25

Similar Documents

Publication Publication Date Title
Villagra et al. A diagnosis-based approach for tire–road forces and maximum friction estimation
US5723768A (en) Process for the early recognition of hydroplaning of a vehicle tire on a wet road
EP1013509B1 (en) Procedure and device for classifying the driving manner of a vehicle driver
US20050128092A1 (en) Method and computer program for identification of inattentiveness by the driver of a vehicle
JP4583028B2 (en) Method for estimating the mass of a vehicle driven on a road with varying slope and method for estimating the slope of a road
US6725136B2 (en) Tire pressure and parameter monitoring system and method using accelerometers
Mu¨ ller et al. Estimation of the maximum tire-road friction coefficient
US20110102166A1 (en) Vehicle and method of advising a driver therein
US4651290A (en) Road condition discriminating system
EP1600757B1 (en) Rough road drive simulation and evaluation for vehicle control system
CN104044585B (en) vehicle dynamic load estimation system and method
US7263458B2 (en) Tire pressure estimation
WO2011054363A1 (en) Surface classification
US6668637B2 (en) Tire air pressure estimating apparatus
US6640623B2 (en) Road surface state estimating device
FR2683776A1 (en) System for obtaining a signal representing the surface of the pavement, used for systems for adjusting, controlling the dynamic market of a motor vehicle.
US20140207328A1 (en) Method and device for the diagnosis of defects in components of chassis systems of motor vehicles
JP2004538458A (en) How to determine tire characteristics from stress
DE10153072B4 (en) Method for determining the impending tread detachment of a pneumatic tire on a vehicle
Cabrera et al. A fuzzy logic control for antilock braking system integrated in the IMMa tire test bench
Gustafsson et al. Virtual sensors of tire pressure and road friction
Singh et al. Estimation of tire–road friction coefficient and its application in chassis control systems
JP2003182475A (en) Method for estimating road surface condition and tire traveling condition
JP3771960B2 (en) Method for determining tire pressure reduction in a running vehicle
US20040024562A1 (en) Advanced wheel slip detection using suspension system information

Legal Events

Date Code Title Description
OM8 Search report available as to paragraph 43 lit. 1 sentence 1 patent law
8181 Inventor (new situation)

Inventor name: GOLLEWSKI, THORSTEN, 85101 LENTING, DE

Inventor name: KOHN, DIETMAR, DR., 88400 BIBERACH, DE

Inventor name: SCHILLINGER, JAKOB, DR., 85080 GAIMERSHEIM, DE

8141 Disposal/no request for examination