WO2020050761A1 - Procédé de détection d'une défaillance d'un composant de véhicule ou d'un système - Google Patents

Procédé de détection d'une défaillance d'un composant de véhicule ou d'un système Download PDF

Info

Publication number
WO2020050761A1
WO2020050761A1 PCT/SE2019/050783 SE2019050783W WO2020050761A1 WO 2020050761 A1 WO2020050761 A1 WO 2020050761A1 SE 2019050783 W SE2019050783 W SE 2019050783W WO 2020050761 A1 WO2020050761 A1 WO 2020050761A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
data
failure
control unit
vehicle data
Prior art date
Application number
PCT/SE2019/050783
Other languages
English (en)
Inventor
Christoffer NORÉN
Mikael Johansson
Original Assignee
Scania Cv Ab
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 Scania Cv Ab filed Critical Scania Cv Ab
Publication of WO2020050761A1 publication Critical patent/WO2020050761A1/fr

Links

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
    • G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
    • B60K28/00—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions
    • B60K28/10—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the vehicle 
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT 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
    • B60W50/00—Details 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
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT 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
    • B60W50/00—Details 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
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0205—Diagnosing or detecting failures; Failure detection models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT 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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/007—Emergency override
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
    • B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
    • B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT 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
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/54—Audio sensitive means, e.g. ultrasound
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/45—External transmission of data to or from the vehicle

Definitions

  • the present invention relates to a method performed by a control unit adapted to be comprised in a vehicle, in particular to methods for detecting a vehicle component or system failure.
  • the invention further relates to a control unit and a vehicle comprising the control unit.
  • This may include detecting vehicle component and/or system failures.
  • the human ability to detect vehicle component and/or system failures relies on the human senses.
  • a failure is detected by listening to the sounds and/or the vibrations generated by the vehicle, e.g. noises made by the engine, noises made by the driveline, noises made by the steering actuators, noises made by tire explosions, noises made by air leakages and noises resulting from low tire pressures.
  • a failure is detected by noticing a smell or heat generated by the vehicle.
  • An objective of embodiments of the present invention is to provide a solution which mitigates or solves the drawbacks described above.
  • the objects of the invention is achieved by a method performed by a control unit adapted to be comprised in a vehicle, the method comprising obtaining vehicle data, wherein obtaining the vehicle data is at least performed by receiving sensor data, wherein the sensor data is indicative of sound data, checking for an anomaly using the vehicle data, checking for a failure using the vehicle data, determining that a vehicle operation is required using a result of the checking, and if it is determined that a vehicle operation is required, the method further comprises performing the vehicle operation.
  • At least one advantage of the first aspect of the invention is that vehicle safety is improved as by improving the ability to detect vehicle component and/or system failures.
  • the objects of the invention is achieved by a control unit performing the method according to the first aspect.
  • a vehicle comprising the control unit according to the second aspect.
  • Fig. 1 shows a vehicle according to one or more embodiments of the present disclosure.
  • Fig. 2 illustrates functional modules according to one or more embodiments of the present disclosure.
  • Fig. 3 illustrates an example of determining a vehicle operation according to one or more embodiments of the present disclosure.
  • Fig. 4 illustrates a model training system according to one or more embodiments of the present disclosure.
  • Fig. 5 shows a control unit according to one or more embodiments of the present disclosure.
  • Fig. 6 shows a flowchart of a method according to one or more embodiments of the present disclosure.
  • training of a model signifies the step of producing a model from a set of vehicle data by using machine learning.
  • this involves obtaining a training data set, having predetermined input values and/or desired output values.
  • the model may then be trained using machine learning, e.g. unsupervised or supervised learning, by repeatedly providing the input values to candidate models and registering model output values and calculating performance measure for each candidate model based on the training output values and model output values.
  • the candidate model producing the highest performance measure is then selected as the trained model.
  • the trained model may e.g. be configured to classify vehicle data.
  • a known or predetermined classification of vehicle data may be used as desired output of a training set for the model.
  • the model may in one example be trained by selecting from a number of candidate models forming a hypothesis space based on a performance measure.
  • the performance measure may indicate how well the model output corresponds to the desired output in the training set for the model.
  • the candidate model producing the highest performance measure may then be selected as the trained model. This may also be seen as tuning parameters of the model.
  • machine learning training methods are supervised classification methods such as Support Vector Machines, Naive Bayes and k-Nearest Neighbour.
  • Fig. 1 shows a vehicle 100 according to one or more embodiments of the present disclosure
  • the vehicle may comprise a communications network 130, such as a Controller Area Network ,CAN, bus.
  • the vehicle 100 may further comprise a control unit 110, such as an Electronic Control Unit, ECU, which is communicatively connected to the communications network 130.
  • the control unit may 110 may further comprise a memory (not shown in the figure).
  • the memory may contain instructions executable by the control unit 110, or processing circuitry therein, to perform the methods described herein.
  • the vehicle 100 may further comprise one or more sensors 121 -123 configured to monitor the vehicle, e.g. sounds, vibrations or smells generated by the vehicle 100.
  • the sensors 121 -123 may further be communicatively coupled to the communications network 130, e.g. configured and send one or more sensor signals comprising sensor data and/or vehicle data to the control unit 110.
  • the sensor data or vehicle data may e.g. be sent as CAN bus signals.
  • the vehicle data may then be used to check for anomalies or failures, e.g. a bad wheel bearing, a flat tire etc.
  • the vehicle 100 may further comprise one or more environment sensors (Not shown in the figure).
  • the one or more environment sensors may be configured to detect and/or register and/or capture first sensor data indicative of the environment of the vehicle.
  • the one or more environment sensors may further be configured to send the first sensor data as a signal to the control unit 110.
  • Examples of environment sensors may be any selection of radar sensor, lidar sensor, video camera, infrared camera, GPS with map, traffic information receiver or any other suitable environment sensor.
  • the environment sensors may include a radar detecting obstacles in front of the vehicle, such as pedestrians and/or vehicles.
  • the environment sensors may include a camera detecting e.g. road markings in front of the vehicle, such as white lines outlining the road surface.
  • the vehicle 100 is shown in Fig. 1 to be a bus, but may be any type of a road vehicle, such as a truck or a car. It is envisioned that the vehicle may be any type of vehicle or craft, such as an aircraft, ship or boat.
  • a single control unit 110 may be operating alone or in collaboration with one or more other control units 110.
  • Fig. 2 illustrates functional modules according to one or more embodiments of the present disclosure.
  • the control unit 110 comprises three functional modules, e.g. implemented in hardware or software.
  • the functional modules include an anomaly detector 210, a failure detector 220 and an operation determination module 230.
  • the modules are shown as three separate modules in Fig. 2, but it is understood that the functionality may be distributed over one or any suitable number of functional modules within the scope of the present disclosure.
  • the anomaly detector 210 obtains vehicle data, checks if an anomaly has occurred and outputs an anomaly detection result, using the vehicle data, to the operation determination module 230.
  • the anomaly detector 210 can detect abnormal behavior by either listening to the internal vehicle communication or by listening to one or more sensors and/or microphones installed in the vehicle.
  • the vehicle data may e.g. comprise data exchanged between ECU:s over the CAN bus or sensor data registered by the one or more sensors 121 -123.
  • a trained model comprised in the anomaly detector 210 is initially trained by processing big data sets representing normal operational conditions. When an abnormal/anomaly situation occur, the anomaly detector 210 detect that the vehicle data deviate from normal operational condition and signals that an anomaly is detected.
  • the failure detector 220 obtains the vehicle data, checks if a specific failure has occurred, and outputs a failure detection result using the vehicle data to the operation determination module 230.
  • the vehicle data may e.g. comprise data exchanged between ECU:s over the CAN bus or sensor data registered by the one or more sensors 121 -123.
  • a trained model, e.g. neural networks, comprised in the failure detector 220 is initially trained using vehicle data indicative of a specific set of failures/events Failure-i, Failure2, ... , FailureM, e.g. air leakages, noises made by the driveline, noises made by the steering actuator system and driving with flat tires.
  • the failure detector 220 detect the specific failure and signals that a failure is detected.
  • the vehicle data is typically obtained using microphones/other suitable sensors and/or by monitoring the communications network 130. The data can then be used to train models for each failure using e.g. neural networks.
  • the operation determination module 230 determines that a vehicle operation is required using a result of the checking by the anomaly detector 210 and/or as a result of the checking by the failure detector 220. In one embodiment, the operation determination module 230 further determines a confidence rating of the required vehicle operation.
  • Fig. 3 illustrates an example of determining a vehicle operation according to one or more embodiments of the present disclosure.
  • the operation determination module 230 determines that no vehicle operation is required.
  • the operation determination module 230 determines that a vehicle operation is required, where the vehicle operation is selected depending on the indicated (specific) failure, e.g. scheduling a vehicle service operation.
  • a low confidence rating of the required vehicle operation is determined, as only the results of the failure detector 220 and not the anomaly detector 210 indicates that a failure/fault has occurred.
  • the trained model of the anomaly detector 210 may have been trained to identify anomalies of normal operational conditions, e.g. when operating a tire at a normal tire pressure, and the trained model of the failure detector 220 may have been trained to identify a specific fault of low air pressure in the tire.
  • the trained model of the anomaly detector 210 may have been trained using vehicle data comprising sound data indicative of sounds generated from the tire during normal operation.
  • the trained model of the failure detector 220 may have been trained using vehicle data comprising sound data indicative of sounds generated from the tire experiencing a fault or specific fault, e.g. operating the tire under low tire pressure.
  • the operation determination module 230 determines that a vehicle operation is required, e.g. to degrade the functionality of the vehicle to a safe state.
  • a low confidence rating of the required vehicle operation is determined, as only the results of the anomaly detector 210 and not the failure detector 220 indicates that a failure/fault has occurred.
  • the trained model of the anomaly detector 210 may have been trained to identify anomalies of normal operational condition, e.g. when operating a tire at a normal tire pressure, and the trained model of the failure detector 220 may have been trained to identify a specific fault of low air pressure in the tire.
  • the trained model of the anomaly detector 210 may have been trained using vehicle data comprising sound data indicative of sounds generated from the tire during normal operation.
  • the trained model of the failure detector 220 may have been trained using vehicle data comprising sound data indicative of sounds generated from the tire experiencing a fault or specific fault, e.g. operating the tire under low tire pressure.
  • the operation determination module 230 determines that a vehicle operation is required, e.g. to bring the vehicle 100 to a stop.
  • a high confidence rating of the required vehicle operation is determined, as both the results of the anomaly detector 210 and the results of the failure detector 220 indicates that a failure/fault has occurred.
  • the trained model of the anomaly detector 210 may have been trained to identify anomalies normal operational condition, e.g. when operating a tire at a normal tire pressure, and the trained model of the failure detector 220 may have been trained to identify a specific fault of low air pressure in the tire.
  • the trained model of the anomaly detector 210 may have been trained using vehicle data, e.g. sensor data, comprising sound data indicative of sounds generated from the tire during normal operation.
  • the trained model of the failure detector 220 may have been trained using vehicle data comprising sound data indicative of sounds generated from the tire experiencing a fault or specific fault, e.g. operating the tire under low tire pressure.
  • Fig. 4 illustrates a model training system according to one or more embodiments of the present disclosure.
  • the system may comprise any combination of any of one or more vehicles 301 -303, a server 310 and a communications network 320.
  • the server 310 may comprise one or more servers, one or more virtual servers, a cloud infrastructure, cloud computing units or any other distributed computing units.
  • the one or more vehicles 301 -303 and the server 310 may communicate wirelessly directly or via the communications network 3200.
  • the wireless communications network 320 may comprise e.g. any of a Bluetooth, WiFi, GSM, UMTS, LTE or LTE advanced communications network or any other wired or wireless communication network known in the art.
  • Each of the one or more vehicles 301 -303 is equipped with sensors 121-123, internal communications networks 130 and a control units, further described in relation to Fig. 1.
  • the respective control unit in each of the one or more vehicles 301 -303 monitors it’s respective vehicle, e.g. register sounds, vibrations or smells generated by the vehicle 100, and generates vehicle data resulting from the monitoring. Monitoring of the vehicle is further described in relation to Fig. 1.
  • the generated vehicle data is then sent to the server 310, and/or optionally locally stored in the vehicle.
  • the server stores the received vehicle data from each of the one or more vehicles 301 -303.
  • the server 310 further trains the trained model of the anomaly detector 210 and the trained model of the failure detector 220 using the received vehicle data.
  • the trained model of the anomaly detector 210 may be trained to detect anomalies from normal operational condition, e.g. to classify vehicle data as “operating under normal operational condition” or to classify vehicle data as “operating under an anomaly of normal operational condition”.
  • the trained model of the failure detector 220 is trained using vehicle data associated with a determined failure/fault, e.g. any of Failure-i, Failure2, ... , FailureM.
  • the model of the failure detector 220 is trained to detect/identify a set of specific failures/faults of Failure-i, Failure2, ... , FailureM using vehicle data recorded when the failure/fault occurred.
  • the determined failure/fault is determined by a mechanic at a workshop and the determination is fed to the server 310. The server 310 may then associate received vehicle data to the determined failure/fault and train the model of the failure detector 220.
  • the trained model of the failure detector 220 may have been trained using vehicle data comprising sound data indicative of sounds generated from the tire experiencing a fault or specific fault, e.g. operating the tire under low tire pressure.
  • vehicles are equipped with microphones or other type of suitable sensors and/or a loggers connected to the internal vehicle network 130 for collecting relevant vehicle data.
  • a failure occurs and the vehicle visits a workshop, historical data, before and close to the incident, is uploaded to the server. The data is investigated to see if any significant patterns can be detected. Similar events and failures can then be grouped and used for training the model.
  • the trained model of the anomaly detector 210 and the trained model of the failure detector 220 are stored in memory 515 of the control unit 110 of the vehicle.
  • the trained model of the anomaly detector 210 and the trained model of the failure detector 220 may be stored using a wired connection from the server 310 or a service computer or stored using a wireless connection from the server via the communications network 320. E.g. by sending a message to the vehicle comprising the trained model of the anomaly detector 210 and the trained model of the failure detector 220.
  • Fig. 5 shows a control unit 110 according to an embodiment of the present disclosure.
  • the control unit 110 may be in the form of a selection of any of one or more Electronic Control Units, a server, an on-board computer, an digital information display, a stationary computing device, a laptop computer, a tablet computer, a handheld computer, a wrist-worn computer, a smart watch, a PDA, a Smartphone, a smart TV, a telephone, a media player, a game console, a vehicle mounted computer system or a navigation device.
  • the control unit 110 may comprise processing circuitry 512.
  • the control unit 110 may further comprise a communications interface 504, e.g. a wireless transceiver 504 and/or a wired/wireless communications network adapter, which is configured to send and/or receive data values or parameters as a signal to or from the processing circuitry 512 to or from other communication network nodes or units, e.g. to/from the sensors 121 -123 and/or to/from the server 310.
  • the communications interface 504 communicates directly between communication network nodes or via the communications network.
  • the communications interface 504, such as a transceiver may be configured for wired and/or wireless communication.
  • the communications interface 504 communicates using wired and/or wireless communication techniques.
  • the wired or wireless communication techniques may comprise any of a CAN bus, Bluetooth, WiFi, GSM, UMTS, LTE or LTE advanced communications network or any other wired or wireless communication network known in the art.
  • the communications interface 504 may further comprise at least one optional antenna (not shown in figure).
  • the antenna may be coupled to the communications interface 504 and is configured to transmit and/or emit and/or receive a wireless signals in a wireless communication system, e.g. send/receive control signals to/from the one or more sensors or any other control unit or sensor.
  • the processing circuitry 512 may be any of a selection of processor and/or a central processing unit and/or processor modules and/or multiple processors configured to cooperate with each-other.
  • the control unit 110 may further comprise a memory 515.
  • the one or more memory 515 may comprise a selection of a hard RAM, disk drive, a floppy disk drive, a magnetic tape drive, an optical disk drive, a CD or DVD drive (R or RW), or other removable or fixed media drive.
  • the memory 515 may contain instructions executable by the processing circuitry to perform any of the methods and/or method steps described herein.
  • control unit 110 may further comprise an input device 517, configured to receive input or indications from a user and send a user- input signal indicative of the user input or indications to the processing circuitry 512.
  • control unit 110 may further comprise a display 518 configured to receive a display signal indicative of rendered objects, such as text or graphical user input objects, from the processing circuitry 512 and to display the received signal as objects, such as text or graphical user input objects.
  • a display signal indicative of rendered objects such as text or graphical user input objects
  • the display 518 is integrated with the user input device 517 and is configured to receive a display signal indicative of rendered objects, such as text or graphical user input objects, from the processing circuitry 512 and to display the received signal as objects, such as text or graphical user input objects, and/or configured to receive input or indications from a user and send a user-input signal indicative of the user input or indications to the processing circuitry 512.
  • the processing circuitry 512 is communicatively coupled to the memory 515 and/or the communications interface 504 and/or the input device 517 and/or the display 518 and/or one or more sensors 121 -123.
  • the control unit 110 may be configured to receive the sensor data directly from a sensor or via the wired and/or wireless communications network.
  • control unit 110 may further comprise and/or be coupled to one or more additional sensors (not shown) configured to receive and/or obtain and/or measure physical properties pertaining to the vehicle 100 and send one or more sensor signals indicative of the physical properties to the processing circuitry 512, e.g. sensor data indicative sounds generated by the vehicle.
  • Fig. 6 shows a flowchart of a method 600 performed by a control unit 110 adapted to be comprised in a vehicle 100.
  • the method comprises:
  • Step 610 obtaining vehicle data, wherein obtaining the vehicle data is at least performed by receiving sensor data.
  • the vehicle data is typically received from sensors 121 -123 monitoring the vehicle 100 and is received directly or via a communications network 130 comprised in the vehicle, as further described in relation to fig.1. I.e. the vehicle data comprises sensor data.
  • the sensor data is indicative of sound data.
  • the sensors 121- 123 are typically configured to register sound or vibrations of the vehicle 100 and send sensor signals indicative of the monitoring directly to the control unit 110 or via the communications network 130. Examples of such sensors are microphones, piezo electric vibration sensors and accelerometers.
  • obtaining the vehicle data is alternatively or additionally performed by monitoring a communications network 130 of the vehicle, such as the CAN bus, e.g. by monitoring data exchanged between ECU:s over the CAN bus.
  • the vehicle data is obtained by monitoring values and/or messages sent over the CAN bus, such as various temperatures, which may be indicative of a fire, air pressures, engine operation values, compressor operation values. An anomaly or failure may then be detected based on the monitored vehicle data.
  • the vehicle data is obtained by monitoring values and/or messages sent over the CAN bus originating from environmental sensors, such as lidar, radar etc.
  • An anomaly or failure may then be detected based on the monitored vehicle data, e.g. by detecting invalid detections or false positives. This could be one sensor detecting objects/detections surrounding the vehicle and other similar sensors detecting“free line of sight”, which could be an indication of smoke generated by the vehicle.
  • Step 620 checking for an anomaly using the vehicle data.
  • checking for the anomaly is performed by providing the obtained vehicle data to a trained model of the anomaly detector 210 and receiving a result at the operation determination module 230.
  • an anomaly is detected if the vehicle data comprises sound data deviating from sound data collected during normal operation.
  • the vehicle data comprises sound data deviating from sound data collected during normal operation.
  • a microphone detecting that a normally relatively quiet wheel bearing is generating a loud noise.
  • checking for an anomaly comprises detecting an anomaly using the vehicle data and a first trained model.
  • the first trained model is initially trained using unsupervised machine learning and historical vehicle data.
  • the trained model of the anomaly detector 210 may be trained to detect anomalies from normal operational condition, e.g. to classify vehicle data as “operating under normal operational condition” or to classify vehicle data as “operating under an anomaly of normal operational condition”. In one further example, the trained model of the anomaly detector 210 may be trained to detect anomalies from normal operational condition, e.g. to classify vehicle data as “anomaly detected” or to classify vehicle data as“anomaly not detected”.
  • Step 630 checking for a failure using the vehicle data.
  • checking for the anomaly is performed by providing the obtained vehicle data to a trained model of the failure detector 220 and receiving a result at the operation determination module 230.
  • the failure is typically identified from and checked against a limited or specific set of failures Failure-i, Failure2, ... , FailureM which the trained model of the failure detector 220 can detect.
  • checking for a failure comprises detecting a failure using the vehicle data and a second trained model.
  • the second trained model is trained to detect one or more failures selected from of a set of specific failures range No failure, Failure-i, Failure2, ... , FailureM using supervised machine learning and historical vehicle data where one or more of the set of specific failures have occurred.
  • the trained model of the failure detector 220 may be trained to detect one or more failures from a limited or specific set of failures Failure-i, Failure2, ... , Failureivi, e.g. to classify vehicle data as any one of the value range [No failure, Failure-i, Failure2, Failureivi].
  • an failure is detected if the vehicle data comprises sound data detected to correspond to a bad wheel bearing, typically the wheel bearing is generating a loud noise.
  • Step 640 determining that a vehicle operation is required using a result of the checking in steps 620 and 630. Determining that a vehicle operation is required is further described in relation to Fig. 2 and Fig. 3.
  • the method further comprises: Optional step 650: performing (550) the vehicle operation.
  • performing the vehicle operation comprises bringing the vehicle 100 to a stop or scheduling a vehicle service operation.
  • the operation determination module 230 may then determine that a proper action can be to stop at nearest safe place (parking, etc) and carry out a leakage test to examine how big the leakage is. If the leakage is big the vehicle needs to be repaired at the current location or be towed to a workshop. If the leakage is small or in a circuit that isn’t related to the brake circuit, a workshop time can be booked. The reason to why an emergency stop isn’t triggered in this example is that there may be explicit sensors on-board detecting when the air pressure level is below a critical threshold.
  • a control unit 110 is provided and adapted to be comprised in a vehicle 100, the control unit 110 being configured to perform any of the method steps disclosed herein.
  • a vehicle 100 comprising the control unit 110 is provided.
  • a computer program comprising computer- executable instructions for causing the control unit 110 when the computer- executable instructions are executed on processing circuitry comprised in the control unit 110, to perform any of the methods described herein.
  • a computer program product is provided comprising a computer- readable storage medium, the computer-readable storage medium having the computer program above embodied therein.
  • a carrier containing the computer program above wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.
  • the communications network 130,320 communicate using wired or wireless communication techniques that may include at least one of a Controller Area Network ,CAN, bus network, a Local Area Network (LAN), Metropolitan Area Network (MAN), Global System for Mobile Network (GSM), Enhanced Data GSM Environment (EDGE), Universal Mobile Telecommunications System, Long term evolution, High Speed Downlink Packet Access (HSDPA), Wideband Code Division Multiple Access (W-CDMA), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth®, Zigbee®, Wi-Fi, Voice over Internet Protocol (VoIP), LTE Advanced, IEEE802.16m, WirelessMAN-Advanced, Evolved High-Speed Packet Access (HSPA+), 3GPP Long Term Evolution (LTE), Mobile WiMAX (IEEE 802.16e), Ultra Mobile Broadband (UMB) (formerly Evolution-Data Optimized (EV-DO) Rev.
  • LAN Local Area Network
  • MAN Metropolitan Area Network
  • GSM Global System for Mobile Network
  • EDGE Enhanced Data GSM Environment
  • Flash-OFDM Flash-OFDM
  • High Capacity Spatial Division Multiple Access iBurst®
  • Mobile Broadband Wireless Access IEEE 802.20
  • HIPERMAN High Performance Radio Metropolitan Area Network
  • BDMA Beam-Division Multiple Access
  • Wi-MAX World Interoperability for Microwave Access
  • ultrasonic communication etc., but is not limited thereto.
  • control unit 110 may comprise the necessary communication capabilities in the form of e.g., functions, means, units, elements, etc., for performing the present solution.
  • means, units, elements and functions are: processors, memory, buffers, control logic, encoders, decoders, rate matchers, de-rate matchers, mapping units, multipliers, decision units, selecting units, switches, interleavers, de-interleavers, modulators, demodulators, inputs, outputs, antennas, amplifiers, receiver units, transmitter units, DSPs, MSDs, encoder, decoder, power supply units, power feeders, communication interfaces, communication protocols, etc. which are suitably arranged together for performing the present solution.
  • the processing circuitry of the present disclosure may comprise one or more instances of processor and/or processing means, processor modules and multiple processors configured to cooperate with each-other, Central Processing Unit (CPU), a processing unit, a processing circuit, a processor, an Application Specific Integrated Circuit (ASIC), a microprocessor, a Field-Programmable Gate Array (FPGA) or other processing logic that may interpret and execute instructions.
  • CPU Central Processing Unit
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • the expression “processing circuitry” may thus represent a processing circuitry comprising a plurality of processing circuits, such as, e.g., any, some or all of the ones mentioned above.
  • the processing means may further perform data processing functions for inputting, outputting, and processing of data comprising data buffering and device control functions, such as call processing control, user interface control, or the like.

Abstract

L'invention concerne un procédé (500) exécuté par une unité de commande (110) configurée pour être comprise dans un véhicule (100), le procédé consistant à obtenir (510) des données du véhicule, l'obtention des données du véhicule étant au moins effectuée par la réception de données de capteur, les données de capteur étant révélatrices de données de son, à vérifier (520) une anomalie à l'aide des données du véhicule, à vérifier (530) une défaillance à l'aide des données du véhicule, à déterminer (540) qu'un fonctionnement du véhicule est requis à l'aide d'un résultat de la vérification (520, 530), et s'il est déterminé qu'un fonctionnement du véhicule est requis, le procédé consiste en outre à exécuter (550) le fonctionnement du véhicule.
PCT/SE2019/050783 2018-09-03 2019-08-27 Procédé de détection d'une défaillance d'un composant de véhicule ou d'un système WO2020050761A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
SE1851040-4 2018-09-03
SE1851040 2018-09-03

Publications (1)

Publication Number Publication Date
WO2020050761A1 true WO2020050761A1 (fr) 2020-03-12

Family

ID=69722708

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/SE2019/050783 WO2020050761A1 (fr) 2018-09-03 2019-08-27 Procédé de détection d'une défaillance d'un composant de véhicule ou d'un système

Country Status (1)

Country Link
WO (1) WO2020050761A1 (fr)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210174616A1 (en) * 2019-12-04 2021-06-10 Hyundai Motor Company Apparatus and Method for Determining Error of Vehicle
CN113428165A (zh) * 2021-06-28 2021-09-24 安徽海博智能科技有限责任公司 一种基于mdc300的矿车自动驾驶安全系统及方法
FR3125908A1 (fr) * 2021-08-02 2023-02-03 Psa Automobiles Sa Procédé, dispositif et système de détermination d’une défaillance d’un composant d’un véhicule
CN116226212A (zh) * 2023-02-02 2023-06-06 上海信宝博通电子商务有限公司 用于车辆检测的数据处理方法和装置
CN116701846A (zh) * 2023-08-04 2023-09-05 长江水利委员会长江科学院 一种基于无监督学习的水电站调度运行数据清洗方法

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070005202A1 (en) * 1995-06-07 2007-01-04 Automotive Technologies International, Inc. Remote Vehicle Diagnostic Management
US20070255471A1 (en) * 2006-04-28 2007-11-01 Caterpillar Inc. Torque estimator for a machine
US20120277949A1 (en) * 2011-04-29 2012-11-01 Toyota Motor Engin. & Manufact. N.A.(TEMA) Collaborative multi-agent vehicle fault diagnostic system & associated methodology
US20140052499A1 (en) * 2009-02-23 2014-02-20 Ronald E. Wagner Telenostics performance logic
KR20150021609A (ko) * 2013-08-20 2015-03-03 한양대학교 산학협력단 차량에 구비된 마이크를 이용한 차량 상태 모니터링 장치 및 방법
US20170057521A1 (en) * 2015-09-01 2017-03-02 Ford Global Technologies, Llc Aberrant Driver Classification and Reporting
CN107458383A (zh) * 2016-06-03 2017-12-12 法拉第未来公司 使用音频信号的车辆故障自动检测
US20180052463A1 (en) * 2016-08-17 2018-02-22 Omnitracs, Llc Emergency stopping for autonomous commercial vehicles
US20180247467A1 (en) * 2015-08-18 2018-08-30 Carfit Corp. Automotive activity monitor

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070005202A1 (en) * 1995-06-07 2007-01-04 Automotive Technologies International, Inc. Remote Vehicle Diagnostic Management
US20070255471A1 (en) * 2006-04-28 2007-11-01 Caterpillar Inc. Torque estimator for a machine
US20140052499A1 (en) * 2009-02-23 2014-02-20 Ronald E. Wagner Telenostics performance logic
US20120277949A1 (en) * 2011-04-29 2012-11-01 Toyota Motor Engin. & Manufact. N.A.(TEMA) Collaborative multi-agent vehicle fault diagnostic system & associated methodology
KR20150021609A (ko) * 2013-08-20 2015-03-03 한양대학교 산학협력단 차량에 구비된 마이크를 이용한 차량 상태 모니터링 장치 및 방법
US20180247467A1 (en) * 2015-08-18 2018-08-30 Carfit Corp. Automotive activity monitor
US20170057521A1 (en) * 2015-09-01 2017-03-02 Ford Global Technologies, Llc Aberrant Driver Classification and Reporting
CN107458383A (zh) * 2016-06-03 2017-12-12 法拉第未来公司 使用音频信号的车辆故障自动检测
US20180052463A1 (en) * 2016-08-17 2018-02-22 Omnitracs, Llc Emergency stopping for autonomous commercial vehicles

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LI, ZIYE ET AL.: "Engine Failure Diagnosis with Sound Signal Using Wavelet Transform", SAE PAPER 970034 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210174616A1 (en) * 2019-12-04 2021-06-10 Hyundai Motor Company Apparatus and Method for Determining Error of Vehicle
US11908252B2 (en) * 2019-12-04 2024-02-20 Hyundai Motor Company Apparatus and method for determining error of vehicle
CN113428165A (zh) * 2021-06-28 2021-09-24 安徽海博智能科技有限责任公司 一种基于mdc300的矿车自动驾驶安全系统及方法
FR3125908A1 (fr) * 2021-08-02 2023-02-03 Psa Automobiles Sa Procédé, dispositif et système de détermination d’une défaillance d’un composant d’un véhicule
CN116226212A (zh) * 2023-02-02 2023-06-06 上海信宝博通电子商务有限公司 用于车辆检测的数据处理方法和装置
CN116701846A (zh) * 2023-08-04 2023-09-05 长江水利委员会长江科学院 一种基于无监督学习的水电站调度运行数据清洗方法

Similar Documents

Publication Publication Date Title
WO2020050761A1 (fr) Procédé de détection d'une défaillance d'un composant de véhicule ou d'un système
KR102495816B1 (ko) 상황 기반 비정상 모니터링을 위한 방법들 및 시스템들
TWI808937B (zh) 用於使用從多個感測器收集之資訊來保護車輛免受惡意軟體及攻擊之方法及系統
CN110806739B (zh) 诊断车辆健康状况的设备和方法
US8952800B2 (en) Prevention of texting while operating a motor vehicle
US9852553B2 (en) Apparatus and method of requesting emergency call for vehicle accident by using travelling information about vehicle
US9764689B2 (en) System and method for monitoring driving behavior
US20150210258A1 (en) Method for carrying out a safety function of a vehicle and system for carrying out the method
US10489994B2 (en) Vehicle sound activation
CN110189735B (zh) 使用前馈信息消除部件噪声的方法和设备
JP2017521792A (ja) 運転行為ガイダンス情報の生成方法、装置及びシステム
KR101275287B1 (ko) 원격 차량 감시 시스템
CN108140294A (zh) 车辆内部触觉输出
EP3886090B1 (fr) Évaluation de l'état de situation et d'occupation des passagers en cabine sur la base de l'acoustique
US20200053537A1 (en) Method and device for generating an emergency call for a vehicle
GB2533108A (en) Contactless key localisation
JP2005202762A (ja) 車両用通信システム
US11577679B2 (en) Detection of an impact event
CN103754174A (zh) 一种车用信息处理装置及系统
KR101497574B1 (ko) 이동수단의 충격 및 소리 감응형 시스템 및 방법
US10013964B1 (en) Method and system for controlling noise originating from a source external to a vehicle
US20160118037A1 (en) Apparatus for outputting protecting sound in quieting vehicle
US20230113560A1 (en) Methods and Systems for Determining Diagnostic Coverage of Sensors to Prevent Goal Violations of Autonomous Vehicles
JP2019214249A (ja) 検知装置、コンピュータプログラム、検知方法及び学習モデル
CN203739797U (zh) 一种车用信息处理装置及系统

Legal Events

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

Ref document number: 19857850

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19857850

Country of ref document: EP

Kind code of ref document: A1