Prediction and identification of potential bearing anomalies within electric motor of electric vehicle

Abstract

Systems and methods for predicting anomalies within an electric motor of an electric vehicle. A method includes: receiving sensor information from a knock sensor, wherein the sensor information represents a detected vibration of an electric motor; deriving a signal characteristic from the sensor information; determining potential anomalies within the electric motor based on the signal characteristics; and generating an alert to the user based on the potential anomaly.

Description

Background Art

[0001] Engine knock occurs when the fuel in the engine's combustion chamber ignites incompletely or unevenly. The engine may be included in a passenger car, for example. When engine knock occurs, it may cause damage to the engine. Sensors are traditionally used to detect engine knock in internal combustion engines. Summary of the invention

[0002] In an electric vehicle, bearing degradation in an electric motor (e.g., a main motor that provides power to drive the vehicle) may result in increased friction levels within the motor. This may result in degraded vehicle performance. For example, bearing degradation may cause an increase in motor power consumption, which may reduce the vehicle's mileage, and generate noise and vibration within the vehicle, increase heat within the vehicle, and cause damage to one or more components of the electric motor.

[0003] As mentioned above, knock sensors are traditionally used to detect irregular ignition of fuel in the engine combustion chamber. In the case of electric vehicles, it has been found that knock sensors (which may be less expensive than other types of vibration sensors) can be used to detect anomalies within the electric motor (e.g., bearings), which may potentially cause anomalies within the electric motor.

[0004] It would be beneficial if anomalies within an electric motor bearing (or other component of an electric motor) could be detected early to help avoid damage to the system. Embodiments and aspects described herein provide, among other things, a system and method for predicting anomalies within an electric motor of an electric vehicle via a knock sensor using a deep learning system, and in some cases, using data collected from an electric vehicle network.

[0005] One example provides a system for predicting anomalies in an electric vehicle. The system includes an electric motor, a knock sensor, and an electronic processor. The electronic processor is configured to receive sensor information from the knock sensor, wherein the sensor information represents a vibration detected at a bearing of the electric motor, derive a signal characteristic from the sensor information, determine a potential anomaly within the electric motor based on the signal characteristic, and generate an alert to a user based on the potential anomaly.

[0006] Another example provides a method for predicting an anomaly in an electric motor of an electric vehicle. The method includes receiving sensor information from a knock sensor, wherein the sensor information represents a detected vibration of the electric motor, deriving a signal characteristic from the sensor information, determining a potential anomaly in the electric motor based on the signal characteristic, and generating an alert to a user based on the potential anomaly.

[0007] Other aspects, features, and embodiments will become apparent by consideration of the detailed description and accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The accompanying drawings, together with the following detailed description, are incorporated into and form a part of the specification and are used to further illustrate embodiments and aspects of the concepts including the claimed subject matter and to explain various principles and advantages of the various aspects and embodiments. In the drawings, like reference numerals refer to the same or functionally similar elements throughout the separate views.

[0009] Figure 1 is a block diagram of a vehicle system according to some aspects.

[0010] Figure 2 Schematically illustrates the Figure 1 The electronic controller of the system.

[0011] Figure 3 It is used to predict based on some aspects Figure 1 A flow chart of an example method for detecting an anomaly within an electric motor of a vehicle.

[0012] Figure 4A It is a diagram based on some aspects Figure 1 A schematic block diagram of an electric motor of a vehicle.

[0013] Figure 4B It is a diagram based on some aspects Figure 1 A schematic block diagram of an electric motor of a vehicle.

[0014] Figure 4C It is a diagram based on some aspects Figure 1 A schematic block diagram of an electric motor of a vehicle.

[0015] Figure 5 is a schematic block diagram illustrating another vehicle system according to some aspects.

[0016] Those skilled in the art will appreciate that the elements in the figures are illustrated for simplicity and clarity and are not necessarily drawn to scale. For example, the size of some elements in the figures may be exaggerated relative to other elements to help improve understanding of the embodiments and aspects.

[0017] In the drawings, apparatus and method components have been represented by conventional symbols where appropriate, and only those specific details relevant to an understanding of the embodiments of the invention are shown so as not to obscure the disclosure with details that would be readily apparent to one of ordinary skill in the art having the benefit of the description herein. DETAILED DESCRIPTION

[0018] Before any embodiments, aspects, examples, and features are explained in detail, it is to be understood that the embodiments, aspects, examples, and features are not limited in their application to the details of construction and arrangement of components set forth in the following description or illustrated in the following drawings. Other embodiments, aspects, examples, and features are possible and may be practiced or implemented in various ways.

[0019] It should also be noted that multiple hardware- and software-based devices and multiple different structural components can be used to implement embodiments, aspects, examples, and features. In addition, it should be understood that embodiments, aspects, examples, and features may include hardware, software, and electronic components or modules, which, for the purpose of discussion, may be illustrated and described as if most of the components are implemented only in hardware. However, those of ordinary skill in the art, and based on reading this detailed description, will recognize that, in at least one example, the electronic-based aspects of the present invention may be implemented in software (e.g., stored on a non-transitory computer-readable medium) that can be executed by one or more processors. Therefore, it should be noted that in various cases, multiple hardware- and software-based devices, as well as multiple different structural components, may be utilized. For example, the "control unit" and "controller" described in the specification may include one or more electronic processors, one or more physical memory modules including a non-transitory computer-readable medium, one or more input / output interfaces, and various connections (e.g., a system bus) connecting components.

[0020] For ease of description, some or all of the example systems given herein are illustrated with a single sample of each of their components. Some examples may not describe or illustrate all of the components of the system. Other examples may include more or less of each of the illustrated components, may combine some components, or may include additional or alternative components.

[0021] The systems and methods described herein can be used in any electric vehicle capable of partially or fully autonomous operation, manual control by a driver, or a combination of both. As used herein, the term "driver" generally refers to an occupant of an electric vehicle who sits in the driver's seat, operates the controls of the vehicle in manual mode, or provides control inputs to the vehicle to affect the operation of the vehicle.

[0022] It should be understood that while the examples discussed herein are about using a knock sensor to detect / predict potential anomalies within an electric motor of an electric vehicle, the systems and methods described herein may also be applied to other components of an electric vehicle. Such components may be, for example, inverters, stator windings, permanent magnets, etc. In addition, while the examples explained herein are about electric vehicles, it should be understood that the systems and methods described herein may be applied to other electric or non-electric automotive and non-automotive motor systems (e.g., fan motor systems such as heating and air conditioning systems). Other example systems include axle and brake systems, such as axle and brake systems of mining and construction equipment.

[0023] Figure 1 A system 100 for detecting / predicting anomalies in an electric motor 110 of an electric vehicle 102 is illustrated in accordance with some embodiments. The electric vehicle 102 may be any type of electrically driven motor vehicle, including a hybrid vehicle and a fuel cell electric vehicle. In the example shown, the system 100 includes an electronic controller 104, a vehicle system 106, a battery 108, an electric motor 110, a knock (vibration) sensor 115, and other sensors 120. In some cases, the system 100 also includes a communication network 120 and other electric vehicles 125. Other vehicles 125 include one or more electric vehicles configured similarly to the vehicle 102. The components of the system 100, along with various other modules and components, are electrically coupled to each other by or through one or more control or data buses (e.g., bus 118), which enables communication between them.

[0024] In view of the invention described herein, the use of control and data buses to interconnect and communicate between various modules and components is well known to those skilled in the art. In some cases, bus 118 is a controller area network (CAN TM ) bus. In some cases, bus 118 is an automotive Ethernet TM 、FlexRay TM communication bus or another suitable wired bus. In the alternative, some or all components of system 100 may use a suitable wireless modality (e.g., Bluetooth TM or near field communication) communicatively coupled. For ease of description, Figure 1 The illustrated system 100 includes one of each of the aforementioned components. Alternatives may include one or more of each component, or may exclude or combine some components.

[0025] Electronic controller 104 (see below) Figure 2The electronic controller 104 may be used to control, maintain and / or drive the vehicle 102 (described in more detail in the accompanying drawings). For example, the electronic controller 104 receives sensor telemetry data from the sensor 120 and determines control / maintenance data and commands for the vehicle. The electronic controller 104 may, among other things, transmit vehicle control data to the vehicle system 106 to drive the vehicle (e.g., by generating a braking signal, an acceleration signal, a steering signal).

[0026] The vehicle system 106 includes a controller (e.g., controller 104), a motor (e.g., electric motor 110), a battery (e.g., battery 108), sensors (e.g., sensors 115 and 120), actuators, etc., for autonomously controlling operational aspects of the vehicle 102 (e.g., steering, acceleration, braking, gear shifting, fluid coolant system, etc.) based on user input or, in some cases, sensor telemetry. The vehicle system 106 is configured to send and receive data related to the operation and maintenance of the vehicle 102 to and from the electronic controller 104.

[0027] The battery 108 may be part of a high-voltage or low-voltage system (neither of which is shown) of the vehicle 102. The high-voltage system is the primary power system that provides power to drive the vehicle 102 (e.g., to the motor 110). The low-voltage system is the accessory power system that receives and converts power from the high-voltage system, which provides power to accessories of the vehicle 102 (e.g., headlights, windshield wipers, taillights, etc.).

[0028] The electric motor 110 may be part of a drive system (part of the vehicle system 106) of the vehicle 102 and is configured to provide motive force to move the vehicle 102. The motor 110 is configured to receive power from the battery 108. In some cases, the electric motor 110 may be part of another system 106 of the vehicle 102. For example, the motor 110 may be part of an air conditioning system of the vehicle 102. In some cases, the battery 108 and / or the motor 110 are integrated into an electric axle of the vehicle 102 (e.g., a front or rear tire axle of the vehicle 102, not shown).

[0029] The knock sensor 115 (and, in some cases, other sensors 120) determine one or more properties of the vehicle 102 and communicate information about these properties to other components of the system 100 using, for example, electrical signals. In particular, the knock sensor 115 is a vibration sensor that is conventionally used to detect engine knock in an internal combustion engine. In the illustrated example, the knock sensor is a transducer capable of sensing vibrations in a vehicle component, converting the vibrations into an electrical signal, and transmitting the electrical signal as sensor information to the electronic controller 104. The sensor 115 is positioned so that it detects vibrations of the electric motor 110 (e.g., in a horizontal direction perpendicular to the bearing / shaft direction). In some cases, the knock sensor 115 can be integrated into the electric motor 110. More than one knock sensor 115 can be utilized in the systems and methods described herein.

[0030] In some cases, sensor 115 is integrated into another vehicle sensor (e.g., one or more other sensors 120). For example, sensor 115 can be integrated into an accelerometer. In some cases, sensor 115 is part of a strain gauge, eddy current sensor, gyroscope, microphone, or other suitable vibration sensor. In some cases, multiple sensors are used, for example, mounted at different points on vehicle 102 near motor 110.

[0031] As described herein, the electronic controller 104 processes the electrical signals received from the sensor 115 to generate vibration signal information associated with the electric motor 110, which can be analyzed to determine / identify potential anomalies (e.g., bearing failure) causing the vibrations. In some cases, the sensor 115 includes onboard signal processing circuitry that generates and transmits sensor information, including vibration patterns, to the electronic controller 104 for processing. The electronic controller 104 receives and interprets signals received from the knock sensor 115 (and, in some cases, one or more other sensors 120) to automatically detect / predict wear and failure of the electric motor 110 of the vehicle 102 (e.g., in the bearings 130 of the electric motor 110).

[0032] In addition to the knock sensor 115, the system 100 includes one or more other sensors 120. The sensors 120 determine one or more properties of the vehicle 102 and its surroundings and communicate information about these properties to other components of the system 100 using, for example, electrical signals. Vehicle properties include, for example, the position of the vehicle or a portion or component of the vehicle 102, the motion of the vehicle 102 or a portion or component of the vehicle 102, forces acting on the vehicle 102 or a portion or component of the vehicle 102, the proximity of the vehicle 102 to other vehicles (e.g., other vehicles 125) or objects (stationary or moving), coolant inlet / outlet temperature (e.g., coolant to reduce one or more electrical components of the vehicle 102, such as the electric motor 110 and / or the battery 108), temperature of one or more components, motor current draw, yaw rate, sideslip angle, steering wheel angle, overlay angle, vehicle speed, longitudinal acceleration, and lateral acceleration, etc. Sensors 120 may include, for example, vehicle control sensors (e.g., sensors that detect accelerator pedal position, brake pedal position, and steering wheel position / angle), wheel speed sensors, vehicle speed sensors, yaw sensors, force sensors, odometer sensors, and vehicle proximity sensors (e.g., cameras, radar, LIDAR, and ultrasonic).

[0033] The communication network 120 is a communication network including wireless connections, wired connections, or a combination of both. The communication network 120 may be implemented using a wide area network, such as the Internet (including public and private IP networks), a long-term evolution (LTE) network, a 4G network, a 5G network, and one or more local area networks, such as Bluetooth. TM network or Wi-Fi network, and combinations or derivatives thereof.

[0034] Figure 1 The example shown provides only one example of the components and connections of the system 100. However, these components and connections may be configured in other ways than those shown and described herein. It should be noted that although the system 100 is shown as being included in a four-wheeled vehicle 102, the system 100 may be included in electric vehicles of various types and designs. For example, the system 100 may be included in an automobile, a motorcycle, a truck, a bus, a semi-trailer, an aviation system, an unmanned aircraft, etc.

[0035] Figure 21 is a block diagram of an electronic controller 104 of the system 100. The electronic controller 104 includes a plurality of electrical and electronic components that provide power, operational control, and protection for components and modules within the electronic controller 104. The electronic controller 104 includes, among other things, an electronic processor 205 (such as a programmable electronic microprocessor, microcontroller, or similar device), a memory 210 (e.g., a non-transitory computer-readable memory), and an input / output interface 215. The electronic processor 205 is communicatively connected to the memory 205 and the input / output interface 210. The electronic processor 205 cooperates with the memory 205 and the input / output interface 210 and is configured to, among other things, implement the methods described herein. It should be understood that some or all of the components of the controller 104 (including additional components) may be remote / dispersed from each other within the vehicle 102 and / or remote from the vehicle 102 (e.g., a portion of the knock sensor 115, the communication network 120, and / or other vehicles 125).

[0036] The memory 210 may be composed of one or more non-transitory computer-readable media and include at least a program storage area and a data storage area. The program storage area and the data storage area may include a combination of different types of memory, such as read-only memory ("ROM"), random access memory ("RAM"), flash memory, or other suitable memory devices. The electronic processor 205 is coupled to the memory 210 and the input / output interface 215.

[0037] The electronic processor 205 sends and receives information (e.g., from the memory 210 and / or the input / output interface 215) and processes the information by executing one or more software instructions or modules that can be stored in the memory 210 or another non-transitory computer-readable medium. The software may include firmware, one or more applications, program data, filters, rules, one or more program modules, and other executable instructions. The electronic processor 205 is configured to retrieve from the memory 210 and execute, among other things, software for automatically detecting / predicting anomalies within the electric motor 110 and for running the methods described herein. In the example shown, the memory 210 stores, among other things, a vibration detection algorithm 220, which operates as described herein (e.g., below with respect to Figure 3 The method 300 described herein is used to detect and classify vibration patterns to identify and / or predict anomalies within the electric motor 110 (eg, with respect to the bearings 120 and / or raceways thereof of the electric motor 110 ).

[0038] In some cases, the electronic controller 205 can be implemented in several independent controllers (e.g., programmable electronic controllers), each of which is configured to run a specific function or sub-function. For example, one or more components of the controller 205 can be remote from the vehicle 105 (e.g., part of a remote server not shown of the communication network 120). In addition, the electronic controller 205 can include submodules that include additional electronic processors, memories, or circuits for handling input / output functions, signal processing, and application of the methods listed below. In other cases, the electronic controller 205 includes additional, fewer, or different components. Therefore, the program can also be distributed among one or more processors.

[0039] The input / output interface 215 transmits and receives information from devices external to the electronic controller 104 (e.g., through one or more wired and / or wireless connections), such as components of the system 100, via the bus 118. The input / output interface 215 receives input (e.g., from the knock sensor 115 and the sensor 120, etc.), provides system output (e.g., to the transceiver 225 and / or the HMI 230, etc.), or a combination of both. The input / output interface 215 may also include other input and output mechanisms, which are not described herein for the sake of brevity, and which may be implemented in hardware, software, or a combination of both.

[0040] In some cases, controller 104 also includes a transceiver 225 and a human machine interface (HMI) 230. Transceiver 225 includes a radio transceiver that transmits data over one or more wireless communication networks (e.g., cellular networks, satellite networks, land mobile radio networks, etc.), including communication network 120. Transceiver 225 also uses a suitable network modality (e.g., Bluetooth TM , Near Field Communication (NFC), Wi-Fi TM The transceiver 225 provides wireless communication within the vehicle (e.g., such as the vehicle 102). Thus, the transceiver 225 communicatively couples the electronic controller 104 and other components of the system 100 to networks or electronic devices both inside and outside the vehicle 102. For example, using the transceiver 225, the electronic controller 104 can communicate with one or more devices (e.g., other vehicles 125) via the communication system 120 to send and receive data, commands, and other information (e.g., component abnormality notifications). The transceiver 225 includes other components that enable wireless communication (e.g., amplifiers, antennas, baseband processors, etc.), which are not described herein for the sake of brevity and may be implemented in hardware, software, or a combination of both. Some situations include multiple transceivers or separate transmitting and receiving components (e.g., a transmitter and a receiver) rather than a combined transceiver.

[0041] HMI 230 provides visual output, such as, for example, a graphic indicator (i.e., a fixed or animated icon), light, color, text, image, a combination of the foregoing, etc. HMI 230 includes a suitable display mechanism for displaying visual output, such as, for example, an instrument cluster, a head-up display, a center console display screen (e.g., a touch screen or other suitable mechanism). In some cases, HMI 230 displays a graphical user interface (GUI) (e.g., generated by an electronic controller and presented on a display screen), which enables a driver or passenger to interact with vehicle 102. HMI 230 can also provide audio output, such as a chime, a buzzer, a voice output, or other suitable sounds to the driver by a speaker included in HMI 230 or separated from HMI 230. In some cases, HMI 230 provides tactile output to the driver by, for example, using a vibration motor to vibrate one or more vehicle components (e.g., the steering wheel and seat of the vehicle). In some cases, HMI 230 provides a combination of visual, auditory, and tactile outputs.

[0042] As will be described in further detail below, in some cases, memory 205 includes, among other things, computer executable instructions for detecting, predicting, and / or identifying one or more anomalies within motor 110. In some cases, the computer executable instructions include instructions for training a deep learning system to detect / predict one or more anomalies associated with bearings 130 within electric motor 110 of vehicle 102.

[0043] In some cases, the electronic controller 104 uses one or more machine learning methods (e.g., artificial intelligence algorithms) to analyze sensor information from the knock sensor 115 to identify / predict anomalies within the electric motor 110 (as described herein). Machine learning generally refers to the ability of a computer program to learn without being explicitly programmed. In some cases, a computer program (e.g., a learning engine) is configured to build an algorithm based on input. Supervised learning includes presenting a computer program with example inputs and expected outputs. The computer program is configured to learn general rules for mapping inputs to outputs from the training data it receives. Example machine learning engines include decision tree learning, association rule learning, artificial neural networks, classifiers, edge computing, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity and metric learning, sparse dictionary learning, and genetic algorithms. Using these methods, a computer program can ingest, parse, and understand data, and gradually improve data analysis algorithms.

[0044] As mentioned above, in some cases, one or more components of the electronic controller 104, including additional components (e.g., similar to those described above with respect to Figure 2The knock sensor 115 may be located or distributed throughout the vehicle 102 or remote from the vehicle 102. In some embodiments, the knock sensor 115 is directly coupled to an electronic controller (e.g., the electronic controller 104 or a separate electronic controller not shown that includes components similar to those of the controller 104). The controller may include an electronic processor, a memory, an input / output interface, a transceiver, and / or the like. The controller 104 (and / or a second controller) may include additional components, such as a battery. In some embodiments, the knock sensor 115 and the electronic controller are located on / within a card or circuit board (not shown). Additionally, in some cases, the controller communicates wirelessly with one or more other devices. For example, the electronic controller 104 communicates with one or more other electronic communication devices of the communication network 120.

[0045] Figure 3 The diagram shows a method for predicting electric vehicles (e.g., Figure 1 An example of a method 300 for detecting an abnormality within an electric motor of a vehicle 102 ...

[0046] At box 302, the electronic processor 205 receives sensor information from a first sensor (e.g., knock sensor 115) positioned within the vehicle 102 and configured to sense vibrations of the electric motor 110 of the vehicle 102. The sensor information represents detected vibrations of a bearing (e.g., one or more bearings 130) of the electric motor 110. In some cases, the electronic processor 205 receives the sensor information continuously. In some cases, the electronic processor 205 receives a periodic burst of sensor information from the knock sensor 115. In some cases, the sensor information is stored in a buffer or other memory of the electronic controller 104 until it can be processed. In some embodiments, the knock sensor 115 is configured to automatically collect information periodically and transmit the information to the processor 205 (e.g., once every 24 hours).

[0047] At box 304, the electronic processor 205 derives one or more signal characteristics from the sensor information. The signal characteristics may be, for example, frequency components of a vibration signal detected by the sensor 115. For example, the one or more signal characteristics may be derived via principal component analysis (PCA). In some cases, deriving the signal characteristics includes applying one or more filters to the raw sensor information to remove one or more background vibration noises (e.g., vibrations caused by the road on which the vehicle 102 is traveling). In some cases, the electronic processor 205 compares the sensor information to a vibration noise floor to extract one or more signal characteristics that exceed the noise floor. In some cases, the noise floor is a predetermined value set by the vehicle manufacturer. In some cases, the electronic processor 205 may establish a vibration noise floor as the vehicle 102 operates over time.

[0048] At box 306, the electronic processor 205 determines a potential anomaly within the electric motor 110 based on the signal characteristics. The potential anomaly can be any kind of reduction in the function of the electric motor 110. In some cases, the processor 205 identifies the type of bearing fault of the electric motor 110. The bearing fault can be, for example, damage to the outer race or inner race of the bearing that holds the motor 115. The bearing fault can be damage to one or more ball bearings or rivets of the motor 115. The fault can be dirt levels (e.g., dust or grease in the bearings of the motor 110), damage caused by current in the vehicle 102 ("frost") and / or corrosion, and / or pre-pitting damage. In some cases, the electronic processor 205 is configured to identify a single bearing in the bearing 130 and / or in the raceway of the motor 110 that is causing / will cause a potential anomaly. The electronic processor 205 can use a pattern matching algorithm to determine whether the vibration event matches a known vibration pattern associated with a specific component anomaly of the electric motor 110.

[0049] In some cases, in addition to the signal characteristics, the electronic processor 205 may determine whether a potential anomaly exists / will occur based on one or more vehicle properties (e.g., received from one or more vehicle systems 106 and / or sensors 120). For example, the processor 205 may be configured to determine a potential anomaly based on the current provided to the electric motor 110. Some types of damage (e.g., corrosion) may cause additional electrical power draw of the electric motor 110 and therefore indicate a potential anomaly associated with one or more bearings 130 of the electric motor 110. Such initial damage within the motor 110 may also affect the temperature of the motor 110 (e.g., increase). Therefore, in some cases, the processor 205 may additionally determine whether a potential anomaly exists within the motor 110 based on the temperature of the motor 110 and / or the coolant inlet and / or outlet temperature provided to affect the temperature of the motor 110.

[0050] For example, when some types of vibrations occur during steering or braking maneuvers, they may be more indicative of a particular type of component failure. For example, electronic processor 205 may determine one or more vehicle attributes within a time period that begins just before a vibration pattern begins and ends just after the vibration pattern ends (e.g., three seconds before and after the vibration pattern occurs).

[0051] In some cases, the electronic processor 205 is also configured to determine potential anomalies based on historical knock sensor data. Such data may come from sensors 115 of the vehicle 102 and / or from other vehicles 125. Such data may be stored in a remote device (e.g., an electronic communication device of the communication network 120 and / or other vehicles 125).

[0052] In some cases, the electronic processor 205 determines that a potential anomaly exists / will occur by classifying the signal characteristics using a machine learning algorithm (e.g., a neural network or a classifier) ​​that can be executed by the electronic processor 205. In some cases, the machine learning algorithm is trained using historical data (e.g., a knock sensor from the sensor 115 of the vehicle 102 or another vehicle 125). The machine learning algorithm can be fed with training data that includes example inputs (e.g., information from a knock sensor such as the sensor 115 that represents an abnormality / potential abnormality of a specific component of the electric motor 110) and a corresponding expected output (e.g., an indication of an abnormality). The training data can also include metadata for the vibration pattern. The metadata can include, for example, the vehicle speed at the time of the vibration pattern, the model of the vehicle 102 in which the vibration pattern is sensed, the state of the vehicle 102 at the time of the vibration pattern (e.g., braking, accelerating, turning, etc.), thermal and / or electrical characteristics of one or more vehicle systems 106, and environmental conditions at the time of the vibration pattern (e.g., ambient temperature, ambient humidity, weather conditions, road conditions, etc.). By processing the training data, the machine learning algorithm gradually develops a predictive model that maps the input to the output included in the training data.

[0053] At block 308, electronic processor 205 generates an alert to a user (e.g., a driver of vehicle 102) in response to determining that a potential anomaly exists within electric motor 110. The alert may be an audio and / or visual warning (e.g., provided via HMI 116). In some cases, processor 205 may generate an alert to a user external to vehicle 102 (e.g., a maintenance facility) via communication network 120. In some cases, processor 205 is configured to identify a cause of a potential anomaly of electric motor 110.

[0054] Figure 4A and 4B4 are schematic diagrams (400A and 400B, respectively) illustrating the electronic controller 104, the electric motor 110, the knock sensor 115, the bearing 130, the current sensor 402, and the coolant temperature sensor 404. Figure 4A In the illustrated embodiment, the two knock sensors 115 are positioned so that they detect vibrations at the front bearing 406A and the rear bearing 406B of the motor 110. Figure 4B In the example shown, a single knock sensor 115 is positioned within the motor 110, between the front bearing 406A and the rear bearing 406B. In both cases shown, the controller 104 transmits the sensor information and / or signal characteristics derived therefrom to a telematics control unit 408 (e.g., part of the communication network 120) that is part of or remote from the vehicle 102. The telematics control unit 408 may be one or more servers or communicate with one or more servers, and the telematics control unit 408 includes a processor similar to that described above with respect to FIG. Figure 2 Components of the controller 104 are described.

[0055] For example, Figure 5 As shown in the system 500 of FIG. 1 , sensor information / characteristics can be transmitted from the controller 104 of the vehicle 102 to a public / customer cloud data server 502 (e.g., the control unit 408). In some cases, the system 500 shown is a digital twin system. The server 502 may additionally collect information / characteristics from one or more additional vehicles (e.g., one or more other electric vehicles 125) and provide knock sensor signal information and / or characteristics to the main server 504. Additional information from additional vehicles may also be provided to the main server 504. Such information may include, but is not limited to, location information, historical sensor information, and any information about a particular vehicle. The main server 504 may collect information about other electric vehicles from the server 502 (and additional servers) and use this information to determine potential abnormalities within the engine 115.

[0056] As mentioned above, while the above examples generally relate to prediction / detection of bearing anomalies in electric motor vehicles, it should be understood that the systems and methods can be applied to other components of electric motor systems. For example, torque fluctuations within an electric motor may be caused by one or more harmonics within the motor magnetic field generated during operation. Harmonics may be caused by one or more sources (e.g., the output of an inverter, an unbalanced rotor, an uneven air gap caused by deformation of one or both of the stator and rotor, demagnetization of the permanent magnets of the motor, etc.). Torque fluctuations may cause motor vibrations, which may negatively affect the performance and / or life of one or more components of the motor system.

[0057] Figure 4C400C is a schematic block diagram of a vehicle 100 according to some aspects. The electronic processor 205 receives and analyzes sensor information from the knock sensor 115 to derive signal characteristics, as described above with respect to Figure 3 The electronic processor 205 may be further configured to identify, based on the signal characteristic, whether the characteristic indicates a bearing abnormality or indicates torque fluctuation. When the processor 205 determines that the characteristic indicates torque fluctuation, the electronic processor 205 may adjust the current provided to the inverter 410 of the vehicle, thereby correspondingly adjusting the current provided to the motor to reduce the torque fluctuation.

[0058] Thus, examples described herein provide, among other things, a control system for an electric vehicle configured to detect / predict anomalies within an electric motor of the vehicle.

[0059] In the foregoing description, specific examples, aspects and features have been described. However, it will be appreciated by those skilled in the art that various modifications and variations may be made without departing from the scope of the invention as set forth in the following claims. Therefore, the description and drawings are to be regarded as illustrative rather than restrictive, and all such modifications are intended to be included within the scope of the present teachings.

[0060] In this document, relational terms such as first and second, top and bottom can be used only to distinguish one entity or action from another entity or action, without necessarily requiring or implying any actual such relationship or order between these entities or actions. The term "comprises", "comprising", "has", "having", "includes", "including", "contains", "containing" or any other variation thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment that includes, has, contains, contains a series of elements includes not only those elements, but also other elements that are not explicitly listed or inherent to such process, method, article or equipment. Elements that begin with "includes...", "have...", "includes..." or "containing..." do not exclude the presence of additional identical elements in the process, method, article or equipment that includes, has, contains, contains the element without more restrictions. The terms "one" and "an" are defined as one or more, unless otherwise explicitly stated in this article. The terms "substantially," "essentially," "approximately," "about," or any other versions thereof, are defined as close to, as understood by one of ordinary skill in the art, and in one non-limiting embodiment, within 10%, within 5%, within 1%, and within 0.5%. The term "coupled," as used herein, is defined as connected, although not necessarily directly, and not necessarily mechanically. A device or structure that is "configured" in a particular way is configured in at least that way, but may also be configured in ways that are not listed.

[0061] Various features, aspects, advantages and embodiments are set forth in the following claims.

Claims

1. A system for predicting anomalies in an electric vehicle, the system comprising: Electric motor; Knock sensor; and An electronic processor configured to: receiving sensor information from the knock sensor, wherein the sensor information represents detected vibration of a bearing of the electric motor; deriving signal characteristics from the sensor information; determining a potential anomaly within the electric motor based on the signal characteristic; and An alert is generated to a user based on the potential anomaly.

2. The system according to claim 1, wherein: Determining a potential anomaly within the engine motor is also based on historical data for a plurality of other electric vehicles.

3. The system according to claim 2, wherein: Determining potential anomalies within the electric motor includes utilizing an artificial intelligence algorithm.

4. The system according to claim 1, wherein: Determining the potential anomaly includes identifying a type of bearing fault of the electric motor.

5. The system according to claim 4, wherein: The bearing fault type includes at least one selected from the group consisting of outer race damage, inner race damage, ball damage, rivet damage, corrosion damage, current damage, pre-pitting damage, and fouling level.

6. The system according to claim 1, wherein: The electric motor is the electric axle.

7. The system according to claim 1, wherein: Determining the potential anomaly is further based on at least one selected from the group consisting of: coolant inlet temperature, coolant outlet temperature, vehicle speed, and electric motor current.

8. The system according to claim 1, wherein: Deriving the signal characteristic includes filtering out background vibration components from the sensor information.

9. The system according to claim 1, wherein: The electric vehicle is a hybrid vehicle or a fuel cell electric vehicle.

10. A method for predicting an anomaly in an electric motor of an electric vehicle, the method comprising: receiving sensor information from a knock sensor, wherein the sensor information represents detected vibration of the electric motor; deriving signal characteristics from the sensor information; determining a potential anomaly within the electric motor based on the signal characteristic; and An alert is generated to a user based on the potential anomaly.

11. The method according to claim 10, wherein: Determining a potential anomaly within the engine motor is also based on historical data for a plurality of other electric vehicles.

12. The method according to claim 11, wherein: Determining potential anomalies within the electric motor includes utilizing an artificial intelligence algorithm.

13. The method according to claim 10, wherein: Determining the potential anomaly includes identifying a type of bearing fault of the electric motor.

14. The method according to claim 13, wherein: The bearing fault type includes at least one selected from the group consisting of outer race damage, inner race damage, ball damage, rivet damage, corrosion damage, current damage, pre-pitting damage, and fouling level.

15. The method according to claim 10, wherein: The electric motor is an electric axle.

16. The method according to claim 10, wherein: Determining a potential anomaly is further based on at least one selected from the group consisting of: coolant inlet temperature, coolant outlet temperature, vehicle speed, and electric motor current.

17. The method according to claim 10, wherein: Deriving the signal characteristic includes filtering out background vibration components from the sensor information.

18. The method according to claim 10, wherein: The electric vehicle is a hybrid vehicle or a fuel cell electric vehicle.

Images