Position estimation for a separating device in the drivetrain of vehicles
A machine learning-based method using current, voltage, and load torque, along with solenoid inductance estimation, addresses the inaccuracies in disconnecting device position detection, ensuring precise engagement and preventing damage.
Patent Information
- Authority / Receiving Office
- DE · DE
- Patent Type
- Applications
- Current Assignee / Owner
- RIVIAN HOLDINGS LLC
- Filing Date
- 2025-10-29
- Publication Date
- 2026-05-13
AI Technical Summary
Existing vehicles face inaccuracies in determining the position of a disconnecting device due to electromagnetic interference (EMI) between the solenoid and Hall effect sensor, leading to potential damage when the disconnecting device is incorrectly assessed as locked despite being in a partially locked position.
A machine learning-based approach using multiple parameters such as current, voltage, and load torque to estimate the position of the disconnecting device, supplemented by estimating solenoid inductance through a Kalman filter, to accurately determine the device's position.
This method enhances the accuracy of tracking the disconnecting device's position, reducing the risk of damage by correctly identifying when it is fully engaged, thereby preventing mechanical stress on the device.
Smart Images

Figure 00000000_0000_ABST
Abstract
Description
REFERENCE TO A RELATED REGISTRATION
[0001] This application claims the benefit of provisional U.S. serial no. 63 / 713,766 filed on October 30, 2024, which was transferred to the proprietor of this application and which is hereby expressly incorporated by reference in its entirety as if fully set forth below and for all applicable purposes. INTRODUCTION
[0002] The present disclosure relates to vehicles with a separating device and in particular to techniques for estimating a current position of the separating device. SUMMARY
[0003] In one aspect, a vehicle is provided. The vehicle includes a differential gear; a disengaging device configured to move between a first position in which the disengaging device is configured to engage the differential gear and a second position in which the disengaging device is configured to disengage the differential gear; and a solenoid configured to move the disengaging device between the first and second positions. The vehicle further includes one or more processors configured to: estimate an inductance of the solenoid, at least partially based on the electrical operating characteristics of the solenoid; and estimate, based on the estimated inductance of the solenoid, a current position of the disengaging device corresponding to either the first or second position.
[0004] From another perspective, a method is provided. The method includes: determining the electrical operating characteristics of a solenoid configured to move the disengaging device between a first position, in which the disengaging device engages with a differential gear of a vehicle, and a second position, in which the disengaging device is disengaged from the differential gear; estimating an inductance of the solenoid, at least partially based on the electrical operating characteristics of the solenoid; and estimating the actual position of the disengaging device as corresponding to either the first or second position.
[0005] From another perspective, a computing system is provided. The computing system includes one or more memories containing processor-executable instructions and one or more processors that are coupled to and configured with the one or more memories to execute the processor-executable instructions and cause the computing system to perform the procedure described above.
[0006] Without limiting the scope of the present embodiments, their most prominent features are now discussed below. After considering this discussion, and especially after reading the section "Detailed Description," it will be clear how the features of the present embodiments provide the advantages described here. BRIEF DESCRIPTION OF THE DRAWINGS Fig. Figure 1A illustrates an exemplary vehicle according to certain embodiments. Fig. Figure 1B illustrates a vehicle chassis according to certain embodiments. Fig. 2A is a schematic block diagram of components of a vehicle according to certain embodiments. Fig. 2B is a schematic block diagram of alternative components of a vehicle according to certain embodiments. Fig. 3A is a separating device in an unlocked position according to certain embodiments. Fig. 3B is a separating device in a locked position according to certain embodiments. Fig. Figure 4 is a diagram illustrating an output signal of a Hall effect sensor as a function of an input current to a solenoid when a separating device is in an unlocked position, according to certain embodiments. Fig. 5A is a separating device and a differential gear toothing according to certain embodiments. Fig. 5B is a separating device that is partially locked with a differential gear, according to certain embodiments. Fig. 5C is a separating device that is locked with a differential gear, according to certain embodiments. Fig. Figure 6A is a diagram illustrating a position signal that demonstrates changes in state for a separating device, according to certain embodiments. Fig. Figure 6B is a diagram illustrating an output signal of a position sensor indicating an estimated state of a separating device versus an output signal of a ground truth sensor indicating an actual state of the separating device, according to certain embodiments. Fig. Figure 6C is a diagram illustrating an input current supplied to a solenoid according to certain embodiments. Fig. Figure 7A is a diagram illustrating a position signal indicating state changes for a separating device according to certain embodiments. Fig. Figure 7B is a diagram illustrating an output signal of a position sensor indicating an estimated state of a separating device versus an output signal of a ground truth sensor indicating an actual state of the separating device, according to certain embodiments. Fig. Figure 7C is a diagram illustrating an input current supplied to a solenoid according to certain embodiments. Fig. Figure 7D is a diagram illustrating an input current supplied to a solenoid according to certain embodiments. Fig. Figure 7E is a diagram illustrating a voltage supplied to a solenoid according to certain embodiments. Fig. Figure 7F is a diagram illustrating the difference between an output signal of a position sensor indicating an estimated state of a separating device and an output signal of a ground truth sensor indicating an actual state of the separating device, according to certain embodiments. Fig. Figure 7G is a diagram illustrating the inductance of a solenoid according to certain embodiments. Fig. Figure 8 represents inputs and output(s) for a machine learning model configured to determine the current position of a separating device, according to certain embodiments. Fig. Figure 9 shows a diagram illustrating an output signal associated with the output generated by a machine learning model and indicating the current position of a separating device, as well as an output signal generated by a ground truth sensor and also indicating the current position of the separating device, according to certain embodiments. Fig. Figure 10 represents a block diagram of a section of a drive axle of a vehicle according to certain embodiments. Fig. 11 presents a method for estimating the current position of a separating device according to certain embodiments. DETAILED DESCRIPTION
[0007] Exemplary aspects of the present disclosure relate to a disconnecting device for selectively coupling a power source (e.g., an electric motor) on a vehicle with a load (e.g., wheels) on the vehicle. As with reference to Fig. 3A and Fig. As discussed in section 3B, the disconnecting device (e.g., a shift sleeve) may include teeth that engage (e.g., mesh with) the teeth of an output gear (e.g., a differential gear) coupled to a vehicle engine. The disconnecting device may be disengaged from an unlocked position (e.g., in Fig. 3A illustrates) into a locked position (e.g. in Fig. (3B illustrated) and vice versa. In the unlocked position, the teeth of the separating device do not engage with the teeth of the output gear. In the locked position, the teeth of the separating device engage with the teeth of the output gear.
[0008] To move the disconnecting device into the locked position, a solenoid can be activated (e.g., by applying an input current to it) to move the disconnecting device along a lateral axis (e.g., pushing in a first direction) until the teeth of the disconnecting device engage with the teeth of the output gear. To return the disconnecting device to the unlocked position, the solenoid can be deactivated (e.g., by removing the input current), and a return spring can move the disconnecting device along the lateral axis into the unlocked position (e.g., pushing in a second direction opposite to the first).
[0009] Existing vehicles may include a position sensor configured to determine the position (e.g., unlocked position, locked position) of the disconnecting device. The position sensor typically includes a Hall-effect sensor, which determines the disconnecting device's position based on the sensor's proximity to a target plate that can be connected to the disconnecting device or solenoid. However, as referenced in Fig. As discussed in section 4, the output signal of the Hall effect sensor can be affected by electromagnetic interference (EMI) between the Hall effect sensor and the solenoid.
[0010] EMI between the solenoid and the Hall effect sensor can cause the Hall effect sensor's output signal to be inaccurate. For example, the Hall effect sensor's output signal may incorrectly indicate that the disengagement device is in the locked position, when in fact the disengagement device is in an intermediate position (hereafter referred to as the "partially locked" position) in which the disengagement device's teeth only partially engage with the differential gear's teeth (e.g., are partially meshed). This inaccuracy in the Hall effect sensor's output signal can, in some cases, lead to damage to the disengagement device.For example, the disengaging device can be damaged if the engine applies torque to the wheels and the position sensor output signal incorrectly indicates that the disengaging device is in the locked position, when in fact it is in the partially locked position. More specifically, one or more teeth of the disengaging device that contact the teeth of the differential gear (and do not overlap to the specified minimum overlap length) can be damaged when the shift sleeve is in the partially locked position.
[0011] Exemplary aspects of the present disclosure are directed towards techniques for determining the state of the separating device, which address the aforementioned challenges associated with existing approaches that use a position sensor (e.g., a Hall effect sensor). For example, the disclosed techniques may include a machine learning-based approach in which one or more parameters (e.g., current, voltage, load torque, estimated inductance) are provided as input features to a machine learning model (e.g., a neural network) trained to process the parameter(s) and output a current position (e.g., unlocked, partially locked, or locked) of the separating device.
[0012] In some embodiments, an input signal (e.g., a current signal) to the solenoid can be one of the input features for the machine learning model. For example, each time the input signal is applied to the solenoid, the solenoid can generate a counter-electromotive force (EMF) that appears as a wave in the input signal. The wave in the input signal can indicate that the separating device is moving. More precisely, the movement of the separating device from the partially locked position to the locked position can be determined based on the characteristics of the wave in the input signal.
[0013] In some embodiments, a load torque signal can be one of the input features for the machine learning model. For example, the load torque signal can correspond to a difference in load acceleration (e.g., of the vehicle's wheels) when the disengaging device is engaged versus when it is disengaged. In this way, the machine learning model can use the load torque signal to more accurately determine when the disengaging device transitions from the partially locked position to the locked position.
[0014] In some embodiments, the disclosed techniques can include determining the position of the disconnecting device at least partially based on the position of the solenoid. For example, the solenoid can be in a first position when the disconnecting device is in the unlocked position, in a second position when the disconnecting device is in the partially locked position, and in a third position when the disconnecting device is in the locked position. Furthermore, the solenoid can have a different inductance at each of these positions (e.g., first, second, and third positions). In this way, the disclosed techniques can include determining the position of the disconnecting device at least partially based on an estimated inductance of the solenoid.For example, the inductance of the solenoid can be estimated, at least partially, based on a current and voltage applied to the solenoid. In some embodiments, a filter (e.g., a Kalman filter) can output the estimated inductance of the solenoid, at least partially, based on a measured current and voltage connected to the solenoid. Furthermore, based on the estimated inductance of the solenoid, the solenoid can be determined to be in one of its first, second, or third positions. And based on the determined position of the solenoid, the current position of the disconnecting device can be determined as unlocked, partially locked, or locked.
[0015] Exemplary aspects of the present disclosure provide numerous technical effects and advantages. By using multiple parameters (e.g., current, voltage, and load torque) to determine the current position (e.g., unlocked, partially locked, or locked) of the disconnecting device, the disclosed techniques can, for example, track the current position of the disconnecting device more accurately than existing approaches that rely on a single parameter (i.e., the output of a Hall-effect sensor) to track the current position of the disconnecting device.With this improved accuracy in tracking the current position of the separating device, the disclosed techniques can eliminate (or at least reduce) the probability of damage to the separating device, for example due to the application of torque to the wheels, when the current position of the separating device is incorrectly assessed as locked, although the separating device is actually in the partially locked position.
[0016] Fig. Figure 1A illustrates an example vehicle 100. As in Fig. As can be seen in Figure 1A, the vehicle 100 has several external cameras 102 and one or more front displays 104. Each of these external cameras 102 can capture a particular view or perspective of the exterior of the vehicle 100. The images or videos captured by the external cameras 102 can then be displayed on one or more displays in the vehicle 100, for example, the one or more front displays 104, for viewing by a driver.
[0017] How Fig. As can be seen from 1B, the vehicle 100 can include a chassis 106 which includes a frame 108 that provides a primary structural element of the vehicle 100. The frame 108 can be formed from one or more beams or other structural elements, or it can be integrated into the body of the vehicle (i.e., a unibody construction).
[0018] In embodiments where the vehicle 100 is a battery electric vehicle (BEV) or possibly a hybrid vehicle, a large battery 110 is mounted on the chassis 106 and can occupy a considerable area within the frame 108 (e.g., at least 80 percent of it). For example, the battery 110 can store between 100 and 200 kilowatt-hours (kWh). The battery 110 can be a lithium-ion battery or another type of rechargeable battery. The battery can essentially have a planar shape.
[0019] The power of the battery 110 can be supplied to one or more drive units 112. Each drive unit 112 can consist of an electric motor and possibly a reduction gear. In some embodiments, there is a single drive unit 112 that drives either the front wheels or the rear wheels of the vehicle 100. In another embodiment, there are two drive units 112, each driving either the front wheels or the rear wheels of the vehicle 100. In yet another embodiment, there are four drive units 112, each driving one of the four wheels of the vehicle 100.
[0020] The drive units 112 can be powered by one or more power electronics sets 114 from the battery 110. The power electronics 114 can include inverters configured to convert direct current (DC) from the battery 110 into alternating current (AC), which is supplied to the motors of the drive units 112.
[0021] The drive units 112 are connected to two or more hubs 116, to which wheels can be mounted. Each hub 116 incorporates a corresponding brake 118, such as the illustrated disc brakes. The drive units 112 or other components may also enable regenerative braking. Each hub 116 is further connected to the frame 108 via a suspension 120. The suspension 120 may include metal or air springs for shock absorption. The suspension 120 may be designed as a pneumatic or hydraulic suspension, allowing the ride height of the chassis 106 relative to a support surface to be adjusted. The suspension 120 may include a damper, the damper's characteristics being either fixed or electronically adjustable.
[0022] In the embodiment of Fig. In 1B and in the discussion below, vehicle 100 is a battery-powered electric vehicle. However, the systems and procedures described herein can be used for any type of vehicle, including internal combustion engine (ICE) vehicles, hybrid powertrains, hydrogen fuel cell powertrains, or other types of powertrains that require warm-up in preparation for use, such as diesel engines.
[0023] Fig. 2A illustrates exemplary components of vehicle 100. Fig. 1A. As in Fig. As shown in Figure 2A, the vehicle 100 includes the cameras 102, one or more front displays 104, a user interface 200, one or more sensors 202, a motion sensor 203, and a tracking system 204. The one or more sensors 202 may include ultrasonic sensors, radio detection and range measurement sensors (RADAR sensors), light detection and range measurement sensors (LIDAR sensors), or other sensor types. The tracking system 204 may be implemented as a GPS receiver (Global Positioning System receiver). The user interface 200 allows a user, for example, a driver or passenger in the vehicle 100, to provide input.
[0024] The components of the vehicle 100 may include one or more temperature sensors 205. The temperature sensors 205 may include sensors configured to detect an ambient air temperature, a battery temperature 110, a power electronics temperature 114, a temperature of each drive unit 112 and / or each motor of each drive unit 112, or the temperature of any other component of the vehicle 100.
[0025] A control system 206 executes instructions to perform at least some of the actions or functions of the vehicle 100, including those relating to the Fig. 4 and Fig. 5 described functions. For example, the control system 206, as described in Fig. Figure 2A shows that the vehicle includes one or more electronic control units (ECUs) configured to perform at least some of the actions or functions of the vehicle. In certain embodiments, each ECU is responsible for a specific group of functions. Furthermore, in some embodiments, each ECU may be a computer system.
[0026] Certain features of the embodiments described herein may be controlled by a telematics control module ECU (TCM-ECU). The TCM-ECU may provide a wireless vehicle communication gateway to support functions such as, but not limited to, over-the-air (OTA) software updates, vehicle-to-the-Internet communication, vehicle-to-a-computer communication, on-board navigation, vehicle-to-vehicle communication, vehicle-to-landscape feature communication (e.g., automated toll road sensors, automated toll plazas, power delivery devices at charging stations), or automated calling functionality.
[0027] Certain features of the embodiments described herein can be controlled by a central gateway module ECU (CGM-ECU). The CGM-ECU can serve as the vehicle's communication hub, connecting and transmitting data to and from the various ECUs, sensors, cameras, microphones, motors, displays, and other vehicle components. The CGM-ECU can include a network switch that provides connectivity via Controller Area Network (CAN) ports, Local Interconnect Network (LIN) ports, and Ethernet ports. The CGM-ECU can also act as the master controller over the various vehicle modes (e.g., road mode, park mode, off-road mode, towing mode, camping mode) and thereby control certain vehicle components related to switching the vehicle into one of the vehicle modes.
[0028] In various embodiments, the CGM-ECU collects sensor signals from one or more sensors of the vehicle 100. For example, the CGM-ECU can collect data from cameras 102 and sensors 202. The sensor signals collected by the CGM-ECU are then forwarded to the corresponding ECUs to, for example, process the data related to the Fig. to perform the processes and functions described in 3 to 5.
[0029] The control system 206 may also include one or more additional ECUs, such as, but not limited to: a Vehicle Dynamics Module ECU (VDM ECU), an Experience Management Module ECU (XMM ECU), a Vehicle Access System ECU (VAS ECU), a Near Field Communication ECU (NFC ECU), a Body Control Module ECU (BCM ECU), a Seat Control Module ECU (SCM ECU), a Door Control Module ECU (DCM ECU), a Rear Zone Control ECU (RZC ECU), an Autonomy Control Module ECU (ACM ECU), an Autonomous Safety Module ECU (ASM ECU), a Driver Monitoring System ECU (DMS ECU), and / or a Winch Control Module ECU (WCM ECU).If the vehicle 100 is an electric vehicle, one or more ECUs can provide functions related to the vehicle's battery pack, such as a battery management system ECU (BMS-ECU), a battery power isolation ECU (BPI-ECU), a balancing voltage temperature ECU (BVT-ECU), and / or a thermal management module ECU (TMM-ECU). In various configurations, the XMM-ECU transmits data to the TCM-ECU (e.g., via Ethernet, etc.). Additionally or alternatively, the XMM-ECU can transmit other data (e.g., audio data from microphones 208, etc.) to the TCM-ECU.
[0030] With reference to Fig. 2B: In some embodiments, the control system 206 can be implemented as a plurality of zone controllers 206a, 206b, 206c. Each zone controller 206a, 206b, 206c can control a subset of the vehicle's systems. The subset of systems controlled by each zone controller 206a, 206b, 206c can generally be assigned based on location within the vehicle 100. For example, a west zone controller 206a can control systems on the driver's side of the vehicle 100, an east zone controller 206b can control systems on the passenger side of the vehicle 100, and a south zone controller 206c can control systems in the rear of the vehicle. Each zone controller 206a, 206b, 206c can implement some of the functions that are assigned to the control system 206's ECUs. Fig. 2A. The functions of the ECUs can be distributed across zone controllers 206a, 206b, 206c such that only one zone controller 206a, 206b, 206c implements the functions of each ECU. Alternatively, the functions of an ECU can be duplicated across multiple zone controllers 206a, 206b, 206c, with each zone controller executing the functions of the ECU for the part of the vehicle to which that zone controller 206a, 206b, 206c is assigned.
[0031] The zone controllers 206a, 206b, 206c can be interconnected via a network 206d, for example an Ethernet network, a Controller Area Network (CAN) or another type of network.
[0032] Fig. 3A and Fig. 3B represent a separating device 300 for a vehicle according to certain embodiments of the present disclosure. The separating device 300 can, for example, be described above with reference to Fig. 1A discussed vehicle 100 should be implemented. Fig. 3A shows the separating device 300 in an unlocked position, while Fig. 3B shows the separating device 300 in a locked position.
[0033] In some embodiments, the disconnecting device 300 can be a shift sleeve 302 with teeth (not shown). The teeth of the shift sleeve 302 can engage with teeth (not shown) of an output gear 304, which in some embodiments can be coupled to a motor (not shown) of the vehicle.
[0034] The switching sleeve 302 can be removed from an unlocked position (e.g. in Fig. 3A illustrates) into a locked position (e.g. in Fig. (3B illustrated) and vice versa. In the unlocked position, the teeth of the shift sleeve 302 do not engage with the teeth (not shown) of a differential gear 306, which is coupled to the wheels (not shown) of the vehicle. In the locked position, however, the teeth of the shift sleeve 302 engage with the teeth (not shown) of the differential gear 306.
[0035] To move the switching sleeve 302 into the locked position, a solenoid 308 can be activated (e.g., by applying an input current to it) to move the switching sleeve 302 along a lateral axis L (e.g., to push it in a first direction D1) until the teeth of the switching sleeve 302 engage with the teeth of the output gear 306. To return the switching sleeve 302 to the unlocked position, the solenoid 308 can be deactivated (e.g., by no longer applying an input current to it), and a return spring 310 can move the switching sleeve 302 along the lateral axis L (e.g., to push it in a second direction D2, opposite to the first direction D1) to return the switching sleeve 302 to the unlocked position.
[0036] Fig. Figure 4 is a diagram 400 illustrating the effect of a current signal applied to a solenoid on the output signal of a position sensor (e.g., Hall effect) configured to detect the position of a separating device according to certain embodiments. More specifically, diagram 400 illustrates the effect of the current signal on the output signal while the separating device is unlocked.
[0037] Diagram 400 includes line 402 to illustrate that the voltage (e.g., shown in millivolts along the vertical axis) of the position sensor's output signal decreases as the amplitude of an input signal (e.g., current) to the solenoid increases. The decreasing value (e.g., voltage) of the position sensor's output signal when the disconnect device is held in the unlocked position is incorrect and illustrates the effect that EMI between the solenoid and the position sensor has on the position sensor's output signal.
[0038] Fig. Figures 5A-5C illustrate different arrangements of the teeth 500, 502 of the shift sleeve 302 relative to the teeth 510, 512 of the differential gear 306 according to certain embodiments. In particular, Figures 5A-5C show different arrangements of the teeth 500, 502 of the shift sleeve 302 relative to the teeth 510, 512 of the differential gear 306. Fig. 5A shows the switching sleeve 302 in an unlocked position; Fig. Figure 5B shows the switching sleeve 302 in a partially locked position; and Fig. 5C represents the switching sleeve 302 in a locked position.
[0039] In Fig. In Figure 5A, the teeth 500 and 502 of the shift sleeve 302 are not engaged with the teeth 510 and 512 of the differential gear 306 (i.e., they do not mesh). Furthermore, the shift sleeve 302 is shown rotated relative to the differential gear 306, such that the teeth 500 of the shift sleeve 302 are aligned with the teeth 510 of the differential gear 306, and the teeth 502 of the shift sleeve 302 are aligned with the teeth 512 of the differential gear 306. This particular alignment of the teeth 500 and 502 of the shift sleeve 302 with the teeth 510 and 512 of the differential gear 306 can be called a gear block. And when a gear block is present, a force F causes Solenoid, which is applied to the switching sleeve 302 to move the switching sleeve 302 from the unlocked position, not that the switching sleeve 302 moves into the partially locked position, which is in Fig. As shown in Figure 5B. To remove the gear block, the shift sleeve 302 can be rotated relative to the differential gear 306 so that the teeth 500 of the shift sleeve 302 are no longer aligned with the teeth 510 of the differential gear 306. After rotation, the force F Solenoid to move the switching sleeve 302 into the partially locked position, which is in Fig. 5B is illustrated.
[0040] In Fig. In 5B, the toothing 500 of the shift sleeve 302 is partially positioned in a channel 514, which is defined between the toothing 510 of the differential gear 306 and the toothing 512 of the differential gear 306. As illustrated, a larger portion of the toothing 500 of the shift sleeve 302 is positioned outside the channel 514 than inside it. Thus, the toothing 500 of the shift sleeve 302 only partially engages with the toothings 510 and 512 of the differential gear 306. To engage the shift sleeve 302 in the Fig. 5C illustrated moving the locked position, the solenoid continues to apply force F Solenoid to the shift sleeve 302 to move the toothing 500 of the shift sleeve 302 further into the channel 514 of the differential gear 306 in order to reduce a distance D between the toothing 500 of the shift sleeve 302 and a bottom 516 of the channel 514.
[0041] In some embodiments, the toothing 510 of the differential gear 306 may have a chamfered section 518, as shown in Fig. Figure 5A shows that the chamfered section 518 of the toothing 510 allows a tooth (e.g., tooth 500) of the shift sleeve 302 to slide into the channel 514 defined between the teeth 510 and 512 of the differential gear 306 and thereby engage with the teeth 510 and 512 of the differential gear 306. The speed at which the shift sleeve 302 rotates relative to the differential gear 306 can cause the teeth 500 and 502 of the shift sleeve 302 to ratchet (e.g., to move in and out of mesh with the teeth 510 and 512 of the differential gear 306).
[0042] Fig. 6A-6C represent different signals illustrating position changes (e.g. unlocked to partially locked, partially locked to locked, locked to partially unlocked and partially unlocked to unlocked) of a separating device according to some embodiments of the present disclosure.
[0043] Fig. Figure 6A shows a diagram 600 illustrating a signal 610 which, according to some embodiments of the present disclosure, indicates a movement of the disconnecting device. The signal 610 includes several pulses (e.g., each defined by a rising and a falling edge). For example, a first pulse P1 of the signal 610 represents the transition of the disconnecting device from the unlocked position to the locked position. The first pulse P1 includes the rising edge 612, which represents the start of the actuation and indicates that the disconnecting device is moving from an unlocked position (e.g., in the locked position). Fig. 5A shown) into a partially locked position (e.g. in Fig. 5B) moves, one. The first pulse P1 of signal 610 can also include a falling edge 614, which represents the end of the actuation and indicates that the separating device moves from the partially locked position to the locked position (e.g. in Fig. 5C shown).
[0044] Fig. Figure 6B shows a diagram 620 illustrating an output signal 630 of a position sensor (e.g., Hall effect) versus an output signal 640 of a ground truth sensor (e.g., unaffected by an additional magnetic field generated by the current supply to the solenoid) according to some embodiments of the present disclosure. The output signal 630 of the position sensor can represent an estimated position (e.g., unlocked, partially locked, or locked) of the disconnecting device as measured by the position sensor, while the output signal 640 of the ground truth sensor can represent an actual position of the disconnecting device as measured by the ground truth sensor.
[0045] Fig. Figure 6C shows a diagram 650 illustrating a current signal 660 that corresponds to a solenoid (e.g., the solenoid 308 of Fig. 3A and Fig. 3B) is provided according to certain embodiments of the present disclosure. With reference to Fig. 6B and Fig. 6C, the solenoid may be blocked at time T1 if the solenoid initially attempts to move the separating device. More precisely, at time T1, the teeth of the separating device may be aligned with the teeth of the differential gear, as described above with reference to Fig. 6A is discussed. In this way, the solenoid can be blocked from moving (e.g., pushing) the separating device to engage (e.g., mesh) the teeth of the separating device with the teeth of the differential gear.
[0046] The ground truth sensor detects this event (i.e., the gear block), as indicated by the rising edge 632 of the output signal 640 at time T1. However, the output signal 630 of the position sensor does not exhibit the same behavior at time T1. Instead, the output signal 630 of the position sensor continues to decrease at time T1, as illustrated. Therefore, as illustrated Fig. 6B, that relying on the output signal 630 of the position sensor only at time T1 incorrectly indicates that the position sensor is retracting, which is not possible given the actual state of the disconnecting device (as indicated, for example, by the output signal 640 of the ground truth sensor) at time T1.
[0047] Fig. Figures 7A-7C represent different signals illustrating state transitions (e.g., between locked and unlocked) of a disconnecting device according to some embodiments of the present disclosure.
[0048] Fig. Figure 7A shows a diagram 700 illustrating a signal 710 which, according to some embodiments of the present disclosure, indicates a movement of the disconnecting device. The signal 710 includes several pulses (e.g., each defined by a rising and a falling edge). For example, a first pulse P1 of the signal 710 may include a rising edge 712 indicating that the disconnecting device is moving from an unlocked position (e.g., in Fig. 5A shown) into a partially locked position (e.g. in Fig. 5B shown). The first pulse P1 of signal 710 can also include a falling edge 714, indicating that the disconnecting device is moving from the partially locked position to the locked position (e.g. in Fig. 5C shown).
[0049] Fig. Figure 7B shows a diagram 720 illustrating an output signal 730 of a position sensor (e.g., a Hall-effect sensor) versus an output signal 740 of a ground-truth sensor (e.g., unaffected by an additional magnetic field generated by the current supply to the solenoid) according to some embodiments of the present disclosure. The output signal 730 of the position sensor can represent an estimated position (e.g., unlocked, partially locked, or locked) of the disconnecting device as measured by the position sensor, while the output signal 740 of the ground-truth sensor can represent an actual position of the disconnecting device.
[0050] Fig. Figure 7C shows a diagram 750 illustrating a current signal 760 (e.g., indicating an operating current) provided to a solenoid according to some embodiments of the present disclosure. With reference to Fig. 7B and Fig. 7C, it is possible that the disengaging device rotates too quickly relative to the differential gear between time T1 and time T2, which can cause the disengaging device to ratchet (i.e., engage and disengage from the gear mesh with the differential gear). This behavior is indicated in the output signal 740 of the ground truth sensor as multiple oscillations 742 (e.g., noise). These oscillations are also visible in the output signal 730 of the position sensor. However, the amplitude of these oscillations in output signal 730 is smaller due to the effect of the input signal (e.g., current signal 760) for the solenoid on the output signal 730 (e.g., voltage signal) of the position sensor.
[0051] Fig. 7D-7G also represent different signals illustrating state transitions (e.g., between locked and unlocked) of the disconnecting device according to some embodiments of the present disclosure.
[0052] Fig. Figure 7D shows a diagram 770 illustrating a current signal 772 which, according to some embodiments of the present disclosure, indicates a movement of the disconnecting device. The current signal 772 includes several pulses (e.g., each defined by a rising and a falling edge). For example, a first pulse P1 of the current signal 772 may include a rising edge 774 indicating that the disconnecting device is moving from an unlocked position (e.g., in Fig. 5A shown) into a locked position (e.g. in Fig. 5C) moves. The first pulse P1 of the current signal 772 can also include a falling edge 776, indicating that the disconnecting device moves from the locked position to the unlocked position (e.g., in Fig. 5A shown).
[0053] In contrast to Signal 710 from Fig. 7A can receive the current signal 772 from Fig. 7D includes one or more waves (e.g., indicated by oscillations in the current signal 772) that allow for a more accurate determination of the inductance. In various embodiments, the wave(s) can be added to the current signal 772 to improve the ability of the ECU, for example, its filter (e.g., Kalman filter), to estimate the inductance of the solenoid.
[0054] Fig. Figure 7E shows a diagram 780 illustrating a voltage signal 782 which, according to some embodiments of the present disclosure, indicates a movement of the disconnecting device. The voltage signal 782 can indicate an operating voltage for the solenoid, which is associated with the operation of the solenoid. For example, the operating voltage of the solenoid can vary as the disconnecting device moves between the unlocked, partially locked, and locked positions.
[0055] Similar to the current signal 772 from Fig. 7D can output the voltage signal 782 from Fig. 7E includes one or more waves (e.g., indicated by oscillations in the voltage signal 782) that make the inductance more apparent. It should be understood that the wave(s) can be added to the voltage signal 782 to improve the estimation of the solenoid's inductance.
[0056] Fig. Figure 7F shows a diagram 790 illustrating an output signal 792 of a position sensor (e.g., a Hall-effect sensor) according to some embodiments of the present disclosure. The output signal 792 of the position sensor can represent an estimated position (e.g., unlocked, partially locked, or locked) of the separating device, as measured by the position sensor.
[0057] Fig. Figure 7G shows a diagram 794 illustrating a first signal 796, which indicates an estimated inductance of the solenoid, and a second signal 798, which indicates an actual inductance of the solenoid according to certain embodiments. In particular, diagram 794 illustrates how the estimated inductance (e.g., indicated by the first signal 796) of the solenoid closely matches the actual inductance (e.g., indicated by the second signal 798). It is understood that the improved accuracy in estimating the inductance of the solenoid may be due, at least in part, to the waveform(s) added to the current signal 772 and the voltage signal 782 associated with the solenoid, which are the inputs to the filter (e.g., Kalman) configured to estimate the inductance of the solenoid.
[0058] Fig. Figure 8 shows inputs and outputs of a machine learning model 800 trained to estimate the current position of a disconnecting device according to certain embodiments. As shown, the input features for the machine learning model 800 can include one or more of a current 802, a voltage 804, and a load torque 806. The current 802 can correspond to a current supplied to the solenoid to move the disconnecting device from the unlocked position to the partially locked position and finally to the locked position. The voltage 804 can correspond to a voltage associated with the solenoid. In addition, in some embodiments, an additional input feature for the machine learning model 800 can be determined at least partially based on the current 802 and the voltage 804. For example, an inductance of the solenoid (e.g.,(using a filter, such as a Kalman filter) based on the current 802 and the voltage 804.
[0059] In some embodiments, the input features for the machine learning model 800 can include the load torque 806, which may include one or more signals indicating the torque applied to the vehicle's wheels. Furthermore, the load torque 806 can be used by the machine learning model 800 to determine when the disconnecting device is in the locked position. In some embodiments, the input features for the machine learning model 800 can additionally include the output signal from the position sensor (e.g., a Hall-effect sensor).
[0060] In some embodiments, the input features for the machine learning model 800 can include an estimated inductance 808 of the solenoid. For example, the estimated inductance 808 can be output by the ECM, such as by filtering it, and provided as one of the input features for the machine learning model 800.
[0061] The machine learning model 800 can be configured to process the input features and generate an output 810 indicating the current position of the separating device. For example, the machine learning model 800 can be configured to process the input feature(s) to classify the current position of the separating device as one of: unlocked; partially locked; or locked. Thus, the output 810 of the machine learning model 800 can indicate that the current position of the separating device is one of the aforementioned positions. Fig. 5A-5C corresponds.
[0062] Fig. Figure 9 shows a diagram 900 illustrating an output signal 910 associated with the output of the machine learning model versus an output signal 920 of a ground truth sensor (e.g., unaffected by an additional magnetic field generated by the current supply to the solenoid) according to some embodiments of the present disclosure. The output signal 910 associated with the machine learning model can represent an estimated position (e.g., unlocked, partially locked, or locked) of the disconnecting device, based on the input characteristics (e.g., current, voltage, load torque) provided to the machine learning model, whereas the output signal 920 of the ground truth sensor can represent an actual position of the disconnecting device.
[0063] As illustrated, the output signal 910 associated with the machine learning model closely follows the output signal 920 of the ground truth sensor. For example, the output signal 910 associated with the machine learning model better matches the output signal 920 of the ground truth sensor when the disconnecting device moves from the unlocked position to the partially locked position and then from the partially locked position to the locked position. In this way, the machine learning-based approach to estimating the current position of the disconnecting device is improved (e.g., more accurate) compared to the existing sensor-based approach (e.g., using Hall effect sensors).
[0064] Fig. Figure 10 shows a block diagram of a section of a vehicle's drive axle according to certain embodiments. As shown, an internal toothing 1000 engages with an external toothing 1010 to transmit the torque of a load on the vehicle, for example, the wheels (e.g., rear wheels) coupled to the drive axle. In some embodiments, the internal toothing 1000 of the above may be Fig. 3A and Fig. 3B discussed separating device 300 correspond, and the external toothing 1010 can correspond to the above with reference to Fig. 3A and Fig. 3B discusses differential gear 306.
[0065] As discussed above, a current can flow to a solenoid (e.g., solenoid 308 in Fig. 3A and Fig. 3B) be provided to exert a force F Solenoidto apply a threshold torque to the drive shaft to engage the differential gear. When the disconnecting device is engaged with the differential gear, the motor can then apply torque to the drive shaft to turn the wheels. Exemplary aspects of the present disclosure aim to apply a threshold torque to the drive shaft to keep the disconnecting device (e.g., the internal gear 1000) engaged with the differential gear (e.g., the external gear). More precisely, by applying the threshold torque, a frictional force 1020 can be generated between the disconnecting device and the differential gear, which effectively prevents the disconnecting device from disengaging the differential gear. In this way, the disclosed techniques can, for example, eliminate the need for the solenoid to continue to apply the force F. SolenoidThis occurs after the disengaging device initially engages the differential gear and the motor begins to apply the threshold torque to the drive axle. In this way, the disclosed techniques can enable energy savings (e.g., a reduced solenoid runtime) that can extend the battery life in the vehicle and, consequently, the vehicle's range (i.e., the distance traveled between battery recharging).
[0066] Fig. Figure 11 discloses a method 1100 for estimating the current position of a vehicle's separating device according to certain embodiments of the present disclosure. In some embodiments, one or more steps of the method 1100 can be performed by an ECU on board the vehicle.
[0067] In 1102, the method 1100 includes determining, by one or more processors, the electrical operating characteristics of a solenoid configured to move the separating device between a first position in which the separating device engages with a differential gear of a vehicle and a second position in which the separating device is separated from the differential gear.
[0068] In 1104, method 1100 includes estimating, by one or more processors, the inductance of the solenoid, at least partially based on the electrical operating characteristics of the solenoid. In some embodiments, the inductance estimation includes providing a current signal and a voltage signal by one or more processors as input to a filter (e.g., contained in an ECU) and determining the estimated inductance of the solenoid as the output of the filter.
[0069] In 1106, the method 1100 includes estimating the current position of the separating device as corresponding to either the first position or the second position.
[0070] In some embodiments, estimating the current position of the separating device involves providing one or more input features to a machine learning model configured to classify the current position of the separating device. For example, the one or more input features may include the estimated inductance of the solenoid. Furthermore, estimating the current position of the separating device may involve determining an output from the machine learning model, the output classifying the current position of the separating device as one of the first position, one of the second position, or, in some embodiments, the machine learning model may be further configured to classify the current position of the separating device as one of a third position, in which the separating device partially engages the differential gear.
[0071] In some embodiments, one or more input features may also include the current signal and the voltage signal. Furthermore, in some embodiments, one or more input features may also include a load torque signal indicating whether the disconnecting device is in the first or second position.
[0072] In some embodiments, Method 1100 may further, in response to the estimation that the current position of the disengaging device corresponds to the first position, include applying a threshold torque to a drive axle of the vehicle to prevent the disengaging device from disengaging the differential gear. Furthermore, the operations may include modifying the operation of the solenoid while the threshold torque is applied to the drive axle of the vehicle.
[0073] In some embodiments, modifying the operation of the solenoid may include deactivating (e.g., switching off) the solenoid. For example, in some embodiments, deactivating the solenoid may include switching from operating the solenoid in a first power state (e.g., active power state) to operating the solenoid in a second power state. It is understood that the solenoid may consume less current (e.g., or no current at all) in the second power state than in the first power state.
[0074] In some embodiments, the electrical operating characteristics may include a current signal and a voltage signal. Furthermore, in some embodiments, estimating the inductance of the solenoid may include introducing one or more waves into at least one of the current signal or the voltage signal and estimating the inductance at least partially based on the one or more waves contained in at least one of the current signal or the voltage signal.
[0075] The descriptions of the various embodiments of this disclosure are presented for illustrative purposes. Many modifications and variations will be apparent to those skilled in the art without affecting the scope of protection or the spirit of the described embodiments. The terminology used herein has been chosen to explain the principles of the embodiments, their practical application, or the technical improvement over technologies available on the market, or to enable other skilled persons to understand the embodiments disclosed herein.
[0076] The foregoing refers to the embodiments presented in this disclosure. However, the scope of this disclosure may extend beyond the specifically described embodiments. Instead, any combination of features and elements, regardless of whether they relate to different embodiments, is considered for implementing and practicing the presented embodiments. Furthermore, while the embodiments disclosed herein may have advantages over other possible solutions or over the prior art, the embodiments may have some advantages or no particular advantage at all. Therefore, the considerations, features, embodiments, and advantages discussed herein are merely illustrative.
[0077] Aspects of the present disclosure may take the form of a complete hardware implementation, a complete software implementation (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which may be generally referred to herein as a “circuit”, “module”, or “system”.
[0078] Various aspects of the present disclosure are described by explanatory text, flowcharts, block diagrams of computer systems, and / or block diagrams of machine logic included in embodiments of computer program products (CPPs). In all flowcharts, the operations may be performed in a different sequence than depicted in a particular flowchart, depending on the technology. For example, again depending on the technology, two operations shown in successive flowchart blocks may be performed in reverse order, as a single integrated step, concurrently, or in a manner that overlaps at least partially in time.
[0079] An embodiment of a computer program product (“CPP embodiment” or “CPP”) is a term used in the present disclosure to describe any group of one or more storage media (also called “media”) that are together enclosed in a group of one or more storage devices, which together include machine-readable code corresponding to instructions and / or data for performing computer operations specified in a particular CPP claim. A “storage device” is any tangible device in which instructions for use by one or more computer processing devices can be stored and retained.The computer-readable storage medium may be, without limitation, an electronic storage medium, a magnetic storage medium, an optical storage medium, an electromagnetic storage medium, a semiconductor storage medium, a mechanical storage medium, or a suitable combination of the foregoing. Certain types of storage devices that include these media are: floppy disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), read-only memory for compact discs (CD-ROM), digital versatile discs (DVD), memory stick, floppy disk, mechanically coded devices (such as punched cards or pits / lands formed in a primary surface of a disk), or any suitable combination of the foregoing.According to the use of this term in the present disclosure, a computer-readable storage medium refers to non-transient storage and not to transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide, light pulses traveling through a fiber optic cable, electrical signals transmitted through a wire, and / or other transmission media. As those skilled in the art know, during the normal operation of a storage device, e.g., during access, defragmentation, or data cleanup, data is typically moved at certain times, but the storage device remains non-transient during these operations because the data remains non-transient during storage.
Claims
[1] Vehicle, comprising: a differential gear; a separating device configured to move between a first position in which the separating device is configured to engage the differential gear and a second position in which the separating device is configured to disengage the differential gear; and a solenoid configured to move the separating device between the first position and the second position; and one or more processors configured to: Estimating the inductance of the solenoid, at least partially based on the electrical operating characteristics of the solenoid; and Estimate, based on the estimated inductance of the solenoid, a current position of the separating device as the first position or the second position accordingly. [2] Vehicle according to claim 1, wherein the electrical operating characteristics include a current signal indicating an operating current of the solenoid and a voltage signal indicating an operating voltage of the solenoid. [3] Vehicle according to claim 2, wherein the one or more processors are configured to estimate the inductance of the solenoid: Providing the current signal and the voltage signal as input to a filter; and Determining the estimated inductance of the solenoid as the filter output. [4] Vehicle according to claim 2, wherein one or more processors are configured to estimate the current position of the separating device: Providing one or more input features for a machine learning model configured to classify the current position of the separating device, wherein the one or more input features include the estimated inductance of the solenoid; and Determining an output that classifies the current position of the separating device as one of the first position or the second position. [5] Vehicle according to claim 4, wherein the machine learning model is further configured to classify the current position of the separating device as corresponding to a third position in which the separating device partially engages the differential gear. [6] Vehicle according to claim 4, wherein the one or more input features further include the current signal and the voltage signal. [7] Vehicle according to claim 6, wherein the one or more input features further comprise a load torque signal indicating whether the separating device is in the first position or the second position. [8] Vehicle according to claim 1, wherein, if the current position is estimated to be the first position, the one or more processors are further configured to: Applying a threshold torque to a drive axle of the vehicle to prevent the disconnecting device from disengaging the differential gear; and Modifying the operation of the solenoid while the Threshold torque is applied to the vehicle's drive axle. [9] Vehicle according to claim 8, wherein to modify the operation of the solenoid, one or more processors are configured to deactivate the solenoid. [10] Vehicle according to claim 1, wherein the electrical operating characteristics comprise a current signal and a voltage signal and wherein the one or more processors are configured to: Introducing one or more waves into at least one of the current or voltage signals; and Estimating the inductance at least partially based on the one or more waves contained in at least one of the current or voltage signals. [11] Method for estimating the current position of a separating device on a vehicle, the method comprising: Determine, via one or more processors, the electrical operating characteristics of a solenoid configured to move the separating device between a first position in which the separating device engages with a differential gear of a vehicle and a second position in which the separating device is separated from the differential gear; Estimate, via the one or more processors, an inductance of the solenoid, at least partially based on the electrical operating characteristics of the solenoid; and Estimate, via one or more processors, the current position of the separating device as the first position or the second position accordingly. [12] Method according to claim 11, wherein the electrical operating characteristics comprise a current signal indicating an operating current of the solenoid and a voltage signal indicating an operating voltage of the solenoid. [13] Method according to claim 12, wherein estimating the inductance of the solenoid comprises: Providing the current signal and the voltage signal as input to a filter; and Determining the estimated inductance of the solenoid as the filter output. [14] The method of claim 12, wherein the estimation of the current position of the separating device comprises: Providing one or more input features for a machine learning model configured to classify the current position of the separating device, wherein the one or more input features include the estimated inductance of the solenoid; and Determining an output of the machine learning model, wherein the output classifies the current position of the separating device as either the first position or the second position. [15] Method according to claim 14, wherein the one or more input features further comprise the current signal and the voltage signal. [16] Method according to claim 15, wherein the one or more input features further comprise a load torque signal indicating whether the separating device is in the first position or the second position. [17] The method of claim 12, further comprising: In response to the estimation that the current position of the disengaging device corresponds to the first position, a threshold torque is applied to a drive axle of the vehicle to prevent the disengaging device from disengaging the differential gear; and Modifying the operation of the solenoid while the threshold torque is applied to the vehicle's drive axle. [18] Method according to claim 17, wherein modifying the operation of the solenoid comprises deactivating the solenoid. [19] Method according to claim 12, wherein the electrical operating characteristics comprise a current signal and a voltage signal and wherein the estimation of the inductance of the solenoid comprises: Introducing one or more waves into at least one of the current or voltage signals; and Estimating the inductance at least partially based on the one or more waves contained in at least one of the current or voltage signals. [20] Computing system, comprising: one or more memories, comprising instructions executable by the processor; and one or more processors coupled to and configured with one or more memories to execute the instructions executable by the processor to cause the computing system to do the following: Estimating the inductance of a solenoid configured to move a disengaging device between a first position in which the disengaging device is configured to engage a differential gear, and a second position in which the disengaging device is configured to disengage the differential gear; and Estimate, based on the estimated inductance of the solenoid, a current position of the separating device as the first position or the second position accordingly.