Type identification method and device for wheel speed sensor

Abstract

The embodiment of the invention provides a wheel speed sensor type identification method and device, and relates to the technical field of vehicle control, and the method comprises the steps: receiving a current wheel speed signal which is generated by a newly installed wheel speed sensor; obtaining a first characteristic item according to the current wheel speed signal, wherein the first characteristic item comprises electrical characteristic information of the current wheel speed signal; based on a set classification method, performing classification processing on the first characteristic item by adopting each second characteristic item in a self-learning database and a respective category label to obtain a first equipment type which corresponds to the first characteristic item and represents the sensor type of the newly installed wheel speed sensor, the category label is used for representing the sensor type of the sensor to which the corresponding second characteristic item belongs, and the second characteristic item comprises the electrical characteristic information of the historical wheel speed signal. By adopting the method, the accuracy of determining the equipment type can be improved, the accuracy of vehicle control is ensured, and the efficiency of replacing the wheel speed sensor is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a method and device for identifying the type of a wheel speed sensor. Background Art

[0002] Wheel speed sensors are used to measure a vehicle's wheel speed. Commonly used wheel speed sensors include magnetoelectric and Hall-effect sensors. Currently, the most popular type is the magnetoelectric sensor, which generates a current signal from a magnetic ring sensor. These sensors primarily fall into three categories: active, non-intelligent, PWM-based, and AK-based. In typical vehicles, these three types of sensors are typically equipped with their own dedicated wheel speed signal processing methods, allowing them to be used interchangeably.

[0003] In related technologies, the device type of a wheel speed sensor is typically preconfigured in the ECU (Electronic Control Unit, also known as the "onboard computer" or "vehicle computer"). If a wheel speed sensor is damaged or needs to be replaced for testing, the preconfigured device type in the ECU must be manually re-flashed or the ECU software calibrated. This method can result in manually re-flashing or calibrating the incorrect device type, leading to vehicle control errors and inefficient wheel speed sensor replacement.

[0004] Therefore, there is an urgent need for a method and device for identifying the type of a wheel speed sensor, which can improve the accuracy of determining the device type, ensure the accuracy of vehicle control, and improve the efficiency of replacing the wheel speed sensor. Summary of the Invention

[0005] The embodiments of the present application provide a method and apparatus for identifying the type of a wheel speed sensor, which can improve the accuracy of determining the device type, ensure the precision of vehicle control, and improve the efficiency of replacing the wheel speed sensor.

[0006] In a first aspect, an embodiment of the present application provides a method for identifying a type of a wheel speed sensor, the method comprising: receiving a current wheel speed signal generated by a newly installed wheel speed sensor; acquiring a first characteristic entry according to the current wheel speed signal, wherein the first characteristic entry includes electrical characteristic information of the current wheel speed signal; Based on the set classification method, the first characteristic entry is classified using each second characteristic entry in the self-learning database and the category label of each second characteristic entry to obtain the first device type corresponding to the first characteristic entry. The first device type is used to characterize the sensor type of the newly installed wheel speed sensor, and the category label is used to characterize the sensor type of the sensor to which the corresponding second characteristic entry belongs. The second characteristic entry contains electrical characteristic information of the historical wheel speed signal.

[0007] In a second aspect, an embodiment of the present application provides a device for identifying a type of a wheel speed sensor, the device comprising: a transceiver unit, configured to receive a current wheel speed signal generated by a newly installed wheel speed sensor; a first processing unit, configured to obtain a first characteristic entry according to the current wheel speed signal, wherein the first characteristic entry includes electrical characteristic information of the current wheel speed signal; The second processing unit is configured to classify the first characteristic entry based on a set classification method, using each second characteristic entry in a self-learning database and the respective category labels of the second characteristic entries, to obtain a first device type corresponding to the first characteristic entry, wherein the first device type is used to characterize the sensor type of the newly installed wheel speed sensor, the category label is used to characterize the sensor type of the sensor to which the corresponding second characteristic entry belongs, and the second characteristic entry contains electrical characteristic information of a historical wheel speed signal.

[0008] Optionally, when the number of second characteristic entries in the self-learning database is greater than a first number threshold, the second processing unit is specifically configured to: Calculating the characteristic similarity between each second characteristic item in the self-learning database and the first characteristic item, to obtain the characteristic similarity corresponding to each second characteristic item; If the maximum similarity among the characteristic similarities exceeds the similarity threshold, the first device type corresponding to the first characteristic entry is obtained according to the category label of the second characteristic entry corresponding to the maximum similarity.

[0009] Optionally, the second processing unit is further configured to: updating a first confidence level of a second characteristic entry corresponding to a maximum similarity exceeding the similarity threshold to a second confidence level, where the second confidence level is greater than the first confidence level; If the second confidence is greater than the confidence threshold, the second feature entry and type label corresponding to the maximum similarity exceeding the similarity threshold are solidified into the persistent rule base or non-volatile memory of the self-learning database.

[0010] Optionally, the second processing unit is further configured to: If the maximum similarity among the characteristic similarities does not exceed the similarity threshold, the first characteristic item is classified and analyzed according to an electrical characteristic analysis method to obtain a first device type corresponding to the first characteristic item.

[0011] Optionally, when the number of second characteristic entries in the self-learning database is greater than a second number threshold and less than or equal to a first number threshold, the second processing unit is specifically configured to: Calculating the characteristic similarity between each second characteristic item in the self-learning database and the first characteristic item, to obtain the characteristic similarity corresponding to each second characteristic item; If the maximum similarity among the characteristic similarities exceeds the similarity threshold, obtaining the first intermediate type corresponding to the first characteristic entry according to the category label of the second characteristic entry corresponding to the maximum similarity; performing classification analysis on the first characteristic item according to an electrical characteristic analysis method to obtain a second intermediate type corresponding to the first characteristic item; If the first intermediate type and the second intermediate type are of the same type, the device types of the first intermediate type and the second intermediate type are used as the first device type corresponding to the first characteristic entry.

[0012] Optionally, the second processing unit is further configured to: If the first intermediate type and the second intermediate type are different, the device type of the second intermediate type is used as the first device type corresponding to the first characteristic entry.

[0013] Optionally, the second processing unit is further configured to: If the first intermediate type and the second intermediate type are of the same type, updating the third confidence of the second characteristic item corresponding to the maximum similarity exceeding the similarity threshold to a fourth confidence, where the fourth confidence is greater than the third confidence; If the fourth confidence level is greater than the confidence threshold, the second feature entry and the corresponding type label corresponding to the maximum similarity exceeding the similarity threshold are solidified into the persistent rule base or non-volatile memory of the self-learning database; If the first intermediate type and the second intermediate type are of different types, the third confidence of the second characteristic entry corresponding to the maximum similarity exceeding the similarity threshold is updated to a fifth confidence, and the fifth confidence is smaller than the third confidence.

[0014] Optionally, when the number of second characteristic entries in the self-learning database is less than or equal to a second number threshold, the transceiver unit is further configured to receive a current wheel speed signal, and obtain a third characteristic entry based on the current wheel speed signal, where the current wheel speed signal is generated by a current wheel speed sensor; The second processing unit is further used to classify and analyze the third characteristic item according to the electrical characteristic analysis method to obtain the third device type of the third wheel speed sensor corresponding to the third characteristic item; associate the third characteristic item with the third device type corresponding to the third characteristic item, and store them in the self-learning database.

[0015] Optionally, the second processing unit is further configured to associate the first characteristic entry with the first device type and store the association in a self-learning database.

[0016] Optionally, the electrical characteristics analysis method may be performed as follows: If the highest current value in the signal characteristic entry exceeds the current threshold, a cyclic redundancy check is performed on the transmission protocol identifier in the signal characteristic entry. If the check passes, it is determined that the target wheel speed sensor corresponding to the signal characteristic entry is an intelligent wheel speed sensor using a data transmission protocol, the signal characteristic entry is the first characteristic entry or the third characteristic entry, and the target wheel speed sensor is a newly installed wheel speed sensor or an existing wheel speed sensor. If the duty cycle in the signal characteristic entry is within a preset duty cycle range, and the deviation percentage of the square wave in the signal characteristic entry from the standard square wave is greater than a set percentage, determining that the target wheel speed sensor is an intelligent wheel speed sensor using pulse width modulation; If the voltage amplitude in the signal characteristic entry is within a preset amplitude range, and the frequency in the signal characteristic entry is within a preset frequency range, determining that the target wheel speed sensor is a non-intelligent wheel speed sensor; Or, the signal characteristic entry is classified based on a machine learning classifier to obtain the device type of the target wheel speed sensor corresponding to the signal characteristic entry.

[0017] Optionally, the first processing unit is further configured to: An input capture unit in the single-chip microcomputer is initialized and configured to be in a double-edge capture mode, where the input capture unit is used to obtain the first characteristic item according to the current wheel speed signal.

[0018] Optionally, the first processing unit is specifically configured to: Using a preset fault detection method to detect whether the current wheel speed signal is a fault signal, and when it is determined that the current wheel speed signal is not a fault signal, performing digital filtering processing on the current wheel speed signal to obtain a processed current wheel speed signal; The first characteristic item is obtained according to the processed current wheel speed signal.

[0019] Beneficial effects of this application: An embodiment of the present application provides a method for identifying the type of a wheel speed sensor. The method analyzes the current wheel speed signal generated by a newly installed wheel speed sensor to obtain a first characteristic entry of the current wheel speed signal. A set classification method is then used to determine the sensor type of the newly installed wheel speed sensor corresponding to the first characteristic entry based on each second characteristic entry and its respective category label in a self-learning database. This method automatically determines the device type of the wheel speed sensor based on the real-time wheel speed signal, accurately obtains the device type of the wheel speed sensor in use, and processes the received current wheel speed signal using a corresponding wheel speed signal processing method based on the automatically identified device type of the wheel speed sensor. This method solves the problem in related technologies of manually flashing or calibrating the device type of the wheel speed sensor in the ECU, which may result in incorrect device type settings, and solves the problem of inefficient wheel speed sensor replacement caused by manually flashing or calibrating the device type of the wheel speed sensor in the ECU. This method improves vehicle control accuracy and the efficiency of wheel speed sensor replacement.

[0020] These implementations or other implementations of the present application will be more concise and understandable in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0022] Figure 1 A schematic diagram of a wheel speed signal of an intelligent wheel speed sensor using a data transmission protocol provided in an embodiment of the present application; Figure 2 A schematic diagram of a wheel speed signal of an intelligent wheel speed sensor using pulse width modulation provided in an embodiment of the present application; Figure 3 A schematic diagram of a wheel speed signal of a non-intelligent wheel speed sensor provided in an embodiment of the present application; Figure 4 A simplified schematic diagram of the working process of an input capture unit and a comparator in a single-chip microcomputer provided in an embodiment of the present application; Figure 5 A schematic flow chart of a method for identifying the type of a wheel speed sensor provided in an embodiment of the present application; Figure 6A schematic flow chart of a method for identifying the type of a wheel speed sensor provided in an embodiment of the present application; Figure 7 A schematic flow chart of an analysis method based on an electrical characteristics analysis method provided in an embodiment of the present application; Figure 8 A schematic diagram of a wheel speed sensor type identification device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of this application more clear, this application will be further described in detail below with reference to the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0024] It should be understood that, in the description of this application, words such as "first" and "second" are only used for the purpose of distinguishing the description, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0025] IHB is a highly integrated brake-by-wire product that combines the functions of the electronic brake booster (EBB) and electronic stability control (ESC). This integration makes the vehicle's braking system more compact and lightweight, while also enabling more efficient braking. Wheel speed sensors play a crucial role in the One-Box system. They continuously monitor the rotational speed of each wheel and transmit this information to the electronic control unit (ECU) via the CAN bus. Based on this data, the ECU calculates the vehicle's speed and the speed differences between the wheels. This is essential for detecting slip or locking, implementing the anti-lock braking system (ABS), adjusting the traction control system (TCS), and ensuring the effectiveness of the vehicle stability control (ESC).

[0026] Because modern vehicles must be compatible with a variety of wheel speed sensor types, traditional ECUs must be pre-configured with the sensor type. Changing sensor types requires reflashing or recalibrating the ECU software. This leads to technical pain points such as the inability to recognize sensor type changes or abnormal switching in real time, and the lack of an automatic switching mechanism in the event of a single sensor failure. Furthermore, current technologies are limited, with most using pre-configured static recognition methods, simple type judgment based on fixed thresholds, and no online self-learning capabilities.

[0027] In light of this, embodiments of the present application provide a wheel speed sensor type identification method. This method receives and analyzes a current wheel speed signal generated by a newly installed wheel speed sensor to obtain a first characteristic item of the current wheel speed signal. Then, using a set classification method, the sensor type of the newly installed wheel speed sensor corresponding to the first characteristic item is determined based on each second characteristic item and its corresponding category label in a self-learning database (the second characteristic items and corresponding category labels are obtained based on historical wheel speed signals). This method automatically determines the device type of the wheel speed sensor based on the real-time wheel speed signal, accurately determining the device type of the wheel speed sensor in use. Based on the automatically identified device type of the wheel speed sensor, the received current wheel speed signal is processed using a corresponding wheel speed signal processing method. This method addresses the related art issue of manually flashing or calibrating the device type of a wheel speed sensor in an ECU, which can result in incorrect device type settings and inefficient wheel speed sensor replacement. This improves vehicle control accuracy and the efficiency of wheel speed sensor replacement.

[0028] Based on the foregoing, an embodiment of the present application provides a hardware interface configuration for implementing a method for identifying a wheel speed sensor type, including initializing an input capture unit in a single-chip microcontroller (MCU) and configuring the input capture unit to operate in dual-edge capture mode. The input capture unit is configured to obtain a first characteristic entry based on the current wheel speed signal. Specifically, if the current wheel speed signal is a pulse signal, output as a rectangular wave signal, before obtaining the first characteristic entry based on the current wheel speed signal, the ICU module (input capture unit) of the MCU (microcontroller) is initialized and configured to operate in dual-edge capture mode (rising edge + falling edge). This allows the input capture unit to comprehensively and accurately collect the signal characteristics of the current wheel speed signal and obtain the first characteristic entry.

[0029] In one embodiment, wheel speed sensors include three types of sensors: intelligent wheel speed sensors using the data transmission protocol (AK protocol), intelligent wheel speed sensors using pulse width modulation (PWM protocol), and non-intelligent wheel speed sensors. Wheel speed signals from different types of wheel speed sensors are not completely consistent. The edge triggering characteristics of the wheel speed signal from the intelligent wheel speed sensor using the data transmission protocol are rising edge triggering and falling edge triggering, and the wheel speed signal contains transmission protocol information and related wheel speed information; for example, Figure 1 The figure shows a schematic diagram of a wheel speed signal of an intelligent wheel speed sensor using a data transmission protocol provided in an embodiment of the present application. It should be noted that the wheel speed signal shown in the figure is only used to clearly illustrate the present solution and does not limit the specific implementation of the present solution. The edge triggering characteristics of the wheel speed signal of the intelligent wheel speed sensor using pulse width modulation are rising edge triggering and falling edge triggering. The wheel direction information and air gap information in the wheel speed signal are as follows; Figure 2The figure shows a schematic diagram of a wheel speed signal of an intelligent wheel speed sensor using pulse width modulation provided by an embodiment of the present application. It should be noted that the wheel speed signal shown in the figure is only used to clearly illustrate the present solution and does not limit the specific implementation of the present solution. The edge triggering feature of the wheel speed information of the non-intelligent wheel speed sensor is rising edge triggering, and the pulse width feature of the wheel speed signal is duty cycle; Figure 3 As shown, it is a schematic diagram of the wheel speed signal of a non-intelligent wheel speed sensor provided in an embodiment of the present application. It should be noted that the wheel speed signal in the diagram is only used to clearly illustrate the present solution and does not limit the specific implementation of the present solution.

[0030] In one embodiment, the input capture unit in the microcontroller is initialized and configured in a dual-edge capture mode (rising edge + falling edge), and direct memory access transmission is set. The captured timestamp information is directly stored in a ring buffer (the length can be defined according to requirements, 256 is used as an example here). Then, the comparator module is configured and three current threshold areas are set, including: low current area (0-7mA): invalid signal; medium current area (7-14mA): AK protocol signal speed signal; high current area (14-28mA): speed signal.

[0031] In one embodiment, Figure 1 The high current shown is 28mA. The "long teeth" in the half cycle represent the information of the wheel speed signal, and multiple "short teeth" represent the transmission protocol identifier of the AK protocol. Its waveform generation threshold is 7mA, 14mA, and 28mA. Figure 2 The high current shown is 14mA, and its waveform generation thresholds are 7mA and 14mA. Figure 3 The high current shown is 14mA, and its waveform generation thresholds are 7mA and 14mA.

[0032] Based on the three types of wheel speed sensors described above, the wheel speed sensor type identification method is implemented. For intelligent wheel speed sensors using the AK protocol, a high-current detection channel is added, along with an SPI interface (the SPI interface reads AK protocol data), dual-edge capture is enabled, and a comparator is used. For intelligent wheel speed sensors using the PWM protocol, dual-edge capture is enabled, along with a comparator. For non-intelligent wheel speed sensors, only the comparator is enabled. Furthermore, a digital-to-analog converter is used to acquire channel voltage amplitude, current value, and other information.

[0033] In one embodiment, if Figure 4As shown, it is a simple schematic diagram of the working process of the input capture unit and comparator in a single-chip microcomputer provided by an embodiment of the present application; when targeting an intelligent wheel speed sensor using a data transmission protocol, the input capture unit is enabled, the current detection channel of the input capture unit is initialized, and based on the configured double-edge capture, the upper edge and lower edge of the wheel speed signal are detected, and the timestamp is enabled to obtain timestamp information including the upper edge time information and the lower edge time information, and also obtains information such as current and / or voltage. Based on the configured direct memory access, the obtained timestamp information and information such as current and / or voltage are stored in a ring buffer, so as to facilitate subsequent comparison based on the medium current and low current comparators, and comparison based on the medium current and high current comparators, to determine the device type of the intelligent wheel speed sensor using the data transmission protocol. When targeting an intelligent wheel speed sensor using pulse width modulation, the input capture unit is enabled, its current detection channel is initialized, and based on the configured dual-edge capture, the rising and falling edges of the wheel speed signal are detected. Timestamp information containing the time information of the rising and falling edges is enabled, and current and / or voltage information is also obtained. Based on the configured direct memory access, the obtained timestamp information and current and / or voltage information are stored in a ring buffer for subsequent comparison based on the medium current and low current comparators to determine the device type of the intelligent wheel speed sensor using pulse width modulation. When targeting a non-intelligent wheel speed sensor, the input capture unit is disabled, and only the rising edge of the wheel speed signal is detected to obtain timestamp information containing the time information of the rising edge. Current and / or voltage information is also obtained. Based on the configured direct memory access, the obtained timestamp information and current and / or voltage information are stored in a ring buffer for subsequent comparison based on the medium current and low current comparators to determine the device type of the non-intelligent wheel speed sensor.

[0034] See also Figure 5 As shown, an embodiment of the present application provides a method for identifying the type of a wheel speed sensor, the method comprising: Step 501: Receive a current wheel speed signal, where the current wheel speed signal is generated by a newly installed wheel speed sensor.

[0035] In one embodiment, the current wheel speed signal is a wheel speed signal currently received and being processed.

[0036] Step 502: Obtain a first characteristic entry according to the current wheel speed signal, where the first characteristic entry includes electrical characteristic information of the current wheel speed signal.

[0037] In one embodiment, the timestamp information of the edge of the current wheel speed signal is obtained. According to the time difference between the upper and lower edges, the duration of the high level and the low level can be obtained. The current and voltage information of the high level and the low level can also be obtained to obtain the first characteristic entry. That is, the first characteristic entry can include the current and voltage information of the high level and the low level and their duration.

[0038] Step 503: Based on the set classification method, the first characteristic entry is classified using each second characteristic entry in the self-learning database and the respective category label of each second characteristic entry to obtain the first device type corresponding to the first characteristic entry. The first device type is used to characterize the sensor type of the newly installed wheel speed sensor, and the category label is used to characterize the sensor type of the sensor to which the corresponding second characteristic entry belongs. The second characteristic entry contains electrical characteristic information of the historical wheel speed signal.

[0039] In one embodiment, after step 503, step 504 may be further included to associate the first characteristic entry with the first device type and store the associated information in a self-learning database. Thus, upon receiving the next wheel speed signal, the first characteristic entry and the first device type may serve as the second characteristic entry and corresponding type tag for the next wheel speed signal.

[0040] In one embodiment, the above Figure 5 In the method flow, in the process of analyzing and obtaining the device type of the newly installed wheel speed sensor in step 503, the analysis time must not exceed a certain time limit. If it exceeds, the analysis and identification process is terminated and fault detection is directly performed.

[0041] In one embodiment, the self-learning database may include multiple second characteristic entries and their respective type tags. The second characteristic entries and type tags are obtained based on historical wheel speed signals. That is, the second characteristic entries may include high-level and low-level current and voltage information of the historical wheel speed signals and their duration. The corresponding type tag can characterize the device type of the sensor that issued the historical wheel speed signal.

[0042] In one embodiment, the classification method is set to a clustering method, the first characteristic entry and the second characteristic entry are clustered, and the category label of the second characteristic entry closest to the cluster where the first characteristic entry is located is used as the first device type of the first characteristic entry.

[0043] In one embodiment, the above-mentioned wheel speed sensor type identification method can be used to implement a wheel speed sensor adaptive identification system based on the RH850 / U2A microcontroller (main feature: multi-core processor, usually including two independent CPU cores, supporting multi-threaded processing, improving multi-tasking capabilities and real-time performance).

[0044] The above method can automatically identify three mainstream wheel speed sensor types: non-intelligent wheel speed sensors, intelligent PWM wheel speed sensors with direction recognition, and AK protocol intelligent wheel speed sensors. This completes wheel speed sensor type identification without pre-configuring sensor type parameters, thereby obtaining accurate wheel speed information, which is beneficial for subsequent vehicle control or decision-making modules to perform further action processing.

[0045] Based on the above Figure 5 In the method flow, the embodiment of the present application provides a method for identifying the type of a wheel speed sensor. In step 502, a first characteristic item is obtained according to the current wheel speed signal, including: Step 5021: Use a preset fault detection method to detect whether the current wheel speed signal is a fault signal. When it is determined that the current wheel speed signal is not a fault signal, perform digital filtering on the current wheel speed signal to obtain a processed current wheel speed signal.

[0046] Step 5022: Obtain a first characteristic item according to the processed current wheel speed signal.

[0047] In one embodiment, each time a current wheel speed signal is obtained, before obtaining the first characteristic item based on the current wheel speed signal, it is preferably to first detect whether the current wheel speed signal is a fault signal. If the current wheel speed signal is a fault signal, the information it contains is wrong or meaningless, and it is unnecessary to further analyze and process the current wheel speed signal. Therefore, after confirming that the current wheel speed signal is not a fault signal, the current wheel speed signal is filtered to remove high-frequency noise, and the signal is smoothed using a moving average. Signal loss is detected and compensated, thereby improving the quality of the current wheel speed signal.

[0048] In one embodiment, for fault safety and diagnosis, the processing flow is primarily responsible for continuously monitoring the status of a newly installed wheel speed sensor and responding to abnormalities. The process includes: ① initializing channel status: maintaining each channel independent and using static variables to maintain persistence across calls; ② signal quality monitoring: updating the current wheel speed signal quality. If it is below a threshold, it is determined to be in a signal loss state, and then fault processing is performed, terminating subsequent logic processing; ③ type change detection: if a change in the wheel speed sensor type is detected, the old device type is recorded and updated to the new device type (this process step is performed after the device type corresponding to the first characteristic entry is confirmed based on the wheel speed sensor type identification method of the present application); ④ parameter range detection: detecting whether key parameters exceed a reasonable range based on the signal type of the current wheel speed signal. If so, a corresponding fault code is set; ⑤ specific protocol error detection: performing a CRC check (cyclic redundancy check for transmission protocol identifier) ​​on the AK protocol data of the intelligent wheel speed sensor using the data transmission protocol. If the check fails, a CRC error is marked (performed during the electrical characteristics analysis process); ⑥ fault handling and last valid time update: if the above detection results indicate a fault, a unified processing function is called to handle it; otherwise, the last valid time is updated.

[0049] In one embodiment, Figure 6 FIG. 1 is a flow chart of a method for identifying the type of a wheel speed sensor provided by an embodiment of the present application, comprising: upon receiving a current wheel speed signal, starting identification processing, first checking whether the current wheel speed signal is faulty, and if so, ending the identification processing; if not, the current wheel speed signal (the signal of the newly installed wheel speed sensor) is input normally, and then using a signal characteristic extraction module to extract electrical characteristic features of the current wheel speed signal to obtain a first characteristic entry, and then, The classification method is set as a signal category recognition engine, and combined with the self-learning database, the first characteristic item is identified and processed to obtain the first device type corresponding to the current wheel speed signal, and then enter the wheel speed calculation process to control the vehicle driving state through the vehicle control decision system; if during the identification process of the first characteristic item, a wheel logic fault determines that the current wheel speed signal corresponding to the first characteristic item is a fault signal, corresponding relief measures can also be adopted through the vehicle control decision system.

[0050] Based on the above Figure 5 The method flow in the embodiment of the present application comprises a method for identifying the type of wheel speed sensor, which has three processing stages. In the first stage, the number of second characteristic entries in the self-learning database O≤the second quantity threshold Q2, the second stage is the first quantity threshold Q1≥the second characteristic entry number O in the self-learning database>the second quantity threshold Q2, and the third stage is the number of second characteristic entries in the self-learning database O>the first quantity threshold Q1.

[0051] Phase 1 (number of second characteristic entries O ≤ second quantity threshold Q2): Before the above step 501, in which the current wheel speed signal is received, the following steps are further included: Step A: Receive a current wheel speed signal, and obtain a third characteristic item according to the current wheel speed signal. The current wheel speed signal is generated by a current wheel speed sensor.

[0052] Step B: Classify and analyze the third characteristic item according to the electrical characteristic analysis method to obtain the third device type of the third wheel speed sensor corresponding to the third characteristic item.

[0053] Step C: Associating the third characteristic entry with the third device type corresponding to the third characteristic entry, and storing the associations in a self-learning database.

[0054] In one embodiment, the electrical characteristics analysis process is as follows: Step B11: If the highest current value in the third characteristic entry exceeds the current threshold, a cyclic redundancy check is performed on the transmission protocol identifier in the third characteristic entry. If the check passes, it is determined that the current wheel speed sensor corresponding to the third characteristic entry is an intelligent wheel speed sensor using a data transmission protocol.

[0055] Step B12: If the duty cycle in the third characteristic item is within the preset duty cycle range, and the deviation percentage of the square wave in the third characteristic item from the standard square wave is greater than the set percentage, it is determined that the current wheel speed sensor is an intelligent wheel speed sensor using pulse width modulation.

[0056] Step B13: If the voltage amplitude in the third characteristic item is within the preset amplitude range, and the frequency in the third characteristic item is within the preset frequency range, it is determined that the current wheel speed sensor is a non-intelligent wheel speed sensor.

[0057] Step B14, or classify the third characteristic item based on the machine learning classifier to obtain the device type of the current wheel speed sensor corresponding to the third characteristic item. That is to say, the electrical characteristic analysis method can use the analysis method in steps B11, B12, and B13 to determine the device type of the current wheel speed sensor, or it can also use the analysis method in B14 to determine the device type of the current wheel speed sensor. In other words, the electrical characteristic analysis method can only execute the analysis method in steps B11, B12, and B13, or it can only execute the analysis method in step B14. Among them, the machine learning classifier can be a neural network algorithm, or a decision tree, or a fuzzy classification mechanism, or it can also be a combination algorithm of the aforementioned classification methods. The specific structure of the machine learning classifier is not limited here and can be set as needed.

[0058] In one embodiment, the electrical characteristics analysis process is as follows: Step B21: If the highest current value in the third characteristic entry exceeds the current threshold, a cyclic redundancy check is performed on the transmission protocol identifier in the third characteristic entry. If the check passes, the current wheel speed sensor corresponding to the third characteristic entry is determined to be an intelligent wheel speed sensor using the data transmission protocol. If the highest current value in the third characteristic entry does not exceed the current threshold, or if the check fails, step B22 may be executed.

[0059] Step B22: If the duty cycle in the third characteristic item is within the preset duty cycle range, and the deviation percentage of the square wave in the third characteristic item from the standard square wave is greater than the set percentage, the current wheel speed sensor is determined to be an intelligent wheel speed sensor using pulse width modulation. If the duty cycle in the third characteristic item is not within the preset duty cycle range, and the deviation percentage of the square wave in the third characteristic item from the standard square wave is not less than the set percentage, step B23 may be executed.

[0060] Step B23: If the voltage amplitude in the third characteristic item is within the preset amplitude range, and the frequency in the third characteristic item is within the preset frequency range, then the current wheel speed sensor is determined to be a non-intelligent wheel speed sensor. If the voltage amplitude in the third characteristic item is not within the preset amplitude range, and the frequency in the third characteristic item is not within the preset frequency range, then step B24 may be executed.

[0061] Step B24: If B21, B22, and B23 are unable to obtain the device type of the current wheel speed sensor, the third characteristic item is classified based on the machine learning classifier to obtain the device type of the current wheel speed sensor corresponding to the third characteristic item.

[0062] In one embodiment, Figure 7 FIG. 1 is a flow chart of an analysis method based on an electrical characteristics analysis method provided in an embodiment of the present application, including: In step B21, the judgment conditions corresponding to the intelligent wheel speed sensor using the data transmission protocol include whether the highest current value in the third characteristic item exceeds the current threshold, whether the AK protocol feature setting (transmission protocol identifier) ​​and its CRC (cyclic redundancy check) are valid (if valid, the cyclic redundancy check can pass; otherwise, it cannot pass).

[0063] In step B22, the judgment conditions corresponding to the intelligent wheel speed sensor using pulse width modulation include whether the duty cycle in the third characteristic item is within 30%-70% (preset duty cycle range) and whether the deviation percentage of the square wave in the third characteristic item from the standard square wave is greater than 10% (set percentage).

[0064] Among them, because intelligent wheel speed sensors using pulse width modulation generate asymmetric pulse signals, they are usually accompanied by information such as wheel direction and air gap fault. If the duty cycle is determined to be within the valid range (preset duty cycle range) and the duty cycle deviates from the standard square wave (10%) by more than the set threshold, it is determined to be an intelligent wheel speed sensor using pulse width modulation. Figure 7 A duty cycle between 30% and 70% and >10% deviation from 50% refers to an intelligent wheel speed sensor using pulse width modulation (PWM) that does not have a 50% duty cycle. Assuming a period of 300µs and a high-level duration of 90µs, indicating a left turn, the duty cycle equals high-level duration / period = 30%. Conversely, if the high-level duration is 180µs, the duty cycle is 60%, and so on. Of course, at different vehicle speeds, the high and low-level durations may not be 90µs or 180µs; this depends on the specification or sensor characteristics. A deviation of >10% from 50% means the PWM waveform deviates from the center point by more than 10%.

[0065] In step B23, the judgment conditions corresponding to the non-intelligent wheel speed sensor include whether the voltage amplitude in the third characteristic item is within 0.5-4V (preset amplitude range) and the frequency in the third characteristic item is within 50-500Hz (preset frequency range).

[0066] Since non-intelligent wheel speed sensors generate the most basic wheel speed signal, they only need to meet basic electrical characteristics—that is, the voltage amplitude and frequency must be within a reasonable range—to be classified as non-intelligent. For example, an amplitude of 0.5V to 4V refers to the voltage sampled by the MCU. This is because the sensor emits a current signal, approximately in the range of 7mA, 14mA, and 28mA. However, the MCU can only sample voltage, so hardware processing is required. The frequency corresponds to the speed range, with 50Hz corresponding to a speed range of 1kph to 120kph.

[0067] Step B24: If steps B21, B22, and B23 are all unable to obtain the device type of the current wheel speed sensor, classify the third characteristic entry based on a machine learning classifier to obtain the device type of the current wheel speed sensor corresponding to the third characteristic entry. The machine learning classifier may be a neural network algorithm.

[0068] Finally, if the device type of the current wheel speed sensor corresponding to the third characteristic entry is obtained through steps B21, B22, B23, and B24, the third characteristic entry and the corresponding third device type can be associated and stored in the self-learning database to construct the self-learning database. If step B24 also fails to obtain the device type of the current wheel speed sensor corresponding to the third characteristic entry, the third characteristic entry can be marked as faulty.

[0069] The above, in the first stage, may be the process of building a self-learning database.

[0070] Second stage (first quantity threshold Q1 ≥ second characteristic item quantity O > second quantity threshold Q2): Based on the above Figure 5 Method flow: In an embodiment of the present application, a method for identifying the type of a wheel speed sensor is provided. When the number O of second characteristic entries in a self-learning database is greater than a second number threshold Q2 and less than or equal to a first number threshold Q1, in step 503, based on a set classification method, the first characteristic entries are classified using each second characteristic entry in the self-learning database and the respective category labels of each second characteristic entry to obtain a first device type corresponding to the first characteristic entry, including: Step 5031: Calculate the characteristic similarity between each second characteristic item in the self-learning database and the first characteristic item, and obtain the characteristic similarity corresponding to each second characteristic item.

[0071] Step 5032: If the maximum similarity among the characteristic similarities exceeds the similarity threshold, the first intermediate type corresponding to the first characteristic entry is obtained according to the category label of the second characteristic entry corresponding to the maximum similarity.

[0072] Note: If the maximum similarity among the characteristic similarities does not exceed the similarity threshold, the electrical characteristic analysis method is directly used to obtain the second intermediate type of the first characteristic item, and the second intermediate type is used as the first device type.

[0073] Step 5033: Classify and analyze the first characteristic item according to the electrical characteristic analysis method to obtain a second intermediate type corresponding to the first characteristic item.

[0074] Step 5034: If the first intermediate type and the second intermediate type are of the same type, the device type of the first intermediate type and the second intermediate type is used as the first device type corresponding to the first feature entry. If the first intermediate type and the second intermediate type are of different types, step 5035 is executed.

[0075] Step 5035: If the first intermediate type and the second intermediate type are different, the device type of the second intermediate type is used as the first device type corresponding to the first characteristic entry.

[0076] Step 5036: If the first intermediate type and the second intermediate type are of the same type, the third confidence of the second characteristic item corresponding to the maximum similarity exceeding the similarity threshold is updated to a fourth confidence, and the fourth confidence is greater than the third confidence.

[0077] Step 5037: If the fourth confidence is greater than the confidence threshold, the second feature entry and the corresponding type label corresponding to the maximum similarity exceeding the similarity threshold are solidified into the persistent rule base or non-volatile memory of the self-learning database.

[0078] Step 5038: If the first intermediate type and the second intermediate type are of different types, the third confidence of the second characteristic item corresponding to the maximum similarity exceeding the similarity threshold is updated to a fifth confidence, and the fifth confidence is less than the third confidence.

[0079] In the second phase, the self-learning database and the electrical characteristics analysis method can be mutually verified. It should be noted that the above method flow is merely an example, and the execution order of the method steps does not completely follow the order indicated by the numerical scale. For example, steps 5031-5034, 5036, and 5037 can be executed to represent a process flow in which the first intermediate type and the second intermediate type are of the same type. Alternatively, steps 5031-5033, 5035, and 5038 can be executed to represent a process flow in which the first intermediate type and the second intermediate type are of different types.

[0080] Phase 3 (number of second characteristic entries O> first threshold Q1): Based on the above Figure 5 Method flow: In an embodiment of the present application, a method for identifying the type of a wheel speed sensor is provided. When the number O of second characteristic entries in a self-learning database is greater than a first number threshold Q1, in step 503, based on a set classification method, the first characteristic entries are classified using each second characteristic entry in the self-learning database and the respective category labels of each second characteristic entry to obtain a first device type corresponding to the first characteristic entry, including: Step 503 - 1 : Calculate the characteristic similarity between each second characteristic item in the self-learning database and the first characteristic item, and obtain the characteristic similarity corresponding to each second characteristic item.

[0081] Step 503-2: If the maximum similarity among the characteristic similarities exceeds the similarity threshold, the first device type corresponding to the first characteristic entry is obtained based on the category label of the second characteristic entry corresponding to the maximum similarity. If the maximum similarity among the characteristic similarities does not exceed the similarity threshold, step 503-5 is executed.

[0082] Step 503 - 3 : Update the first confidence of the second characteristic item corresponding to the maximum similarity exceeding the similarity threshold to a second confidence, where the second confidence is greater than the first confidence.

[0083] Step 503-4: If the second confidence is greater than the confidence threshold, the second feature entry and type label corresponding to the maximum similarity exceeding the similarity threshold are solidified into the persistent rule base or non-volatile memory of the self-learning database.

[0084] Step 503 - 5 : If the maximum similarity among the characteristic similarities does not exceed the similarity threshold, classify and analyze the first characteristic entry according to the electrical characteristic analysis method to obtain the first device type corresponding to the first characteristic entry.

[0085] Based on the above method flows, embodiments of the present application provide an analysis method flow for an electrical characteristic analysis method, wherein the signal characteristic item may be referred to as a first characteristic item or a third characteristic item, and the target wheel speed sensor may be referred to as a newly installed wheel speed sensor or a current wheel speed sensor. The steps are as follows: Step a: If the highest current value in the signal characteristic entry exceeds the current threshold, a cyclic redundancy check is performed on the transmission protocol identifier in the signal characteristic entry. If the check passes, it is determined that the target wheel speed sensor corresponding to the signal characteristic entry is an intelligent wheel speed sensor using a data transmission protocol.

[0086] Step b: If the duty cycle in the signal characteristic entry is within a preset duty cycle range, and the deviation percentage of the square wave in the signal characteristic entry from the standard square wave is greater than a set percentage, it is determined that the target wheel speed sensor is an intelligent wheel speed sensor using pulse width modulation.

[0087] Step c: If the voltage amplitude in the signal characteristic entry is within a preset amplitude range, and the frequency in the signal characteristic entry is within a preset frequency range, then it is determined that the target wheel speed sensor is a non-intelligent wheel speed sensor.

[0088] Step d: classify the signal characteristic entries based on a machine learning classifier to obtain the device type of the target wheel speed sensor corresponding to the signal characteristic entries.

[0089] Based on the method flow of steps ad above, the embodiment of the present application provides another analysis method flow of the electrical characteristic analysis method, wherein the signal characteristic item can refer to the first characteristic item or the third characteristic item, and the target wheel speed sensor can refer to the newly installed wheel speed sensor or the current wheel speed sensor. The steps are as follows: In step a', if the highest current value in the signal characteristic entry exceeds the current threshold, a cyclic redundancy check is performed on the transmission protocol identifier in the signal characteristic entry. If the check passes, the target wheel speed sensor corresponding to the signal characteristic entry is determined to be an intelligent wheel speed sensor using the data transmission protocol. If the highest current value in the signal characteristic entry does not exceed the current threshold, or if the check passes, step b' is executed.

[0090] In step b', if the duty cycle in the signal characteristic entry is within the preset duty cycle range, and the deviation percentage of the square wave in the signal characteristic entry from the standard square wave is greater than a set percentage, the target wheel speed sensor is determined to be an intelligent wheel speed sensor using pulse width modulation. If the duty cycle in the signal characteristic entry is not within the preset duty cycle range, or the deviation percentage of the square wave in the signal characteristic entry from the standard square wave is not greater than a set percentage, step c' is executed.

[0091] Step c': If the voltage amplitude in the signal characteristic entry is within the preset amplitude range, and the frequency in the signal characteristic entry is within the preset frequency range, then the target wheel speed sensor is determined to be a non-intelligent wheel speed sensor. If the voltage amplitude in the signal characteristic entry is not within the preset amplitude range, and the frequency in the signal characteristic entry is not within the preset frequency range, then proceed to step d'.

[0092] Step d': classify the signal characteristic items based on the machine learning classifier to obtain the device type of the target wheel speed sensor corresponding to the signal characteristic items.

[0093] Based on the same concept, the embodiment of the present application provides a type identification device for a wheel speed sensor. Figure 8 A schematic diagram of a type identification device for a wheel speed sensor provided in an embodiment of the present application is shown in FIG. Figure 8 including: The transceiver unit 801 is used to receive the current wheel speed signal generated by the newly installed wheel speed sensor; A first processing unit 802 is configured to obtain a first characteristic entry according to the current wheel speed signal, wherein the first characteristic entry includes electrical characteristic information of the current wheel speed signal; The second processing unit 803 is used to classify the first characteristic entry based on the set classification method, using each second characteristic entry in the self-learning database and the category label of each second characteristic entry to obtain a first device type corresponding to the first characteristic entry, where the first device type is used to characterize the sensor type of the newly installed wheel speed sensor, and the category label is used to characterize the sensor type of the sensor to which the corresponding second characteristic entry belongs, and the second characteristic entry contains electrical characteristic information of the historical wheel speed signal.

[0094] Optionally, when the number of second characteristic entries in the self-learning database is greater than a first number threshold, the second processing unit 803 is specifically configured to: Calculating the characteristic similarity between each second characteristic item in the self-learning database and the first characteristic item, to obtain the characteristic similarity corresponding to each second characteristic item; If the maximum similarity among the characteristic similarities exceeds the similarity threshold, the first device type corresponding to the first characteristic entry is obtained according to the category label of the second characteristic entry corresponding to the maximum similarity.

[0095] Optionally, the second processing unit 803 is further configured to: updating a first confidence level of a second characteristic entry corresponding to a maximum similarity exceeding the similarity threshold to a second confidence level, where the second confidence level is greater than the first confidence level; If the second confidence is greater than the confidence threshold, the second feature entry and type label corresponding to the maximum similarity exceeding the similarity threshold are solidified into the persistent rule base or non-volatile memory of the self-learning database.

[0096] Optionally, the second processing unit 803 is further configured to: If the maximum similarity among the characteristic similarities does not exceed the similarity threshold, the first characteristic item is classified and analyzed according to an electrical characteristic analysis method to obtain a first device type corresponding to the first characteristic item.

[0097] Optionally, when the number of second characteristic entries in the self-learning database is greater than a second number threshold and less than or equal to a first number threshold, the second processing unit 803 is specifically configured to: Calculating the characteristic similarity between each second characteristic item in the self-learning database and the first characteristic item, to obtain the characteristic similarity corresponding to each second characteristic item; If the maximum similarity among the characteristic similarities exceeds the similarity threshold, obtaining the first intermediate type corresponding to the first characteristic entry according to the category label of the second characteristic entry corresponding to the maximum similarity; performing classification analysis on the first characteristic item according to an electrical characteristic analysis method to obtain a second intermediate type corresponding to the first characteristic item; If the first intermediate type and the second intermediate type are of the same type, the device types of the first intermediate type and the second intermediate type are used as the first device type corresponding to the first characteristic entry.

[0098] Optionally, the second processing unit 803 is further configured to: If the first intermediate type and the second intermediate type are different, the device type of the second intermediate type is used as the first device type corresponding to the first characteristic entry.

[0099] Optionally, the second processing unit 803 is further configured to: If the first intermediate type and the second intermediate type are of the same type, updating the third confidence of the second characteristic item corresponding to the maximum similarity exceeding the similarity threshold to a fourth confidence, where the fourth confidence is greater than the third confidence; If the fourth confidence level is greater than the confidence threshold, the second feature entry and the corresponding type label corresponding to the maximum similarity exceeding the similarity threshold are solidified into the persistent rule base or non-volatile memory of the self-learning database; If the first intermediate type and the second intermediate type are of different types, the third confidence of the second characteristic entry corresponding to the maximum similarity exceeding the similarity threshold is updated to a fifth confidence, and the fifth confidence is smaller than the third confidence.

[0100] Optionally, when the number of second characteristic entries in the self-learning database is less than or equal to a second number threshold, the transceiver unit 801 is further configured to receive a current wheel speed signal, and obtain a third characteristic entry based on the current wheel speed signal, where the current wheel speed signal is generated by a current wheel speed sensor; The second processing unit 803 is further used to classify and analyze the third characteristic item according to the electrical characteristic analysis method to obtain the third device type of the third wheel speed sensor corresponding to the third characteristic item; associate the third characteristic item with the third device type corresponding to the third characteristic item, and store them in the self-learning database.

[0101] Optionally, the second processing unit 803 is further configured to associate the first characteristic item with the first device type and store the association in a self-learning database.

[0102] Optionally, the electrical characteristics analysis method may be performed as follows: If the highest current value in the signal characteristic entry exceeds the current threshold, a cyclic redundancy check is performed on the transmission protocol identifier in the signal characteristic entry. If the check passes, it is determined that the target wheel speed sensor corresponding to the signal characteristic entry is an intelligent wheel speed sensor using a data transmission protocol, the signal characteristic entry is the first characteristic entry or the third characteristic entry, and the target wheel speed sensor is a newly installed wheel speed sensor or an existing wheel speed sensor. If the duty cycle in the signal characteristic entry is within a preset duty cycle range, and the deviation percentage of the square wave in the signal characteristic entry from the standard square wave is greater than a set percentage, determining that the target wheel speed sensor is an intelligent wheel speed sensor using pulse width modulation; If the voltage amplitude in the signal characteristic entry is within a preset amplitude range, and the frequency in the signal characteristic entry is within a preset frequency range, determining that the target wheel speed sensor is a non-intelligent wheel speed sensor; Or, the signal characteristic entry is classified based on a machine learning classifier to obtain the device type of the target wheel speed sensor corresponding to the signal characteristic entry.

[0103] Optionally, the first processing unit 802 is further configured to: An input capture unit in the single-chip microcomputer is initialized and configured to be in a double-edge capture mode, where the input capture unit is used to obtain the first characteristic item according to the current wheel speed signal.

[0104] Optionally, the first processing unit 802 is specifically configured to: Using a preset fault detection method to detect whether the current wheel speed signal is a fault signal, and when it is determined that the current wheel speed signal is not a fault signal, performing digital filtering processing on the current wheel speed signal to obtain a processed current wheel speed signal; The first characteristic item is obtained according to the processed current wheel speed signal.

[0105] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0107] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0109] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for identifying the type of a wheel speed sensor, characterized in that: The method comprises: receiving a current wheel speed signal generated by a newly installed wheel speed sensor; acquiring a first characteristic entry according to the current wheel speed signal, wherein the first characteristic entry includes electrical characteristic information of the current wheel speed signal; Based on the set classification method, the first characteristic entry is classified using each second characteristic entry in the self-learning database and the category label of each second characteristic entry to obtain the first device type corresponding to the first characteristic entry. The first device type is used to characterize the sensor type of the newly installed wheel speed sensor, and the category label is used to characterize the sensor type of the sensor to which the corresponding second characteristic entry belongs. The second characteristic entry contains electrical characteristic information of the historical wheel speed signal.

2. The method for identifying the type of a wheel speed sensor according to claim 1, wherein: When the number of second characteristic entries in the self-learning database is greater than a first number threshold, the classifying the first characteristic entry based on the set classification method using each second characteristic entry in the self-learning database and a category label of each second characteristic entry to obtain a first device type corresponding to the first characteristic entry includes: Calculating the characteristic similarity between each second characteristic item in the self-learning database and the first characteristic item, to obtain the characteristic similarity corresponding to each second characteristic item; If the maximum similarity among the characteristic similarities exceeds the similarity threshold, the first device type corresponding to the first characteristic entry is obtained according to the category label of the second characteristic entry corresponding to the maximum similarity.

3. The method for identifying the type of a wheel speed sensor as claimed in claim 2, wherein: After obtaining the first device type corresponding to the first characteristic entry according to the category label of the second characteristic entry corresponding to the maximum similarity, the method further includes: updating a first confidence level of a second characteristic entry corresponding to a maximum similarity exceeding the similarity threshold to a second confidence level, where the second confidence level is greater than the first confidence level; If the second confidence is greater than the confidence threshold, the second feature entry and type label corresponding to the maximum similarity exceeding the similarity threshold are solidified into the persistent rule base or non-volatile memory of the self-learning database.

4. The method for identifying the type of a wheel speed sensor as claimed in claim 2, wherein: Also includes: If the maximum similarity among the characteristic similarities does not exceed the similarity threshold, the first characteristic item is classified and analyzed according to an electrical characteristic analysis method to obtain a first device type corresponding to the first characteristic item.

5. The method for identifying the type of a wheel speed sensor as claimed in claim 1, wherein: When the number of second characteristic entries in the self-learning database is greater than a second number threshold and less than or equal to a first number threshold, the classifying the first characteristic entry based on the set classification method using each second characteristic entry in the self-learning database and a category label of each second characteristic entry to obtain a first device type corresponding to the first characteristic entry includes: Calculating the characteristic similarity between each second characteristic item in the self-learning database and the first characteristic item, to obtain the characteristic similarity corresponding to each second characteristic item; If the maximum similarity among the characteristic similarities exceeds the similarity threshold, obtaining the first intermediate type corresponding to the first characteristic entry according to the category label of the second characteristic entry corresponding to the maximum similarity; performing classification analysis on the first characteristic item according to an electrical characteristic analysis method to obtain a second intermediate type corresponding to the first characteristic item; If the first intermediate type and the second intermediate type are of the same type, the device types of the first intermediate type and the second intermediate type are used as the first device type corresponding to the first characteristic entry.

6. The method for identifying the type of a wheel speed sensor as claimed in claim 5, wherein: Also includes: If the first intermediate type and the second intermediate type are different, the device type of the second intermediate type is used as the first device type corresponding to the first characteristic entry.

7. The method for identifying the type of a wheel speed sensor according to claim 6, wherein: Also includes: If the first intermediate type and the second intermediate type are of the same type, updating the third confidence of the second characteristic item corresponding to the maximum similarity exceeding the similarity threshold to a fourth confidence, where the fourth confidence is greater than the third confidence; If the fourth confidence level is greater than the confidence threshold, the second feature entry and the corresponding type label corresponding to the maximum similarity exceeding the similarity threshold are solidified into the persistent rule base or non-volatile memory of the self-learning database; If the first intermediate type and the second intermediate type are of different types, the third confidence of the second characteristic entry corresponding to the maximum similarity exceeding the similarity threshold is updated to a fifth confidence, and the fifth confidence is smaller than the third confidence.

8. The method for identifying the type of a wheel speed sensor as claimed in claim 1, wherein: When the number of second characteristic entries in the self-learning database is less than or equal to a second number threshold, before receiving the current wheel speed signal, the method further includes: receiving a current wheel speed signal, and obtaining a third characteristic item according to the current wheel speed signal, wherein the current wheel speed signal is generated by a current wheel speed sensor; performing classification analysis on the third characteristic item according to an electrical characteristic analysis method to obtain a third device type of the third wheel speed sensor corresponding to the third characteristic item; The third characteristic entry and the third device type corresponding to the third characteristic entry are associated and stored in the self-learning database.

9. The method for identifying the type of a wheel speed sensor as claimed in claim 1, wherein: After obtaining the first device type corresponding to the first characteristic entry, the method further includes: The first characteristic entry is associated with the first device type and stored in a self-learning database.

10. The method for identifying the type of a wheel speed sensor according to any one of claims 4 to 8, wherein: The electrical characteristics analysis method analysis process is as follows: If the highest current value in the signal characteristic entry exceeds the current threshold, a cyclic redundancy check is performed on the transmission protocol identifier in the signal characteristic entry. If the check passes, it is determined that the target wheel speed sensor corresponding to the signal characteristic entry is an intelligent wheel speed sensor using a data transmission protocol, the signal characteristic entry is the first characteristic entry or the third characteristic entry, and the target wheel speed sensor is a newly installed wheel speed sensor or an existing wheel speed sensor. If the duty cycle in the signal characteristic entry is within a preset duty cycle range, and the deviation percentage of the square wave in the signal characteristic entry from the standard square wave is greater than a set percentage, determining that the target wheel speed sensor is an intelligent wheel speed sensor using pulse width modulation; If the voltage amplitude in the signal characteristic entry is within a preset amplitude range, and the frequency in the signal characteristic entry is within a preset frequency range, determining that the target wheel speed sensor is a non-intelligent wheel speed sensor; Or, the signal characteristic entry is classified based on a machine learning classifier to obtain the device type of the target wheel speed sensor corresponding to the signal characteristic entry.

11. The method for identifying the type of a wheel speed sensor according to any one of claims 1 to 9, wherein: The current wheel speed signal is a pulse signal. Before obtaining the first characteristic item according to the current wheel speed signal, the method further includes: An input capture unit in the single-chip microcomputer is initialized and configured to be in a double-edge capture mode, where the input capture unit is used to obtain the first characteristic item according to the current wheel speed signal.

12. The method for identifying the type of a wheel speed sensor according to any one of claims 1 to 9, wherein: The acquiring a first characteristic item according to the current wheel speed signal includes: Using a preset fault detection method to detect whether the current wheel speed signal is a fault signal, and when it is determined that the current wheel speed signal is not a fault signal, performing digital filtering processing on the current wheel speed signal to obtain a processed current wheel speed signal; The first characteristic item is obtained according to the processed current wheel speed signal.

13. A device for identifying the type of a wheel speed sensor, characterized in that: The device comprises: a transceiver unit, configured to receive a current wheel speed signal generated by a newly installed wheel speed sensor; a first processing unit, configured to obtain a first characteristic entry according to the current wheel speed signal, wherein the first characteristic entry includes electrical characteristic information of the current wheel speed signal; The second processing unit is configured to classify the first characteristic entry based on a set classification method, using each second characteristic entry in a self-learning database and the respective category labels of the second characteristic entries, to obtain a first device type corresponding to the first characteristic entry, wherein the first device type is used to characterize the sensor type of the newly installed wheel speed sensor, the category label is used to characterize the sensor type of the sensor to which the corresponding second characteristic entry belongs, and the second characteristic entry contains electrical characteristic information of a historical wheel speed signal.

Images