Deceleration strip detection method, device and equipment and storage medium

Abstract

The invention discloses a deceleration strip detection method, device and equipment and a storage medium, and the method comprises the steps: collecting an acceleration signal and a tire pressure signal of a current vehicle in a driving process in real time, carrying out the preprocessing of the acceleration signal and the tire pressure signal, and obtaining the collected data after preprocessing; performing fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; the abnormal characteristic signals are extracted from the fusion analysis result, deceleration strip judgment is conducted according to the abnormal characteristic signals, the vehicle body function control instruction is generated according to the judgment result, an existing vehicle-mounted sensor can be reused, new equipment does not need to be added, hardware cost optimization is achieved, and compared with a single acceleration sensor scheme, the misjudgment rate is reduced; the environment adaptability and the robustness of complex scenes are enhanced, the vibration interference of a conventional road surface is eliminated, the accuracy of deceleration strip detection is improved, and the speed and efficiency of deceleration strip detection are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicle perception technology, and in particular to a speed bump detection method, device, equipment and storage medium. Background Art

[0002] Currently, speed bump detection mainly relies on the following technologies: Single acceleration sensor solution: The presence of speed bumps is determined by detecting the peak value of the vehicle's vertical acceleration; however, this solution is easily interfered by factors such as potholes and manhole covers, resulting in a high misjudgment rate; in addition, a single acceleration sensor cannot effectively distinguish speed bumps from other similar vibration scenarios (such as bumpy roads); Vision or LiDAR solution: The shape of speed bumps is identified through cameras or LiDAR, but this solution is greatly affected by lighting and weather conditions and is costly; especially in rainy, snowy or nighttime environments, the vision solution is prone to failure; Independent Tire Pressure Monitoring System (TPMS): Currently mainly used for abnormal tire pressure alarms, but has not yet been combined with the speed bump detection function. The TPMS data is not fully utilized, resulting in information redundancy; Overall, the existing detection solutions have failed to fully utilize multi-sensor data fusion technology and lack in-depth correlation analysis of tire dynamic responses, which affects the accuracy and efficiency of speed bump detection. Summary of the Invention

[0003] The main purpose of the present invention is to provide a speed bump detection method, device, equipment and storage medium, aiming to solve the technical problems in the prior art that the existing technology fails to fully utilize multi-sensor data fusion technology, lacks in-depth correlation analysis of tire dynamic response, and has low deceleration detection accuracy and efficiency.

[0004] In a first aspect, the present invention provides a speed bump detection method, comprising the following steps: Real-time acquisition of acceleration signals and tire pressure signals of the current vehicle during driving, pre-processing the acceleration signals and tire pressure signals to obtain pre-processed acquisition data; Performing fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; An abnormal characteristic signal is extracted from the fusion analysis result, a speed bump judgment is performed based on the abnormal characteristic signal, and a vehicle body function control instruction is generated based on the judgment result.

[0005] Optionally, the real-time acquisition of the acceleration signal and the tire pressure signal of the current vehicle during driving, preprocessing the acceleration signal and the tire pressure signal to obtain the preprocessed acquisition data, includes: Acquiring an acceleration signal of the current vehicle during driving by using a wheel-end acceleration sensor of the current vehicle, and obtaining a tire pressure signal of the current vehicle during driving by using a tire pressure monitoring pressure sensor of the current vehicle; After performing noise reduction and smoothing processing on the acceleration signal and the tire pressure signal, pre-processed collected data is obtained.

[0006] Optionally, performing fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result includes: Establishing state space models corresponding to the acceleration signal and the tire pressure signal in the collected data respectively; Predicting state prediction data at the current moment according to the state space model, and correcting the state prediction data by using the Kalman gain to obtain state estimation data; Performing time synchronization processing on the state estimation data, and performing feature extraction on the time-synchronized data to obtain acceleration change features and tire pressure change features; A preset multi-sensor fusion algorithm is used to perform a fusion analysis on the acceleration change characteristics and the tire pressure change characteristics to obtain a fusion analysis result.

[0007] Optionally, predicting state prediction data at a current moment according to the state space model, and correcting the state prediction data by a Kalman gain to obtain state estimation data includes: Obtaining historical acceleration data and historical tire pressure data at a previous moment, and inputting the historical acceleration data and the historical tire pressure data into the state space model to predict state prediction data at a current moment; Acquire actual measurement data of the sensor, compare the actual measurement data of the sensor with the state prediction data, and obtain a noise covariance matrix and a prediction error covariance matrix; Calculating a Kalman gain based on the noise covariance matrix and the prediction error covariance matrix; The state prediction data is corrected by using the Kalman gain to obtain state estimation data.

[0008] Optionally, performing time synchronization processing on the state estimation data and performing feature extraction on the time-synchronized data to obtain acceleration change features and tire pressure change features includes: Unifying the data of different sampling frequencies in the state estimation data into the same time interval, aligning the data on the time axis, and obtaining the target data after time synchronization; Extracting acceleration features from the target data to obtain acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration, and using the acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration as acceleration change features; Perform tire pressure feature extraction on the target data to obtain the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time, and use the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time as tire pressure change features.

[0009] Optionally, extracting an abnormal characteristic signal from the fusion analysis result, performing speed bump judgment based on the abnormal characteristic signal, and generating a vehicle body function control instruction based on the judgment result includes: Extracting abnormal characteristic signals from the fusion analysis results; Comparing the abnormal characteristic signal with a corresponding characteristic threshold, and determining whether the current vehicle is traveling on a speed bump based on the comparison result to obtain a determination result; A vehicle body function control instruction is generated according to the judgment result, so that the current vehicle is controlled accordingly according to the vehicle body function control instruction.

[0010] Optionally, comparing the abnormal characteristic signal with a corresponding characteristic threshold, and determining whether the current vehicle is traveling on a speed bump based on the comparison result, to obtain a determination result, includes: comparing the abnormal acceleration peak value in the abnormal characteristic signal with a preset acceleration threshold, and comparing the abnormal tire pressure instantaneous change rate in the abnormal characteristic signal with a preset tire pressure amplitude value; When the abnormal acceleration peak is greater than the preset acceleration threshold, the abnormal tire pressure instantaneous change rate is equal to the preset tire pressure amplitude value, and the abnormal acceleration peak and the abnormal tire pressure instantaneous change rate are within a preset deviation time sequence, it is determined that the current vehicle is traveling on a speed bump and a judgment result is generated.

[0011] In a second aspect, to achieve the above-mentioned objectives, the present invention further provides a speed bump detection device, the speed bump detection device comprising: An acquisition and processing module is used to acquire acceleration signals and tire pressure signals of the current vehicle in real time during driving, pre-process the acceleration signals and tire pressure signals, and obtain pre-processed acquisition data; A fusion analysis module is used to perform fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; The judgment module is used to extract abnormal characteristic signals from the fusion analysis results, perform speed bump judgment based on the abnormal characteristic signals, and generate vehicle body function control instructions based on the judgment results.

[0012] In the third aspect, in order to achieve the above-mentioned purpose, the present invention also proposes a speed bump detection device, which includes: a memory, a processor, and a speed bump detection program stored on the memory and executable on the processor, wherein the speed bump detection program is configured to implement the steps of the speed bump detection method described above.

[0013] In a fourth aspect, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a speed bump detection program is stored, and when the speed bump detection program is executed by a processor, the steps of the speed bump detection method as described above are implemented.

[0014] The speed bump detection method proposed in the present invention collects the acceleration signal and tire pressure signal of the current vehicle in real time during driving, pre-processes the acceleration signal and the tire pressure signal to obtain pre-processed collected data; performs fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; extracts abnormal characteristic signals from the fusion analysis result, performs speed bump judgment based on the abnormal characteristic signals, and generates vehicle body function control instructions based on the judgment result. The method can reuse existing vehicle-mounted sensors without the need for new equipment, thus achieving hardware cost optimization. Compared with a single acceleration sensor solution, the method reduces the misjudgment rate, enhances environmental adaptability and robustness in complex scenarios, eliminates vibration interference from conventional roads, improves the accuracy of speed bump detection, and improves the speed and efficiency of speed bump detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention; Figure 2 This is a flow chart of a first embodiment of a speed bump detection method according to the present invention; Figure 3 This is a flow chart of a second embodiment of a speed bump detection method according to the present invention; Figure 4 This is a flow chart of a third embodiment of a speed bump detection method according to the present invention; Figure 5 This is a flow chart of a fourth embodiment of a speed bump detection method according to the present invention; Figure 6 This is a functional module diagram of the first embodiment of the speed bump detection device of the present invention.

[0016] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0017] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] The solution of the embodiment of the present invention is mainly: by real-time collection of the acceleration signal and tire pressure signal of the current vehicle during driving, the acceleration signal and the tire pressure signal are pre-processed to obtain the pre-processed collection data; the collection data is fused and analyzed according to a preset fusion algorithm to obtain a fusion analysis result; abnormal feature signals are extracted from the fusion analysis result, speed bump judgment is performed based on the abnormal feature signals, and body function control instructions are generated based on the judgment result. It can reuse existing vehicle-mounted sensors without the need for new equipment, and realizes hardware cost optimization. Compared with a single acceleration sensor solution, it reduces the misjudgment rate, enhances environmental adaptability and robustness in complex scenarios, eliminates vibration interference from conventional roads, improves the accuracy of speed bump detection, and improves the speed and efficiency of speed bump detection. It solves the technical problems in the existing technology that the multi-sensor data fusion technology is not fully utilized, and there is a lack of in-depth correlation analysis of tire dynamic response, resulting in low deceleration detection accuracy and efficiency.

[0019] Reference Figure 1 , Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention.

[0020] like Figure 1 As shown, the device may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement communication between these components. The user interface 1003 may include a display and an input unit such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory, such as a disk storage. The memory 1005 may also be a storage device independent of the processor 1001.

[0021] Those skilled in the art will understand that Figure 1 The device structure shown in the figure does not constitute a limitation of the device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0022] like Figure 1As shown, the memory 1005 as a storage medium may include an operating device, a network communication module, a user interface module and a speed bump detection program.

[0023] The device of the present invention calls the speed bump detection program stored in the memory 1005 through the processor 1001 and performs the following operations: Real-time acquisition of acceleration signals and tire pressure signals of the current vehicle during driving, pre-processing the acceleration signals and tire pressure signals to obtain pre-processed acquisition data; Performing fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; An abnormal characteristic signal is extracted from the fusion analysis result, a speed bump judgment is performed based on the abnormal characteristic signal, and a vehicle body function control instruction is generated based on the judgment result.

[0024] The device of the present invention calls the speed bump detection program stored in the memory 1005 through the processor 1001, and further performs the following operations: Acquiring an acceleration signal of the current vehicle during driving by using a wheel-end acceleration sensor of the current vehicle, and obtaining a tire pressure signal of the current vehicle during driving by using a tire pressure monitoring pressure sensor of the current vehicle; After performing noise reduction and smoothing processing on the acceleration signal and the tire pressure signal, pre-processed collected data is obtained.

[0025] The device of the present invention calls the speed bump detection program stored in the memory 1005 through the processor 1001, and further performs the following operations: Establishing state space models corresponding to the acceleration signal and the tire pressure signal in the collected data respectively; Predicting state prediction data at the current moment according to the state space model, and correcting the state prediction data by using the Kalman gain to obtain state estimation data; Performing time synchronization processing on the state estimation data, and performing feature extraction on the time-synchronized data to obtain acceleration change features and tire pressure change features; A preset multi-sensor fusion algorithm is used to perform a fusion analysis on the acceleration change characteristics and the tire pressure change characteristics to obtain a fusion analysis result.

[0026] The device of the present invention calls the speed bump detection program stored in the memory 1005 through the processor 1001, and further performs the following operations: Obtaining historical acceleration data and historical tire pressure data at a previous moment, and inputting the historical acceleration data and the historical tire pressure data into the state space model to predict state prediction data at a current moment; Acquire actual measurement data of the sensor, compare the actual measurement data of the sensor with the state prediction data, and obtain a noise covariance matrix and a prediction error covariance matrix; Calculating a Kalman gain based on the noise covariance matrix and the prediction error covariance matrix; The state prediction data is corrected by using the Kalman gain to obtain state estimation data.

[0027] The device of the present invention calls the speed bump detection program stored in the memory 1005 through the processor 1001, and further performs the following operations: Unifying the data of different sampling frequencies in the state estimation data into the same time interval, aligning the data on the time axis, and obtaining the target data after time synchronization; Extracting acceleration features from the target data to obtain acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration, and using the acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration as acceleration change features; Perform tire pressure feature extraction on the target data to obtain the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time, and use the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time as tire pressure change features.

[0028] The device of the present invention calls the speed bump detection program stored in the memory 1005 through the processor 1001, and further performs the following operations: Extracting abnormal characteristic signals from the fusion analysis results; Comparing the abnormal characteristic signal with a corresponding characteristic threshold, and determining whether the current vehicle is traveling on a speed bump based on the comparison result to obtain a determination result; A vehicle body function control instruction is generated according to the judgment result, so that the current vehicle is controlled accordingly according to the vehicle body function control instruction.

[0029] The device of the present invention calls the speed bump detection program stored in the memory 1005 through the processor 1001, and further performs the following operations: comparing the abnormal acceleration peak value in the abnormal characteristic signal with a preset acceleration threshold, and comparing the abnormal tire pressure instantaneous change rate in the abnormal characteristic signal with a preset tire pressure amplitude value; When the abnormal acceleration peak is greater than the preset acceleration threshold, the abnormal tire pressure instantaneous change rate is equal to the preset tire pressure amplitude value, and the abnormal acceleration peak and the abnormal tire pressure instantaneous change rate are within a preset deviation time sequence, it is determined that the current vehicle is traveling on a speed bump and a judgment result is generated.

[0030] Through the above-mentioned scheme, this embodiment collects the acceleration signal and tire pressure signal of the current vehicle in real time during driving, pre-processes the acceleration signal and the tire pressure signal to obtain pre-processed collected data; performs fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; extracts abnormal characteristic signals from the fusion analysis result, performs speed bump judgment based on the abnormal characteristic signals, and generates vehicle body function control instructions based on the judgment result. It can reuse existing vehicle-mounted sensors without the need for new equipment, realizes hardware cost optimization, and reduces the misjudgment rate compared to a single acceleration sensor solution, enhances environmental adaptability and robustness in complex scenarios, eliminates vibration interference from conventional roads, improves the accuracy of speed bump detection, and improves the speed and efficiency of speed bump detection.

[0031] Based on the above hardware structure, an embodiment of a speed bump detection method of the present invention is proposed.

[0032] Reference Figure 2 , Figure 2 FIG. 1 is a flow chart of a first embodiment of a speed bump detection method according to the present invention.

[0033] In a first embodiment, the speed bump detection method includes the following steps: Step S10: collecting the acceleration signal and tire pressure signal of the current vehicle in the process of driving in real time, preprocessing the acceleration signal and the tire pressure signal to obtain preprocessed collected data.

[0034] It should be noted that by obtaining the vehicle's status information and preprocessing the status information, the corresponding collected data can be obtained, that is, the acceleration signal and tire pressure signal of the current vehicle during driving are collected in real time, and the acceleration signal and the tire pressure signal are preprocessed to obtain the preprocessed collected data.

[0035] Step S20: performing fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result.

[0036] It should be understood that the fusion analysis can be performed according to a preset fusion algorithm to obtain a fusion analysis result.

[0037] Step S30: extracting abnormal characteristic signals from the fusion analysis results, performing speed bump judgment based on the abnormal characteristic signals, and generating vehicle body function control instructions based on the judgment results.

[0038] It can be understood that abnormal characteristic signals can be extracted from the fusion analysis results, and then speed bump judgment can be performed based on the abnormal characteristic signals, so that body function control instructions can be generated according to the judgment results. At the same time, early warning information can be output in real time and data can be recorded to facilitate subsequent road condition analysis and corresponding body function control.

[0039] Through the above-mentioned scheme, this embodiment collects the acceleration signal and tire pressure signal of the current vehicle in real time during driving, pre-processes the acceleration signal and the tire pressure signal to obtain pre-processed collected data; performs fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; extracts abnormal characteristic signals from the fusion analysis result, performs speed bump judgment based on the abnormal characteristic signals, and generates vehicle body function control instructions based on the judgment result. It can reuse existing vehicle-mounted sensors without the need for new equipment, realizes hardware cost optimization, and reduces the misjudgment rate compared to a single acceleration sensor solution, enhances environmental adaptability and robustness in complex scenarios, eliminates vibration interference from conventional roads, improves the accuracy of speed bump detection, and improves the speed and efficiency of speed bump detection.

[0040] Furthermore, Figure 3 This is a flow chart of the second embodiment of the speed bump detection method of the present invention. Figure 3 As shown, a second embodiment of the speed bump detection method of the present invention is proposed based on the first embodiment. In this embodiment, step S10 specifically includes the following steps: Step S11: collecting the acceleration signal of the current vehicle during driving through the wheel-end acceleration sensor of the current vehicle, and obtaining the tire pressure signal of the current vehicle during driving through the tire pressure monitoring pressure sensor of the current vehicle.

[0041] It should be noted that the vertical acceleration and tire pressure data are monitored in real time through the wheel-end acceleration sensors and tire pressure sensors, and the vehicle speed data is obtained through the CAN signal (used for real-time adjustment of the set threshold value). That is, the wheel-end acceleration sensors and tire pressure monitoring pressure sensors of the current vehicle can collect the acceleration signals and tire pressure signals of the current vehicle in real time during driving.

[0042] Step S12: After performing noise reduction and smoothing processing on the acceleration signal and the tire pressure signal, pre-processed collected data is obtained.

[0043] It can be understood that denoising and smoothing the wheel-end acceleration signal and the tire pressure data can ensure the accuracy of subsequent data fusion, that is, after denoising and smoothing the acceleration signal and the tire pressure signal, the pre-processed data can be obtained as the collected data.

[0044] Through the above scheme, this embodiment collects the acceleration signal of the current vehicle during driving through the wheel-end acceleration sensor of the current vehicle, and obtains the tire pressure signal of the current vehicle during driving through the tire pressure monitoring pressure sensor of the current vehicle; after noise reduction and smoothing processing are performed on the acceleration signal and the tire pressure signal, pre-processed collected data is obtained. The pre-processed collected data can be obtained quickly, the vibration interference of conventional road surfaces is eliminated, and the accuracy of speed bump detection is improved.

[0045] Furthermore, Figure 4 This is a flow chart of the third embodiment of the speed bump detection method of the present invention. Figure 4 As shown, a third embodiment of the speed bump detection method of the present invention is proposed based on the first embodiment. In this embodiment, step S20 specifically includes the following steps: Step S21: establishing state space models corresponding to the acceleration signal and tire pressure signal in the collected data.

[0046] It should be noted that Kalman filtering and multi-sensor fusion algorithms can be used to comprehensively analyze acceleration data and tire pressure data. First, a corresponding state-space model can be established, that is, a state-space model corresponding to the acceleration signal and tire pressure signal in the collected data can be established.

[0047] Step S22: predicting state prediction data at the current moment according to the state space model, and correcting the state prediction data by using the Kalman gain to obtain state estimation data.

[0048] It is understandable that the state prediction data at the current moment can be predicted by the state space model, and then the data can be corrected by the Kalman gain to obtain a more accurate state estimation value, that is, the state estimation data.

[0049] Furthermore, the step S22 specifically includes the following steps: Obtaining historical acceleration data and historical tire pressure data at a previous moment, and inputting the historical acceleration data and the historical tire pressure data into the state space model to predict state prediction data at a current moment; Acquire actual measurement data of the sensor, compare the actual measurement data of the sensor with the state prediction data, and obtain a noise covariance matrix and a prediction error covariance matrix; Calculating a Kalman gain based on the noise covariance matrix and the prediction error covariance matrix; The state prediction data is corrected by using the Kalman gain to obtain state estimation data.

[0050] In specific implementations, the state at the current moment can be predicted based on the state estimate at the previous moment and the state transition equation of the system. For acceleration signals, the dynamic model is used to predict the acceleration at the current moment based on the acceleration and velocity at the previous moment. For tire pressure signals, the current tire pressure is predicted based on historical tire pressure data and the physical properties of the tire (such as gas diffusion). The acceleration and tire pressure data actually measured by the sensor are compared with the predicted values. The Kalman gain can be calculated based on the measurement noise covariance matrix and the prediction error covariance matrix. The predicted value is corrected by the Kalman gain to obtain a more accurate state estimate. This can effectively filter out noise in the acceleration signal and tire pressure signal, improving the quality and reliability of the data.

[0051] Step S23: performing time synchronization processing on the state estimation data, performing feature extraction on the time-synchronized data, and obtaining acceleration change features and tire pressure change features.

[0052] It should be understood that by performing time synchronization processing on the state estimation data and then performing feature extraction on the time-synchronized data, acceleration change characteristics and tire pressure change characteristics can be obtained.

[0053] Furthermore, the step S23 specifically includes the following steps: Unifying the data of different sampling frequencies in the state estimation data into the same time interval, aligning the data on the time axis, and obtaining the target data after time synchronization; Extracting acceleration features from the target data to obtain acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration, and using the acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration as acceleration change features; Perform tire pressure feature extraction on the target data to obtain the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time, and use the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time as tire pressure change features.

[0054] It should be noted that since the sampling frequencies of the acceleration sensor and tire pressure sensor may be different, the collected data needs to be time-synchronized so that they are aligned on the time axis for subsequent fusion analysis; methods such as linear interpolation can be used to unify data with different sampling frequencies to the same time interval.

[0055] In specific implementations, the Kalman filtered acceleration signal is analyzed to extract characteristic parameters that reflect road conditions, such as the RMS value, peak value, and frequency of acceleration. The RMS value reflects the overall intensity of vehicle vibration, the peak value indicates the magnitude of the instantaneous impact encountered, and the frequency of variation reflects the frequency of road bumps. By analyzing changes in the tire pressure signal, characteristics such as the rate of change and the amplitude of pressure fluctuations can be extracted. When a vehicle travels on an abnormal road surface (such as a pothole), the interaction between the tire and the road surface causes a certain degree of change in tire pressure. These characteristics can be used as a basis for determining whether the road surface is abnormal.

[0056] It should be understood that Kalman filtering and multi-sensor fusion algorithms are used to comprehensively analyze the two types of data, extract characteristic signals of abnormal road surfaces such as speed bumps and potholes, and set reasonable thresholds to distinguish various types of road abnormalities; the acceleration sensor is analyzed and extracted for data such as acceleration peak, vibration frequency, and waveform duration, and the tire pressure signal is analyzed and extracted for data such as the instantaneous rate of change of tire pressure, bilateral tire pressure synchronization (left / right tire comparison), and pressure recovery time.

[0057] Step S24: Using a preset multi-sensor fusion algorithm to perform fusion analysis on the acceleration change characteristics and the tire pressure change characteristics to obtain a fusion analysis result.

[0058] It is understandable that the acceleration change characteristics and the tire pressure change characteristics can be fused and analyzed through a pre-set multi-sensor fusion algorithm to obtain a fusion analysis result.

[0059] In a specific implementation, the features extracted from the acceleration signal and the tire pressure signal are fused using methods such as weighted averaging, DS evidence theory, and neural networks, which are not limited in this embodiment. For example, the weighted averaging method assigns a corresponding weight to each feature based on its importance to the judgment of abnormal road surface, and then calculates the weighted feature value as the basis for comprehensive judgment of abnormal road surface.

[0060] This embodiment adopts the above scheme, by establishing state space models corresponding to the acceleration signal and tire pressure signal in the collected data respectively; predicting the state prediction data at the current moment according to the state space model, correcting the state prediction data through the Kalman gain, and obtaining state estimation data; performing time synchronization processing on the state estimation data, performing feature extraction on the time-synchronized data, and obtaining acceleration change characteristics and tire pressure change characteristics; using a preset multi-sensor fusion algorithm to perform fusion analysis on the acceleration change characteristics and the tire pressure change characteristics to obtain a fusion analysis result, which can quickly perform feature fusion analysis, eliminate the vibration interference of conventional road surfaces, improve the accuracy of speed bump detection, and improve the speed and efficiency of speed bump detection.

[0061] Furthermore, Figure 5 This is a flow chart of a fourth embodiment of the speed bump detection method of the present invention. Figure 5 As shown, a fourth embodiment of the speed bump detection method of the present invention is proposed based on the first embodiment. In this embodiment, step S30 specifically includes the following steps: Step S31: extract abnormal feature signals from the fusion analysis results.

[0062] It should be noted that abnormal acceleration characteristic signals and abnormal tire pressure characteristic signals can be extracted from the fusion analysis results.

[0063] Step S32: Compare the abnormal characteristic signal with the corresponding characteristic threshold, and determine whether the current vehicle is traveling on a speed bump based on the comparison result to obtain a determination result.

[0064] It is understandable that after comparing the abnormal characteristic signal with the corresponding characteristic threshold, it is possible to determine whether the current vehicle is traveling on a speed bump based on the generated comparison result, thereby obtaining a judgment result.

[0065] Furthermore, the step S32 specifically includes the following steps: comparing the abnormal acceleration peak value in the abnormal characteristic signal with a preset acceleration threshold, and comparing the abnormal tire pressure instantaneous change rate in the abnormal characteristic signal with a preset tire pressure amplitude value; When the abnormal acceleration peak is greater than the preset acceleration threshold, the abnormal tire pressure instantaneous change rate is equal to the preset tire pressure amplitude value, and the abnormal acceleration peak and the abnormal tire pressure instantaneous change rate are within a preset deviation time sequence, it is determined that the current vehicle is traveling on a speed bump and a judgment result is generated.

[0066] It should be understood that after comparing the abnormal acceleration peak value in the abnormal characteristic signal with a preset acceleration threshold, and comparing the abnormal tire pressure instantaneous change rate in the abnormal characteristic signal with a preset tire pressure amplitude value; if the acceleration peak value is greater than the first acceleration threshold, the tire pressure instantaneous change rate is greater than the first tire pressure amplitude value, and the acceleration peak value and the tire pressure fluctuation time sequence are within the first deviation time sequence value, then it is determined to be a speed bump. If not, the signal acquisition module is returned. Specifically, the so-called first acceleration threshold, first tire pressure amplitude value, and first deviation time sequence value can be set accordingly based on vehicle speed.

[0067] In the specific implementation, after extracting the acceleration peak, oscillation frequency and tire pressure change amplitude, if the acceleration peak is greater than the first acceleration threshold and the instantaneous tire pressure change rate is greater than the first tire pressure amplitude value, and the time difference between the two is less than the first deviation timing value, it is determined to be a speed bump; if the acceleration oscillation frequency is greater than the first acceleration oscillation frequency and the duration is greater than the first acceleration duration and the tire pressure drop amplitude is greater than the second tire pressure amplitude value, it is determined to be a pothole.

[0068] Step S33: Generate a vehicle body function control instruction according to the judgment result, so that the current vehicle performs corresponding control according to the vehicle body function control instruction.

[0069] It should be understood that a vehicle body function control instruction may be generated according to the judgment result, so that the current vehicle is controlled accordingly according to the vehicle body function control instruction.

[0070] In the specific implementation, when it is determined that the vehicle is driving on an abnormal road surface, the corresponding abnormal road surface characteristic signal is output, such as the type of abnormal road surface (potholes, bumps, speed bumps, etc.), severity and other information, and the body function control instructions are generated so that the subsequent vehicle control system (such as suspension system adjustment, driving assistance system prompts, etc.) can make corresponding control responses.

[0071] This embodiment uses the above-mentioned scheme to extract abnormal characteristic signals from the fusion analysis results; compare the abnormal characteristic signals with corresponding characteristic thresholds, and determine whether the current vehicle is traveling on a speed bump based on the comparison result to obtain a judgment result; generate body function control instructions based on the judgment result, so that the current vehicle is controlled accordingly according to the body function control instructions; it can reuse existing vehicle-mounted sensors without the need for new equipment, thereby achieving hardware cost optimization. Compared with a single acceleration sensor solution, it reduces the misjudgment rate, enhances environmental adaptability and robustness in complex scenarios, eliminates vibration interference from conventional roads, improves the accuracy of speed bump detection, and improves the speed and efficiency of speed bump detection.

[0072] Accordingly, the present invention further provides a speed bump detection device.

[0073] Reference Figure 6 , Figure 6 This is a functional module diagram of the first embodiment of the speed bump detection device of the present invention.

[0074] In a first embodiment of the speed bump detection device of the present invention, the speed bump detection device comprises: The acquisition and processing module 10 is used to acquire the acceleration signal and tire pressure signal of the current vehicle in the process of driving in real time, pre-process the acceleration signal and the tire pressure signal, and obtain the pre-processed acquisition data.

[0075] The fusion analysis module 20 is used to perform fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result.

[0076] The judgment module 30 is used to extract abnormal characteristic signals from the fusion analysis results, perform speed bump judgment based on the abnormal characteristic signals, and generate vehicle body function control instructions based on the judgment results.

[0077] The acquisition and processing module 10 is also used to acquire the acceleration signal of the current vehicle during driving through the wheel-end acceleration sensor of the current vehicle, and obtain the tire pressure signal of the current vehicle during driving through the tire pressure monitoring pressure sensor of the current vehicle; after denoising and smoothing the acceleration signal and the tire pressure signal, the pre-processed acquisition data is obtained.

[0078] The fusion analysis module 20 is also used to establish state space models corresponding to the acceleration signals and tire pressure signals in the collected data respectively; predict the state prediction data at the current moment based on the state space model, correct the state prediction data through the Kalman gain, and obtain state estimation data; perform time synchronization processing on the state estimation data, perform feature extraction on the time-synchronized data, and obtain acceleration change characteristics and tire pressure change characteristics; use a preset multi-sensor fusion algorithm to perform fusion analysis on the acceleration change characteristics and the tire pressure change characteristics to obtain a fusion analysis result.

[0079] The fusion analysis module 20 is also used to obtain historical acceleration data and historical tire pressure data at the previous moment, and input the historical acceleration data and the historical tire pressure data into the state space model to predict the state prediction data at the current moment; obtain actual measurement data of the sensor, compare the actual measurement data of the sensor with the state prediction data, and obtain a noise covariance matrix and a prediction error covariance matrix; calculate the Kalman gain based on the noise covariance matrix and the prediction error covariance matrix; and correct the state prediction data through the Kalman gain to obtain state estimation data.

[0080] The fusion analysis module 20 is also used to unify the data of different sampling frequencies in the state estimation data into the same time interval, so that each data is aligned on the time axis to obtain the target data after time synchronization; the target data is subjected to acceleration feature extraction to obtain the acceleration root mean square value, acceleration peak value, acceleration vibration frequency and waveform duration, and the acceleration root mean square value, the acceleration peak value, the acceleration vibration frequency and the waveform duration are used as acceleration change features; the target data is subjected to tire pressure feature extraction to obtain the tire pressure instantaneous change rate, bilateral tire pressure synchronization, tire pressure fluctuation amplitude and pressure recovery time, and the tire pressure instantaneous change rate, the bilateral tire pressure synchronization, the tire pressure fluctuation amplitude and the pressure recovery time are used as tire pressure change features.

[0081] The judgment module 30 is further used to extract abnormal characteristic signals from the fusion analysis results; compare the abnormal characteristic signals with corresponding characteristic thresholds, and determine whether the current vehicle is traveling on a speed bump based on the comparison results to obtain a judgment result; and generate a body function control instruction based on the judgment result, so that the current vehicle is controlled accordingly according to the body function control instruction.

[0082] The judgment module 30 is further used to compare the abnormal acceleration peak value in the abnormal characteristic signal with a preset acceleration threshold, and compare the abnormal tire pressure instantaneous change rate in the abnormal characteristic signal with a preset tire pressure amplitude value; when the abnormal acceleration peak value is greater than the preset acceleration threshold, the abnormal tire pressure instantaneous change rate is equal to the preset tire pressure amplitude value, and the abnormal acceleration peak value and the abnormal tire pressure instantaneous change rate are within a preset deviation time sequence, it is determined that the current vehicle is traveling on a speed bump and a judgment result is generated.

[0083] The steps implemented by the functional modules of the speed bump detection device may refer to the various embodiments of the speed bump detection method of the present invention, and will not be described in detail here.

[0084] In addition, an embodiment of the present invention further provides a storage medium, wherein a speed bump detection program is stored on the storage medium. When the speed bump detection program is executed by a processor, the following operations are performed: Real-time acquisition of acceleration signals and tire pressure signals of the current vehicle during driving, pre-processing the acceleration signals and tire pressure signals to obtain pre-processed acquisition data; Performing fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; An abnormal characteristic signal is extracted from the fusion analysis result, a speed bump judgment is performed based on the abnormal characteristic signal, and a vehicle body function control instruction is generated based on the judgment result.

[0085] Furthermore, when the speed bump detection program is executed by the processor, the following operations are also implemented: Acquiring an acceleration signal of the current vehicle during driving by using a wheel-end acceleration sensor of the current vehicle, and obtaining a tire pressure signal of the current vehicle during driving by using a tire pressure monitoring pressure sensor of the current vehicle; After performing noise reduction and smoothing processing on the acceleration signal and the tire pressure signal, pre-processed collected data is obtained.

[0086] Furthermore, when the speed bump detection program is executed by the processor, the following operations are also implemented: Establishing state space models corresponding to the acceleration signal and the tire pressure signal in the collected data respectively; Predicting state prediction data at the current moment according to the state space model, and correcting the state prediction data by using the Kalman gain to obtain state estimation data; Performing time synchronization processing on the state estimation data, and performing feature extraction on the time-synchronized data to obtain acceleration change features and tire pressure change features; A preset multi-sensor fusion algorithm is used to perform a fusion analysis on the acceleration change characteristics and the tire pressure change characteristics to obtain a fusion analysis result.

[0087] Furthermore, when the speed bump detection program is executed by the processor, the following operations are also implemented: Obtaining historical acceleration data and historical tire pressure data at a previous moment, and inputting the historical acceleration data and the historical tire pressure data into the state space model to predict state prediction data at a current moment; Acquire actual measurement data of the sensor, compare the actual measurement data of the sensor with the state prediction data, and obtain a noise covariance matrix and a prediction error covariance matrix; Calculating a Kalman gain based on the noise covariance matrix and the prediction error covariance matrix; The state prediction data is corrected by using the Kalman gain to obtain state estimation data.

[0088] Furthermore, when the speed bump detection program is executed by the processor, the following operations are also implemented: Unifying the data of different sampling frequencies in the state estimation data into the same time interval, aligning the data on the time axis, and obtaining the target data after time synchronization; Extracting acceleration features from the target data to obtain acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration, and using the acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration as acceleration change features; Perform tire pressure feature extraction on the target data to obtain the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time, and use the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time as tire pressure change features.

[0089] Furthermore, when the speed bump detection program is executed by the processor, the following operations are also implemented: Extracting abnormal characteristic signals from the fusion analysis results; Comparing the abnormal characteristic signal with a corresponding characteristic threshold, and determining whether the current vehicle is traveling on a speed bump based on the comparison result to obtain a determination result; A vehicle body function control instruction is generated according to the judgment result, so that the current vehicle is controlled accordingly according to the vehicle body function control instruction.

[0090] Furthermore, when the speed bump detection program is executed by the processor, the following operations are also implemented: comparing the abnormal acceleration peak value in the abnormal characteristic signal with a preset acceleration threshold, and comparing the abnormal tire pressure instantaneous change rate in the abnormal characteristic signal with a preset tire pressure amplitude value; When the abnormal acceleration peak is greater than the preset acceleration threshold, the abnormal tire pressure instantaneous change rate is equal to the preset tire pressure amplitude value, and the abnormal acceleration peak and the abnormal tire pressure instantaneous change rate are within a preset deviation time sequence, it is determined that the current vehicle is traveling on a speed bump and a judgment result is generated.

[0091] Those skilled in the art will understand that all or part of the steps in the above-mentioned implementation methods can be implemented by instructing related hardware through a program. The program is stored in a storage medium and includes a number of instructions for enabling a device (which may be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application; and the aforementioned storage medium is a computer-readable storage medium, including: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0092] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0093] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0094] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A speed bump detection method, characterized in that: The speed bump detection method comprises: Real-time acquisition of acceleration signals and tire pressure signals of the current vehicle during driving, pre-processing the acceleration signals and tire pressure signals to obtain pre-processed acquisition data; Performing fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; An abnormal characteristic signal is extracted from the fusion analysis result, a speed bump judgment is performed based on the abnormal characteristic signal, and a vehicle body function control instruction is generated based on the judgment result.

2. The speed bump detection method according to claim 1, wherein: The real-time acquisition of the acceleration signal and the tire pressure signal of the current vehicle during driving, pre-processing the acceleration signal and the tire pressure signal to obtain the pre-processed acquisition data, includes: Acquiring an acceleration signal of the current vehicle during driving by using a wheel-end acceleration sensor of the current vehicle, and obtaining a tire pressure signal of the current vehicle during driving by using a tire pressure monitoring pressure sensor of the current vehicle; After performing noise reduction and smoothing processing on the acceleration signal and the tire pressure signal, pre-processed collected data is obtained.

3. The speed bump detection method according to claim 1, wherein: The performing fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result includes: Establishing state space models corresponding to the acceleration signal and the tire pressure signal in the collected data respectively; Predicting state prediction data at the current moment according to the state space model, and correcting the state prediction data by using the Kalman gain to obtain state estimation data; performing time synchronization processing on the state estimation data, and performing feature extraction on the time-synchronized data to obtain acceleration change features and tire pressure change features; A preset multi-sensor fusion algorithm is used to perform a fusion analysis on the acceleration change characteristics and the tire pressure change characteristics to obtain a fusion analysis result.

4. The speed bump detection method according to claim 3, wherein: The step of predicting the state prediction data at the current moment according to the state space model and correcting the state prediction data by using the Kalman gain to obtain the state estimation data includes: Obtaining historical acceleration data and historical tire pressure data at a previous moment, and inputting the historical acceleration data and the historical tire pressure data into the state space model to predict state prediction data at a current moment; Acquire actual measurement data of the sensor, compare the actual measurement data of the sensor with the state prediction data, and obtain a noise covariance matrix and a prediction error covariance matrix; Calculating a Kalman gain based on the noise covariance matrix and the prediction error covariance matrix; The state prediction data is corrected by using the Kalman gain to obtain state estimation data.

5. The speed bump detection method according to claim 3, wherein: The performing time synchronization processing on the state estimation data and extracting features from the time-synchronized data to obtain acceleration change features and tire pressure change features includes: Unifying the data of different sampling frequencies in the state estimation data into the same time interval, aligning the data on the time axis, and obtaining the target data after time synchronization; Extracting acceleration features from the target data to obtain acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration, and using the acceleration root mean square value, acceleration peak value, acceleration vibration frequency, and waveform duration as acceleration change features; Perform tire pressure feature extraction on the target data to obtain the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time, and use the instantaneous rate of change of tire pressure, the synchronization of bilateral tire pressure, the tire pressure fluctuation amplitude and the pressure recovery time as tire pressure change features.

6. The speed bump detection method according to claim 1, wherein: The extracting of abnormal characteristic signals from the fusion analysis results, performing speed bump determination based on the abnormal characteristic signals, and generating vehicle body function control instructions based on the determination results include: Extracting abnormal characteristic signals from the fusion analysis results; Comparing the abnormal characteristic signal with a corresponding characteristic threshold, and determining whether the current vehicle is traveling on a speed bump based on the comparison result to obtain a determination result; A vehicle body function control instruction is generated according to the judgment result, so that the current vehicle is controlled accordingly according to the vehicle body function control instruction.

7. The speed bump detection method according to claim 6, wherein: The step of comparing the abnormal characteristic signal with a corresponding characteristic threshold, and determining whether the current vehicle is traveling on a speed bump based on the comparison result, to obtain a determination result, includes: comparing the abnormal acceleration peak value in the abnormal characteristic signal with a preset acceleration threshold, and comparing the abnormal tire pressure instantaneous change rate in the abnormal characteristic signal with a preset tire pressure amplitude value; When the abnormal acceleration peak is greater than the preset acceleration threshold, the abnormal tire pressure instantaneous change rate is equal to the preset tire pressure amplitude value, and the abnormal acceleration peak and the abnormal tire pressure instantaneous change rate are within a preset deviation time sequence, it is determined that the current vehicle is traveling on a speed bump and a judgment result is generated.

8. A speed bump detection device, characterized in that: The speed bump detection device comprises: An acquisition and processing module is used to acquire acceleration signals and tire pressure signals of the current vehicle in real time during driving, pre-process the acceleration signals and tire pressure signals, and obtain pre-processed acquisition data; A fusion analysis module is used to perform fusion analysis on the collected data according to a preset fusion algorithm to obtain a fusion analysis result; The judgment module is used to extract abnormal characteristic signals from the fusion analysis results, perform speed bump judgment based on the abnormal characteristic signals, and generate vehicle body function control instructions based on the judgment results.

9. A speed bump detection device, characterized in that: The speed bump detection device includes: a memory, a processor, and a speed bump detection program stored in the memory and executable on the processor, wherein the speed bump detection program is configured to implement the steps of the speed bump detection method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a speed bump detection program, which, when executed by a processor, implements the steps of the speed bump detection method according to any one of claims 1 to 7.

Images