A commercial vehicle beidou ETC device anti-fraud system and method based on multi-source information fusion

Abstract

The application discloses a kind of based on multi-source information fusion's commercial vehicle Beidou ETC device anti-fraud system and method, it is related to intelligent transportation and vehicle information security cross technical field, including data acquisition module, for synchronous satellite positioning information, transaction information, vehicle attitude and motion information and vehicle bottom layer state information;Multi-source information fusion and fraud determination module is used to perform motion state consistency and integrity monitoring based on adaptive extended Kalman filtering, and multidimensional fraud behavior discrimination is carried out in combination with ETC transaction information;Data processing and response module is used to generate evidence chain with mathematical traceability when determining that fraud behavior occurs, and local storage and remote real-time reporting are carried out.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation and vehicle information security, and in particular to an anti-fraud system and method for Beidou ETC devices in commercial vehicles based on multi-source information fusion. Background Technology

[0002] With the rapid development of highway networks, Electronic Toll Collection (ETC) systems have become a core infrastructure for improving traffic efficiency and realizing intelligent transportation. Meanwhile, according to relevant policies and regulations, commercial vehicles such as heavy-duty trucks, long-distance buses, and hazardous materials transport vehicles (collectively referred to as "two-passenger-one-hazardous" vehicles) must install and use BeiDou satellite navigation system on-board terminals to achieve real-time dynamic monitoring and management of vehicles. Therefore, intelligent on-board terminals integrating ETC and BeiDou positioning functions have become standard equipment in the commercial vehicle sector. Toll fees for commercial vehicles are typically calculated in tiers based on factors such as vehicle type, number of axles, total weight, and mileage, with rates significantly higher than those for ordinary passenger vehicles.

[0003] Currently, the main types of ETC fraud are divided into two categories: identity fraud and route fraud.

[0004] Currently, the main technologies for combating spoofing signals from vehicle terminals can be divided into two categories: detection based on a single information source and detection based on simple information association. Detection based on a single information source mainly relies on the data source of a single sensor, identifying abnormal behavior by analyzing its characteristics. The most common methods are GNSS signal integrity monitoring and CAN bus data anomaly analysis. Detection based on simple information association combines multiple information sources in a simple way, performing preliminary comparisons after the fact or during the event: such as simple comparison of GNSS and CAN bus data, and background binding of ETC cards to vehicle models.

[0005] A simple comparison of GNSS and CAN bus data is a common practice that provides basic security and can be used for post-incident investigation. However, this correlation is static and rudimentary, lacking a dynamic and continuous verification mechanism. If a fraudster can simultaneously forge CAN bus data, this comparison will fail. Furthermore, this method relies heavily on post-incident data analysis and lacks real-time early warning capabilities, failing to immediately issue alerts or prevent fraud when it occurs.

[0006] The method of linking ETC cards to vehicle models in the background can effectively prevent identity fraud such as "plate cloning" or "card swapping." However, it relies on the accurate identification of the gantry camera system and can only be verified when an ETC transaction occurs. This method cannot deal with illegal card swapping that is not detected by the camera system, or fraud that occurs while driving on the highway.

[0007] CN116794966A discloses a BeiDou secure timing system, method, electronic equipment, and storage medium for rail transit. It achieves time synchronization through communication between the control center and the timing systems of each station, and utilizes a timing security protection unit for anti-interference and anti-spoofing reinforcement. By leveraging a quasar timing system, it improves clock consistency and timing security within rail transit, achieving protection at the timing link level. However, its protection primarily targets fixed nodes within the rail transit system, focusing on "time synchronization" rather than "motion behavior verification." Essentially, it still falls under the category of security reinforcement based on GNSS signal integrity monitoring, i.e., determining whether interference or spoofing has occurred by detecting characteristic parameters such as signal power, chip phase, and Doppler shift. Since this method cannot effectively distinguish between real satellite signals and highly simulated spoofed signals, its protection capability mainly relies on external signal protection units rather than dynamic consistency analysis within the terminal. Furthermore, the rail transit scenario is a closed system, lacking a real-time coupling mechanism for multi-source data in the onboard environment, thus failing to jointly identify vehicle trajectory, path consistency, and identity spoofing.

[0008] CN116609797A discloses a GNSS spoofing identification method, device, electronic device, and storage medium. It calculates the credibility of the positioning data by matching and comparing GNSS positioning data acquired by a positioning device with target trusted data provided by a secure terminal. It cleverly utilizes the secure terminal's signature verification mechanism to improve the accuracy of GNSS data authenticity judgment, effectively reducing false detection and false negative rates. However, this invention is essentially a static identification mechanism based on a single information source comparison. The spoofing identification process relies on external trusted data cache verification and lacks dynamic fusion of multi-source information from the vehicle system, such as CAN bus, speed sensor, and ETC communication. Its working logic is similar to a simple comparison of GNSS and CAN bus data, providing only post-event or periodic checks, lacking continuous verification and real-time early warning. When a spoofer can simultaneously forge CAN bus data, the credibility comparison of this method will fail. Furthermore, it does not design detection strategies for identity spoofing or card-swapping spoofing, nor does it achieve multimodal consistency verification of vehicle dynamic behavior. Therefore, it has significant shortcomings in real-time performance, protection depth, and adaptability to complex spoofing scenarios.

[0009] In summary, existing technologies each have their limitations to varying degrees. Detection methods based on a single information source are easily bypassed by sophisticated deception devices, while simple information association methods lack real-time performance and deep fusion capabilities, making them ill-suited for complex and ever-changing deception scenarios. This is precisely the core problem that this invention aims to solve: by deeply fusing multi-source information to construct a dynamic and high-precision motion state trust model, thereby achieving proactive and real-time identification of deception behavior. Summary of the Invention

[0010] The purpose of this section is to outline some aspects of the embodiments of the present invention and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this section, the abstract and title of the invention. Such simplifications or omissions shall not be used to limit the scope of the present invention.

[0011] In view of the aforementioned existing problems, the present invention is proposed.

[0012] To address the aforementioned technical problems, this invention provides the following technical solution: a commercial vehicle Beidou ETC device anti-fraud system based on multi-source information fusion, characterized in that it includes: a data acquisition module for synchronizing satellite positioning information, transaction information, vehicle attitude and motion information, and vehicle underlying state information; a multi-source information fusion and fraud judgment module for performing motion state consistency and integrity monitoring based on adaptive extended Kalman filtering, and combining ETC transaction information to perform multi-dimensional fraud behavior judgment; and a data processing and response module for generating a mathematically traceable evidence chain when fraud behavior is determined to have occurred, and performing local storage and remote real-time reporting.

[0013] As a preferred embodiment of the present invention, the data acquisition module includes: a BeiDou GNSS module, used to calculate the vehicle's longitude, latitude, elevation, speed, heading, and time information based on satellite and other compatible GNSS signals, and output quality assessment parameters; an ETC communication module, using DSRC technology to communicate with the roadside unit, used to read the vehicle identity information in the ETC card and obtain the transaction information when the vehicle passes through the ETC gantry; an IMU sensor module, with a built-in three-axis accelerometer and three-axis gyroscope, outputting the vehicle's three-axis acceleration and angular velocity data to sense the vehicle's dynamic attitude and motion changes; and a vehicle CAN bus interface module, connected to the vehicle's controller area network via an OBD interface or direct connection, to read the status data of the vehicle's underlying sensors and ECU.

[0014] This invention also provides the following technical solution: a method for preventing fraud in commercial vehicle Beidou ETC devices based on multi-source information fusion, further comprising: synchronously collecting Beidou GNSS data, IMU data, and CAN bus data with a unified time reference; using IMU data and CAN bus wheel speed data to predict the theoretical motion state of the vehicle at high frequency through a dead reckoning algorithm; using Beidou GNSS data as an observation value and fusing it with the theoretical motion state; dynamically adjusting the noise parameters of the Kalman filter during the fusion process, and performing a Chi-Squared (χ²) analysis on the difference between the observation value and the theoretical motion state. 2The statistical hypothesis test of the distribution is performed; when a vehicle triggers a transaction by passing through the ETC gantry, multi-level verification is immediately performed; based on the comprehensive verification results, multi-level alarm logic is used to make a final judgment on the fraudulent behavior, and trigger the corresponding data storage, evidence generation and real-time alarm reporting process.

[0015] As a preferred embodiment of the present invention, the high-frequency prediction of the theoretical motion state of the vehicle using the dead reckoning algorithm includes: constructing a vehicle motion state trust model using an adaptive local Kalman filter algorithm based on the acceleration, angular velocity information provided by the IMU sensor module and the wheel speed information provided by the vehicle CAN bus interface module; solving the measurement values ​​of the BeiDou GNSS module using least squares or Kalman filtering; taking the optimal estimate of the current time k in the vehicle motion state trust model as the predicted state of this Kalman filter, and using the solution result of the BeiDou GNSS module as the observation value for fusion and consistency verification.

[0016] As a preferred embodiment of the present invention, the core parameters of the Kalman filter are defined as follows: state vector ,in, Indicates location, Indicates speed, Indicates northward. Indicates eastward. The time is indicated by: process noise covariance matrix Q and measurement noise covariance matrix R for the wheel speed sensor; the initial value of the process noise covariance matrix Q is determined based on the IMU sensor datasheet and empirical values ​​from actual vehicle tests under stable road conditions; the initial value of the measurement noise covariance matrix R for the wheel speed sensor is determined based on the accuracy specifications of the wheel speed sensor and actual vehicle measurements under non-slip conditions.

[0017] As a preferred embodiment of the present invention, the dynamic joint adaptive correction of the process noise covariance matrix Q includes:

[0018] γ=1+

[0019] Where γ is the amplification factor, >0 represents the proportionality coefficient. The longitudinal acceleration is obtained in real time by the accelerometer of the onboard IMU; The yaw rate is obtained in real time by the onboard IMU. Let the intensity of the exercise be a function, defined as:

[0020]

[0021] in, and These are the normalized baseline values ​​for longitudinal acceleration and yaw rate, respectively; the corrected process noise covariance matrix. for: The dynamic joint adaptive correction of the measurement noise covariance matrix R includes:

[0022]

[0023] =

[0024] in, As a penalty factor, >0 represents the proportionality coefficient. Indicates the inertial navigation interpretation speed Compared with wheel speed sensor observations deviation, This is the ABS status indicator, where 1 indicates ABS is triggered and 0 indicates it is not triggered. The comprehensive weighting function is defined as follows:

[0025]

[0026] in, For speed normalization, These are the weighting coefficients; the corrected measurement noise covariance matrix for the wheel speed sensor. for: .

[0027] In a preferred embodiment of the present invention, the Kalman filter performs prediction and update once per sampling period.

[0028] The prediction is divided into attitude update and inertial navigation prediction;

[0029] The attitude update utilizes the angular velocity measured by the IMU three-axis gyroscope, and updates the vehicle's attitude in real time through integration;

[0030] The attitude calculation is performed using the quaternion method;

[0031] Attitude is obtained based on the angular velocity increment of the IMU gyroscope in each sampling period. The attitude at the current moment is obtained by iterative integration from the attitude at the previous moment.

[0032] As a preferred embodiment of the present invention, the inertial navigation prediction includes:

[0033] Acceleration measured using an IMU triaxial accelerometer Through the attitude matrix By projecting from the vehicle coordinate system to the local plane coordinate system and subtracting the gravitational acceleration g, we obtain the vehicle's acceleration in the local coordinate system. ;

[0034] Using acceleration Perform dead reckoning to predict the state at the next moment. And calculate the predicted covariance matrix. :

[0035]

[0036]

[0037] in, It is the state transition matrix. It is a control input matrix. It is the acceleration measurement value provided by the IMU accelerometer, where T is the transpose;

[0038] Using wheel speed observations from the vehicle's CAN bus Update the predicted state, including:

[0039] First, calculate the Kalman gain. The calculation formula is as follows:

[0040] ;

[0041] For the state vector Covariance Matrix Make corrections:

[0042]

[0043]

[0044] Where I is the identity matrix, These are the obtained wheel speed observation values. It is the observation matrix, mapped to the total forward velocity via the heading angle ψ: .

[0045] As a preferred embodiment of the present invention, fusing with the theoretical motion state includes: taking a state vector. Covariance Matrix These serve as the prior states for GNSS fusion at the current moment. and prior covariance ; Obtain the wheel velocity observation value from the Beidou GNSS module at the current moment. It then performs the Kalman filter update step and calculates the innovation vector. :

[0046]

[0047] Calculate the normalized innovation squared value (NIS) in the multi-source information fusion and deception detection module:

[0048]

[0049]

[0050]

[0051] in, Let NIS be the information covariance matrix, with dimensions 4×4; NIS is a dimensionless scalar. It is a 4×4 unit observation matrix. For GNSS measurement noise covariance matrix,

[0052] This is the dynamically adjusted GNSS measurement noise covariance matrix. This is a scaling factor related to the observation quality.

[0053] As a preferred embodiment of the present invention, the multi-layer verification includes consistency verification of the vehicle's fixed identity and ETC card identity, as well as spatiotemporal consistency verification of the gantry's geographical location and the current filtered location; the multi-level alarm logic for the final judgment of deception includes: if the identity consistency verification fails or the Chi-Squared (χ²) error occurs... 2 If a GNSS spoofing test is performed and a spatiotemporal inconsistency occurs simultaneously, then the spoofing signal is confirmed; if Chi-Squared(χ²) is also present, then the spoofing signal is confirmed. 2 If the GNSS spoofing is detected, it is considered a highly suspicious spoofing signal; if the results at a single point or the spatiotemporal inconsistency over a short period of time is not consistent, but the Chi-Squared (χ²) result is consistent, it is considered a highly suspicious spoofing signal. 2 If the test is normal, it is determined to be a transient anomaly.

[0054] The beneficial effects of this invention are as follows: This invention not only accurately identifies identity fraud such as "license plate / card swapping" through identity consistency verification, but also effectively identifies "trajectory forgery" based on GNSS deception through AEK and Chi-Squared testing mechanisms, achieving comprehensive defense against mainstream ETC fraud methods. The adaptive filtering mechanism can closely track the real dynamics of vehicles, while the discrimination method based on statistical hypothesis testing can effectively distinguish between random noise and maliciously injected systematic biases, greatly reducing the false alarm rate in complex environments such as tunnel entrances and urban canyons compared to the fixed threshold method. This invention is entirely based on mature filtering theory and statistical methods, with controllable computational complexity, requiring no dedicated AI hardware acceleration unit, making it very suitable for deployment on cost-sensitive and resource-constrained in-vehicle embedded platforms. The system can quickly detect and respond within seconds of a fraud attack occurring. The generated "mathematically traceable" evidence chain includes algorithm-level judgment criteria (such as NIS values, test statistics, etc.), with high evidentiary strength, providing solid technical support for subsequent recovery. Attached Figure Description

[0055] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0056] Figure 1 This is a schematic diagram of the functional module structure of the anti-fraud system for Beidou ETC devices in commercial vehicles based on multi-source information fusion, as shown in this invention.

[0057] Figure 2 This is an overall flowchart of the anti-fraud method for Beidou ETC devices in commercial vehicles based on multi-source information fusion, as shown in this invention.

[0058] Figure 3 This is a flowchart of the adaptive Kalman filtering and chi-square test as shown in this invention. Detailed Implementation

[0059] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0060] Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort should fall within the scope of protection of this invention.

[0061] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0062] According to an embodiment of the present invention, in combination Figure 1 The schematic diagram shown illustrates a modular structure of a commercial vehicle Beidou ETC device anti-fraud system based on multi-source information fusion, comprising:

[0063] The data acquisition module synchronously collects satellite positioning information output by the BeiDou GNSS module, transaction information acquired by the ETC communication module, vehicle attitude and motion information output by the IMU sensor module, and low-level vehicle status information read by the vehicle CAN bus interface module. The multi-source information fusion and deception detection module, as the core of the system, performs motion state consistency and integrity monitoring based on adaptive extended Kalman filtering (AEKF) and combines ETC transaction information to perform multi-dimensional deception behavior detection. The data processing and response module generates a digitally traceable chain of evidence when deception is detected, and performs local storage and remote real-time reporting.

[0064] Specifically, in this embodiment of the invention, the data acquisition module includes:

[0065] Beidou GNSS module: Used to calculate the vehicle's longitude, latitude, altitude, speed, heading and time information based on satellite and other compatible GNSS (such as GPS) signals, and output quality assessment parameters such as satellite number, signal quality, geometric precision factor (HDOP).

[0066] ETC Communication Module: Employs DSRC (Dedicated Short Range Communication) technology to communicate with the Roadside Unit (RSU). When passing through an ETC gantry, it is responsible for reading the vehicle identification information (vehicle type, license plate number, etc.) from the ETC card and obtaining the timestamp of the transaction, the precise geographical coordinates of the gantry, and other information.

[0067] IMU sensor module: Built-in three-axis accelerometer and three-axis gyroscope, outputting three-axis acceleration and angular velocity data of the vehicle at high frequency (e.g., ≥100Hz) to sense the dynamic attitude and motion changes of the vehicle.

[0068] Vehicle CAN bus interface module: It connects to the vehicle's controller area network via OBD interface or direct connection to read the status data of the vehicle's underlying sensors and ECU (electronic control unit), including at least the vehicle speed and steering wheel angle calculated by the wheel speed sensor.

[0069] The multi-source information fusion and deception judgment module internally incorporates the anti-deception algorithm of this invention. It receives multi-source data from the data acquisition module and performs real-time analysis, according to the system's preset significance level (…). The chi-square test is used to determine whether one has been deceived.

[0070] The data processing and response module is responsible for executing actions after a deception event is determined, including storing the deception evidence chain in the local storage and reporting the alarm information and evidence package to the background monitoring and auditing platform in real time through the vehicle communication module (such as 4G / 5G).

[0071] Under the teachings of the above embodiments, such as Figure 2 and Figure 3 As shown, other aspects disclosed in the embodiments of the present invention also propose a method for preventing fraud of Beidou ETC devices for commercial vehicles based on multi-source information fusion, including:

[0072] S1: Synchronously collects BeiDou GNSS data, IMU data, and CAN bus data using a unified time reference.

[0073] After the system is powered on, it is initialized and each sensor module starts working. The system uses the pulse-per-second (PPS) or high-precision time information provided by the BeiDou GNSS module as the unified time reference for the entire system, ensuring that the data from different modules are strictly aligned in time.

[0074] S2: Using IMU data and CAN bus wheel speed data, the theoretical motion state of the vehicle is predicted at high frequency through dead reckoning algorithm.

[0075] S2.1: Utilizing the acceleration and angular velocity information provided by the IMU sensor module and the wheel speed information provided by the vehicle CAN bus interface module, a high-frequency, high-precision vehicle motion state trust model, or trust core, is constructed through an adaptive local Kalman filter algorithm. This model provides continuous and high-precision vehicle position and speed information when GNSS signals are abnormal or lost, and provides a reliable prediction benchmark for subsequent spoofing detection.

[0076] S2.1.1: Define the parameters of the local Kalman filter, where the Kalman filter is used to fuse IMU inertial navigation predictions and wheel speedometer measurements. The core parameters are defined as follows:

[0077] State vector This is used to describe the vehicle's position and velocity in the local plane coordinate system, where... Indicates location, Indicates speed, Indicates northward. Indicates eastward. Indicates the time.

[0078] State covariance matrix , representing the state vector The uncertainty is 4×4. Its initial value is typically set to a large diagonal matrix, with diagonal elements set to 3600 to reflect the high degree of uncertainty in the initial state of the system. As the Kalman filter runs, the state covariance matrix... It will be continuously updated, and its diagonal elements will gradually decrease and tend to stabilize.

[0079] The process noise covariance matrix Q is used to describe the uncertainty of the dead reckoning model (based on IMU and vehicle kinematics model).

[0080] The measurement noise covariance matrix R for the wheel speed sensor is used to describe the uncertainty of the wheel speed sensor measurement.

[0081] It should be noted that, in order to simplify the design of Kalman filters, improve computational efficiency, and facilitate the fusion of multi-source data, the local plane coordinate system is selected here.

[0082] S2.1.2: The initial value of the process noise covariance matrix Q is determined based on the IMU sensor datasheet (zero bias instability, random walk, etc.) and empirical values ​​from real vehicle tests under stable road conditions.

[0083] The initial value of the measurement noise covariance matrix R for the wheel speed sensor is determined based on the accuracy specifications of the wheel speed sensor and the actual vehicle measurement value under non-slip conditions.

[0084] To address the challenges posed by vehicles under varying driving conditions, this invention proposes a navigation fusion method based on adaptive adjustment of the covariance matrix. This method dynamically and adaptively corrects the process noise covariance matrix Q and the measurement noise covariance matrix R for the wheel speed sensors based on the vehicle's dynamic state and sensor anomalies.

[0085] When the vehicle CAN bus interface module detects that the vehicle is in a sharp turn (large steering wheel angle), rapid acceleration, or rapid deceleration, or when the IMU sensor module detects severe vibration, an amplification factor γ is introduced into the diagonal elements of the process noise covariance matrix Q, defined as follows:

[0086] γ=1+

[0087] in, >0 represents the proportionality coefficient. The longitudinal acceleration is obtained in real time by the accelerometer of the onboard IMU; The yaw rate is obtained in real time by the onboard IMU. Let the intensity of the exercise be a function, defined as:

[0088]

[0089] in, and These are the normalized reference values ​​for longitudinal acceleration and yaw rate, respectively, used to eliminate the influence of dimensions.

[0090] Therefore, the corrected process noise covariance matrix for: .

[0091] When the CAN bus detects wheel slippage or the anti-lock braking system (ABS) is activated, a penalty factor β is applied to the diagonal elements of the measurement noise covariance matrix R to reduce the reliability of the wheel speed observation data. The penalty factor β is defined as follows:

[0092]

[0093] =

[0094] in, >0 represents the proportionality coefficient. Indicates the inertial navigation interpretation speed Compared with wheel speed sensor observations deviation, This is the ABS status indicator (1 indicates ABS is triggered, 0 indicates it is not triggered). The comprehensive weighting function is defined as follows:

[0095]

[0096] in, For speed normalization, These are the weighting coefficients. Therefore, the corrected measurement noise covariance matrix... for: .

[0097] S2.1.3: The Kalman filter performs a prediction and update once per sampling period.

[0098] The prediction is divided into attitude update and inertial navigation prediction. Attitude update utilizes the angular velocity measured by the IMU's three-axis gyroscope. The vehicle's attitude is updated in real time through points.

[0099] To avoid the gimbal lock problem inherent in Euler angles, the quaternion method is used for attitude calculation:

[0100]

[0101] in, It is the first derivative of the quaternion, representing the attitude update rate; It is a posture quaternion; It is the quaternion representation of the IMU angular velocity in the carrier coordinate system; It is a quaternion multiplication operator.

[0102] Attitude is obtained based on the angular velocity increment of the IMU gyroscope in each sampling period. The attitude at the current moment is obtained by iterative integration from the attitude at the previous moment.

[0103] Inertial navigation prediction uses acceleration measured by a three-axis IMU accelerometer. Through the attitude matrix (Obtained from quaternion q) Project the vehicle's coordinates from the carrier coordinate system onto the local plane coordinate system in the north / east direction (n / e), and subtract the gravitational acceleration g to obtain the vehicle's acceleration in the local coordinate system. :

[0104]

[0105] Then use acceleration Perform dead reckoning to predict the state at the next moment. And calculate the predicted covariance matrix. :

[0106]

[0107]

[0108] in, It is the state transition matrix. It is a control input matrix. It is the acceleration measurement value provided by the IMU accelerometer, and T is the transpose.

[0109] It should be noted that the state transition matrix is ​​obtained by linearizing the system motion model; the control input matrix represents the changes in position, velocity, and attitude measured by the IMU per unit time.

[0110] Update steps: First, calculate the Kalman gain. The calculation formula is as follows:

[0111]

[0112] In the above formula, the dynamically adjusted measurement noise covariance matrix R is used to calculate the Kalman gain. .when When it increases, It will decrease, thereby reducing the impact of the measured value on the final state correction, and vice versa.

[0113] Furthermore, the state vector and covariance matrix are corrected:

[0114]

[0115]

[0116] Where I is the identity matrix, The wheel speed observation value is obtained from the CAN bus. This is the observation matrix, which maps the northward and eastward velocity components in the state vector to the total forward velocity through the heading angle ψ. .

[0117] Among them, heading angle It is obtained from the attitude update process.

[0118] It should be noted that the Kalman filter uses wheel speed sensor data to correct the speed prediction calculated by inertial navigation, effectively suppressing the accumulation of IMU errors and outputting the optimal fused vehicle state. and covariance matrix .

[0119] It should be noted that the above fused prediction results are reliable in the short term. Considering that IMU errors (such as zero bias and random noise) are integrated with acceleration and angle, the velocity error increases linearly or quadratically with time, and the position error increases quadratically or cubically with time, the short term here is generally no more than 1 minute.

[0120] S2.2: The measurements from the BeiDou GNSS module are solved using least squares or Kalman filtering to obtain the vehicle's latitude, longitude, altitude, three-dimensional velocity, and corresponding covariance matrix in the WGS84 coordinate system. The coordinate system is then transformed to the local horizontal coordinate system, which serves as the measurement value for multi-source information fusion and deception detection. .

[0121] S2.3: Dynamically Adjusting the GNSS Measurement Noise Covariance Matrix The initial values ​​need to be calibrated in advance through static and dynamic tests or assigned according to the specifications of the BeiDou GNSS module.

[0122] When receiving signals from the BeiDou GNSS module with a low number of satellites, a high HDOP (Geometric Precision Factor), a low signal-to-noise ratio, or when multipath effects are detected, the measurement noise covariance matrix is ​​dynamically expanded to reduce the confidence in the observation information. The specific method is as follows:

[0123]

[0124] in, The scaling factor related to observation quality is defined as:

[0125]

[0126] in, Number of visible satellites; Geometric precision factor; This represents the average signal-to-carrier-to-noise ratio. As an indicator of multipath effects; ~ These are weighting coefficients; This is a normalization function used to map various indicators to the [0,1] interval.

[0127] S3: Using BeiDou GNSS data as observations, this data is fused with the predicted theoretical motion state. During the fusion process, the noise parameters of the Kalman filter are dynamically adjusted, and the difference between the observed and predicted values ​​is analyzed based on Chi-Squared (χ²) values. 2 The statistical hypothesis of the distribution is tested, and finally the state is updated after fusion.

[0128] Take the output of S2.1 and As a priori state for this GNSS update and prior covariance .

[0129] First, the multi-source information fusion and deception detection module obtains the measurement value from the BeiDou GNSS module at the current moment. It then performs the Kalman filter update step and calculates the innovation vector. :

[0130]

[0131] in, It is the innovation vector, with a dimension of 4 x 1; It is a 4 x 4 identity matrix I.

[0132] Secondly, the normalized innovation square value (NIS) is calculated in the multi-source information fusion and deception judgment module.

[0133]

[0134]

[0135] in, Let NIS be the innovation covariance matrix with a dimension of 4×4. NIS is a dimensionless scalar that quantifies the magnitude of the innovation and takes into account uncertainty.

[0136] Under ideal conditions where the system is operating normally without being affected by deceptive signals and the measurement noise follows a Gaussian distribution, a single NIS value follows a chi-square distribution with degrees of freedom equal to the dimension of the observation vector. In this invention, since the observation vector contains position and velocity information and has a dimension of 4, the degrees of freedom of a single NIS value are 4.

[0137] Furthermore, to effectively distinguish between occasional signal anomalies and persistent malicious spoofing, this invention does not rely on a single NIS value for judgment, but instead employs a composite chi-square test based on a sliding window. The composite test statistic is:

[0138] Based on the properties of the chi-square distribution, the statistic... It follows a chi-square distribution with 4N degrees of freedom (N takes the value of 60).

[0139] Null hypothesis H0: GNSS observations and predictions are consistent, and the deviation comes only from Gaussian noise;

[0140] Alternative hypothesis H1: GNSS observations are subject to systematic bias, i.e., they may be deceived.

[0141] The system presets a significance level of α = 0.001 (i.e., a confidence level of 99.9%). When the statistic... When the corresponding threshold is exceeded, the null hypothesis is rejected, the integrity of the GNSS data is determined to be compromised, and a spoofing alarm is triggered.

[0142] It is important to note that there is a trade-off between the sliding window size N and the detection latency and false alarm rate. The smaller the sliding window size N, the lower the detection latency, but the higher the false alarm rate; conversely, the larger the sliding window size N, the lower the false alarm rate, but the higher the detection latency.

[0143] Finally, if the above checks pass, the fused state update is performed, and the Kalman filter gain matrix is ​​calculated. and the updated optimal state estimate Otherwise, no state update will be performed.

[0144] S4: When a vehicle triggers a transaction by passing through an ETC gantry, immediately perform consistency checks on the vehicle's fixed identity, the ETC card identity, and the spatiotemporal consistency check between the gantry's geographical location and the current filtered location.

[0145] Identity consistency verification: Compare the vehicle information (license plate, vehicle model) read from the ETC card with the vehicle information pre-installed in the ETC system to see if they are completely consistent. If they are inconsistent, it is directly judged as "identity fraud".

[0146] Spatiotemporal consistency verification: Compare the distance between the precise geographic coordinates issued by the ETC gantry and the optimal position output by the current Kalman filter of the system, i.e., the output result of S3. If the distance exceeds a reasonable threshold, this invention sets the threshold to 100 meters, and then determines it as a "spatiotemporal anomaly".

[0147] It should be noted that this invention, by triggering identity and spatiotemporal consistency verification when an ETC transaction occurs, can complete dual verification against "identity fraud" and "path fraud" at the instant of the actual vehicle transaction, significantly improving the real-time performance and targeting of anti-fraud detection. The event-driven mechanism can proactively complete identity comparison and spatial consistency judgment without relying on continuous monitoring, avoiding the computational redundancy and response delay caused by traditional periodic detection. Simultaneously, based on real-time difference analysis of gantry coordinates and filter positions, anomalies can be identified in time before fraudulent behavior causes economic losses, achieving simultaneous identification of GNSS path anomalies and identity forgery, thereby improving the protection accuracy and dynamic response capability of the vehicle-mounted system.

[0148] S5: Based on the comprehensive integrity monitoring results, identity verification results, and spatiotemporal verification results, a multi-level alarm logic is used to make the final judgment on the deceptive behavior and trigger the corresponding data storage, evidence generation, and real-time alarm reporting process.

[0149] Spoofing signal confirmation (highest level): Identity consistency check failed or Chi-Squared (χ²) 2 The test results indicated GNSS spoofing, and at the same time, spatiotemporal inconsistency occurred.

[0150] Highly suspicious deception signal (second highest level): Chi-Squared (χ 2 ) Verify and determine GNSS deception.

[0151] Transient anomalies (low level): Inconsistencies in spatiotemporal data at a single location or over short periods, but Chi-Squared (χ²) 2 The test results were normal.

[0152] Based on the discrimination level, the data processing and response module performs the corresponding operation.

[0153] For the highest and second-highest level of deception, a mathematically traceable chain of evidence will be immediately generated, including the original sensor data, Kalman filter intermediate variables (NIS value sequence, Q, R, conditioning records), and test statistics, and then reported in real time.

[0154] Furthermore, after completing one cycle, the system returns to step S2.2 to continue real-time monitoring.

[0155] The system also includes one or more processors and memory.

[0156] The memory is used to store operable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, including the processes of the anti-fraud system for commercial vehicle Beidou ETC devices based on multi-source information fusion as described in the foregoing embodiments, especially... Figure 1 The flowchart of the system is shown.

[0157] Other aspects disclosed in the embodiments of the present invention also propose a computer-readable medium for storing software including instructions executable by one or more computers, which, upon execution, cause the one or more computers to perform operations, including the flow of the anti-fraud system for commercial vehicle Beidou ETC devices based on multi-source information fusion as described in the foregoing embodiments, particularly... Figure 1 The flowchart of the system is shown.

[0158] It should be recognized that embodiments of the present invention may be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable storage medium.

[0159] The method can be implemented using standard programming techniques, including a non-transitory computer-readable storage medium configured with a computer program in the computer program, wherein the storage medium is configured such that the computer operates in a specific and predefined manner.

[0160] Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system; however, if required, the program can be implemented in assembly or machine language.

[0161] In any case, the language can be either compiled or interpreted.

[0162] Furthermore, for this purpose, the program can run on programmed application-specific integrated circuits.

[0163] The processes described herein (or variations and / or combinations thereof) can be executed under the control of one or more computer systems configured with executable instructions, and can be implemented by hardware or a combination thereof as code (e.g., executable instructions, one or more computer programs, or one or more applications) that commonly executes on one or more processors. The computer program includes a plurality of instructions executable by one or more processors.

[0164] Furthermore, the method can be implemented in any suitable type of computing platform, including but not limited to personal computers, minicomputers, mainframes, workstations, networked or distributed computing environments, standalone or integrated computer platforms, or in communication with charged particle tools or other imaging devices.

[0165] Various aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether portable or integrated into a computing platform, such as a hard disk, optical read and / or write storage medium, RAM, ROM, etc., such that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein.

[0166] Furthermore, machine-readable code, or parts thereof, can be transmitted via wired or wireless networks.

[0167] When such media includes instructions or programs that combine with a microprocessor or other data processor to implement the steps described above, the invention described herein includes these and other different types of non-transitory computer-readable storage media.

[0168] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A deception prevention system for Beidou ETC devices in commercial vehicles based on multi-source information fusion, characterized in that, include: The data acquisition module is used to synchronize satellite positioning information, transaction information, vehicle attitude and motion information, and vehicle underlying status information. The multi-source information fusion and deception judgment module is used to perform motion state consistency and integrity monitoring based on adaptive extended Kalman filtering, and to judge multi-dimensional deception behavior in combination with ETC transaction information; The data processing and response module is used to generate a digitally traceable chain of evidence when fraudulent behavior is determined to have occurred, and to store it locally and report it remotely in real time. In the adaptive extended Kalman filter, the process noise covariance matrix Q is dynamically and jointly adaptively corrected. The correction formula includes: γ=1+ Where γ is the amplification factor, >0 represents the proportionality coefficient. The longitudinal acceleration is obtained in real time by the accelerometer of the onboard IMU; The yaw rate is obtained in real time by the onboard IMU. Let the intensity of the exercise be a function, defined as: in, and These are the normalized baseline values ​​for longitudinal acceleration and yaw rate, respectively; Corrected process noise covariance matrix for: ; And a dynamic joint adaptive correction is performed on the measurement noise covariance matrix R, the correction formula is: = in, As a penalty factor, >0 represents the proportionality coefficient. Indicates the inertial navigation interpretation speed Compared with wheel speed sensor observations deviation, This is the ABS status indicator, where 1 indicates ABS is triggered and 0 indicates it is not triggered. The comprehensive weighting function is defined as follows: in, For speed normalization, These are the weighting coefficients; Corrected measurement noise covariance matrix for wheel speed sensor for: .

2. The anti-fraud system for commercial vehicle Beidou ETC devices based on multi-source information fusion as described in claim 1, characterized in that: The data acquisition module includes: The BeiDou GNSS module is used to calculate the vehicle's longitude, latitude, altitude, speed, heading, and time information based on satellite and other compatible GNSS signals, and output quality assessment parameters. The ETC communication module uses DSRC technology to communicate with the roadside unit. It is used to read the vehicle identity information in the ETC card and obtain the transaction information when the vehicle passes through the ETC gantry. The IMU sensor module, which integrates a three-axis accelerometer and a three-axis gyroscope, outputs three-axis acceleration and angular velocity data of the vehicle to sense the vehicle's dynamic attitude and motion changes. The vehicle CAN bus interface module connects to the vehicle's controller area network via the OBD interface or direct connection to read the status data of the vehicle's underlying sensors and ECU.

3. A method for preventing fraud of Beidou ETC devices for commercial vehicles based on multi-source information fusion, based on the anti-fraud system for Beidou ETC devices for commercial vehicles based on multi-source information fusion as described in any one of claims 1 to 2, characterized in that: Also includes: Simultaneously collect BeiDou GNSS data, IMU data, and CAN bus data using a unified time reference; Using IMU data and CAN bus wheel speed data, the theoretical motion state of the vehicle is predicted at high frequency through dead reckoning algorithm; BeiDou GNSS data is used as the observed value and fused with the theoretical motion state. During the fusion process, the noise parameters of the Kalman filter are dynamically adjusted, and the difference between the observed value and the theoretical motion state is analyzed based on Chi-Squared (χ²) values. 2 Statistical hypothesis testing of the distribution; When a vehicle triggers a transaction by passing through an ETC gantry, multi-level verification is immediately performed; Based on the comprehensive verification results, a multi-level alarm logic is used to make a final judgment on the deceptive behavior and trigger the corresponding data storage, evidence generation and real-time alarm reporting process.

4. The anti-fraud method for commercial vehicle Beidou ETC devices based on multi-source information fusion as described in claim 3, characterized in that: The high-frequency prediction of the vehicle's theoretical motion state using dead reckoning algorithms includes: Using acceleration and angular velocity information provided by the IMU sensor module and wheel speed information provided by the vehicle CAN bus interface module, an adaptive local Kalman filter algorithm is used to construct a vehicle motion state trust model. The measurement values ​​of the BeiDou GNSS module are solved using least squares or Kalman filtering; In the vehicle motion state trust model, the optimal estimate of the current time k is used as the predicted state of this Kalman filter, and the solution result of the Beidou GNSS module is used as the observation value for fusion and consistency verification.

5. The anti-fraud method for commercial vehicle Beidou ETC devices based on multi-source information fusion as described in claim 4, characterized in that: The core parameters of the Kalman filter are defined as follows: State vector ,in, Indicates location, Indicates speed, Indicates northward. Indicates eastward. Indicates time; The process noise covariance matrix Q and the measurement noise covariance matrix R for the wheel speed sensor; The initial value of the process noise covariance matrix Q is determined based on the IMU sensor datasheet and empirical values ​​from real vehicle tests under stable road conditions. The initial value of the measurement noise covariance matrix R for the wheel speed sensor is determined based on the accuracy specifications of the wheel speed sensor and the actual vehicle measurement value under non-slip conditions.

6. The anti-fraud method for commercial vehicle Beidou ETC devices based on multi-source information fusion as described in claim 5, characterized in that: The Kalman filter performs a prediction and update once per sampling period: The predictions include attitude updates and inertial navigation predictions; The attitude update utilizes the angular velocity measured by the IMU three-axis gyroscope, and updates the vehicle's attitude in real time through integration; The attitude calculation is performed using the quaternion method; Attitude is obtained based on the angular velocity increment of the IMU gyroscope in each sampling period. The attitude at the current moment is obtained by iterative integration from the attitude at the previous moment.

7. The anti-fraud method for commercial vehicle Beidou ETC devices based on multi-source information fusion as described in claim 6, characterized in that: The inertial navigation prediction includes: Acceleration measured using an IMU triaxial accelerometer Through the attitude matrix By projecting from the vehicle coordinate system to the local plane coordinate system and subtracting the gravitational acceleration g, we obtain the vehicle's acceleration in the local coordinate system. ; Using acceleration Perform dead reckoning to predict the state vector at the next moment. And calculate the predicted covariance matrix. : in, It is the state transition matrix. It is a control input matrix. This is the acceleration measurement value provided by the IM accelerometer, where T stands for transpose; Using wheel speed observations from the vehicle's CAN bus Update the predicted state, including: Calculate Kalman gain The calculation formula is as follows: ； Correct the state vector and covariance matrix: Where I is the identity matrix, These are the obtained wheel speed observation values. It is the observation matrix, obtained through the heading angle. Mapped to total forward speed: .

8. The anti-fraud method for commercial vehicle Beidou ETC devices based on multi-source information fusion as described in claim 7, characterized in that: Fusion with the theoretical motion state includes: Take the state vector Covariance Matrix These serve as the prior states for GNSS fusion at the current moment. and prior covariance ; Obtain the wheel velocity observation value from the BeiDou GNSS module at the current moment. It then performs the Kalman filter update step and calculates the innovation vector. : Calculate the Normalized Innovation Squared (NIS) value in the multi-source information fusion and deception detection module: in, Let NIS be the information covariance matrix, with dimensions 4×4; NIS is a dimensionless scalar. It is a 4×4 unit observation matrix. For the GNSS measurement noise covariance matrix, This is the dynamically adjusted GNSS measurement noise covariance matrix. This is a scaling factor related to the observation quality.

9. The anti-fraud method for commercial vehicle Beidou ETC devices based on multi-source information fusion as described in claim 8, characterized in that: The multi-layer verification includes consistency verification of the vehicle's fixed identity and ETC card identity, as well as spatiotemporal consistency verification of the gantry's geographical location and the current filtered location. The multi-level alarm logic used for the final determination of deceptive behavior includes: If identity consistency verification fails or Chi-Squared (χ²) 2 If GNSS spoofing is detected and a spatiotemporal inconsistency occurs simultaneously, then the spoofing signal is confirmed. like (χ) 2 If the GNSS signal is detected and identified as spoofing, it is determined to be a highly suspicious spoofing signal. If the results at a single location or over a short period of time are inconsistent in spatiotemporal, but Chi-Squared (χ²) 2 If the test is normal, it is determined to be a transient anomaly.

Images