CN-121637578-B - Commercial vehicle Beidou ETC device anti-deception system and method based on multi-source information fusion

CN121637578BCN 121637578 BCN121637578 BCN 121637578BCN-121637578-B

Abstract

The invention discloses a multi-source information fusion-based commercial vehicle Beidou ETC device anti-deception system and method, which relate to the technical field of intelligent traffic and vehicle-mounted information safety intersection and comprise a data acquisition module, a multi-source information fusion and deception judgment module, a data processing and response module and a data processing and response module, wherein the data acquisition module is used for synchronizing satellite positioning information, transaction information, vehicle posture and motion information and vehicle bottom layer state information, the multi-source information fusion and deception judgment module is used for executing motion state consistency and integrity monitoring based on self-adaptive extended Kalman filtering and carrying out multi-dimensional deception judgment by combining ETC transaction information, and the data processing and response module is used for generating an evidence chain with mathematical traceability and carrying out local storage and remote real-time reporting when deception is judged.

Inventors

DIAO AIGUO
LU YE
GUO YUAN

Assignees

货车之家(南京)科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260204

Claims (9)

1. Commercial car big dipper ETC device anti-fraud system based on multisource information fusion, its characterized in that includes: the data acquisition module is used for synchronizing satellite positioning information, transaction information, vehicle posture and motion information and vehicle bottom layer state information; The multi-source information fusion and deception judging module is used for executing motion state consistency and integrity monitoring based on self-adaptive extended Kalman filtering and carrying out multi-dimensional deception judgment by combining ETC transaction information; The data processing and responding module is used for generating an evidence chain with digital traceability when judging that fraud occurs, and carrying out local storage and remote real-time reporting; In the adaptive extended kalman filtering, dynamic joint adaptive correction is performed on a process noise covariance matrix Q, and a correction formula comprises: γ=1+ Wherein, gamma is an amplifying factor, And >0 is a scaling factor of, The longitudinal acceleration is obtained in real time by an accelerometer of the on-board IMU; The yaw rate is obtained by the vehicle-mounted IMU in real time, As a function of the intensity of the movement, it is defined as: Wherein, the And Normalized reference values of the longitudinal acceleration and the yaw rate, respectively; Corrected process noise covariance matrix The method comprises the following steps: ; And carrying out dynamic joint self-adaptive correction on the measurement noise covariance matrix R, wherein the correction formula is as follows: = Wherein, the In order to be a penalty factor, And >0 is a scaling factor of, Representing inertial navigation interpretation speed And wheel speed sensor observations Is used for the deviation of (a), Is an ABS status indicator, wherein 1 indicates ABS triggered, 0 indicates not triggered, For the comprehensive weight function, it is defined as: Wherein, the For the purpose of the speed normalization, Is a weight coefficient; corrected measurement noise covariance matrix for wheel speed sensor The method comprises the following steps: 。
2. the multi-source information fusion-based commercial vehicle Beidou ETC device anti-deception system of claim 1, wherein the data acquisition module comprises: The Beidou GNSS module is used for calculating longitude, latitude, elevation, speed, course and time information of the vehicle according to satellites and other compatible GNSS signals and outputting quality evaluation parameters; The ETC communication module is communicated with the road side unit by adopting a DSRC technology and is used for reading the vehicle identity information in the ETC card and acquiring the transaction information when the vehicle passes through the ETC portal; The IMU sensor module is internally provided with a triaxial accelerometer and a triaxial gyroscope, outputs triaxial acceleration and angular velocity data of the vehicle, and senses dynamic posture and motion change of the vehicle; And the vehicle CAN bus interface module is accessed into a controller local area network of the vehicle through an OBD interface or a direct connection mode, and reads state data of a vehicle bottom sensor and an ECU.
3. The commercial vehicle Beidou ETC device anti-deception method based on multi-source information fusion is based on the commercial vehicle Beidou ETC device anti-deception system based on multi-source information fusion as claimed in any one of claims 1-2, and is characterized by further comprising: synchronously acquiring Beidou GNSS data, IMU data and CAN bus data according to a unified time reference; predicting the theoretical motion state of the vehicle at high frequency by using IMU data and CAN bus wheel speed data through a dead reckoning algorithm; Taking Beidou GNSS data as an observation value, fusing the Beidou GNSS data with the theoretical motion state, dynamically adjusting noise parameters of a Kalman filter in the fusion process, and carrying out statistical hypothesis test based on Chi-square (χ 2 ) distribution on the difference between the observation value and the theoretical motion state; When the vehicle triggers a transaction through the ETC portal, immediately executing multi-layer verification; And (3) comprehensively checking the result, finally judging the fraud by adopting a multi-stage alarm logic, and triggering corresponding data storage, evidence generation and real-time alarm reporting processes.
4. The method for preventing cheating by the Beidou ETC device of the commercial vehicle based on multi-source information fusion as set forth in claim 3, wherein the step of predicting the theoretical motion state of the vehicle at high frequency through a dead reckoning algorithm comprises the following steps: utilizing acceleration and angular velocity provided by the IMU sensor module and wheel speed information provided by the vehicle CAN bus interface module to construct a vehicle motion state trust model through a self-adaptive local Kalman filtering algorithm; the least square or Kalman filtering is adopted to calculate the measured value of the Beidou GNSS module; And taking the optimal estimation of the current moment k in the vehicle motion state trust model as the prediction state of the Kalman filtering, taking the resolving result of the Beidou GNSS module as an observation value, and carrying out fusion and consistency check.
5. The method for preventing cheating of the Beidou ETC device of the commercial vehicle based on multi-source information fusion as set forth in claim 4, wherein the kernel parameters of the Kalman filter are defined as follows: state vector , wherein, The position is indicated by the position of the object, The speed is indicated by the velocity of the light, Indicating the north direction of the wafer, Indicating the direction of the east, Representing the time; A process noise covariance matrix Q and a measurement noise covariance matrix R for the wheel speed sensor; The initial value of the process noise covariance matrix Q is determined according to a data manual of the IMU sensor and a real vehicle test experience value under stable road conditions; the initial value of the measurement noise covariance matrix R for the wheel speed sensor is determined according to the accuracy specification of the wheel speed sensor and the actual vehicle measurement value in the slip-free state.
6. The method for preventing fraud of the Beidou ETC device of the commercial vehicle based on multi-source information fusion as set forth in claim 5, wherein the Kalman filter performs prediction and updating once in each sampling period: the predictions include attitude update and inertial navigation predictions; The attitude updating utilizes the angular velocity measured by the IMU triaxial gyroscope to update the attitude of the vehicle in real time through integration; performing gesture calculation by adopting a quaternion method; The attitude acquisition is based on the angular velocity increment of the IMU gyroscope in each sampling period, and the attitude at the current moment is obtained from the attitude at the previous moment in a recursion mode through an iterative integration mode.
7. The method for preventing cheating of the Beidou ETC device of the commercial vehicle based on multi-source information fusion of claim 6 is characterized in that the inertial navigation prediction comprises: acceleration measured by IMU triaxial accelerometer By means of a gesture matrix Projecting from the carrier coordinate system to the ground plane coordinate system, and subtracting the gravitational acceleration g to obtain the acceleration of the vehicle in the local coordinate system ; Using acceleration Dead reckoning and predicting a state vector at a next time And calculates a predicted covariance matrix : Wherein, the Is a state transition matrix that is a state transition matrix, Is a matrix of control inputs, The acceleration measurement value provided by the IM accelerometer is provided, and T is the transposition; Using wheel speed observations from a vehicle CAN bus Updating the predicted state includes: Calculating Kalman gain The calculation formula is as follows: ; correcting the state vector and the covariance matrix: wherein I is an identity matrix, Is an obtained wheel speed observation value, Is an observation matrix through course angle Mapped to the total forward speed: 。
8. the method for preventing cheating by using the Beidou ETC device of commercial vehicle based on multi-source information fusion as set forth in claim 7, wherein the fusion with the theoretical motion state comprises the following steps: Taking state vectors Sum covariance matrix Respectively used as prior states of GNSS fusion at the current moment Prior covariance ; Acquiring wheel speed observation value from Beidou GNSS module at current moment And performing the updating step of Kalman filtering to calculate the innovation vector : Calculating a normalized innovation square value NIS in a multi-source information fusion and deception judgment module: Wherein, the For the innovation covariance matrix, the dimension is 4 x 4, nis is a dimensionless scalar, Is a unit observation matrix of 4 x 4, For a GNSS to measure a noise covariance matrix, For a dynamically adjusted GNSS survey noise covariance matrix, Is a scaling factor related to the observed quality.
9. The method for preventing cheating of the Beidou ETC device of the commercial vehicle based on multi-source information fusion of claim 8, wherein the multi-layer verification comprises consistency verification of a vehicle curing identity and an ETC card identity and space-time consistency verification of a portal geographic position and a current filtered position; final discrimination of fraud using multi-level alert logic includes: If the identity consistency check fails or the Chi-square (χ 2 ) check judges GNSS deception and simultaneously the space-time inconsistency occurs, judging that deception signal confirmation is carried out; If it is (Χ 2 ) checking to determine GNSS fraud, determining a highly suspected fraud signal; If the single point result or the short time space is inconsistent, but the Chi-square (χ 2 ) is checked to be normal, the instantaneous abnormality is determined.

Description

Commercial vehicle Beidou ETC device anti-deception system and method based on multi-source information fusion Technical Field The invention relates to the technical field of intelligent traffic and vehicle-mounted information safety intersection, in particular to a commercial vehicle Beidou ETC device anti-deception system and method based on multi-source information fusion. Background With the rapid development of expressway networks, electronic Toll Collection (ETC) systems have become a core infrastructure for improving traffic efficiency and realizing intelligent traffic. Meanwhile, according to related policy and regulation, commercial operation vehicles such as heavy trucks, coaches, dangerous goods transport vehicles (abbreviated as 'two passengers and one danger') and the like must be installed and used with a vehicle-mounted terminal of a Beidou satellite navigation system so as to realize real-time dynamic monitoring and management of the vehicles. Therefore, the intelligent vehicle-mounted terminal integrating the ETC function and the Beidou positioning function has become standard configuration in the field of commercial vehicles. The traffic cost of the commercial vehicle is generally calculated stepwise according to the factors of vehicle type, axle number, gross weight, driving mileage and the like, and the rate of the commercial vehicle is far higher than that of a common small-sized passenger car. Currently, the main current ETC fraud is mainly divided into two categories, identity fraud and path fraud. At present, the main technologies for dealing with the cheating signals of the vehicle-mounted terminal can be divided into two main categories, namely detection based on a single information source and detection based on simple information association. Detection based on a single information source relies primarily on a single sensor data source, the characteristics of which are analyzed to identify abnormal behavior. The most common method is to monitor the integrity of the GNSS signals and analyze the data of the CAN bus abnormally. The detection based on simple information association is to simply combine a plurality of information sources to perform post-event or in-event preliminary comparison, such as simple comparison of GNSS and CAN bus data and background binding of ETC card and vehicle model. The simple comparison of GNSS and CAN bus data is a common practice at present, CAN provide basic precaution capability, and CAN be used for post-inspection. But this association is static and coarse, lacking a dynamic, continuous authentication mechanism. Such comparison may fail if a fraudster is able to synchronously falsify CAN bus data. Meanwhile, the method mainly relies on post-hoc data analysis, lacks real-time early warning capability, and cannot immediately give an alarm or prevent cheating. The method for binding the ETC card and the background of the vehicle model can effectively prevent identity fraud such as fake license plate or card changing. But relies on accurate identification of the portal camera system and verification can only be done when an ETC transaction occurs. For illegal card changing behavior which is not recognized by the camera system or deception which occurs during the driving of the expressway, the method cannot cope with. CN116794966a discloses a system, a method, an electronic device and a storage medium for the Beidou safety time service of rail transit, which are communicated with the time service systems of stations through a control center to realize time synchronization, and an anti-interference and anti-deception reinforcement is carried out by utilizing a time service safety protection unit. The star-like time service system improves clock consistency and time service safety in rail transit, and realizes protection of time service link layers. However, its protection object is mainly a fixed node of rail traffic, and the core focus is on "time synchronization" rather than "athletic performance verification". The method is still in the safety reinforcement category based on GNSS signal integrity monitoring, namely whether the signal is interfered or deceptively judged by detecting the characteristic parameters such as signal power, chip phase, doppler frequency shift and the like. Because the method cannot effectively distinguish the real satellite signals from the high-simulation deception signals, the protection capability mainly depends on an external signal protection unit, and is not used for dynamic consistency analysis in the terminal. In addition, the track traffic scene is a closed system, and a real-time coupling mechanism of multi-source data in a vehicle-mounted environment is lacked, so that joint identification cannot be carried out on the running track, the path consistency and the identity spoofing of the vehicle. CN116609797a discloses a GNSS spoofing identification method, a device, an electronic apparatus and a storage medium, and