Automobile intelligent traffic control integrated system based on electrical and electronic technology

Abstract

The invention discloses an automobile intelligent traffic control integrated system based on an electrical and electronic technology, and the system comprises a traffic flow monitoring module which is used for monitoring the traffic flow on a road, and obtaining the number of vehicles and the driving speed data; the acquired data are sent to the central control module; the central control module comprises a processor, a storage unit and a communication interface and is used for receiving the data transmitted by the traffic flow monitoring module and analyzing and processing the data; the signal lamp control module is used for controlling the traffic signal lamps by adjusting the on-off time and the switching sequence of the signal lamps according to the instruction sent by the central control module; and the vehicle communication module is mounted on the vehicle and used for communication between vehicles and between the vehicle and the infrastructure. According to the invention, accurate monitoring, intelligent signal lamp control and traffic optimization, real-time navigation and energy-saving travel, cooperative communication and automatic driving development, energy optimization and power grid stability can be realized, and data security and traceability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation, and more particularly to an intelligent transportation control integration system for vehicles based on electrical and electronic technology. Background Art

[0002] With the acceleration of the urbanization process and the continuous growth of the vehicle ownership, problems such as traffic congestion and traffic safety have become increasingly severe. The traditional traffic management methods are gradually difficult to meet the requirements, and the intelligent transportation system has emerged as the times require. However, there are many problems to be solved in the existing intelligent transportation technologies, which are mainly reflected in the following aspects:

[0003] 1) Traditional traffic flow monitoring means, such as geomagnetic sensors, induction coils, etc., are greatly affected by environmental factors, with limited monitoring ranges, and cannot accurately obtain detailed information such as the driving speed and trajectory of vehicles in real time. Facing complex road conditions and changing traffic situations, it is difficult to quickly and accurately master the dynamic changes of traffic flow, and the data support provided for traffic management decisions is not timely and accurate enough;

[0004] 2) The existing traffic data analysis methods are often limited to simple data statistics and analysis, and cannot fully explore the spatio-temporal correlation characteristics in traffic flow data. When predicting traffic flow changes, the accuracy is not high, and it is difficult to formulate effective traffic guidance and planning strategies in advance, resulting in the traffic congestion situation not being alleviated in time and reducing the road traffic efficiency;

[0005] 3) At present, most signal lamp control methods are controlled according to fixed timing schemes or simple traffic flow detection results, and cannot be dynamically adjusted according to real-time traffic conditions. In case of uneven traffic flow or sudden traffic events, problems such as waste of green light time and too long vehicle waiting time are likely to occur, and the optimal allocation of traffic resources cannot be achieved, further exacerbating traffic congestion;

[0006] 4) Although the in-vehicle navigation system can provide route planning for drivers, the traffic information obtained often has a delay and cannot reflect the actual situations such as road congestion and accidents in real time. When planning routes, factors such as real-time traffic flow changes and vehicle energy consumption are not fully considered, resulting in the planned route may not be optimal and cannot effectively guide drivers to avoid congested sections and save travel time and costs;

[0007] 5) The communication technologies between vehicles and between vehicles and infrastructure are not yet mature, with poor information interaction, and it is difficult to achieve efficient coordination between vehicles and the traffic system. In the context of the gradual popularization of autonomous driving technology, the existing communication methods cannot meet the requirements of autonomous driving vehicles for real-time and accurate traffic information, restricting the application and development of autonomous driving technology in complex traffic environments;

[0008] Therefore, those skilled in the art are committed to providing an automotive intelligent traffic control integration system based on electrical and electronic technology. Summary of the Invention

[0009] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is to provide an automotive intelligent traffic control integration system based on electrical and electronic technology.

[0010] To achieve the above object, the present invention provides an automotive intelligent traffic control integration system based on electrical and electronic technology, including:

[0011] Traffic flow monitoring module: used to monitor the traffic flow on the road, obtain vehicle quantity and driving speed data; and send the obtained data to the central control module;

[0012] Central control module: includes a processor, a storage unit and a communication interface, used to receive the data transmitted by the traffic flow monitoring module and analyze and process the data;

[0013] Signal lamp control module: according to the instructions sent by the central control module, control the traffic signal lamp by adjusting the on-off time and switching sequence of the signal lamp;

[0014] Navigation information push module: communicates with the in-vehicle navigation system, obtains data from the central control module, uses the path planning algorithm to plan a route for the driver, and pushes the traffic information and the planned route to the in-vehicle navigation system for the driver to view;

[0015] Vehicle communication module: installed on the vehicle, used for communication between vehicle and vehicle, vehicle and infrastructure.

[0016] Further, the traffic flow monitoring module includes:

[0017] A millimeter-wave radar array is set on both sides or above the detected road, and it works by emitting millimeter-wave signals and receiving the echo signals reflected by the target vehicle. The driving speed of the vehicle is calculated according to the frequency change of the echo signal. When the vehicle enters the detection area of the radar array, the radar will track the position change of the vehicle. By analyzing the time series of the radar signal and combining the detection data of different radars in the array, the trajectory of each vehicle is identified and the vehicle quantity is counted.

[0018] Further, the calculation of the driving speed of the vehicle according to the frequency change of the echo signal is specifically:

[0019] The radar emits multiple millimeter-wave signals with different frequencies, and the emitted frequencies are respectively f1, f2,... f n, when these signals of different frequencies propagate in space, they will generate reflected echoes when encountering a vehicle. The radar receives these echo signals and separates and collects the echoes corresponding to each frequency;

[0020] According to the Doppler effect, when there is relative motion between the vehicle and the radar, the frequency of the echo signal will change. For a transmitted signal with a frequency of f i , the Doppler frequency shift f di of its echo is:

[0021]

[0022] where u is the radial velocity of the vehicle relative to the radar;

[0023] is the wavelength of the millimeter-wave signal with a frequency of f i , and c is the speed of light;

[0024] By performing spectral analysis on the echo signals of each frequency, the corresponding Doppler frequency shift f di is obtained;

[0025] Using the multiple Doppler frequency shift information obtained by transmitting multi-frequency signals, the preliminary speed of the vehicle is calculated by means of weighted fusion. A weight w i is assigned to the Doppler frequency shift corresponding to each frequency. The determination of the weight considers factors such as signal strength and frequency stability; the preliminary speed of the vehicle is u pre , and the u pre is:

[0026]

[0027] where, is the coefficient in the formula, which is derived from the relevant principles of the Doppler effect and is used to convert the subsequent calculation results into the actual speed;

[0028] is the summation expression, where n represents the number of different frequency signals transmitted by the radar; i is a counting variable from 1 to n; w i is the weight corresponding to the i-th frequency signal, f di is the Doppler frequency shift of the echo of the i-th frequency signal; λ i is the wavelength of the i-th frequency signal;

[0029] is the sum of the weights of all n frequency signals, which is used to eliminate the influence of the total weight on the calculation results;

[0030] The preliminarily calculated speed u preAnd the echo signal characteristics of each frequency are used as inputs and fed into a pre-trained machine learning model. During the training phase of the model, vehicle speed data and corresponding radar echo data in different scenarios are used. The model corrects the initial speed by learning the relationships between the data.

[0031] By monitoring the rate of change of the distance and the angle change between the radar and the vehicle.

[0032] Furthermore, in the central control module, the analysis and processing of data specifically include:

[0033] Calculating the parameters of traffic flow through a processor;

[0034] Using an analysis model based on a spatio-temporal graph convolutional network to mine spatio-temporal correlation features in traffic flow data. The output of the model is used to predict traffic flow changes, where

[0035] yt+k = gST-GCN(X t ,A)

[0036] where yt+k represents the predicted value of traffic flow at the future k-th moment;

[0037] gST-GCN represents the spatio-temporal graph convolutional network function, which mines spatio-temporal correlation features in the data through specific spatio-temporal graph convolutional operations on the input data;

[0038] X t, is the traffic flow data at time t;

[0039] A is the adjacency matrix of the traffic network;

[0040] Adopt anomaly detection combining isolation forest and deep autoencoder. Identify the isolated points in the data through the isolation forest, learn the normal patterns of the data through the deep autoencoder, and detect anomalies by comparing the differences between the actual data and the learned normal patterns, where

[0041] where E is the anomaly score, X is the actual data, is the data reconstructed by the deep autoencoder. When E exceeds the preset threshold, it is determined as abnormal data.

[0042] Furthermore, before the analysis and processing of the data, data reception is also included, specifically:

[0043] The traffic flow monitoring module is connected to the communication interface of the central control module; when the data is transmitted to the central control module, the data is verified through the communication interface. By using the method of combining cyclic redundancy check and hash algorithm, it is detected whether there are errors in the data during the transmission process, and the data source and transmission path are located through the hash value.

[0044] Further, the storage unit adopts a distributed storage architecture to classify and store the received traffic flow data. For real-time data with high-frequency updates, an in-memory database is used for caching. For historical data, it is stored in a disk array. At the same time, the stored data is compressed.

[0045] Further, the specific method of cyclic redundancy check is as follows:

[0046] Set the rule for dynamically generating polynomials, pre-define a polynomial library, and select a generating polynomial from it;

[0047] Receive the data D to be transmitted and determine its length n. According to the determined dynamic generating polynomial, select or dynamically generate a generating polynomial G(x) from the polynomial library, and determine its highest order r. The generating polynomial is a binary number with r + 1 bits in binary representation;

[0048] Add r zeros at the end of the data D to obtain a new data sequence D', making its length become n + r to reserve space for subsequent modulo-2 division operations;

[0049] Divide D' by the binary number corresponding to the generating polynomial G(x) to perform modulo-2 division. In each step of the modulo-2 division operation, determine the remainder obtained in that step by performing an exclusive OR operation on the dividend and the divisor. After the operation, the obtained remainder R is the check code, and its length is r bits;

[0050] Replace the r zeros added at the end of the data D with the obtained check code R to form the data T to be finally transmitted. At this time, the length of T is n + r bits;

[0051] After the receiving end receives the data T, also determine the corresponding generating polynomial G(x) according to the pre-agreed dynamic generating polynomial rule, divide the received data T by the binary number corresponding to G(x), and perform the modulo-2 division operation again. If the obtained remainder is 0, it means that the data has not been corrupted during transmission; if the remainder is not 0, it indicates that the data has an error.

[0052] Further, the specific hash algorithm is as follows:

[0053] First, initialize the parameters, set the initial hash value H0, and then determine a set of dynamic weight factors W = [W1, W2,... Wn], and the weight factors are adjusted according to dynamic information;

[0054] Group the data D to be processed to obtain data groups D1, D2,... Dm, and assign a position identifier P = [P1, P2,... Pm] to each data group to record the position information of the group in the original data;

[0055] Starting from the first data packet, calculate the intermediate hash value of each packet. For the i-th data packet Di, the calculation method of its intermediate hash value Hi is as follows:

[0056] Hi = (Hi-1 + Σ(Di[j]) * wj * pj)) % M

[0057] where Hi represents the intermediate hash value calculated for the i-th data packet;

[0058] Hi-1 is the intermediate hash value calculated for the (i - 1)-th data packet;

[0059] Σ(Di[j]) * wj * pj) is a summation expression, where: Di[j] represents the j-th element in the i-th data packet Di;

[0060] wj is a dynamic weight factor, adjusted according to the data, and different wj are used to reflect the different importance degrees of different data elements in the hash value calculation;

[0061] pj is the position identifier of the j-th element in the data packet, recording the position information of the element in the original data, so that data at different positions have different influences on the hash value;

[0062] % is the modulo operator;

[0063] M is a pre-set prime number.

[0064] Furthermore, the control of the traffic signal by adjusting the on / off time and switching sequence of the signal lights includes

[0065] The central control module collects data from the traffic flow monitoring module and the vehicle communication module; cleans the collected data to remove outliers and duplicate data; fuses data from different sources to construct a data set; constructs a multi-dimensional traffic state evaluation index system;

[0066] Predict the change of traffic flow within the next 5 - 15 minutes through machine learning algorithms;

[0067] Dynamically adjust the weights of the evaluation indicators according to the traffic conditions and prediction results;

[0068] Assign priorities to vehicle flows in different directions according to the traffic state evaluation and prediction results;

[0069] Adopt a multi-objective optimization algorithm, with the goal of minimizing the average vehicle waiting time, maximizing the intersection throughput, and balancing the waiting times of vehicle flows in all directions, to generate a control strategy for the signal lights;

[0070] Dynamically adjust the phases of the signal lights according to the changes in traffic conditions.

[0071] The central control module sends the generated signal lamp control instruction to the signal lamp control module;

[0072] After the signal lamp control module executes the instruction, it feeds back the status of the signal lamp and relevant feedback data to the central control module; the central control module monitors the operation of the signal lamp through the received feedback data;

[0073] If the central control module finds that the actual traffic condition does not match the expectation according to the feedback data, it immediately re-evaluates and predicts the traffic state, adjusts the signal lamp control strategy, and sends the control instruction again to achieve dynamic control of the signal lamp.

[0074] Furthermore, it also includes

[0075] A perception fusion module, which is used to integrate environmental data and fuse and process the integrated environmental data with traffic data;

[0076] An autonomous driving cooperation module, which communicates and interacts with autonomous driving vehicles, and is also connected to the traffic flow monitoring module, the central control module, and the navigation information push module to realize data circulation and sharing; it is used to ensure the safe operation of autonomous driving vehicles and assist in optimizing traffic resource allocation;

[0077] An energy management and optimization module, which is interconnected with electric vehicles, smart grids, navigation information push modules, central control modules, and vehicle communication modules; realizes information interaction and sharing.

[0078] The beneficial effects of the present invention are:

[0079] 1) Precise monitoring and efficient decision-making, which can obtain detailed information such as vehicle speed and trajectory in real time and accurately, predict traffic flow changes, formulate dredging and planning strategies in advance, effectively relieve traffic congestion, and improve road traffic efficiency;

[0080] 2) Intelligent signal lamp control optimizes traffic, reduces the waste of green light time, balances the waiting time of vehicle flows in all directions, significantly improves the passing capacity of intersections, and can quickly respond and flexibly adjust signal lamps in case of unbalanced traffic flow or sudden accidents to ensure smooth traffic;

[0081] 3) Real-time navigation and energy-saving travel, plan the optimal route, ordinary vehicles can avoid congested sections and save travel time; electric vehicles can also plan driving and charging schemes in combination with battery power and the distribution of charging piles to achieve energy-saving travel, which not only improves travel efficiency, but also reduces vehicle energy consumption and emissions;

[0082] 4) Cooperative communication and the development of autonomous driving, provide real-time traffic instructions and guidance for vehicles, ensure the safe operation of autonomous driving vehicles, and at the same time, promote the wide application of autonomous driving technology in complex traffic environments;

[0083] 5) Energy optimization and grid stability, reducing the burden on the power grid, preventing electric vehicles from running out of power during driving, with the navigation information push module guiding the driver to charge reasonably, and the vehicle communication module promoting energy information interaction to improve energy utilization efficiency;

[0084] 6) Data security and system reliability, ensuring stable data transmission, detecting errors and locating the source path, classifying and storing data and compressing it to improve data security and traceability, and ensuring the reliable operation of the system. Description of the Drawings

[0085] Figure 1 It is a schematic diagram of the system structure of a specific embodiment of the present invention.

[0086] Figure 2 It is a flowchart of the traffic control integration system in the present invention. Specific Embodiments

[0087] The present invention will be further described below with reference to the drawings and embodiments:

[0088] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0089] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installed", "set", "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0090] As Figures 1 to 2 shown,

[0091] An intelligent vehicle traffic control integration system based on electrical and electronic technology includes:

[0092] S100: Traffic flow monitoring module: used to monitor the traffic flow on the road, obtain vehicle quantity and driving speed data; and send the obtained data to the central control module;

[0093] S110: Central control module: It includes a processor, a storage unit, and a communication interface, and is used to receive the data transmitted by the traffic flow monitoring module and analyze and process the data.

[0094] S120: Signal light control module: According to the instructions sent by the central control module, it controls the traffic signal lights by adjusting the on-off time and switching sequence of the signal lights.

[0095] S130: Navigation information push module: Communicates with the in-vehicle navigation system, obtains data from the central control module, uses path planning algorithms to plan the optimal route for the driver to avoid congested sections, and pushes traffic information and the planned route to the in-vehicle navigation system for the driver to view.

[0096] S140: Vehicle communication module: Installed on the vehicle, it is used for communication between vehicle and vehicle (V2V) and between vehicle and infrastructure (V2I).

[0097] The traffic flow monitoring module includes:

[0098] Millimeter-wave radar arrays are set on both sides or above the detected road (such as street lamp poles, gantries), and they work by emitting millimeter-wave signals and receiving the echo signals reflected by the target vehicles. The driving speed of the vehicle is calculated based on the frequency change of the echo signal. When the vehicle enters the detection area of the radar array, the radar will track the position change of the vehicle. By analyzing the time series of the radar signals and combining the detection data of different radars in the array, the trajectory of each vehicle is identified and the number of vehicles is counted.

[0099] The calculation of the driving speed of the vehicle according to the frequency change of the echo signal is specifically:

[0100] The radar emits multiple millimeter-wave signals with different frequencies, and the emitted frequencies are set as f1, f2, … f n , When these signals with different frequencies propagate in space and encounter a vehicle, they will generate reflected echo signals. The radar receives these echo signals and separates and collects the echo corresponding to each frequency; the echo signals with different frequencies are separated by a filter bank and sent to the corresponding receiving channels for digital processing.

[0101] According to the Doppler effect, when there is relative motion between the vehicle and the radar, the frequency of the echo signal will change. For the transmitted signal with frequency f i , the Doppler frequency shift f di of its echo is:

[0102]

[0103] where u is the radial velocity of the vehicle relative to the radar; (i.e., the component of the vehicle's traveling speed in the direction of the radar's line of sight)

[0104] is the wavelength of the millimeter-wave signal with frequency f i , c is the speed of light;

[0105] By performing spectral analysis on the echo signals of each frequency (such as using the fast Fourier transform FFT), the corresponding Doppler frequency shift f di is obtained; In actual operation, due to the existence of noise and interference, the directly obtained frequency shift may have errors. Therefore, it is necessary to filter the spectral analysis results to remove noise peaks and retain the true Doppler frequency shift signal.

[0106] Using the multiple Doppler frequency shift information obtained by transmitting multi-frequency signals, the preliminary speed of the vehicle is calculated by means of weighted fusion. A weight w i is assigned to the Doppler frequency shift corresponding to each frequency. The determination of the weight takes into account factors such as signal strength and frequency stability; for example, the frequency shift with high signal strength and good frequency stability has a larger corresponding weight. The preliminary speed of the vehicle is u pre , and the u pre is:

[0107]

[0108] where, is the coefficient in the formula, which is derived from the relevant principles of the Doppler effect and is used to convert the subsequent calculation results into the actual speed;

[0109] is the summation expression, where n represents the number of different frequency signals transmitted by the radar; i is the counting variable from 1 to n; w i is the weight corresponding to the i-th frequency signal, and the weight is determined by factors such as signal strength and frequency stability; f di is the Doppler frequency shift of the echo of the i-th frequency signal, which reflects the influence of the vehicle's movement on the signal frequency; λ i is the wavelength of the i-th frequency signal; related to the signal frequency;

[0110] is the summation of the weights of all n frequency signals, which plays a role in normalization and is used to eliminate the influence of the total weight on the calculation results; making the calculation results more representative and accurate; by comprehensively considering the weights, Doppler frequency shifts, and wavelength information of multiple different frequency signals, the preliminary speed of the vehicle is calculated.

[0111] The preliminarily calculated speed u preAnd the echo signal characteristics (signal intensity, phase information, etc.) at each frequency are used as inputs and fed into a pre-trained machine learning model (such as a neural network model). During the training phase of this model, a large amount of vehicle speed data and corresponding radar echo data under different scenarios (such as different weather conditions, different traffic densities, etc.) are used; the model corrects the initial speed by learning the relationships between the data.

[0112] Since the environment is dynamically changing during vehicle driving, the relative position and angle between the radar and the vehicle are also constantly changing. To ensure the accuracy of speed calculation, it is necessary to monitor these changes in real time and make adaptive adjustments to the calculation process.

[0113] By monitoring the rate of change of the distance between the radar and the vehicle (which can be obtained by radar measurement) and the angle change (obtained through array signal processing technology). Dynamically adjust the transmission strategy and weight allocation of multi-frequency signals; when the vehicle approaches the radar quickly, increase the transmission power and weight of high-frequency signals to improve the accuracy of speed measurement; when the vehicle turns, re-adjust the signal processing direction according to the angle change to ensure accurate Doppler frequency shift information is always obtained.

[0114] In the central control module, the specific data analysis and processing include:

[0115] Calculate the parameters of traffic flow through a processor; (these parameters include traffic volume, average speed, vehicle density)

[0116] Use an analysis model based on a spatio-temporal graph convolutional network to mine the spatio-temporal correlation features in traffic flow data. This model regards the traffic network as a graph structure, where nodes represent different monitoring points and edges represent the correlation relationships between monitoring points. Through spatio-temporal graph convolutional operations, the mutual influence between spatially adjacent monitoring points and the dynamic changes in the time series are considered simultaneously. The output of the model is used to predict the traffic flow changes in the future for a certain period of time, and is

[0117] yt + k = gST - GCN(X t, A)

[0118] where yt + k represents the predicted value of traffic flow at the future k-th moment; the result obtained after the operation of this model is subsequently used for traffic planning, guidance and other decisions.

[0119] gST - GCN represents the spatio-temporal graph convolutional network function, which is the core operation part of the entire model. By performing specific spatio-temporal graph convolutional operations on the input data, the spatio-temporal correlation features in the data are mined;

[0120] X t, is the traffic flow data at time t; it contains various traffic flow-related information such as traffic volume, vehicle speed, vehicle density, etc.

[0121] A is the adjacency matrix of the traffic network; it is used to help the model consider the mutual influence between spatially adjacent monitoring points.

[0122] Anomaly detection based on the combination of isolation forest and deep autoencoder is adopted. Isolated points in the data are identified through the isolation forest, the normal mode of the data is learned through the deep autoencoder, and anomalies are detected by comparing the differences between the actual data and the learned normal mode. For

[0123] where E is the anomaly score, X is the actual data, is the data reconstructed by the deep autoencoder. When E exceeds the preset threshold, it is determined as abnormal data. This preset threshold is obtained through training with normal traffic flow data and is a judgment criterion for measuring the anomaly score E.

[0124] Before analyzing and processing the data, data reception is also included, specifically:

[0125] The traffic flow monitoring module is connected to the communication interface of the central control module; in the present invention, the communication interface adopts an adaptive communication protocol, which can automatically adjust the transmission rate and data format according to the network environment to ensure stable and efficient data transmission. After the data is transmitted to the central control module, the data is verified through the communication interface. The cyclic redundancy check combined with the hash algorithm is used to detect whether errors occur in the data during the transmission process, and the data source and transmission path are located through the hash value; the data security and traceability are increased.

[0126] The storage unit adopts a distributed storage architecture to classify and store the received traffic flow data (according to dimensions such as time, location, data type, etc.); for real-time data with high-frequency updates (such as vehicle real-time speed and location information), an in-memory database is used for caching for quick reading and processing; for historical data, it is stored in a disk array; for subsequent long-term analysis and mining. At the same time, the stored data is compressed.

[0127] The specific method of the cyclic redundancy check is:

[0128] Dynamically generate polynomial rules based on the scenarios and requirements of data transmission, and determine its form considering factors such as data type, transmission rate, and network environment stability. For example, for video stream data transmission with high requirements for error rate control, a complex polynomial is used, and for ordinary text transmission, a simple form is used; pre-define a polynomial library and select a generating polynomial from it;

[0129] Receive the data D to be transmitted, and determine its length n. According to the determined dynamically generated polynomial, select or dynamically generate a generating polynomial G(x) from the polynomial library, and determine its highest order r. The generating polynomial is a binary number with r + 1 bits in binary representation;

[0130] Add r zeros at the end of the data D to obtain a new data sequence D', making its length become n + r, reserving space for subsequent modulo-2 division operations;

[0131] Divide D' by the binary number corresponding to the generating polynomial G(x) to perform modulo-2 division (binary division without borrowing). In each step of the modulo-2 division operation, determine the remainder obtained in that step by performing an exclusive OR operation on the dividend and the divisor. After the operation, the obtained remainder R is the check code, and its length is r bits;

[0132] Replace the r zeros previously added at the end of the data D with the obtained check code R to form the data T to be finally transmitted. At this time, the length of T is n + r bits; specifically, after obtaining the check code R by completing the modulo-2 division operation, the r zeros previously added at the end of the data D will be removed, and then the check code R will be added bit by bit in sequence to the end position of the data D, thus forming the data T to be finally transmitted; since the original data D becomes n + r bits after adding r zeros, removing these r zeros and adding the check code R of the same length, the length of the final data T still remains n + r bits;

[0133] After the receiving end receives the data T, also determine the corresponding generating polynomial G(x) according to the pre-agreed dynamically generated polynomial rule, divide the received data T by the binary number corresponding to G(x), and perform the modulo-2 division operation again. If the obtained remainder is 0, it means that the data has not been in error during transmission; if the remainder is not 0, it indicates that the data has an error. The data can be requested to be retransmitted or error correction operations can be performed according to the specific situation.

[0134] The specific hash algorithm is as follows:

[0135] First, initialize the parameters, set the initial hash value H0, which can be a fixed value or generated according to specific system rules, and then determine a set of dynamic weight factors W = [W1, W2,... Wn]. The weight factors are adjusted according to dynamic information such as data type and transmission timestamp; for example, for traffic flow data with high real-time requirements, the weights are different in different time periods.

[0136] Group the data D to be processed (such as dividing according to the number of bytes or the logical structure of the data) to obtain data groups D1, D2,... Dm, and assign a position identifier P = [P1, P2,... Pm] to each data group to record the position information of the group in the original data;

[0137] Starting from the first data packet, calculate the intermediate hash value for each packet. For the i-th data packet Di, the calculation method of its intermediate hash value Hi is as follows:

[0138] Hi = (Hi-1 + Σ(Di[j]) * wj * pj)) % M

[0139] where Hi represents the intermediate hash value calculated for the i-th data packet;

[0140] Hi-1 is the intermediate hash value calculated for the (i - 1)-th data packet; when calculating the first data packet (i.e., when i = 1), H0 is the initialized hash value. This value plays a role in continuing and associating the hash calculation results of the previous data packets, enabling the entire hash calculation process to consider the order of the data.

[0141] Σ(Di[j]) * wj * pj) is a summation expression, where: Di[j] represents the j-th element in the i-th data packet Di; it represents the specific data content in the data packet.

[0142] wj is a dynamic weight factor, which is adjusted according to dynamic information such as the type of data and the transmission timestamp. Different wj values are used to reflect the different importance degrees of different data elements in the hash value calculation;

[0143] pj is the position identifier of the j-th element in the data packet, recording the position information of the element in the original data, so that data at different positions has different effects on the hash value;

[0144] % is the modulo operator;

[0145] M is a pre-set large prime number. The role of the modulo operation %M is to map the calculation result to a fixed range, ensuring the uniform distribution of the hash value and reducing the possibility of hash collisions.

[0146] In summary, this formula generates the intermediate hash value for each data packet by combining the previous hash value, the elements of the current data packet and their weights and position information, and through the modulo operation, which is a key step in the entire hash calculation process.

[0147] The control of traffic lights by adjusting the on-off time and switching order of the signal lights includes

[0148] The central control module collects data from the traffic flow monitoring module, the vehicle communication module, and other relevant data sources (such as historical traffic data, weather information); this data includes the real-time traffic flow, vehicle driving speed, number of waiting vehicles in different directions, road capacity, accident information, and weather conditions (severe weather will affect road traffic efficiency) of each section.

[0149] Clean the collected data to remove outliers and duplicate data; specifically, use an outlier detection algorithm based on statistical methods to identify and eliminate traffic flow or speed data that significantly deviates from the normal range. For duplicate data, ensure data accuracy and consistency through data comparison and deduplication operations.

[0150] Fuse data from different sources to construct a comprehensive traffic condition dataset; for example, combine the traffic flow data obtained from the traffic flow monitoring module with the vehicle location and speed information provided by the vehicle communication module to more accurately depict the distribution and movement state of vehicles on the road.

[0151] Comprehensively consider multiple factors such as traffic flow, average vehicle speed, vehicle density, and queue length to construct a multi-dimensional traffic state evaluation index system; including setting different thresholds to divide traffic congestion, slow traffic, and smooth traffic states, and evaluating the current traffic state of each intersection and road section in real time according to these indicators.

[0152] Use machine learning algorithms (such as Long Short-Term Memory Network LSTM), combined with historical traffic data and real-time data, to predict the change of traffic flow within the next 5 - 15 minutes; the model inputs include current traffic state data, time information (weekday, weekend, morning and evening peak hours, etc.), and weather data, etc., and the outputs are predicted values of future traffic flow, vehicle speed, etc. for each road section and intersection.

[0153] Dynamically adjust the weights of evaluation indicators according to traffic conditions and prediction results; when traffic congestion is severe, increase the weights of traffic flow and queue length indicators; when traffic is relatively smooth, increase the weight of the average vehicle speed indicator to more accurately reflect the change of traffic conditions.

[0154] Assign priorities to vehicle flows in different directions according to traffic state evaluation and prediction results; for directions with severe congestion or rapidly increasing traffic flow, give higher priorities and preferentially ensure the passage of vehicles in these directions. For example, when the queue length of vehicles in a certain direction exceeds a certain threshold and it is predicted that the future traffic flow will continue to increase, set this direction as a high priority.

[0155] Adopt a multi-objective optimization algorithm with the goals of minimizing the average waiting time of vehicles, maximizing the intersection passing capacity, and balancing the waiting time of vehicle flows in each direction to generate a signal control strategy; based on considering the priorities of different directions, the algorithm determines the green light duration, red light duration, and switching sequence of each signal phase by iteratively searching for the optimal solution.

[0156] Dynamically adjust the phase of the traffic lights according to the changes in traffic conditions; when it is detected that the vehicles in a certain direction are cleared in advance, or a new congestion point appears, adjust the phase sequence and duration in a timely manner to avoid waste of green light time and improve the overall traffic efficiency at the intersection.

[0157] The central control module sends the generated traffic light control instructions to the traffic light control module through wired or wireless communication; the instructions include the on / off time, switching sequence of each traffic light, and emergency control instructions in special cases (such as temporary traffic control instructions during accidents).

[0158] After the traffic light control module executes the instructions, it feeds back the status of the traffic lights and relevant feedback data (such as whether the traffic lights switch normally, the change in the traffic flow of the current green light direction, etc.) to the central control module; the central control module monitors the operation of the traffic lights through the received feedback data to ensure that the control instructions are correctly executed.

[0159] If the central control module finds that the actual traffic conditions do not match the expectations based on the feedback data, or new traffic events occur (such as sudden accidents, traffic flow mutations caused by large-scale events), it will immediately re-evaluate and predict the traffic status, adjust the traffic light control strategy, and send control instructions again to achieve dynamic control of the traffic lights.

[0160] Furthermore, the present invention further includes a perception fusion module for integrating environmental data (including but not limited to meteorological data, road conditions); monitoring temperature, humidity, wind speed, precipitation with meteorological sensors, and detecting road surface friction, water accumulation conditions, etc. with road surface sensors; and fusing and processing the integrated environmental data with traffic data; specifically, when the central control module evaluates the traffic status and generates the traffic light control strategy, it can take environmental factors into account. For example, if it is rainy or the road surface is icy, extend the green light time of the traffic lights and lower the expected vehicle driving speed to ensure traffic safety. There is also a navigation information push module that can plan a more reasonable route for the driver according to the real-time meteorological and road conditions and help the driver avoid those potentially dangerous sections.

[0161] An autonomous driving cooperation module, which communicates and interacts with autonomous vehicles, and is also connected to the traffic flow monitoring module, the central control module, and the navigation information push module to achieve data circulation and sharing; it is used to ensure the safe operation of autonomous vehicles and assist in optimizing traffic resource allocation;

[0162] Specifically, with the development of autonomous driving technology, this module aims to achieve the collaborative operation of autonomous vehicles and intelligent transportation systems. It can communicate with autonomous vehicles, obtain information such as driving intentions and speed planning of the vehicles, and provide real-time traffic instructions and guidance for the vehicles. At the same time, it monitors the operating status of autonomous vehicles to ensure their safe operation in the traffic system; in the traffic flow monitoring module, it can identify autonomous vehicles and analyze their data separately. When formulating signal control strategies and traffic guidance plans, the central control module fully considers the characteristics of autonomous vehicles, such as more precise stop and start control, higher reaction speed, etc., to achieve more optimized allocation of traffic resources. The navigation information push module can provide more detailed route and traffic information for autonomous vehicles to help them better plan driving paths.

[0163] The energy management and optimization module is interconnected with electric vehicles, the smart grid, the navigation information push module, the central control module, and the vehicle communication module; it realizes the interactive sharing of information such as battery power, charging demand, traffic conditions, and charging pile distribution.

[0164] Specifically, it is responsible for managing and optimizing the energy use of electric vehicles in the traffic system, real-time monitoring information such as the battery power and charging demand of electric vehicles, and combining traffic conditions and charging pile distribution to plan the optimal driving and charging schemes for electric vehicles. At the same time, it interacts with the smart grid to achieve the orderly charging of electric vehicles and reduce the impact on the grid; meanwhile, the navigation information push module can provide navigation routes including the location and usage status of charging piles for electric vehicle drivers to guide them to reasonably arrange charging time and locations. When conducting traffic flow regulation, the central control module considers the charging demand of electric vehicles to avoid the depletion of the battery power of electric vehicles due to traffic congestion. The vehicle communication module can realize the information interaction between electric vehicles, charging piles, and the smart grid to promote the efficient utilization of energy.

[0165] This invention focuses on the collaboration of each module and realizes intelligent traffic control and convenient vehicle travel by collecting, processing, and applying data, specifically as follows:

[0166] S210: System startup and initialization, turning on each module device, including the millimeter-wave radar array of the traffic flow monitoring module, the processor and storage unit of the central control module, the signal lamp control module device, the navigation information push module components, the vehicle communication module device, etc. The central control module initializes system parameters, such as setting the parameters of the spatio-temporal graph convolutional network model, the anomaly detection threshold, the initial value and weight factor of the hash algorithm, etc., and at the same time establishes communication connections with other modules.

[0167] S220: Data collection and transmission. The millimeter-wave radar array of the traffic flow monitoring module continuously emits millimeter-wave signals, receives vehicle echo signals, calculates vehicle speed, identifies trajectories, and counts the number of vehicles, and transmits the data to the central control module through the communication interface. The vehicle communication module collects communication data between vehicles (V2V) and between vehicles and infrastructure (V2I), such as vehicle driving intentions, surrounding road conditions, etc., and sends them to the central control module. The perception fusion module uses meteorological and road surface sensors to collect environmental data, integrates them, and transmits them to the central control module.

[0168] S230: Data processing and analysis. After receiving the data, the central control module first verifies the data accuracy through an adaptive communication protocol, and uses cyclic redundancy check combined with a hash algorithm to detect errors, locate the source and path. The processor is used to calculate traffic flow parameters, and a spatio-temporal graph convolutional network is used to analyze spatio-temporal correlation features and predict traffic flow changes. The method combining isolation forest and deep autoencoder is used to detect data anomalies.

[0169] S240: Signal light control. The central control module collects multi-source data, cleans and fuses them to construct a traffic condition dataset, evaluates the traffic state, and predicts traffic flow changes. According to the evaluation and prediction results, the weights of evaluation indicators are dynamically adjusted, priorities are assigned to vehicle flows, a multi-objective optimization algorithm is used to generate a signal light control strategy, the signal light phase is dynamically adjusted according to traffic condition changes, and finally the control instruction is sent to the signal light control module, and the strategy is optimized in real time according to the feedback.

[0170] S250: Navigation information push. The navigation information push module obtains traffic data, environmental data, etc. from the central control module, combines with vehicle position information, and uses a path planning algorithm to plan a route for the driver. For ordinary vehicles, congested sections are avoided; for electric vehicles, the driving and charging plans are considered in terms of battery power and charging pile distribution, and traffic information and the planned route are pushed to the in-vehicle navigation system.

[0171] S260: Autopilot coordination (if there are autonomous vehicles). The autopilot coordination module communicates with autonomous vehicles to obtain information such as driving intentions and speed planning, and monitors the operating status. The traffic flow monitoring module identifies autonomous vehicles and analyzes the data separately. When formulating strategies, the central control module considers their characteristics to optimize resource allocation. The navigation information push module provides detailed routes and traffic information to assist in planning paths.

[0172] S270: Energy management (for electric vehicles). The energy management and optimization module monitors the battery power and charging requirements of electric vehicles in real time, combines with traffic and charging pile distribution to plan driving and charging plans, and interacts with the smart grid to achieve orderly charging. The navigation information push module provides charging pile information for the driver. The central control module avoids the exhaustion of the battery power of electric vehicles when regulating traffic flow. The vehicle communication module realizes information interaction between electric vehicles, charging piles, and the smart grid.

[0173] The preferred specific embodiments of the present invention have been described in detail above. It should be understood that those of ordinary skill in the art can make many modifications and variations based on the concept of the present invention without creative efforts. Therefore, all technical solutions that can be obtained by those skilled in the art in this technical field based on the concept of the present invention through logical analysis, reasoning, or limited experiments on the basis of the prior art should fall within the protection scope determined by the claims.

Claims

1. An intelligent transportation control integration system for automobiles based on electrical and electronic technology, characterized in that, Including: Traffic flow monitoring module: used to monitor the traffic flow on the road and obtain vehicle quantity and driving speed data; And send the obtained data to the central control module; Central control module: including a processor, a storage unit and a communication interface, used to receive the data transmitted by the traffic flow monitoring module and analyze and process the data; Signal light control module: according to the instructions sent by the central control module, control the traffic signal lights by adjusting the on-off time and switching sequence of the signal lights; Navigation information push module: communicate with the in-vehicle navigation system, obtain data from the central control module, use the path planning algorithm to plan a route for the driver, and push traffic information and the planned route to the in-vehicle navigation system; Vehicle communication module: installed on the vehicle for communication between vehicle and vehicle, and between vehicle and infrastructure.

2. The integrated system for intelligent transportation control of automobiles based on electrical and electronic technology according to claim 1, characterized in that, The traffic flow monitoring module includes: Set a millimeter-wave radar array on both sides or above the detected road, work by emitting millimeter-wave signals and receiving the echo signals reflected by the target vehicle, calculate the driving speed of the vehicle according to the frequency change of the echo signal, when the vehicle enters the detection area of the radar array, the radar will track the position change of the vehicle, and through the time series analysis of the radar signal, combined with the detection data of different radars in the array, identify the trajectory of each vehicle and count the vehicle quantity.

3. The integrated automotive intelligent transportation control system based on electrical and electronic technology according to claim 2, characterized in that, The calculating the driving speed of the vehicle according to the frequency change of the echo signal is specifically: The radar emits millimeter-wave signals of multiple different frequencies. Let the emitted frequencies be f1, f2, … f n , When these signals of different frequencies propagate in space, they will generate reflected echoes when encountering a vehicle. The radar receives these echo signals and separates and collects the echoes corresponding to each frequency; According to the Doppler effect, when there is relative motion between the vehicle and the radar, the frequency of the echo signal will change. For a transmitted signal with a frequency of f i , the Doppler frequency shift f di of its echo is as follows: where u is the radial speed of the vehicle relative to the radar; is the wavelength of the millimeter wave signal with frequency f i , where c is the speed of light; By performing spectral analysis on the echo signals of each frequency, the corresponding Doppler frequency shift f is obtained di ; Use multiple Doppler frequency shift information obtained by multi-frequency signal transmission, calculate the preliminary speed of the vehicle in a weighted fusion manner, assign a weight wi to the Doppler frequency shift corresponding to each frequency, and determine the weight considering factors such as signal strength and frequency stability; The initial speed of the vehicle is u pre , where the u pre is as follows: Among them, is the coefficient in the formula, which is derived through the principle related to the Doppler effect and is used to convert the subsequent calculation result into the actual speed; is a summation expression, where n represents the number of different frequency signals transmitted by the radar; i is a counting variable from 1 to n ; w i is the weight corresponding to the i-th frequency signal, f di is the Doppler frequency shift of the echo of the i-th frequency signal; λ i is the wavelength of the i-th frequency signal; It is the sum of the weights of all n frequency signals, used to eliminate the influence of the total weight on the calculation result; Take the initially calculated speed u pre and the characteristics of the echo signals at each frequency as inputs and feed them into a pre-trained machine learning model. During the training phase of this model, vehicle speed data and corresponding radar echo data in different scenarios were used; The model corrects the preliminary speed by learning the relationship between data; By monitoring the rate of change of the distance and the angle change between the radar and the vehicle.

4. The integrated automotive intelligent transportation control system based on electrical and electronic technology as claimed in claim 3, wherein In the central control module, the analysis and processing of the data specifically includes; Calculate the parameters of the traffic flow through the processor; Through an analysis model based on a spatio-temporal graph convolutional network, used to mine the spatio-temporal correlation features in the traffic flow data, and the output of the model is used to predict the traffic flow change, for yt + k = gST-GCN(X t, A) where yt + k represents the predicted value of the traffic flow at the future k moment; gST-GCN represents the spatio-temporal graph convolutional network function, and by performing specific spatio-temporal graph convolutional operations on the input data, mine the spatio-temporal correlation features in the data; X t, is the traffic flow data at time t; A is the adjacency matrix of the traffic network; Adopt anomaly detection combining isolation forest and deep autoencoder, identify the isolated points in the data through the isolation forest, learn the normal mode of the data through the deep autoencoder, and detect anomalies by comparing the difference between the actual data and the learned normal mode, for Among them, E is the anomaly score, X is the actual data, is the data reconstructed by the deep autoencoder. When E exceeds the preset threshold, it is determined as abnormal data.

5. The integrated system for intelligent transportation control of automobiles based on electrical and electronic technology as claimed in claim 4, characterized in that, Before the analysis and processing of the data, data reception is also included, specifically: The traffic flow monitoring module is connected to the communication interface of the central control module; when the data is transmitted to the central control module, the data is verified through the communication interface, and a cyclic redundancy check combined with a hash algorithm is used to detect whether an error occurs in the data during transmission, and the data source and transmission path are located through the hash value.

6. The integrated automotive intelligent transportation control system based on electrical and electronic technology according to claim 5, characterized in that, The storage unit adopts a distributed storage architecture to classify and store the received traffic flow data. For real-time data with high-frequency updates, an in-memory database is used for caching. For historical data, it is stored in a disk array. At the same time, the stored data is compressed.

7. The integrated vehicle intelligent transportation control system based on electrical and electronic technology according to claim 6, characterized in that, The specific method of the cyclic redundancy check is as follows: Set the rule for dynamically generating polynomials, predefined polynomial libraries, and select a generating polynomial from them; Receive the data D to be transmitted and determine its length n. According to the determined dynamic generating polynomial, select or dynamically generate a generating polynomial G(x) from the polynomial library and determine its highest order r. The generating polynomial is a binary number with r + 1 bits in binary representation; Add r zeros at the end of the data D to obtain a new data sequence D', making its length become n + r to reserve space for subsequent modulo-2 division operations; Divide D' by the binary number corresponding to the generating polynomial G(x) for modulo-2 division. In each step of the modulo-2 division operation, determine the remainder obtained in that step by performing an exclusive OR operation on the dividend and the divisor. After the operation, the obtained remainder R is the check code, and its length is r bits; Replace the r zeros added at the end of the data D with the obtained check code R to form the final data T to be transmitted. At this time, the length of T is n + r bits; After the receiving end receives the data T, similarly, according to the pre-agreed dynamic generating polynomial rule, determine the corresponding generating polynomial G(x), divide the received data T by the binary number corresponding to G(x), and perform the modulo-2 division operation again. If the obtained remainder is 0, it means that the data has not been corrupted during transmission; If the remainder is not 0, it indicates that an error has occurred in the data.

8. The integrated automotive intelligent transportation control system based on electrical and electronic technology according to claim 7, characterized in that, The specific hash algorithm is as follows: First, initialize the parameters, set the initial hash value H0, and then determine a set of dynamic weight factors W = [W1, W2,... Wn]. The weight factors are adjusted according to dynamic information; Group the data D to be processed to obtain data groups D1, D2,... Dm, and assign a position identifier P = [P1, P2,... Pm] to each data group to record the position information of the group in the original data; Starting from the first data group, calculate the intermediate hash value of each group. For the i-th data group Di, the calculation method of its intermediate hash value Hi is, Hi = (Hi-1 + Σ(Di[j]) * wj * pj)) % M where Hi represents the intermediate hash value calculated for the i-th data group; Hi-1 is the intermediate hash value calculated for the (i - 1)-th data group; Σ(Di[j]) * wj * pj) is a summation expression, where: Di[j] represents the j-th element in the i-th data group Di; wj is a dynamic weight factor, adjusted according to the data. Different wj are used to reflect the different importance degrees of different data elements in the calculation of the hash value; pj is the position identifier of the j-th element in the data group, recording the position information of the element in the original data, making the data in different positions have different influences on the hash value; % is the modulo operator; M is a predefined prime number.

9. The integrated automotive intelligent transportation control system based on electrical and electronic technology according to claim 8, characterized in that, The control of traffic lights by adjusting the on-off time and switching sequence of the signal lights includes The central control module collects data from the traffic flow monitoring module and the vehicle communication module; Clean the collected data to remove outliers and duplicate data; fuse data from different sources to construct a data set; construct a multi-dimensional traffic state evaluation index system; Predict the change of traffic flow within the next 5 - 15 minutes through machine learning algorithms; Dynamically adjust the weights of the evaluation indicators according to the traffic conditions and prediction results; Assign priorities to vehicle flows in different directions according to the traffic state evaluation and prediction results; Adopt a multi-objective optimization algorithm to minimize the average vehicle waiting time, maximize the intersection throughput, and balance the waiting times of vehicle flows in all directions as the goals, and generate the control strategy of the signal lights; Dynamically adjust the phase of the signal lights according to the change of traffic conditions; The central control module sends the generated signal light control instructions to the signal light control module; After the signal light control module executes the instructions, it feeds back the status of the signal lights and relevant feedback data to the central control module; the central control module monitors the operation of the signal lights through the received feedback data; If the central control module finds that the actual traffic conditions do not match the expectations based on the feedback data, it immediately re-evaluates and predicts the traffic state, adjusts the signal light control strategy, and sends control instructions again to achieve the dynamic control of the signal lights.

10. The integrated automotive intelligent transportation control system based on electrical and electronic technology according to claim 9, characterized in that, It also includes The perception fusion module is used to integrate environmental data and fuse the integrated environmental data with traffic data; The autonomous driving cooperation module communicates and interacts with autonomous driving vehicles, and is also connected to the traffic flow monitoring module, the central control module, and the navigation information push module to achieve data circulation and sharing; it is used to ensure the safe operation of autonomous driving vehicles and assist in optimizing traffic resource allocation; The energy management and optimization module is interconnected with electric vehicles, the smart grid, the navigation information push module, the central control module, and the vehicle communication module; it realizes the interactive sharing of information.

Images