Electric vehicle violation behavior monitoring method based on radio frequency wireless transmission technology

Abstract

The invention discloses an electric vehicle violation behavior monitoring method based on a radio frequency wireless transmission technology, and relates to the technical field of electric vehicle violation behavior monitoring, and the method comprises the following steps: firstly, a vehicle-mounted radio frequency sensor of an electric vehicle transmits a wireless signal at a preset power, and guarantees that the signal of each electric vehicle is stably and reliably transmitted in a monitoring area; according to the method, the radio frequency wireless transmission technology and the machine learning model are combined, so that the problems of signal interference and collision of the electric vehicles in the traffic-intensive area are effectively solved. The signal of the vehicle-mounted radio frequency sensor is obtained in real time, the transmitting power is adjusted through intelligent evaluation, interference can be reduced, and the data transmission accuracy and the monitoring precision are improved. According to the scheme, it is ensured that the electric vehicle violation behaviors are accurately recognized in a high-density traffic environment, the intelligent level of a traffic management system is optimized, the response capacity to dynamic traffic conditions is enhanced, and therefore traffic safety and flow management efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring the illegal behavior of electric vehicles, and in particular to a method for monitoring the illegal behavior of electric vehicles based on radio frequency wireless transmission technology. Background Art

[0002] Electric vehicle violation behavior monitoring based on radio frequency wireless transmission technology refers to the use of radio frequency (RF) technology to monitor and transmit data of electric vehicle behavior in real time through wireless signals. Specifically, radio frequency technology can install radio frequency sensors on electric vehicles to communicate with receiving equipment in the road or traffic management system to obtain real-time information such as the speed, position, driving trajectory, and parking status of electric vehicles. When an electric vehicle violates traffic rules, such as running a red light, illegally parking, or driving on the road, the system can make judgments by analyzing the data transmitted back, and promptly issue an alarm or record the violation. Radio frequency wireless technology has the characteristics of high efficiency, low power consumption, and long distance, so it can be widely used in urban traffic management to achieve automated monitoring, rapid response, and processing of electric vehicle violations.

[0003] The existing technology has the following deficiencies: In the existing technology, the radio frequency sensor on the electric vehicle usually transmits a fixed power signal, the purpose is to ensure the stability and reliability of signal transmission, while saving energy and extending the service life of the sensor. The fixed power signal can ensure effective communication between the radio frequency sensor and the receiving device within a certain distance, avoiding transmission attenuation or failure to receive due to too low signal power. However, in areas with dense traffic, when multiple electric vehicles pass through the monitoring area at the same time, the radio frequency signal may interfere, resulting in the monitoring system being unable to accurately identify the behavior of each vehicle. This situation may lead to serious consequences: signal interference will cause the signal of some vehicles to be lost or confused, and the traffic management system may not be able to distinguish the signals of different electric vehicles, or mix the behavior data of different vehicles. This information loss or confusion will cause monitoring blind spots, making it impossible for the traffic management system to fully and accurately track and record the dynamics of each vehicle, thereby affecting the regulation and safety warning of traffic flow, and may even make certain violations unable to be discovered and handled in time, thereby increasing the risk of traffic accidents.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a method for monitoring electric vehicle violations based on radio frequency wireless transmission technology. By combining radio frequency wireless transmission technology and machine learning models, this method effectively solves the problems of electric vehicle signal interference and collision in traffic-intensive areas. Real-time acquisition of on-board radio frequency sensor signals and adjustment of transmission power through intelligent evaluation can reduce interference and improve data transmission accuracy and monitoring accuracy. This solution ensures accurate identification of electric vehicle violations in high-density traffic environments, optimizes the intelligence level of traffic management systems, and enhances the ability to respond to dynamic traffic conditions, thereby improving traffic safety and flow management efficiency to solve the problems in the above-mentioned background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for monitoring electric vehicle traffic violations based on radio frequency wireless transmission technology, comprising the following steps:

[0007] First, the RF sensor on the electric vehicle transmits wireless signals at a preset power to ensure that the signal of each electric vehicle is stably and reliably transmitted within the monitoring area;

[0008] The RF receiver acquires the signal data sent by the vehicle-mounted RF sensors passing through the monitoring area in real time. Through the captured wireless signals, the receiver obtains the real-time dynamic information of each vehicle;

[0009] The acquired wireless signal data is constructed into a data set and preprocessed to lay the foundation for subsequent data analysis. The key features reflecting signal conflicts are extracted from the preprocessed signal data, and the extracted key features are deeply analyzed under the detection window to evaluate the current signal status.

[0010] The analyzed key features are input into the pre-trained machine learning model, and the wireless signal status is intelligently evaluated through the machine learning model;

[0011] Based on the evaluation results of the machine learning model, wireless signals are divided into two categories: RF signal collision and RF signal non-interference propagation;

[0012] For interference-free propagation of RF signals, the RF sensors on electric vehicles continue to send wireless signals at a preset power to ensure stable and reliable signal coverage;

[0013] In the event of signal collision, the signal transmission power of different electric vehicle onboard RF sensors is dynamically adjusted based on the evaluation results of the machine learning model to ensure the optimization of signal transmission quality in high-density traffic environments, reduce interference, and improve the accuracy and reliability of data transmission.

[0014] Preferably, key features reflecting signal conflicts are extracted from the preprocessed signal data, the extracted features including the symbol error rate during data transmission and the consistency of the same signal at different time points. Within the detection window, the symbol error rate during data transmission and the consistency of the same signal at different time points are analyzed to generate a symbol error rate factor and a signal autocorrelation coefficient factor, respectively. The symbol error rate factor is used to quantify the degree of mismatch between the received symbol and the original symbol during signal transmission, and the signal autocorrelation coefficient factor is used to quantify the consistency of the same signal at different time points, that is, the stability of the signal over time.

[0015] Preferably, the specific steps of analyzing the error rate of symbols in the data transmission process under the detection window to generate the symbol error rate factor are as follows:

[0016] First, the received signal symbols are compared with the original symbols sent during data transmission to calculate the bit error rate. Suppose the received signal symbol set is R = {r i}={r 1 、r 2 ,……,r n}, and the original symbol set is G = {g i}={g 1 , g 2 ,……,g n}, where r i is the i-th symbol received by the receiver during the transmission process, g i is the i-th symbol sent by the transmitter, n is the total number of symbols, and the bit error rate of each symbol position is calculated by the following formula:

[0017]

[0018] , where e i is the error flag of the i-th symbol;

[0019] Next, the symbol error rate within the entire detection window is calculated, and the calculation expression is as follows:

[0020]

[0021] , where BER is the symbol error rate;

[0022] In order to accurately reflect the performance of the signal in a complex environment, the characteristics of the signal in the time domain and frequency domain are considered, and the interference influence coefficient is introduced. The calculation expression is as follows:

[0023]

[0024] , where α is a power index used to adjust the influence of the error part, β is an index used to adjust the influence of the signal amplitude on the overall calculation, γ is an index to adjust the influence of the signal amplitude part, and D is the interference influence coefficient;

[0025] The final symbol error rate factor is calculated using the following formula:

[0026] SBER=BER·D

[0027] , where SBER is the symbol error rate factor.

[0028] Preferably, the specific steps of analyzing the consistency of the same signal at different time points under the detection window to generate the signal autocorrelation coefficient factor are as follows:

[0029] First, we need to calculate the signal autocorrelation function to quantify the consistency of the signal at different time points. Assuming that the signal s(t) is transmitted in the time interval [0, T], the signal autocorrelation function calculation expression is as follows:

[0030]

[0031] , where s(t) is the signal value at time t, τ is the time delay measure of the signal, T is the detection window length, s(t+τ) is the value of the signal s(t) at the position after a time delay of τ, and R(τ) is the autocorrelation function, which is used to quantify the consistency of the signal at different time points;

[0032] Next, based on the calculation results of the autocorrelation function, the autocorrelation coefficient factor of the signal is generated, and the enhanced nonlinear metric is used to describe the periodic consistency of the signal. The autocorrelation coefficient index calculation expression is as follows:

[0033]

[0034] , where R max is the maximum value of the autocorrelation function within the detection window, ω is the parameter that controls the exponential decay, R(τ)-R max It is the amplitude of the change in signal autocorrelation, which measures the degree of fluctuation of the signal under different delays. ACF is the signal autocorrelation coefficient factor.

[0035] Preferably, the analyzed symbol error rate factor and signal autocorrelation coefficient factor are input into a pre-learned machine learning model, a signal conflict coefficient is generated by the machine learning model, and the signal conflict coefficient is used to intelligently evaluate the wireless signal conflict status during wireless signal propagation in the current detection area.

[0036] Preferably, the signal conflict coefficient generated when the wireless signal conflict state in the wireless signal propagation process in the current detection area is intelligently evaluated by the pre-learned machine learning model is compared and analyzed with the pre-set signal conflict coefficient reference threshold, and the RF wireless signal state in the current detection area is divided, and the division steps are as follows:

[0037] If the signal conflict coefficient is greater than a preset signal conflict coefficient reference threshold, the radio frequency wireless signal in the current detection area is classified as a radio frequency signal collision;

[0038] If the signal conflict coefficient is less than or equal to a preset signal conflict coefficient reference threshold, the radio frequency wireless signal in the current detection area is classified as radio frequency signal non-interference propagation.

[0039] Preferably, in the case of RF signal collision, based on the evaluation results of the machine learning model, the signal transmission power of different electric vehicle onboard RF sensors is dynamically adjusted to ensure the optimization of signal transmission quality in a high-density traffic environment, reduce interference, and improve the accuracy and reliability of data transmission. The specific steps are as follows:

[0040] After confirming that there is a radio frequency signal collision in the current area, the signal transmission power of each electric vehicle's onboard radio frequency sensor is dynamically adjusted based on the results of the machine learning model evaluation. The transmission power of each vehicle is adjusted based on the preset signal transmission power and the machine learning model evaluation results. The specific adjustment formula is as follows:

[0041]

[0042] , where P adj is the adjusted signal transmission power, P pre is the preset signal transmission power, ΔP factor is the power adjustment factor, SC is the signal conflict coefficient, SC ref is the reference threshold of the signal conflict coefficient, β is an adjustment parameter used to control the nonlinear relationship between the conflict degree and power adjustment;

[0043] After adjusting the signal transmission power of the electric vehicle's onboard RF sensor, the following optimization strategy is adopted to accurately control the signal transmission quality by continuously optimizing the transmission power, reducing the interference caused by signal collision, reducing data loss and transmission errors, and ensuring the reliability of the communication link:

[0044]

[0045] , where Q optis the signal transmission quality after optimization, θ is the proportional coefficient of signal optimization, which indicates the influence of power adjustment on signal quality, InterferenceFactor is the interference factor calculated by the interference degree of the current environment, and γ is the exponential adjustment parameter used to control the influence of power adjustment on signal quality.

[0046] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0047] The present invention can effectively solve the signal interference and collision problems of electric vehicles in traffic-intensive areas by combining radio frequency wireless transmission technology and machine learning models. By acquiring the wireless signals emitted by the on-board radio frequency sensors in real time, using machine learning models to intelligently evaluate the signal status, and dynamically adjusting the signal transmission power according to the evaluation results, it can ensure that in high-density traffic environments, signal interference is reduced, the accuracy of data transmission and the accuracy of the monitoring system are improved, thereby achieving accurate identification and timely processing of electric vehicle violations. This method effectively improves the intelligence and reliability of the traffic management system, enhances the system's ability to respond to dynamic traffic conditions, and thereby improves the efficiency of traffic safety and flow management. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0049] Figure 1 The present invention is a method flow chart of a method for monitoring electric vehicle traffic violations based on radio frequency wireless transmission technology. DETAILED DESCRIPTION

[0050] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0051] The present invention provides Figure 1 A method for monitoring electric vehicle traffic violation behavior based on radio frequency wireless transmission technology is shown, comprising the following steps:

[0052] First, the RF sensor on the electric vehicle transmits wireless signals at a preset power to ensure that the signal of each electric vehicle is stably and reliably transmitted within the monitoring area;

[0053] In a traffic environment, the RF sensors on electric vehicles communicate with surrounding receiving devices through wireless signals. These RF sensors usually transmit signals at a fixed power to ensure that the signals of each vehicle can be effectively transmitted within the monitoring area. The signals transmitted with preset power can ensure stable signal strength between the vehicle and the receiving device, avoid signal attenuation or failure to receive, and provide a reliable data basis for subsequent signal collection and analysis. The fixed power setting also helps save battery energy, extend the service life of the sensor, and ensure stable operation in different traffic environments.

[0054] The RF receiver acquires the signal data sent by the vehicle-mounted RF sensors passing through the monitoring area in real time. Through the captured wireless signals, the receiver obtains the real-time dynamic information of each vehicle;

[0055] In the monitoring area, the receiving device will receive the signals emitted by the RF sensors on the electric vehicles in real time. The working principle of these receivers is to continuously scan the signals and collect the corresponding data. Through the captured wireless signals, the receivers can obtain the real-time dynamic information of each vehicle, such as vehicle location, speed, signal strength, etc. This process ensures that the monitoring system can grasp the status of the electric vehicles in a timely manner and provide data support for subsequent data analysis. Through real-time data collection, the system can quickly respond to changes in traffic flow and provide real-time information for traffic management.

[0056] The acquired wireless signal data is constructed into a data set and preprocessed to lay the foundation for subsequent data analysis. The key features reflecting signal conflicts are extracted from the preprocessed signal data, and the extracted key features are deeply analyzed under the detection window to evaluate the current signal status.

[0057] Once the receiver acquires the signal data from the electric vehicle, the data will be organized into a data set for processing. The preprocessing process includes steps such as denoising, calibration, and standardization. Denoising is to remove stray information from the signal and improve the clarity of the signal; calibration is to synchronize the signal in time to ensure that all signal data are compared on the same time scale; standardization is to uniformly process data from different sources so that all types of data can be analyzed under the same standard. These preprocessing steps are crucial to ensure the accuracy and validity of the data, and to ensure that subsequent analysis can be based on high-quality data.

[0058] Key features reflecting signal conflicts are extracted from the preprocessed signal data. The extracted features include the symbol error rate during data transmission and the consistency of the same signal at different time points. Under the detection window, the symbol error rate during data transmission and the consistency of the same signal at different time points are analyzed to generate symbol error rate factors and signal autocorrelation coefficient factors, respectively. The symbol error rate factor is used to quantify the degree of mismatch between the received symbol and the original symbol during signal transmission. The signal autocorrelation coefficient factor is used to quantify the consistency of the same signal at different time points, that is, the stability of the signal over time.

[0059] The abnormal increase in the symbol error rate during data transmission usually indicates that the wireless RF signal in the current detection area is in an interference state. The symbol error rate is a key indicator to measure the proportion of erroneous symbols in data transmission. Under normal circumstances, the symbol error rate value should be kept at a low level to ensure that the signal can be accurately decoded. When the wireless RF signal encounters interference, the interference source may come from multiple directions, including signal collision, reflection, noise, etc. of other devices, all of which will affect the decoding process of the receiving device. When the signal is interfered, the received signal will contain more errors, which directly lead to incorrect decoding of the symbol, thereby increasing the bit error rate. If the signal bit error rate increases abnormally in a short period of time, it usually means that the signal quality has encountered greater interference or signal collision, and the data cannot be accurately transmitted. Furthermore, the increase in the symbol error rate may cause the monitoring system to be unable to correctly obtain the electric vehicle behavior data, thereby affecting the normal operation of the traffic management system, and may even miss the timely identification of violations. Therefore, the abnormal increase in the symbol error rate is an important basis for judging that the wireless RF signal in the current monitoring area is in an interference state.

[0060] The specific steps of analyzing the error rate of symbols in the data transmission process under the detection window to generate the symbol error rate factor are as follows:

[0061] First, the received signal symbols are compared with the original symbols sent during data transmission to calculate the bit error rate. In order to accurately evaluate the signal quality, the symbol error rate index is not only based on the number of bit errors, but also takes into account the time-varying nature of the signal and the environmental impact. Suppose the received signal symbol set is R = {r i}={r 1 、r 2 ,……,r n}, and the original symbol set is G = {g i}={g 1 , g 2 ,……,g n}, where r i is the i-th symbol received by the receiver during the transmission process, g iis the i-th symbol sent by the transmitter and should be received by the receiver, n is the total number of symbols, and the bit error rate of each symbol position is calculated by the following formula:

[0062]

[0063] , where e i is the error flag of the i-th symbol;

[0064] The above formula is used to determine whether an error has occurred in the i-th received symbol. Specifically, if the received symbol r i The symbol g sent originally i If they are not the same, it means that an error occurred during the transmission, so e i The value is 1, indicating that the symbol is wrong; if r i and g i If the received symbols are the same, it means that the received symbols are correct. i The value of is 0, indicating that the symbol has no error. Through the above formula, we can calculate whether an error has occurred for each symbol, and further calculate the bit error rate in the entire data transmission process by counting the bit errors of all symbols.

[0065] Next, the symbol error rate within the entire detection window is calculated, and the calculation expression is as follows:

[0066]

[0067] , where BER is the symbol error rate, which indicates the proportion of symbols with errors among n symbols;

[0068] The purpose of the above steps is to quantify the error conditions in the transmission of each signal symbol and provide a basis for the generation of the subsequent symbol bit error rate index. BER reflects the frequency of errors in the signal transmission process, and the change of the symbol bit error rate index will be directly related to the size of this value.

[0069] In order to accurately reflect the performance of the signal in a complex environment, the characteristics of the signal in the time domain and frequency domain are considered, and the interference influence coefficient is introduced. This coefficient is obtained by quantitatively calculating different interference sources in the transmission environment. The calculation expression is as follows:

[0070]

[0071] , where α is a power index used to adjust the influence of the error part, β is an index used to adjust the influence of the signal amplitude on the overall calculation, γ is an index to adjust the influence of the signal amplitude part, used to control the proportion of the signal amplitude in the final calculation, and D is the interference influence coefficient;

[0072] This step comprehensively considers the impact of the square of the symbol error (reflecting the degree of error) and the symbol strength (reflecting the signal strength) on the signal quality, and then introduces the interference influence coefficient D to adjust the bit error rate index.

[0073] The final symbol error rate factor is calculated using the following formula:

[0074] SBER=BER·D

[0075] , where SBER is the symbol error rate factor.

[0076] The above steps combine the basic symbol error rate with the interference coefficient to generate a comprehensive bit error rate index, which effectively reflects the quality and interference status of the wireless signal. Error A larger value indicates that the current signal is strongly interfered with during transmission and the signal quality is poor; conversely, a smaller value indicates that the signal transmission process is relatively stable and the interference is small.

[0077] The larger the value of the symbol error rate factor generated by analyzing the error rate of the symbol during data transmission under the detection window, the more erroneous symbols occurred during the transmission process, which is usually due to the influence of factors such as interference, collision or noise on the signal. When the signal quality decreases and the bit error rate increases, it means that the wireless RF signal encountered obstacles or interference during the transmission process, resulting in the inability to accurately transmit the data, thereby increasing the error rate. Therefore, the larger the value of the symbol error rate index, it usually indicates that the wireless RF signal in the current detection area is in an interference state, which may be caused by conflicts between multiple electric vehicle signals or environmental interference. On the contrary, when the symbol error rate index is low, it indicates that the signal maintains a high quality during the transmission process, and the bit error rate is low, which means that the signal is in an interference-free propagation state and the data transmission is relatively stable and reliable.

[0078] A sharp change in the consistency of the same signal at different time points usually indicates that the wireless RF signal in the current detection area is in an interference state. This is because the stability and consistency of wireless signals are usually directly related to their transmission quality. Under normal circumstances, the consistency of the signal should be relatively stable, especially for signals transmitted by the same signal source, and the change of the signal waveform should be smooth and predictable over time. If the consistency of the signal changes dramatically between different time points, it may be caused by external interference, signal conflicts from other devices, or environmental changes (such as weather, electromagnetic interference, etc.). When the RF signals of multiple electric vehicles are transmitted simultaneously in the same monitoring area, the signals will interfere with each other, resulting in significant fluctuations in the signal at the receiving end, and may even cause phase distortion, frequency drift, or data loss. This sharp change in consistency indicates that the signal is significantly affected by external factors, resulting in its stability being destroyed, which in turn affects the transmission quality of the signal and the accuracy of data decoding. Therefore, the sharp change in signal consistency is an important indicator of signal interference, which can help the system to identify the interference state in a timely manner and take appropriate measures, such as adjusting the signal transmission power or optimizing the signal scheduling strategy, to ensure the accuracy and reliability of the monitoring system.

[0079] The specific steps for analyzing the consistency of the same signal at different time points under the detection window to generate the signal autocorrelation coefficient factor are as follows:

[0080] First, we need to calculate the signal autocorrelation function to quantify the consistency of the signal at different time points. Assuming that the signal s(t) is transmitted in the time interval [0, T], the signal autocorrelation function calculation expression is as follows:

[0081]

[0082] , where s(t) is the signal value at time t, τ is the time delay measure of the signal, reflecting the delay difference between the current signal and the previous signal, T is the detection window length, s(t+τ) is the value of the signal s(t) at the position after a time delay of τ, and R(τ) is the autocorrelation function, which is used to quantify the consistency of the signal at different time points;

[0083] The autocorrelation function R(τ) reflects the similarity of the signal at different delays τ. By comparing the similarity of the signal itself at different time points, we can determine whether the signal is stable and whether there are periodic or repetitive components. For example, when the signal has a high autocorrelation at certain delay values, it means that the signal exhibits periodicity or stability, while a low autocorrelation indicates that the signal fluctuates greatly and may lack periodicity or regularity.

[0084] Next, based on the calculation results of the autocorrelation function, the autocorrelation coefficient factor of the signal is generated, and the enhanced nonlinear metric is used to describe the periodic consistency of the signal. The autocorrelation coefficient index calculation expression is as follows:

[0085]

[0086] , where R max is the maximum value of the autocorrelation function within the detection window, ω is the parameter that controls the exponential decay, usually n>1, which is used to emphasize the part where the signal similarity changes greatly. By adjusting ω, the irregularity or interference of the signal can be captured more finely. R(τ)-R max It is the amplitude of the change in signal autocorrelation, which measures the degree of fluctuation of the signal under different delays. ACF is the signal autocorrelation coefficient factor.

[0087] Through nonlinear measurement, the signal's autocorrelation coefficient factor α can more accurately reflect the stability and interference level of the signal. A larger autocorrelation coefficient factor indicates that the signal has a stronger temporal consistency, which may imply the presence of periodic or overlapping interference sources in the signal; a smaller autocorrelation coefficient factor indicates that the signal fluctuates more, has less interference, or propagates more freely.

[0088] The larger the value of the signal autocorrelation coefficient factor expression generated after analyzing the consistency of the same signal at different time points under the detection window, the stronger the consistency of the signal in time, which may mean that there are periodic or repetitive components in the signal, which is usually related to the presence of interference sources, such as the overlap of multiple signal sources or external electromagnetic interference. In this case, signal transmission may be interfered with, resulting in inaccurate or lost data. If the autocorrelation coefficient index is small, it means that the signal fluctuates greatly in time and lacks strong periodicity, which may indicate that the signal propagates more freely without obvious interference.

[0089] The analyzed key features are input into the pre-trained machine learning model, and the wireless signal status is intelligently evaluated through the machine learning model;

[0090] The analyzed symbol error rate factor and signal autocorrelation coefficient factor are input into the pre-learned machine learning model, and the signal conflict coefficient is generated by the machine learning model. The signal conflict coefficient is used to intelligently evaluate the wireless signal conflict status during the wireless signal propagation process in the current detection area.

[0091] The machine learning model is not limited here, and any machine learning model that can generate a signal conflict coefficient SC after comprehensive analysis of the symbol error rate factor SBER and the signal autocorrelation coefficient factor ACF is acceptable. To implement the technical solution of the present invention, the present invention provides a specific implementation method;

[0092] The signal conflict coefficient SC is generated by the following formula: SC = f 1 ·SBER+f 2 ACF, where f 1 、f 2 are the preset proportional coefficients of the symbol bit error rate factor SBER and the signal autocorrelation coefficient factor ACF, respectively. 1 、f 2 And both are greater than 0.

[0093] The "preset scaling factor" refers to a specific scaling constant set in a machine learning model to adjust the importance or weight of different features in signal generation. In this formula, the preset scaling factor f 1 and f 2 They are proportional coefficients related to the signal bit error rate factor SBER and the signal autocorrelation coefficient factor ACF, respectively. They adjust the contribution of different features in the signal generation model to the final signal conflict coefficient S. In short, the role of the preset proportional coefficient is to optimize the signal generation process by controlling the influence of different input features on the model output, ensuring that the final result has appropriate accuracy and responsiveness.

[0094] It can be seen from the signal conflict coefficient that the larger the symbol error rate factor expression value generated after analyzing the error rate of the symbol in the data transmission process under the detection window, the larger the signal autocorrelation coefficient factor expression value generated after analyzing the consistency of the same signal at different time points under the detection window, and the larger the signal conflict coefficient expression value generated when the wireless signal status is intelligently evaluated by the pre-learned machine learning model, it indicates that the wireless RF signal in the current detection area is in an interference state, otherwise it indicates that the RF signal in the current detection area is in interference-free propagation.

[0095] Pre-learned machine learning models usually refer to models that have been trained and optimized on certain data sets that contain a large amount of representative historical signal data and their relationship with interference status and signal propagation quality. Machine learning models can provide intelligent prediction or classification for new, unseen data by learning the characteristics, patterns and laws of these data. In this case, the "pre-learning" of the model means that before being deployed in actual applications, it has been trained with historical signal data and labels (such as signal interference, bit error rate and consistency, etc.) so that it can automatically recognize and process new signal inputs and evaluate signal status. Common machine learning algorithms include decision trees, support vector machines (SVM), neural networks, etc., which learn potential laws from complex data through feature extraction and feature selection.

[0096] In the on-board RF sensor system of electric vehicles, the pre-learned model is trained through signal conflict cases marked in historical data. These data may include characteristics such as signal strength, symbol error rate, signal autocorrelation coefficient in different traffic environments, and labels of whether the signal conflicts and whether it is interfered. By using this data, the machine learning model can identify potential patterns of signal conflicts and interference and form a predictive model. The model will automatically determine whether the signal is in a conflict state based on the new signal data input and the existing knowledge, thereby providing a basis for subsequent decisions (such as dynamic power adjustment or continuing to maintain the current signal power). In this way, the machine learning model provides intelligent decision-making support for the system, and can quickly and accurately handle signal conflict problems in actual operation.

[0097] In practical applications, the pre-learned machine learning model can receive characteristic parameters such as the symbol error rate index and the signal autocorrelation coefficient index from the monitored area as input, and generate a "signal conflict coefficient", which is used to quantify whether the current signal conflicts and evaluate the quality of the signal. The higher the signal conflict coefficient, the greater the possibility of signal conflict or interference; conversely, a lower conflict coefficient indicates better signal transmission quality and less interference. The key to this process lies in the "intelligent" nature of the model, that is, the machine learning model can analyze new signal features and make judgments in real time based on the rules and experience learned from historical data without human intervention.

[0098] The advantage of machine learning models is that they can process complex, high-dimensional data and automatically discover nonlinear relationships between signals and between signals and interference. When the input data undergoes certain changes or new types of interference, the model gradually optimizes its predictive capabilities through continuous learning (such as incremental learning or online learning). This adaptability enables the system to cope with dynamically changing traffic environments and maintain efficient and stable performance in conditions of dense vehicle traffic and frequent signal conflicts. In addition, the pre-learned model can further improve the accuracy of signal conflict recognition by continuously accumulating data feedback from actual operations, thereby achieving more accurate interference control and signal tuning, ensuring that the electric vehicle monitoring system can still operate stably in complex environments.

[0099] Based on the evaluation results of the machine learning model, wireless signals are divided into two categories: RF signal collision and RF signal non-interference propagation;

[0100] The signal conflict coefficient generated by the intelligent evaluation of the wireless signal conflict status during the wireless signal propagation process in the current detection area through the pre-learned machine learning model is compared and analyzed with the pre-set signal conflict coefficient reference threshold, and the RF wireless signal status in the current detection area is divided. The division steps are as follows:

[0101] If the signal conflict coefficient is greater than a preset signal conflict coefficient reference threshold, the radio frequency wireless signal in the current detection area is classified as a radio frequency signal collision;

[0102] If the signal conflict coefficient is less than or equal to a preset signal conflict coefficient reference threshold, the radio frequency wireless signal in the current detection area is classified as radio frequency signal non-interference propagation;

[0103] RF signal collision means that in the same monitoring area, multiple electric vehicle on-board RF sensors or other wireless devices transmit signals at the same time, causing signals to interfere with or overlap each other, resulting in signal data loss, confusion or transmission errors. RF signal interference-free propagation means that within the monitoring area, the signals of electric vehicle on-board RF sensors can be stably and unimpededly transmitted to the receiving device, and the received signals are clear and reliable, and are not affected by any external interference or other signal sources.

[0104] For interference-free propagation of RF signals, the RF sensors on electric vehicles continue to send wireless signals at a preset power to ensure stable and reliable signal coverage;

[0105] When the RF signal is transmitted without interference, the RF sensor on the electric vehicle continues to send wireless signals at a preset power to ensure the stability and reliability of the signal and to ensure that the monitoring system can continuously and accurately receive signals from the vehicle without interference. This approach can maintain the signal coverage in the monitoring area, avoid signal attenuation or loss due to low signal power, and ensure that the traffic management system can effectively track vehicle behavior in real time and conduct dynamic monitoring and data collection. By maintaining a constant signal power, the system can operate efficiently and provide reliable data support for subsequent traffic scheduling and safety monitoring.

[0106] In the case of RF signal collision, based on the evaluation results of the machine learning model, the signal transmission power of different electric vehicle onboard RF sensors is dynamically adjusted to ensure the optimization of signal transmission quality in high-density traffic environments, reduce interference, and improve the accuracy and reliability of data transmission;

[0107] In the case of RF signal collision, based on the evaluation results of the machine learning model, the signal transmission power of different electric vehicle onboard RF sensors is dynamically adjusted to ensure the optimization of signal transmission quality in high-density traffic environments, reduce interference, and improve the accuracy and reliability of data transmission. The specific steps are as follows:

[0108] After confirming that there is a radio frequency signal collision in the current area, the signal transmission power of each electric vehicle's onboard radio frequency sensor is dynamically adjusted based on the results of the machine learning model evaluation. The adjustment process aims to optimize signal quality, reduce interference, and ensure the accuracy and reliability of data transmission. The transmission power of each vehicle is adjusted based on the preset signal transmission power and the machine learning model evaluation results. The specific adjustment formula is as follows:

[0109]

[0110] , where P adj is the adjusted signal transmission power. By adjusting the power of different electric vehicle-mounted RF sensors, the signal transmission quality can be optimized, interference can be reduced, and the signal stability and reliability can be ensured. pre is the preset signal transmission power, ΔP factor It is the power adjustment factor, which is used to control the power adjustment range. It determines the influence of the signal conflict coefficient and the reference threshold ratio on the transmission power. SC is the signal conflict coefficient. ref is the reference threshold of the signal conflict coefficient, β is an adjustment parameter used to control the nonlinear relationship between the conflict degree and power adjustment;

[0111] This step dynamically adjusts the signal transmission power of the electric vehicle's onboard RF sensor based on the result of signal conflict detection to optimize the signal transmission quality. The signal conflict coefficient SC evaluated by the machine learning model and the preset reference threshold SC ref , can adjust the signal transmission power in real time to cope with signal interference and conflict in high-density traffic environments. The adjusted transmission power can reduce interference, improve signal reliability and accuracy, ensure the stability of data transmission and the efficient operation of the traffic monitoring system.

[0112] After adjusting the signal transmission power of the electric vehicle's onboard RF sensor, the following optimization strategy is adopted to accurately control the signal transmission quality by continuously optimizing the transmission power, reducing the interference caused by signal collision, reducing data loss and transmission errors, and ensuring the reliability of the communication link:

[0113]

[0114] , where Q opt is the signal transmission quality after optimization, θ is the proportional coefficient of signal optimization, which indicates the influence of power adjustment on signal quality, InterferenceFactor is the interference factor calculated by the current environmental interference level, and γ is the exponential adjustment parameter used to control the influence of power adjustment on signal quality.

[0115] This step optimizes the signal transmission quality, reduces interference, and improves the accuracy and reliability of data transmission by dynamically adjusting the transmission power of the electric vehicle's onboard RF sensor. Through precise power adjustment, the system can cope with signal conflicts in high-density traffic environments and ensure stable and interference-free signal transmission, thereby improving the stability of the communication link and ensuring that the traffic management system can accurately and timely receive and process data. This process allows the signal to maintain efficient transmission quality in complex environments and avoid data loss or transmission errors.

[0116] By dynamically adjusting the signal transmission power of the RF sensors on electric vehicles based on the evaluation results of the machine learning model, the problem of RF signal collision in high-density traffic environments can be addressed. With the increase in the number of electric vehicles and the dense traffic flow, the RF signals of multiple electric vehicles may interfere with each other, resulting in signal collisions, which in turn affects the quality of data transmission and the accuracy of the monitoring system. In this case, the traditional fixed-power signal transmission method cannot effectively solve the signal interference problem, often resulting in signal loss or misreading, thus affecting the monitoring of violations and the real-time nature of traffic management.

[0117] By dynamically adjusting the signal transmission power, the system can flexibly adjust the signal strength of each electric vehicle's onboard RF sensor based on the real-time assessment of signal conflicts, ensuring that the signals of different vehicles do not interfere with each other and that the signals can be transmitted with optimal strength. This dynamic adjustment can not only achieve better signal isolation between different vehicles, but also optimize the signal coverage and quality, avoiding signal attenuation caused by too low power or excessive interference caused by too high power.

[0118] In addition, the machine learning model plays a key role in this process. By analyzing and evaluating the collected signal data in real time, it can accurately identify the patterns and trends of signal conflicts, thereby providing a scientific basis for adjusting the transmission power. This intelligent, real-time adjustment method can effectively reduce interference in complex traffic environments, improve the stability and reliability of signal transmission, ensure the monitoring system's accurate identification of electric vehicle behavior, and enhance the response speed and decision-making efficiency of the traffic management system. Ultimately, the application of this technology can improve overall traffic safety, reduce the occurrence of traffic accidents, and improve the management efficiency of traffic flow.

[0119] The present invention can effectively solve the signal interference and collision problems of electric vehicles in traffic-intensive areas by combining radio frequency wireless transmission technology and machine learning models. By acquiring the wireless signals emitted by the on-board radio frequency sensors in real time, using machine learning models to intelligently evaluate the signal status, and dynamically adjusting the signal transmission power according to the evaluation results, it can ensure that in high-density traffic environments, signal interference is reduced, the accuracy of data transmission and the accuracy of the monitoring system are improved, thereby achieving accurate identification and timely processing of electric vehicle violations. This method effectively improves the intelligence and reliability of the traffic management system, enhances the system's ability to respond to dynamic traffic conditions, and thereby improves the efficiency of traffic safety and flow management.

[0120] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0121] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0122] It should be noted that, in this article, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0123] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0124] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0125] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0128] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0129] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for monitoring electric vehicle traffic violations based on radio frequency wireless transmission technology, characterized in that: The following steps are involved: First, the RF sensor on the electric vehicle transmits wireless signals at a preset power to ensure that the signal of each electric vehicle is stably and reliably transmitted within the monitoring area; The RF receiver acquires the signal data sent by the vehicle-mounted RF sensors passing through the monitoring area in real time. Through the captured wireless signals, the receiver obtains the real-time dynamic information of each vehicle; The acquired wireless signal data is constructed into a data set and preprocessed to lay the foundation for subsequent data analysis. The key features reflecting signal conflicts are extracted from the preprocessed signal data, and the extracted key features are deeply analyzed under the detection window to evaluate the current signal status. The analyzed key features are input into the pre-trained machine learning model, and the wireless signal status is intelligently evaluated through the machine learning model; Based on the evaluation results of the machine learning model, wireless signals are divided into two categories: RF signal collision and RF signal non-interference propagation; For interference-free propagation of RF signals, the RF sensors on electric vehicles continue to send wireless signals at a preset power to ensure stable and reliable signal coverage; In the event of signal collision, the signal transmission power of different electric vehicle onboard RF sensors is dynamically adjusted based on the evaluation results of the machine learning model to ensure the optimization of signal transmission quality in high-density traffic environments, reduce interference, and improve the accuracy and reliability of data transmission.

2. According to claim 1, a method for monitoring electric vehicle violations based on radio frequency wireless transmission technology is characterized in that: Key features reflecting signal conflicts are extracted from the preprocessed signal data. The extracted features include the symbol error rate during data transmission and the consistency of the same signal at different time points. Under the detection window, the symbol error rate during data transmission and the consistency of the same signal at different time points are analyzed to generate symbol error rate factors and signal autocorrelation coefficient factors, respectively. The symbol error rate factor is used to quantify the degree of mismatch between the received symbol and the original symbol during signal transmission. The signal autocorrelation coefficient factor is used to quantify the consistency of the same signal at different time points, that is, the stability of the signal over time.

3. The method for monitoring electric vehicle violations based on radio frequency wireless transmission technology according to claim 2 is characterized in that: The specific steps of analyzing the error rate of symbols in the data transmission process under the detection window to generate the symbol error rate factor are as follows: First, the received signal symbols are compared with the original symbols sent during data transmission to calculate the bit error rate. Suppose the received signal symbol set is R = {r i }={r1, r2, ..., r n }, and the original symbol set is G = {g i }={g1, g2, ..., g n }, where r i is the i-th symbol received by the receiver during the transmission process, g i is the i-th symbol sent by the transmitter, n is the total number of symbols, and the bit error rate of each symbol position is calculated by the following formula: In the formula, e i is the error flag of the i-th symbol; Next, the symbol error rate within the entire detection window is calculated, and the calculation expression is as follows: Where BER is the symbol error rate; In order to accurately reflect the performance of the signal in a complex environment, the characteristics of the signal in the time domain and frequency domain are considered, and the interference influence coefficient is introduced. The calculation expression is as follows: In the formula, α is a power index used to adjust the influence of the error part, β is an index used to adjust the influence of the signal amplitude on the overall calculation, γ is an index to adjust the influence of the signal amplitude part, and D is the interference influence coefficient; The final symbol error rate factor is calculated using the following formula: SBER=BER·D Where SBER is the symbol error rate factor.

4. The method for monitoring electric vehicle violations based on radio frequency wireless transmission technology according to claim 2 is characterized in that: The specific steps for analyzing the consistency of the same signal at different time points under the detection window to generate the signal autocorrelation coefficient factor are as follows: First, we need to calculate the signal autocorrelation function to quantify the consistency of the signal at different time points. Assuming that the signal s(t) is transmitted in the time interval [0, T], the signal autocorrelation function calculation expression is as follows: Where s(t) is the signal value at time t, τ is the time delay measure of the signal, T is the detection window length, s(t+τ) is the value of the signal s(t) at the position after a time delay of τ, and R(τ) is the autocorrelation function, which is used to quantify the consistency of the signal at different time points. Next, based on the calculation results of the autocorrelation function, the autocorrelation coefficient factor of the signal is generated, and the enhanced nonlinear metric is used to describe the periodic consistency of the signal. The autocorrelation coefficient index calculation expression is as follows: In the formula, R max is the maximum value of the autocorrelation function within the detection window, ω is the parameter that controls the exponential decay, R(τ)-R max It is the amplitude of the change in signal autocorrelation, which measures the degree of fluctuation of the signal under different delays. ACF is the signal autocorrelation coefficient factor.

5. The method for monitoring electric vehicle violations based on radio frequency wireless transmission technology according to claim 2 is characterized in that: The analyzed symbol error rate factor and signal autocorrelation coefficient factor are input into the pre-learned machine learning model, and the signal conflict coefficient is generated by the machine learning model. The signal conflict coefficient is used to intelligently evaluate the wireless signal conflict status during the wireless signal propagation process in the current detection area.

6. The method for monitoring electric vehicle violations based on radio frequency wireless transmission technology according to claim 5 is characterized in that: The signal conflict coefficient generated by the intelligent evaluation of the wireless signal conflict status during the wireless signal propagation process in the current detection area through the pre-learned machine learning model is compared and analyzed with the pre-set signal conflict coefficient reference threshold, and the RF wireless signal status in the current detection area is divided. The division steps are as follows: If the signal conflict coefficient is greater than a preset signal conflict coefficient reference threshold, the radio frequency wireless signal in the current detection area is classified as a radio frequency signal collision; If the signal conflict coefficient is less than or equal to a preset signal conflict coefficient reference threshold, the radio frequency wireless signal in the current detection area is classified as radio frequency signal non-interference propagation.

7. The method for monitoring electric vehicle traffic violation based on radio frequency wireless transmission technology according to claim 6 is characterized in that: In the case of RF signal collision, based on the evaluation results of the machine learning model, the signal transmission power of different electric vehicle onboard RF sensors is dynamically adjusted to ensure the optimization of signal transmission quality in high-density traffic environments, reduce interference, and improve the accuracy and reliability of data transmission. The specific steps are as follows: After confirming that there is a radio frequency signal collision in the current area, the signal transmission power of each electric vehicle's onboard radio frequency sensor is dynamically adjusted based on the results of the machine learning model evaluation. The transmission power of each vehicle is adjusted based on the preset signal transmission power and the machine learning model evaluation results. The specific adjustment formula is as follows: Where P adj is the adjusted signal transmission power, P pre is the preset signal transmission power, ΔP factor is the power adjustment factor, SC is the signal conflict coefficient, SC ref is the reference threshold of the signal conflict coefficient, β is an adjustment parameter used to control the nonlinear relationship between the conflict degree and power adjustment; After adjusting the signal transmission power of the electric vehicle's onboard RF sensor, the following optimization strategy is adopted to accurately control the signal transmission quality by continuously optimizing the transmission power, reducing the interference caused by signal collision, reducing data loss and transmission errors, and ensuring the reliability of the communication link: In the formula, Q opt is the signal transmission quality after optimization, θ is the proportional coefficient of signal optimization, which indicates the influence of power adjustment on signal quality, InterferenceFactor is the interference factor calculated by the interference degree of the current environment, and γ is the exponential adjustment parameter used to control the influence of power adjustment on signal quality.

Images