AI analysis-based motor train unit communication management method and system

Abstract

The application is suitable for the technical field of motor train unit communication management, and provides a motor train unit communication management method and system based on AI analysis.The method comprises the following steps: when it is predicted that a target motor train unit communication system has a link stability risk caused by pantograph instantaneous interruption in a future period, the current route priority improvement range of a backup link is obtained, a predicted voltage disturbance index corresponding to the future period is obtained, and historical operation condition data of the communication system is extracted.The application introduces a double correction factor mechanism under the condition of predicted voltage disturbance by constructing a motor train unit communication management method based on AI analysis, dynamically corrects the route priority improvement range of the backup link, and thus realizes fine adjustment of a link scheduling strategy.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of EMU communication management, and particularly relates to an EMU communication management method and system based on AI analysis. BACKGROUND

[0002] In the process of EMU operation, the train-ground communication system is a key basis for ensuring the real-time transmission of train dispatching instructions, state feedback and safety control data, and the link stability thereof is directly related to the operation safety and control efficiency of the whole train. In the existing communication management technology, a multi-link redundancy mechanism is generally adopted to trigger a backup link access mechanism when a main link is interrupted or the quality thereof is reduced, and common methods include route switching based on channel quality indicators, static priority configuration or link scheduling strategies based on preset rules. Most of these methods are based on real-time communication parameters (such as signal strength, packet loss rate, delay, etc.) for single-point judgment, lack depth analysis of the evolution trend of link performance, and cannot fully adapt to dynamic disturbances in complex environments, especially in high-frequency and high-speed operation scenarios, there are problems of scheduling response lag and link selection error when facing sudden electrical abnormalities.

[0003] Taking voltage disturbance caused by catenary instantaneous interruption as an example, such disturbance usually occurs in transient states such as short-time poor contact of the catenary and interruption of the current, although the duration is short, but it is easy to affect the power supply stability of the on-board communication module, and then cause communication interruption or link reconnection, affecting the continuity of train-ground communication. In the existing technical framework, such disturbance is usually treated as an abnormal event, and only reconnection or link switching is performed after the occurrence, lacking of pre-emptive prediction evaluation and link scheduling preparation based on disturbance risk. In addition, the priority promotion mechanism of the existing backup link is usually statically set, and the historical performance of the main and backup links in similar disturbance environments is not combined, resulting in that the scheduling strategy is difficult to accurately match the current risk situation, and the reliability and resource efficiency are difficult to guarantee. SUMMARY

[0004] The purpose of the present application is to provide an EMU communication management method and system based on AI analysis, which aims to solve the problems raised in the background art.

[0005] The present application is implemented in the following way: an EMU communication management method based on AI analysis, the method comprising:

[0006] When it is predicted that the target EMU communication system has a link stability risk caused by catenary instantaneous interruption in a future period, the current route priority promotion range of the backup link is obtained, and the predicted voltage disturbance index corresponding to the future period is obtained, and the historical operation condition data of the communication system is extracted;

[0007] Based on historical operation condition data, analyze the transmission reliability performance of the main link and the standby link under the predicted voltage disturbance index, and generate a first correction factor according to the performance deviation between the two;

[0008] Based on historical operation condition data, analyze the transmission reliability performance of the main link and the standby link under the predicted voltage disturbance index, and generate a first correction factor according to the performance deviation between the two;

[0009] Comprehensively correct the current routing priority of the standby link based on the first correction factor and the second correction factor.

[0010] As a further limitation of the technical scheme of the embodiment of the application, based on historical operation condition data, analyze the transmission reliability performance of the main link and the standby link under the predicted voltage disturbance index, and generate a first correction factor according to the performance deviation between the two.

[0011] Based on historical operation condition data, analyze the transmission reliability performance of the main link and the standby link under the predicted voltage disturbance index, and generate a first correction factor according to the performance deviation between the two;

[0012] Determine the first packet loss rate and the second packet loss rate corresponding to each set of first local operation data and second local operation data, respectively, and calculate the average value of the first packet loss rate and the second packet loss rate of the preset number;

[0013] Quantify the deviation between the two average values, and take the deviation value as the first correction factor.

[0014] As a further limitation of the technical scheme of the embodiment of the application, based on historical operation condition data, analyze the transmission reliability performance of the main link and the standby link under the predicted voltage disturbance index, and generate a first correction factor according to the performance deviation between the two.

[0015] Based on historical operation condition data, analyze the transmission reliability performance of the main link and the standby link under the predicted voltage disturbance index, and generate a first correction factor according to the performance deviation between the two;

[0016] According to the time sequence, draw the preset number of first transmission interruption rates and second transmission interruption rates as the anti-interference performance evolution curve of the main link communication unit and the anti-interference performance evolution curve of the standby link communication unit, respectively;

[0017] The average slope of the anti-interference performance evolution curves of the primary link and the backup link communication units is calculated separately, and the deviation between the two slopes is quantified, with the deviation as the second correction factor.

[0018] As a further limitation of the technical solution of this invention, the step of dynamically correcting the current routing priority increase of the backup link by combining the first correction factor and the second correction factor includes:

[0019] Obtain the preset improvement magnitude correction formula, and substitute the first correction factor and the second correction factor into the improvement magnitude correction formula to dynamically correct the current routing priority improvement magnitude of the backup link;

[0020] The revised route priority increase will be applied to the backup link priority evaluation and scheduling strategy.

[0021] As a further limitation of the technical solution of this embodiment of the invention, the formula for correcting the improvement magnitude is: ,in This refers to the magnitude of the priority increase after the route correction. This refers to the extent to which the current route priority is increased. This refers to the average of the first packet loss rate for a preset number of packets. This refers to the average of the second packet loss rate for a preset number of packets. This refers to the first correction factor, which is the deviation between the average of the first packet loss rate and the second packet loss rate for a preset number of packets. This refers to the denominator The minimum tolerance threshold is set. This refers to the adjustment coefficient corresponding to the first correction factor. This refers to the average slope of the anti-interference performance evolution curve of the primary link communication unit. This refers to the average slope of the anti-interference performance evolution curve of the backup link communication unit. This refers to the second correction factor, which is the deviation of the slope between the average slopes of the anti-interference performance evolution curves of the primary link and the backup link communication units. This refers to the denominator The minimum tolerance threshold is set. This refers to the adjustment coefficient corresponding to the second correction factor.

[0022] The AI-based EMU communication management system includes: a data acquisition module, a first correction factor determination module, a second correction factor determination module, and an increase magnitude correction module, wherein:

[0023] The data acquisition module is configured to acquire a current route priority promotion range of the backup link when it is predicted that the target motor train communication system has a link stability risk caused by pantograph instantaneous interruption in a future period, acquire a predicted voltage disturbance index corresponding to the future period, and extract historical operation condition data of the communication system;

[0024] The first correction factor determination module is configured to analyze transmission reliability performances of the main link and the backup link under the predicted voltage disturbance index based on the historical operation condition data, and generate a first correction factor according to a performance deviation between the main link and the backup link.

[0025] The second correction factor determination module is configured to analyze an anti-interference performance evolution trend of a communication unit corresponding to the main link and a communication unit corresponding to the backup link under the predicted voltage disturbance index based on the historical operation condition data, and generate a second correction factor based on a difference between evolution characteristics of the two communication units.

[0026] The promotion range correction module is configured to dynamically correct the current route priority promotion range of the backup link by comprehensively considering the first correction factor and the second correction factor.

[0027] As a further limitation of the technical scheme of the embodiment of the present application, the first correction factor determination module specifically comprises:

[0028] The data filtering unit is configured to analyze the historical operation condition data, backtrack from a current time point, and filter out a preset number of first local operation data and second local operation data of the main link and the backup link under the predicted voltage disturbance index.

[0029] The packet loss rate calculation unit is configured to determine a first packet loss rate and a second packet loss rate corresponding to each set of first local operation data and second local operation data, respectively, and calculate an average value of the preset number of first packet loss rates and second packet loss rates, respectively.

[0030] The deviation value calculation unit is configured to quantify a deviation between the two average values and take the deviation value as the first correction factor.

[0031] As a further limitation of the technical scheme of the embodiment of the present application, the second correction factor determination module specifically comprises:

[0032] The transmission interruption rate calculation unit is configured to analyze the first local operation data and the second local operation data extracted from the historical operation condition data, and determine a first transmission interruption rate and a second transmission interruption rate of a communication unit corresponding to the main link and a communication unit corresponding to the backup link under the predicted voltage disturbance index.

[0033] The curve generation unit is used to plot the anti-interference performance evolution curves of the primary link communication unit and the backup link communication unit respectively, according to the time sequence, using a preset number of first transmission interruption rates and second transmission interruption rates.

[0034] The slope deviation magnitude determination unit is used to calculate the average slope of the anti-interference performance evolution curves of the primary link and the backup link communication units respectively, and to quantify the slope deviation magnitude between the two, using the deviation magnitude as the second correction factor.

[0035] As a further limitation of the technical solution of this embodiment of the invention, the improvement magnitude correction module specifically includes:

[0036] The elevation correction unit is used to obtain a preset elevation correction formula and substitute the first correction factor and the second correction factor into the elevation correction formula to dynamically correct the current routing priority elevation of the backup link.

[0037] The correction magnitude application unit is used to apply the corrected route priority increase to the backup link priority evaluation and scheduling strategy.

[0038] As a further limitation of the technical solution of this embodiment of the invention, the formula for correcting the improvement magnitude is: ,in This refers to the magnitude of the priority increase after the route correction. This refers to the extent to which the current route priority is increased. This refers to the average of the first packet loss rate for a preset number of packets. This refers to the average of the second packet loss rate for a preset number of packets. This refers to the first correction factor, which is the deviation between the average of the first packet loss rate and the second packet loss rate for a preset number of packets. This refers to the denominator The minimum tolerance threshold is set. This refers to the adjustment coefficient corresponding to the first correction factor. This refers to the average slope of the anti-interference performance evolution curve of the primary link communication unit. This refers to the average slope of the anti-interference performance evolution curve of the backup link communication unit. This refers to the second correction factor, which is the deviation of the slope between the average slopes of the anti-interference performance evolution curves of the primary link and the backup link communication units. This refers to the denominator The minimum tolerance threshold is set. This refers to the adjustment coefficient corresponding to the second correction factor.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The application realizes fine adjustment of the link scheduling strategy by constructing an AI analysis-based motor train unit communication management method, introducing a double correction factor mechanism under the condition of predicting voltage disturbance, and dynamically correcting the route priority elevation range of the standby link.

[0041] Compared with the priority allocation mode based on single link state or static indicators in the prior art, the application has stronger environmental perception ability and adaptability, and can guarantee the continuity and robustness of the communication system under sudden disturbances such as bow net instantaneous interruption. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 The flowchart of the method provided for the embodiment of the application is shown in Figure 1.

[0043] Figure 2 The flowchart of determining the first correction factor in the method provided for the embodiment of the application is shown in Figure 2.

[0044] Figure 3 The flowchart of determining the second correction factor in the method provided for the embodiment of the application is shown in Figure 3.

[0045] Figure 4 The flowchart of correcting the current route priority elevation range of the standby link in the method provided for the embodiment of the application is shown in Figure 4.

[0046] Figure 5 The application architecture diagram of the system provided for the embodiment of the application is shown in Figure 5.

[0047] Figure 6 The structural block diagram of the first correction factor determination module in the system provided for the embodiment of the application is shown in Figure 6.

[0048] Figure 7 The structural block diagram of the second correction factor determination module in the system provided for the embodiment of the application is shown in Figure 7.

[0049] Figure 8 The structural block diagram of the elevation range correction module in the system provided for the embodiment of the application is shown in Figure 8. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical scheme and advantages of the application clearer, further detailed description of the application is made below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application and do not limit the application.

[0051] Figure 1A flow chart of the method provided by the embodiment of the application is shown.

[0052] Specifically, the AI analysis-based EMU communication management method specifically comprises the following steps:

[0053] In step S100, when it is predicted that the target EMU communication system has a link stability risk caused by pantograph instantaneous disconnection in a future period, the current route priority promotion range of the backup link is obtained, the predicted voltage disturbance index corresponding to the future period is obtained, and the historical operation condition data of the communication system is extracted.

[0054] In the embodiment of the application, the application background of the application mainly focuses on the stability guarantee of the EMU communication system in a high-speed running environment. With the wide application of intelligent dispatching and control systems in railway transportation, various key functions of the EMU put forward higher requirements on the real-time performance, stability and reliability of the communication link. However, when instantaneous disconnection occurs between the pantograph and the catenary (i.e., pantograph instantaneous disconnection), the system voltage will be disturbed, which is easy to cause communication link state fluctuation or even interruption, thereby affecting the stable operation of the EMU control and monitoring function. Therefore, in order to realize the forward-looking maintenance and dispatching optimization of the communication system, it is necessary to complete accurate prediction before the link stability risk appears, and to actively adjust the communication strategy based on the prediction result, which is the technical foothold and actual demand background of the subsequent scheme proposed by the application.

[0055] The target EMU communication system mainly refers to the data link system deployed on the EMU for realizing bidirectional communication between the train and the ground, which usually includes a main link and a backup link, and its functions include key tasks such as operation instruction transmission, state reporting, and abnormal alarm. The link stability risk caused by pantograph instantaneous disconnection refers to the short-time voltage drop or fluctuation event caused by the instantaneous loss of contact between the catenary and the pantograph. Such voltage disturbance will directly affect the power supply quality of the communication system, causing signal attenuation, rising of data packet loss rate, or temporary interruption of the link, thereby reducing the availability of the main link. The risk prediction means for such events belongs to the existing technical category, and has been initially applied in some rail transit systems, commonly using power fluctuation detection, operation data fitting, historical fault statistics and other methods for voltage disturbance trend analysis and risk judgment.

[0056] The current route priority promotion range of the standby link refers to the dynamic priority level allocated by the standby communication link to the main link state change in the link scheduling strategy. In the existing communication scheduling technology, the link priority is usually set according to the link quality, historical stability and service load and the like, and can be dynamically adjusted according to the link health degree, so that the initial priority evaluation and adjustment mechanism also belongs to the prior art category and has a certain application maturity. In the present application, the "promotion range" is introduced as a key variable to provide a basis for subsequent dynamic correction based on AI.

[0057] The predicted voltage disturbance index is a prediction of the degree of voltage fluctuation that may occur in the power supply system within a certain period of time, reflecting the potential risk of link stability facing electrical disturbance. The index is generally obtained by analyzing the statistical model of the vehicle-mounted voltage monitoring device, the state of the overhead line power supply and historical voltage disturbance events, and combining a machine learning model (such as LSTM, Bayesian network, etc.) for time series prediction. At present, in the electrical safety warning system, voltage disturbance prediction has gradually matured, and related methods include time series data regression, residual analysis and pattern recognition.

[0058] The historical operating condition data should include detailed operating information of the main link and the standby link under different voltage disturbance conditions, such as the operating stability performance of each link under different amplitude, duration and frequency of voltage disturbance scenarios. In addition, it should include basic communication indicators related to link performance, such as packet loss rate, transmission delay, link recovery time, etc., as well as specific model, technical parameters and hardware capability information of the communication units corresponding to each link. For different communication units, the transmission interruption rate, anti-interference ability and other data exhibited under various operating conditions also need to be recorded.

[0059] Further, the EMU communication management method based on AI analysis further comprises the following steps:

[0060] Step S200, based on the historical operating condition data, analyzing the transmission reliability performance of the main link and the standby link under the predicted voltage disturbance index, and generating a first correction factor according to the performance deviation between the two.

[0061] Specifically, Figure 2 A flowchart for determining the first correction factor is shown.

[0062] Among them, based on the historical operating condition data, analyzing the transmission reliability performance of the main link and the standby link under the predicted voltage disturbance index, and generating a first correction factor according to the performance deviation between the two, specifically includes the following steps:

[0063] Step S201, analyze the historical running condition data, and filter out the first local running data and the second local running data of the primary link and the backup link under the condition of the predicted voltage disturbance index from the current time point to the past;

[0064] Step S202, respectively determine the first packet loss rate and the second packet loss rate corresponding to each set of first local running data and second local running data, and respectively calculate the average values of the preset number of first packet loss rate and second packet loss rate;

[0065] Step S203, quantize the deviation between the two average values, and take the deviation value as the first correction factor.

[0066] In the embodiment of the application, the local running data of the preset number of primary links and backup links under the condition of the predicted voltage disturbance index is selected, mainly based on the balance between data stability and representativeness. On the one hand, by limiting the number, the size of the analysis and calculation can be effectively controlled, and the processing efficiency is improved; on the other hand, selecting a certain number of historical samples can help to avoid the interference of individual abnormal data on the overall analysis result, and ensure that the extracted link performance characteristics have statistical significance. The specific screening process is usually from the current time point to the past, and the historical disturbance segment similar or close to the predicted voltage disturbance index is matched according to the set disturbance condition, and the running data of the primary and backup links in the corresponding period is extracted. This process can realize intelligent screening by setting parameters such as disturbance amplitude tolerance interval, disturbance time window length and disturbance occurrence frequency.

[0067] In addition to the packet loss rate, a plurality of quality indicators commonly used in communication systems can also be included as performance evaluation characteristics, such as average delay, delay jitter, link recovery time, bit error rate, instantaneous throughput, etc. These indicators can reflect the actual transmission performance of the link under the condition of voltage disturbance from different dimensions, and if they are normalized and incorporated into the analysis process, the comprehensive judgment ability of the first correction factor can be further improved, and the adaptability of the correction model to complex disturbance conditions can be enhanced.

[0068] The difference between the average packet loss rates of the primary link and the backup link under the same predicted voltage disturbance index is introduced as the first correction factor, which can directly reflect the actual running reliability of the backup link in the historical similar voltage disturbance environment. When the average packet loss rate of the backup link is significantly lower than that of the primary link, it means that it has stronger stability and transmission capacity in the current predicted disturbance environment, so the improvement range of the current set routing priority of the backup link should be further enhanced to intervene in the link takeover or backup scheduling process in advance, and reduce the risk of communication interruption caused by the fluctuation of the primary link.

[0069] On the contrary, if the packet loss rate of the backup link is higher than that of the main link in the historical similar environment, it means that the backup link may not be able to provide more reliable communication guarantee under the current predicted condition, and at this time, the routing priority promotion range of the backup link should be appropriately adjusted to avoid the secondary instability caused by mis-triggering of link switching.

[0070] Therefore, the deviation between the two average values is used as the first correction factor to dynamically correct the current routing priority promotion range of the backup link, which can realize a more effective and environment-adaptive scheduling strategy. This data-driven priority adjustment mechanism can enhance the response capability and recovery robustness of the system when facing sudden events such as instantaneous voltage disturbance (e.g. instantaneous interruption of pantograph-catenary), effectively reducing the overall impact of communication interruption on the control system of the EMU.

[0071] Further, the EMU communication management method based on AI analysis further comprises the following steps:

[0072] Step S300, analyze the historical operating condition data, analyze the anti-interference performance evolution trend of the communication unit corresponding to the main link and the communication unit corresponding to the backup link under the predicted voltage disturbance index, and generate a second correction factor based on the difference between the evolution characteristics of the two.

[0073] Specifically, Figure 3 A flowchart for determining the second correction factor is shown.

[0074] The historical operating condition data is analyzed to analyze the anti-interference performance evolution trend of the communication unit corresponding to the main link and the communication unit corresponding to the backup link under the predicted voltage disturbance index, and a second correction factor is generated based on the difference between the evolution characteristics of the two. Specifically, the following steps are included:

[0075] Step S301, analyze the first local operating data and the second local operating data extracted from the historical operating condition data, and determine the first transmission interruption rate and the second transmission interruption rate of the communication unit corresponding to the main link and the communication unit corresponding to the backup link under the predicted voltage disturbance index;

[0076] Step S302, according to the time sequence, draw the first transmission interruption rate and the second transmission interruption rate as the anti-interference performance evolution curve of the main link communication unit and the anti-interference performance evolution curve of the backup link communication unit, respectively;

[0077] Step S303, calculate the average slope of the anti-interference performance evolution curve of the main link and the backup link communication unit, respectively, and quantify the slope deviation between the two based on the slope deviation, and take the deviation as the second correction factor.

[0078] In the embodiments of the present application, the "determining the first transmission interruption rate and the second transmission interruption rate of the communication unit corresponding to the primary link and the communication unit corresponding to the backup link under the predicted voltage disturbance index condition" refers to analyzing a plurality of time segments in the historical operation condition data under the matching condition with the current predicted voltage disturbance index, calculating the number of interruptions per unit time by counting the frequency of transmission interruption events of the communication unit in these segments, and then forming the first transmission interruption rate and the second transmission interruption rate. In order to improve the calculation accuracy, the window sliding statistics, event tagging or interval interpolation method can be used in specific implementation to ensure the consistency of the interruption statistics and the disturbance index. In addition, in addition to the transmission interruption rate, performance indicators such as the number of data packet retransmissions, the average transmission delay jitter amplitude, the signal-to-noise ratio dynamic fluctuation value, and the average connection recovery time can also be introduced as extended features of the anti-interference capability analysis to enrich the description dimension of the stability evolution trend of the communication unit.

[0079] In the process of drawing the anti-interference performance evolution curve, first, the first transmission interruption rate and the second transmission interruption rate of a preset number are structured in time sequence, which can be converted into a discrete sampling point sequence by using time series modeling. Then, based on the sequence, the anti-interference performance evolution curves of the communication units of the primary link and the backup link are drawn respectively. In order to improve the representativeness and reliability of the curve, the original interruption rate sequence needs to be preprocessed if necessary, including low-pass filtering, wavelet denoising, local anomaly rejection or sliding average smoothing, to weaken the interference of incidental noise and extract more trend information features.

[0080] In actual scenarios, since the voltage disturbance will continuously affect the communication performance within a certain time window, the interruption rates of the communication units of the primary link and the backup link often show an upward trend. However, if the average slope of the evolution curve of a communication unit is significantly smaller than that of another communication unit, it means that the interruption rate of the former rises more slowly under the same disturbance intensity, i.e., the anti-interference capability is relatively stronger. Therefore, the slope deviation amplitude not only reflects the rate difference of link performance changes, but also can be used as an important indicator to measure the stability evolution trend of the backup link.

[0081] Based on this, the use of the slope deviation amplitude as the second correction factor has the following significance: on the one hand, it describes the degradation speed of the transmission stability of the communication unit in the disturbance environment, making up for the shortcoming of the static index in capturing trend changes; on the other hand, applying this correction factor to the adjustment of the current routing priority increase amplitude can realize the dynamic quantitative judgment of the scheduling value of the backup link, making the decision mechanism more trend-predictive and adaptive to the running environment. In this way, not only the reliability screening accuracy of the backup link in the takeover process is improved, but also the recovery robustness of the overall communication system in the face of instantaneous disturbances is further enhanced.

[0082] Further, the high-speed train communication management method based on AI analysis further comprises the following steps:

[0083] In step S400, the first correction factor and the second correction factor are integrated to dynamically correct the current route priority promotion range of the backup link.

[0084] Specifically, Figure 4 A flowchart for correcting the current route priority promotion range of the backup link is shown.

[0085] The integration of the first correction factor and the second correction factor to dynamically correct the current route priority promotion range of the backup link specifically comprises the following steps:

[0086] In step S401, a preset promotion range correction formula is obtained, and the first correction factor and the second correction factor are substituted into the promotion range correction formula to dynamically correct the current route priority promotion range of the backup link.

[0087] In step S402, the corrected route priority promotion range is applied to the backup link priority evaluation and scheduling strategy.

[0088] The promotion range correction formula is: wherein represents the corrected route priority promotion range, represents the current route priority promotion range, represents the average value of a preset number of first packet loss rates, represents the average value of a preset number of second packet loss rates, represents the first correction factor, i.e., the deviation value between the average value of a preset number of first packet loss rates and second packet loss rates, represents the minimum tolerance threshold set for the denominator, represents the adjustment coefficient corresponding to the first correction factor, represents the average slope of the anti-interference performance evolution curve of the primary link communication unit, represents the average slope of the anti-interference performance evolution curve of the backup link communication unit, represents the second correction factor, i.e., the slope deviation range between the average slopes of the anti-interference performance evolution curves of the primary link and backup link communication units, represents the minimum tolerance threshold set for the denominator, represents the adjustment coefficient corresponding to the second correction factor.

[0089] ​​In the embodiment of the present application, the joint use of the first correction factor and the second correction factor to correct the current routing priority of the standby link is based on the comprehensive trade-off of the link reliability and the anti-interference ability. The first correction factor reflects the difference in transmission stability by comparing the packet loss rate of the main link and the standby link under historical disturbance conditions; the second correction factor evaluates the robustness of the communication unit anti-interference performance over time. The joint application of the two can identify the long-term performance of the link in the steady state and perceive the adaptability trend of the link when facing disturbance, significantly improving the discrimination accuracy and adjustment flexibility of the scheduling mechanism in complex dynamic environment.

[0090] This kind of double-factor fusion strategy breaks through the one-sidedness brought by a single index. The traditional method often only adjusts based on single-point data or a certain type of features in the current state, which easily ignores the potential performance evolution difference between links. The joint introduction of correction factors into the same calculation framework realizes the quantitative description of the coupling relationship between different dimensional features without explicitly introducing additional model structures, thereby bringing more stable and sensitive decision adjustment ability.

[0091] The preset correction formula of the lifting range is an intuitive and efficient calculation method, which can realize the joint correction of the link performance state and the evolution trend, has simple form and is easy to deploy, and has good sensitivity control for parameter adjustment. In addition to the linear weighted offset model, nonlinear functions (such as exponential decay, logic functions, etc.) can be introduced to weight the correction factors to improve the suppression ability of extreme disturbance; or a flexible evaluation mechanism can be constructed based on fuzzy reasoning, Bayesian estimation, etc. to enhance its processing ability for uncertain information. These methods can be further expanded in the future for more complex multi-link dynamic environment.

[0092] Further, Figure 5 The application architecture diagram of the system provided by the embodiment of the present application is shown.

[0093] In another preferred embodiment provided by the present application, the EMU communication management system based on AI analysis comprises:

[0094] The data acquisition module 100 is configured to, when it is predicted that the target EMU communication system has a link stability risk caused by pantograph instantaneous interruption in a future period, acquire the current routing priority lifting range of the standby link, acquire the predicted voltage disturbance index corresponding to the future period, and extract historical operation condition data of the communication system.

[0095] Further, the EMU communication management system based on AI analysis further comprises:

[0096] The first correction factor determination module 200 is configured to analyze transmission reliability performances of the main link and the standby link under the predicted voltage disturbance index based on the historical operation condition data, and generate the first correction factor according to a performance deviation between the main link and the standby link.

[0097] Specifically, Figure 6 A structure block diagram of the first correction factor determination module 200 in the system provided by the embodiment of the application is shown.

[0098] In the preferred embodiment provided by the application, the first correction factor determination module 200 specifically includes:

[0099] The data screening unit 201 is configured to parse the historical operation condition data, and backtrace from a current time point to filter out a preset number of first local operation data and second local operation data of the main link and the standby link under the predicted voltage disturbance index condition.

[0100] The packet loss rate calculation unit 202 is configured to determine a first packet loss rate and a second packet loss rate corresponding to each set of the first local operation data and the second local operation data, respectively, and calculate average values of the preset number of the first packet loss rate and the second packet loss rate, respectively.

[0101] The deviation value calculation unit 203 is configured to quantify a deviation between the two average values, and take the deviation value as the first correction factor.

[0102] Further, the EMU communication management system based on AI analysis further includes:

[0103] The second correction factor determination module 300 is configured to parse the historical operation condition data, analyze an anti-interference performance evolution trend of the communication unit corresponding to the main link and the communication unit corresponding to the standby link under the predicted voltage disturbance index, and generate the second correction factor based on a difference between evolution characteristics of the two.

[0104] Specifically, Figure 7 A structure block diagram of the second correction factor determination module 300 in the system provided by the embodiment of the application is shown.

[0105] In the preferred embodiment provided by the application, the second correction factor determination module 300 specifically includes:

[0106] The transmission interruption rate calculation unit 301 is configured to parse the first local operation data and the second local operation data extracted from the historical operation condition data, and determine a first transmission interruption rate and a second transmission interruption rate of the communication unit corresponding to the main link and the communication unit corresponding to the standby link under the predicted voltage disturbance index condition.

[0107] The curve generation unit 302 is used to plot the anti-interference performance evolution curves of the primary link communication unit and the backup link communication unit respectively, according to the time sequence, using a preset number of first transmission interruption rates and second transmission interruption rates.

[0108] The slope deviation magnitude determination unit 303 is used to calculate the average slope of the anti-interference performance evolution curves of the primary link and the backup link communication units respectively, and to quantify the slope deviation magnitude between the two, using the deviation magnitude as the second correction factor.

[0109] Furthermore, the AI-based EMU communication management system also includes:

[0110] The elevation correction module 400 is used to dynamically correct the current routing priority elevation of the backup link by combining the first correction factor and the second correction factor.

[0111] Specifically, Figure 8 A structural block diagram of the boost magnitude correction module 400 in the system provided by an embodiment of the present invention is shown.

[0112] In a preferred embodiment of the present invention, the boost correction module 400 specifically includes:

[0113] The improvement magnitude correction unit 401 is used to obtain a preset improvement magnitude correction formula and substitute the first correction factor and the second correction factor into the improvement magnitude correction formula to dynamically correct the current routing priority improvement magnitude of the backup link.

[0114] The correction magnitude application unit 402 is used to apply the corrected route priority increase magnitude to the backup link priority evaluation and scheduling strategy.

[0115] The formula for correcting the increase is: ,in This refers to the magnitude of the priority increase after the route correction. This refers to the extent to which the current route priority is increased. This refers to the average of the first packet loss rate for a preset number of packets. This refers to the average of the second packet loss rate for a preset number of packets. This refers to the first correction factor, which is the deviation between the average of the first packet loss rate and the second packet loss rate for a preset number of packets. This refers to the denominator The minimum tolerance threshold is set. This refers to the adjustment coefficient corresponding to the first correction factor. This refers to the average slope of the anti-interference performance evolution curve of the primary link communication unit. denotes the average slope of the evolution curve of the anti-interference performance of the backup link communication unit, denotes the second correction factor, i.e. the slope deviation between the average slope of the evolution curve of the anti-interference performance of the backup link communication unit and the primary link, denotes the denominator of the minimum tolerance threshold set, denotes the adjustment coefficient corresponding to the second correction factor.

[0116] It should be understood that, although each step in the flowchart of each embodiment of the present application is shown in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or sub-steps or stages of other steps.

[0117] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the program can be stored in a non-volatile computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of each method. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0118] Any technical features in the above-described embodiments can be combined in any manner, and for the sake of brevity, not all possible combinations are described, but it is understood that the scope of the present specification includes all possible combinations.

[0119] The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

[0120] The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims. The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for communication management of a motor train unit based on AI analysis, characterized in that, The method comprises: When it is predicted that the target motor train communication system has a link stability risk caused by pantograph instantaneous interruption in a future period, the current route priority promotion range of the backup link is obtained, a predicted voltage disturbance index corresponding to the future period is obtained, and historical operation condition data of the communication system is extracted; Based on the historical operation condition data, the transmission reliability performance of the main link and the backup link under the predicted voltage disturbance index is analyzed, and a first correction factor is generated according to the performance deviation between the main link and the backup link; The steps comprise: The historical operation condition data is analyzed, and a preset number of first local operation data and second local operation data of the main link and the backup link under the predicted voltage disturbance index are filtered out from the current time point; The first packet loss rate and the second packet loss rate corresponding to each set of first local operation data and second local operation data are determined respectively, and the average values of the preset number of first packet loss rates and second packet loss rates are calculated respectively; The deviation between the two average values is quantified, and the deviation value is taken as the first correction factor; The historical operation condition data is analyzed, the anti-interference performance evolution trend of the communication unit corresponding to the main link and the communication unit corresponding to the backup link under the predicted voltage disturbance index is analyzed, and a second correction factor is generated based on the difference between the evolution characteristics of the two; The current route priority promotion range of the backup link is dynamically corrected by comprehensively considering the first correction factor and the second correction factor. 2.The AI analysis-based EMU communication management method of claim 1, wherein, The steps of analyzing the historical operation condition data, analyzing the anti-interference performance evolution trend of the communication unit corresponding to the main link and the communication unit corresponding to the backup link under the predicted voltage disturbance index, and generating a second correction factor based on the difference between the evolution characteristics of the two comprise: The first transmission interruption rate and the second transmission interruption rate of the communication unit corresponding to the main link and the communication unit corresponding to the backup link under the predicted voltage disturbance index are determined by analyzing the first local operation data and the second local operation data extracted from the historical operation condition data; According to the time sequence, the preset number of first transmission interruption rates and second transmission interruption rates are respectively drawn as the anti-interference performance evolution curve of the communication unit of the main link and the anti-interference performance evolution curve of the communication unit of the backup link; The average slope of the anti-interference performance evolution curve of the communication unit of the main link and the backup link is calculated respectively, and the slope deviation between the two is quantified, and the deviation is taken as the second correction factor. 3.The AI analysis-based EMU communication management method of claim 2, wherein, The steps of dynamically correcting the current route priority promotion range of the backup link by comprehensively considering the first correction factor and the second correction factor comprise: A preset promotion range correction formula is obtained, and the first correction factor and the second correction factor are substituted into the promotion range correction formula to dynamically correct the current route priority promotion range of the backup link; The corrected route priority promotion range is applied to the backup link priority evaluation and scheduling strategy. 4.The AI analysis-based EMU communication management method of claim 3, wherein, The promotion amplitude correction formula is: Wherein denotes the corrected route priority promotion amplitude, denotes the current route priority promotion amplitude, denotes the average value of the preset number of first packet loss rates, denotes the average value of the preset number of second packet loss rates, denotes the first correction factor, i.e. the deviation value between the average value of the preset number of first packet loss rates and second packet loss rates, denotes the minimum tolerance threshold set for the denominator , denotes the adjustment coefficient corresponding to the first correction factor, denotes the average slope of the anti-interference performance evolution curve of the primary link communication unit, denotes the average slope of the anti-interference performance evolution curve of the backup link communication unit, denotes the second correction factor, i.e. the slope deviation amplitude between the average slopes of the anti-interference performance evolution curves of the primary link and backup link communication units, denotes the minimum tolerance threshold set for the denominator , denotes the adjustment coefficient corresponding to the second correction factor.

5. The communication management system for EMU based on AI analysis, characterized in that, The system comprises a data acquisition module, a first correction factor determination module, a second correction factor determination module, and a promotion range correction module, wherein: The data acquisition module is configured to acquire a current route priority promotion range of the backup link when it is predicted that the target motor train communication system has a link stability risk caused by pantograph instantaneous interruption in a future period, acquire a predicted voltage disturbance index corresponding to the future period, and extract historical operation condition data of the communication system; The first correction factor determination module is configured to analyze transmission reliability performances of the main link and the backup link under the predicted voltage disturbance index based on the historical operation condition data, and generate a first correction factor according to a performance deviation between the main link and the backup link. The first correction factor determination module specifically includes: The data screening unit is configured to parse the historical operation condition data, backtrack from a current time point, and screen out a preset number of first local operation data and second local operation data of the main link and the backup link under the predicted voltage disturbance index. The packet loss rate calculation unit is configured to determine a first packet loss rate and a second packet loss rate corresponding to each set of first local operation data and second local operation data respectively, and calculate average values of the preset number of first packet loss rates and second packet loss rates respectively. The deviation value calculation unit is configured to quantify a deviation between the two average values and take the deviation value as the first correction factor. The second correction factor determination module is configured to parse the historical operation condition data, analyze anti-interference performance evolution trends of a communication unit corresponding to the main link and a communication unit corresponding to the backup link under the predicted voltage disturbance index, and generate a second correction factor based on differences in evolution characteristics of the two communication units. The promotion range correction module is configured to dynamically correct the current route priority promotion range of the backup link by comprehensively considering the first correction factor and the second correction factor. 6.The AI analysis-based EMU communication management system according to claim 5, characterized in that, The second correction factor determination module specifically includes: The transmission interruption rate calculation unit is configured to parse the first local operation data and the second local operation data extracted from the historical operation condition data, and determine a first transmission interruption rate and a second transmission interruption rate of the communication unit corresponding to the main link and the communication unit corresponding to the backup link under the predicted voltage disturbance index. The curve generation unit is configured to draw the preset number of first transmission interruption rates and second transmission interruption rates as an anti-interference performance evolution curve of the communication unit of the main link and an anti-interference performance evolution curve of the communication unit of the backup link respectively in chronological order. The slope deviation range determination unit is configured to calculate average slopes of the anti-interference performance evolution curves of the communication units of the main link and the backup link respectively, and quantify a slope deviation range between the two based on the slope deviation range, and take the deviation range as the second correction factor. 7.The AI analysis-based EMU communication management system according to claim 6, characterized in that, The promotion range correction module specifically includes: The promotion range correction unit is configured to acquire a preset promotion range correction formula, and substitute the first correction factor and the second correction factor into the promotion range correction formula to dynamically correct the current route priority promotion range of the backup link. The correction range application unit is configured to apply the corrected route priority promotion range to a backup link priority evaluation and scheduling strategy. 8.The AI analysis-based EMU communication management system according to claim 7, characterized in that, The formula for correcting the increase is: ,in This refers to the magnitude of the priority increase after the route correction. This refers to the extent to which the current route priority is increased. This refers to the average of the first packet loss rate for a preset number of packets. This refers to the average of the second packet loss rate for a preset number of packets. This refers to the first correction factor, which is the deviation between the average of the first packet loss rate and the second packet loss rate for a preset number of packets. This refers to the denominator The minimum tolerance threshold is set. This refers to the adjustment coefficient corresponding to the first correction factor. This refers to the average slope of the anti-interference performance evolution curve of the primary link communication unit. This refers to the average slope of the anti-interference performance evolution curve of the backup link communication unit. This refers to the second correction factor, which is the deviation of the slope between the average slopes of the anti-interference performance evolution curves of the primary link and the backup link communication units. This refers to the denominator The minimum tolerance threshold is set. This refers to the adjustment coefficient corresponding to the second correction factor.

Images