Intelligent early warning method and system for urban rail transit power supply system

Abstract

The invention discloses an intelligent early warning method and system for an urban rail transit power supply system, relates to the technical field of rail transit power supply early warning, and solves the technical problems that harmonic distortion rate evaluation deviates from an actual working condition due to the fact that the influence of environmental factors is not considered in the prior art, and early warning lags due to lack of a correction mechanism for fundamental wave fluctuation. The method comprises the following steps: acquiring harmonic data and environmental data of an urban rail transit power supply system; calculating a harmonic distortion rate influence factor based on the distortion rate data; correcting the harmonic distortion rate influence factor based on environmental data to obtain an initial evaluation factor; correcting the initial evaluation factor based on the fundamental wave fluctuation data to obtain a target evaluation factor; calculating a resonance sensitivity factor based on the harmonic power data; calculating a power supply system evaluation coefficient based on the target evaluation factor and the resonance sensitivity factor; and whether early warning is carried out is judged based on the power supply system evaluation coefficient. The technical problem is solved.

Description

Technical Field

[0001] The present invention belongs to the field of rail transit power supply early warning, and in particular relates to an intelligent early warning method and system for an urban rail transit power supply system. Background Art

[0002] The development of urban rail vehicles is placing increasing pressure on maintenance. While the traditional maintenance model was viable in the early stages of urban rail transit construction, the expansion of the network, the aging of electrical equipment, rising labor costs, and increasing passenger demand for service levels have made ensuring reliable system operation increasingly difficult and challenging. The current maintenance model is no longer sustainable.

[0003] The existing early warning systems for urban rail transit power supply systems mostly rely on single parameter monitoring or simple threshold judgment. For example, early warning is issued only by whether the current, voltage or specific harmonic amplitude exceeds the preset threshold. Some technologies will combine the static values ​​of fundamental current and voltage to assist in judgment, but there are significant limitations: First, the impact of environmental factors is not taken into account, and the dynamic changes of temperature and humidity on equipment electrical parameters (such as resistance and impedance) are ignored, resulting in the harmonic distortion rate assessment deviating from the actual working conditions. For example, high temperature exacerbates equipment loss but is not reflected in the early warning model; second, there is a lack of a correction mechanism for fundamental fluctuations. When the fundamental current or voltage suddenly increases, the ratio of harmonics to fundamental waves is underestimated, which can easily mask the risk of the actual absolute amplitude of harmonics and cause early warning lag.

[0004] Therefore, the present invention proposes an intelligent early warning method and system for an urban rail transit power supply system to solve the above problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes an intelligent early warning method and system for an urban rail transit power supply system, which is used to solve the technical problem that the prior art does not take into account the influence of environmental factors, resulting in the deviation of the harmonic distortion rate assessment from the actual working conditions, and lacks a correction mechanism for the fundamental wave fluctuation. When the fundamental current or voltage suddenly increases, the ratio of the harmonic to the fundamental wave is underestimated, which easily masks the risk of the actual absolute amplitude of the harmonic and causes a delayed early warning.

[0006] To achieve the above objectives, a first aspect of the present invention provides an intelligent early warning method for an urban rail transit power supply system, comprising: Obtain harmonic data and environmental data of the urban rail transit power supply system; harmonic data includes: distortion rate data and harmonic power data; The harmonic distortion rate influencing factor is calculated based on the distortion rate data; Correct the harmonic distortion rate influencing factors based on environmental data and initially evaluate the factors; The initial evaluation factor is modified based on the fundamental wave fluctuation data to obtain the target evaluation factor; The resonance sensitivity factor is calculated based on the harmonic power data; The power supply system evaluation coefficient is calculated based on the target evaluation factor and the resonance sensitivity factor; Determine whether to issue an early warning based on the power supply system evaluation coefficient.

[0007] In conjunction with the first aspect above, in one possible implementation, obtaining harmonic data and environmental data of the urban rail transit power supply system includes: The distortion rate data of the urban rail transit power supply system is collected in real time through a harmonic analyzer. The distortion rate data includes the total harmonic distortion rate of current and the total harmonic distortion rate of voltage. The power quality analyzer is used to collect harmonic power data of the urban rail transit power supply system in real time. The harmonic power data includes the current amplitude and voltage amplitude of each harmonic. Environmental data is collected in real time through data sensors; the environmental data includes: ambient temperature and ambient humidity.

[0008] It should be noted that the so-called harmonics refer to the harmonic components in the power supply system whose frequencies are integer multiples of the fundamental frequency, where the fundamental frequency is the rated frequency of the system, and the nth harmonic has a frequency of n×the fundamental frequency (n is an integer greater than 1, such as 2nd, 3rd, 5th, etc.); they are mainly generated by nonlinear loads (such as power electronic converters, rectifier equipment, etc.), which will be superimposed on the fundamental wave, causing the voltage or current waveform to deviate from the sine wave, forming distortion. They are specific subdivisions of the total harmonic distortion, and their amplitude and frequency characteristics directly affect the power supply quality of the system and the operating status of the equipment.

[0009] In combination with the first aspect above, in one possible implementation, calculating the harmonic distortion rate impact factor based on the distortion rate data includes: The total harmonic distortion rate of current is marked as I, and the total harmonic distortion rate of voltage is marked as V; The harmonic distortion rate influence factor is calculated using the formula X=α×e^(I / (I+1))+β×ln(tanh(V)+1). Here, X is the harmonic distortion rate influence factor, and α and β are weight coefficients.

[0010] It should be noted that the total harmonic distortion (THD) of current reflects the proportion of harmonic components in the current waveform. A higher THD means a higher proportion of harmonic current in the total current, significantly increasing the additional losses of transformers, cables, reactors and other equipment in the power supply system. High-frequency harmonic currents increase equipment resistance due to skin effect and proximity effect, generating additional heat, accelerating insulation aging, and even causing overheating failures. At the same time, harmonic currents interfere with relay protection devices and automated control systems, potentially causing malfunctions or reduced control accuracy, affecting the stability of train traction and braking. A lower THD means the current waveform is closer to an ideal sine wave, significantly reducing equipment losses, lowering the probability of interference with protection systems and control equipment, improving the energy transmission efficiency of the power supply network, extending equipment life, and making system operation more stable. The total harmonic distortion (THD) of voltage reflects the degree of distortion of the voltage waveform. When the THD is higher, the distorted voltage will directly affect sensitive power electronic equipment on the train, such as the traction converter and auxiliary power supply system, resulting in reduced equipment efficiency, increased heat generation, and even control logic disorder (such as abnormal PWM modulation). At the same time, high THD may trigger resonance in the power supply network, causing abnormal local voltage increases, breaking down equipment insulation or causing overvoltage damage to components such as capacitors and lightning arresters. In severe cases, it may cause train power interruption. When the THD is lower, the voltage waveform is purer, sensitive equipment can operate stably, the resonance risk is effectively suppressed, the power supply quality is better, the train's traction performance, braking feedback efficiency and the reliability of the on-board electronic system can be guaranteed, and the overall operational safety of the system is significantly improved.

[0011] In conjunction with the first aspect above, in one possible implementation, the correcting the harmonic distortion rate influencing factor based on the environmental data includes: The ambient temperature and ambient humidity are taken as independent variables and marked as T and H respectively; the initial evaluation factor obtained after correction is taken as the dependent variable and marked as CP; The independent variables and dependent variables are fitted by polynomial fitting to construct the first revised model; Based on the first correction model, the harmonic distortion rate influencing factor is corrected to obtain the initial evaluation factor; The first correction model is specifically: CP=X[1+A1×ln(e^(|T-ZT| / ZT))+A2×ln(e^(|H-ZH| / ZH))]; where A1 and A2 are proportional adjustment coefficients, ZT is the standard temperature, and ZH is the standard humidity.

[0012] It should be noted that environmental data (ambient temperature and humidity) indirectly affects the harmonic distortion rate by influencing the electrical parameters and operating status of power supply system equipment, thereby affecting the harmonic distortion rate influencing factor. When the ambient temperature is too high, the heat dissipation efficiency of equipment such as transformers and cables decreases, and the resistance increases due to the temperature rise. This may aggravate the skin effect and proximity effect of harmonic current, leading to higher current and voltage harmonic distortion rates and an increase in X. Excessively low temperatures may affect the switching characteristics of power electronic devices (such as converters), resulting in abnormal switching losses, which may also increase the harmonic distortion rate and increase X. When the ambient humidity is too high, the dielectric properties of the equipment's insulation materials degrade, which can easily cause partial discharge or increased leakage current, changing the equipment's impedance characteristics, potentially exacerbating harmonic distortion and increasing X. Excessively low humidity may lead to increased dust accumulation on the equipment surface, causing local electric field distortion, which may also increase harmonic components and increase X.

[0013] In conjunction with the first aspect above, in a possible implementation, the correcting the initial assessment factor based on the fundamental wave fluctuation data includes: The fundamental wave fluctuation data of the rail transit power supply system is collected in real time through the power quality analyzer; wherein the fundamental wave fluctuation data includes: fundamental wave current change value and fundamental wave voltage change value; The fundamental current change value is marked as I, the fundamental voltage change value is marked as V; Based on the fundamental wave fluctuation data, a second correction model is constructed to correct the initial evaluation factor to obtain the target evaluation factor; The second correction model is specifically: MP=CP[1+B1×ln(e^(| I| / (| I|+1)))+B2×ln(e^(| V| / (| V|+1)))]; where MP is the target evaluation factor, B1 and B2 are proportional adjustment coefficients, and when When I>0, 0<B1<1, 0<B2<1; when When I<0, -1<B1<0, -1<B2<0.

[0014] It should be noted that the fundamental current change value refers to the deviation of the real-time value of the fundamental current in the power supply system from its rated value (or benchmark reference value) (which can be expressed as an amplitude difference or percentage change), and the fundamental voltage change value refers to the deviation of the real-time value of the fundamental voltage from its rated value (or benchmark reference value); Fluctuations in the fundamental voltage or current (such as sudden increases) can reduce the ratio of harmonic current to fundamental current, causing the uncorrected initial assessment factor to underestimate the actual resonance risk. For example, because the total harmonic distortion rate of current I = √(∑Ih^2) / I1, when the fundamental current I1 suddenly increases, even if the harmonic current Ih remains unchanged, the total harmonic distortion rate I will decrease, making the initial assessment factor appear lower. However, the absolute amplitude of the actual harmonics may still cause resonance.

[0015] In combination with the first aspect above, in a possible implementation, calculating the resonance sensitivity factor based on the harmonic power data includes: The current amplitude of each harmonic and the voltage amplitude of each harmonic are marked as Ih and Vh respectively; where h is the harmonic order; The network impedance spectrum of harmonics is obtained in real time based on frequency domain impedance measurement technology; wherein the frequency domain impedance measurement technology includes: small signal injection method or impedance frequency response reconstruction method; Obtain the impedance value corresponding to each harmonic based on the network impedance spectrum, and mark the impedance value corresponding to each harmonic as Zh; The resonance sensitivity value corresponding to each harmonic is calculated using the formula Yh=(Ih×Vh) / |Zh|; where Yh refers to the resonance sensitivity value corresponding to the hth harmonic; The resonance sensitivity factor corresponding to each harmonic is obtained by normalizing the resonance sensitivity value.

[0016] It should be noted that the larger the resonance sensitivity factor, the higher the matching degree between the subharmonic and the local impedance, and the greater the resonance risk.

[0017] In combination with the first aspect above, in a possible implementation, calculating the power supply system evaluation coefficient based on the target evaluation factor and the resonance sensitivity factor includes: Extract the target evaluation factor MP and the resonance sensitivity factor, and mark the resonance sensitivity factor as Gh; The power supply system evaluation coefficient is calculated using the formula P=L1×MP+L2×∑(wh×Gh); where P is the power supply system evaluation coefficient, L1 and L2 are weight coefficients, wh is the weight coefficient of each harmonic, and the summation range of ∑ is h.

[0018] In conjunction with the first aspect above, in one possible implementation, determining whether to issue an early warning based on the power supply system evaluation coefficient includes: Determine whether the power supply system evaluation coefficient is greater than the preset evaluation coefficient threshold; if yes, generate an early warning message and send it to the client; if not, continue monitoring and judgment.

[0019] It should be noted that the preset evaluation coefficient threshold is set by experts in this field based on experience.

[0020] A second aspect of the present invention provides an intelligent early warning system for an urban rail transit power supply system, comprising: a data acquisition module, a data analysis module, and an early warning module; Data acquisition module: used to obtain harmonic data and environmental data of urban rail transit power supply system; Data analysis module: Calculates harmonic distortion rate impact factor based on distortion rate data; modifies harmonic distortion rate impact factor based on environmental data to obtain initial assessment factor; modifies initial assessment factor based on fundamental wave fluctuation data to obtain target assessment factor; and calculates resonance sensitivity factor based on harmonic power data; calculates power supply system assessment coefficient based on target assessment factor and resonance sensitivity factor; Early warning module: determines whether to issue an early warning based on the power supply system evaluation coefficient.

[0021] In combination with the first aspect above, in a possible implementation, the data analysis module is in communication and / or electrically connected to the data acquisition module and the early warning module respectively.

[0022] Compared with the prior art, the present invention has the following beneficial effects: The present invention breaks through the limitations of single parameter monitoring by comprehensively collecting harmonic data (distortion rate data, power data of each harmonic), environmental data (temperature, humidity) and fundamental wave fluctuation data (fundamental wave current / voltage change value); when constructing the harmonic distortion rate influencing factor, the first correction model is used to introduce environmental data correction to quantify the impact of temperature and humidity on equipment parameters, thereby avoiding evaluation deviations caused by environmental anomalies; the second correction model is used to dynamically compensate for the fundamental wave fluctuation, correct the problem of inaccurate harmonic risk caused by fundamental wave changes, and ensure that the evaluation factor truly reflects the actual risk; at the same time, the resonance sensitivity factor is calculated for each harmonic, and the matching risk of specific harmonics and local impedance is accurately identified, making up for the lack of resonance risk segmentation analysis in the existing technology; the target evaluation factor and the resonance sensitivity factor are integrated through the comprehensive evaluation coefficient, and the dynamic weight is combined to adapt to the changes in system variables to achieve an upgrade from "single threshold judgment" to "multi-dimensional dynamic early warning", significantly improving the accuracy and reliability of the early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 Schematic diagram of the method steps of an embodiment of the present invention; Figure 2 Schematic diagram of system modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] See also Figure 1 The first embodiment of the present invention provides an intelligent early warning method for an urban rail transit power supply system, comprising: Obtain harmonic data and environmental data of the urban rail transit power supply system; harmonic data includes: distortion rate data and harmonic power data; The harmonic distortion rate influencing factor is calculated based on the distortion rate data; Correct the harmonic distortion rate influencing factors based on environmental data and initially evaluate the factors; The initial evaluation factor is modified based on the fundamental wave fluctuation data to obtain the target evaluation factor; The resonance sensitivity factor is calculated based on the harmonic power data; The power supply system evaluation coefficient is calculated based on the target evaluation factor and the resonance sensitivity factor; Determine whether to issue an early warning based on the power supply system evaluation coefficient.

[0027] Obtain harmonic and environmental data for urban rail transit power supply systems, including: The distortion rate data of the urban rail transit power supply system is collected in real time through a harmonic analyzer. The distortion rate data includes the total harmonic distortion rate of current and the total harmonic distortion rate of voltage. The power quality analyzer is used to collect harmonic power data of the urban rail transit power supply system in real time. The harmonic power data includes the current amplitude and voltage amplitude of each harmonic. Environmental data is collected in real time through data sensors; the environmental data includes: ambient temperature and ambient humidity.

[0028] The harmonic distortion rate influencing factors are calculated based on the distortion rate data, including: The total harmonic distortion rate of current is marked as I, and the total harmonic distortion rate of voltage is marked as V; The harmonic distortion rate influence factor is calculated using the formula X=α×e^(I / (I+1))+β×ln(tanh(V)+1). Here, X is the harmonic distortion rate influence factor, and α and β are weight coefficients.

[0029] Correct the harmonic distortion rate influencing factors based on environmental data, including: The ambient temperature and ambient humidity are taken as independent variables and marked as T and H respectively; the initial evaluation factor obtained after correction is taken as the dependent variable and marked as CP; The independent variables and dependent variables are fitted by polynomial fitting to construct the first revised model; Based on the first correction model, the harmonic distortion rate influencing factor is corrected to obtain the initial evaluation factor; The first correction model is specifically: CP=X[1+A1×ln(e^(|T-ZT| / ZT))+A2×ln(e^(|H-ZH| / ZH))]; where A1 and A2 are proportional adjustment coefficients, ZT is the standard temperature, and ZH is the standard humidity.

[0030] The initial assessment factors are modified based on the fundamental fluctuation data, including: The fundamental wave fluctuation data of the rail transit power supply system is collected in real time through the power quality analyzer; wherein the fundamental wave fluctuation data includes: fundamental wave current change value and fundamental wave voltage change value; The fundamental current change value is marked as I, the fundamental voltage change value is marked as V; A second correction model is constructed based on the fundamental wave fluctuation data to correct the initial evaluation factor and obtain the target evaluation factor; The second correction model is specifically: MP=CP[1+B1×ln(e^(| I| / (| I|+1)))+B2×ln(e^(| V| / (| V|+1)))]; where MP is the target evaluation factor, B1 and B2 are proportional adjustment coefficients, and when When I>0, 0<B1<1, 0<B2<1; when When I<0, -1<B1<0, -1<B2<0.

[0031] The resonance sensitivity factor is calculated based on the harmonic power data, including: The current amplitude of each harmonic and the voltage amplitude of each harmonic are marked as Ih and Vh respectively; where h is the harmonic order; The network impedance spectrum of harmonics is obtained in real time based on frequency domain impedance measurement technology; wherein the frequency domain impedance measurement technology includes: small signal injection method or impedance frequency response reconstruction method; Obtain the impedance value corresponding to each harmonic based on the network impedance spectrum, and mark the impedance value corresponding to each harmonic as Zh; The resonance sensitivity value corresponding to each harmonic is calculated using the formula Yh=(Ih×Vh) / |Zh|; where Yh refers to the resonance sensitivity value corresponding to the hth harmonic; The resonance sensitivity factor corresponding to each harmonic is obtained by normalizing the resonance sensitivity value.

[0032] The power supply system evaluation coefficient is calculated based on the target evaluation factor and the resonance sensitivity factor, including: Extract the target evaluation factor MP and the resonance sensitivity factor, and mark the resonance sensitivity factor as Gh; The power supply system evaluation coefficient is calculated using the formula P=L1×MP+L2×∑(wh×Gh); where P is the power supply system evaluation coefficient, L1 and L2 are weight coefficients, wh is the weight coefficient of each harmonic, and the summation range of ∑ is h.

[0033] Determine whether to issue an early warning based on the power supply system evaluation coefficient, including: Determine whether the power supply system evaluation coefficient is greater than the preset evaluation coefficient threshold; if yes, generate an early warning message and send it to the client; if not, continue monitoring and judgment.

[0034] For example, the application process of the present invention is described in detail by taking the intelligent early warning monitoring of a traction substation (rated voltage 35kV, rated current 800A) of a subway line 3 as an example: 1. Data collection; During the morning rush hour on a certain weekday, the monitoring system of the traction substation collected the following data: 1. Harmonic data: Total harmonic distortion of current (I = 4.2%) (mainly generated by the converters of the three trains started simultaneously); Voltage total harmonic distortion (V=3.8%); Harmonic data (focus on monitoring 3rd, 5th, and 7th harmonics): 3rd harmonic: current (I3=52A), voltage (V3=1.2kV), impedance (Z3=25Ω); 5th harmonic: current (I5=38A), voltage (V5=0.9kV), impedance (Z5=30Ω); 7th harmonic: current (I7=22A), voltage (V7=0.6kV), impedance (Z7=40Ω).

[0035] 2. Environmental data: Ambient temperature (T=38°C) (high temperature in summer), standard temperature (ZT=25°C) (optimal temperature for equipment design); Ambient humidity (H=65%), standard humidity (ZH=50%) (optimal humidity for equipment insulation).

[0036] 3. Fundamental wave fluctuation data: Fundamental current change value ( I=+15%) (due to intensive train starts, the fundamental current increases from the rated 800A to 920A); Fundamental voltage change value ( V=+8%).

[0037] 2. Coefficient setting; The weight coefficients and proportional adjustment coefficients are set by those skilled in the art based on historical data and industry experience; 1. Harmonic distortion factor weights: α=0.6, β=0.4; For example, current distortion I directly affects the additional losses of transformers and cables. 60% of historical faults were related to current distortion, so α is slightly larger. Voltage distortion V mainly affects electronic equipment, accounting for 40%, so β ​​= 0.4.

[0038] 2. Proportional adjustment coefficient of environmental correction: A1=0.05, A2=0.03; For example, historical data shows that harmonic distortion caused by abnormal temperature accounts for more than 50% of environmental factors, so temperature has a more significant impact on equipment resistance. For example, for every 10°C increase in temperature, the resistance of the substation transformer increases by an average of 8%, and the harmonic loss increases by 12% (temperature has a more significant impact). For every 10% increase in humidity above the standard value, the insulation leakage current increases by an average of 5%, and the harmonic distortion rate increases by 3%. Therefore, A1>A2.

[0039] 3. Proportional adjustment coefficient of fundamental wave fluctuation correction: B1=0.08, B2=0.05; For example, fundamental current fluctuations have a more direct impact on Ih / I1 (the current ratio is the core of harmonic risk assessment). In historical data, the risk underestimated due to sudden increases in fundamental current accounts for 70%, so B1>B2.

[0040] 4. Comprehensive evaluation weight: L1=0.4, L2=0.6; harmonic weight w3=0.5, w5=0.3, w7=0.2; For example, the resonance risk Yh is more likely to cause equipment breakdown. 80% of emergency failures in historical faults are related to resonance, so L2>L1. The third harmonic is a zero-sequence component and is easily amplified in a neutral-grounded system. It has the highest probability of causing resonance (50%), so w3 is the largest.

[0041] 5. Preset evaluation coefficient threshold: The threshold is set to 0.4 (based on the failure data statistics of this line in the past five years, the failure probability is ≥90% when this value is exceeded).

[0042] 3. Calculation of early warning process; 1. Calculate the harmonic distortion factor (X): The harmonic distortion factor is calculated using the formula X=α×e^(I / (I+1))+β×ln(tanh(V)+1); Substituting the data into the equation, we get: X≈0.6395; 2. Environmental correction: Calculate the initial assessment factor (CP); According to the first revised model: CP=X[1+A1×ln(e^(|T-ZT| / ZT))+A2×ln(e^(|H-ZH| / ZH))]; calculate the initial assessment factor; Substituting the data, we get: CP≈0.662; 3. Fundamental wave fluctuation correction: Calculate the target evaluation factor (MP); According to the second revised model: MP=CP[1+B1×ln(e^(| I| / (| I|+1)))+B2×ln(e^(| V| / (| V|+1)))]; calculate the target evaluation factor; Substituting the data, we obtain: MP≈0.671; 4. Calculate the resonance sensitivity factor of each harmonic; The resonance sensitivity value corresponding to each harmonic is calculated using the formula Yh=(Ih×Vh) / |Zh|; Substituting the data into the equation: 3rd harmonic: Y3=2496; 5th harmonic: Y5=1140; 7th harmonic: Y7=330; Based on the historical monitoring data of the subway line, the normalized range of each parameter is determined: Assume that the historical minimum value of the resonance sensitivity value Yh is Ymin= (risk-free state) and the maximum value Ymax=5000 (severe resonance state); After normalization, we get: The resonance sensitivity factor of the third harmonic G3: G3≈0.489; The resonance sensitivity factor of the 5th harmonic G5: G5≈0.212; The resonance sensitivity factor of the 7th harmonic G7: G7≈0.047; Weighted sum: ∑(wh×Gh)=0.3175; 5. Calculate the power supply system evaluation coefficient (P); The power supply system evaluation coefficient is calculated using the formula P=L1×MP+L2×∑(wh×Gh); Substituting the data into the data, we obtained: P ≈ 0.4589; 6. Early warning judgment; Since P≈0.4589>the preset evaluation coefficient threshold (0.4), the system generates an early warning message and sends it to the operation and maintenance client, prompting "the risk of harmonic resonance is high, and the traction inverter and filter device need to be urgently checked."

[0043] This embodiment embodies the entire process from multi-dimensional data collection to final warning, where the weight coefficient is set based on historical failure statistics and equipment characteristics, ensuring that the assessment results are consistent with the actual risks and effectively avoiding the limitations of single parameter monitoring.

[0044] See Figure 2 , a second aspect of the present invention provides an intelligent early warning system for an urban rail transit power supply system, comprising: a data acquisition module, a data analysis module and an early warning module; Data acquisition module: used to obtain harmonic data and environmental data of urban rail transit power supply system; Data analysis module: Calculates harmonic distortion rate impact factor based on distortion rate data; modifies harmonic distortion rate impact factor based on environmental data to obtain initial assessment factor; modifies initial assessment factor based on fundamental wave fluctuation data to obtain target assessment factor; and calculates resonance sensitivity factor based on harmonic power data; calculates power supply system assessment coefficient based on target assessment factor and resonance sensitivity factor; Early warning module: determines whether to issue an early warning based on the power supply system evaluation coefficient.

[0045] Some of the data in the above formula are calculated by removing the dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0046] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent early warning method for an urban rail transit power supply system, characterized in that: include: Obtain harmonic data and environmental data of the urban rail transit power supply system; harmonic data includes: distortion rate data and harmonic power data; The harmonic distortion rate influencing factor is calculated based on the distortion rate data; Correct the harmonic distortion rate influencing factors based on environmental data and initially evaluate the factors; The initial evaluation factor is modified based on the fundamental wave fluctuation data to obtain the target evaluation factor; The resonance sensitivity factor is calculated based on the harmonic power data; The power supply system evaluation coefficient is calculated based on the target evaluation factor and the resonance sensitivity factor; Determine whether to issue an early warning based on the power supply system evaluation coefficient.

2. The intelligent early warning method for urban rail transit power supply system according to claim 1, characterized in that: The obtaining of harmonic data and environmental data of the urban rail transit power supply system includes: The distortion rate data of the urban rail transit power supply system is collected in real time through a harmonic analyzer. The distortion rate data includes the total harmonic distortion rate of current and the total harmonic distortion rate of voltage. The power quality analyzer is used to collect harmonic power data of the urban rail transit power supply system in real time. The harmonic power data includes the current amplitude and voltage amplitude of each harmonic. Environmental data is collected in real time through data sensors; the environmental data includes: ambient temperature and ambient humidity.

3. The intelligent early warning method for urban rail transit power supply system according to claim 1, characterized in that: The harmonic distortion rate influencing factor calculated based on the distortion rate data includes: The total harmonic distortion rate of current is marked as I, and the total harmonic distortion rate of voltage is marked as V; The harmonic distortion rate influence factor is calculated using the formula X=α×e^(I / (I+1))+β×ln(tanh(V)+1). Here, X is the harmonic distortion rate influence factor, and α and β are weight coefficients.

4. The intelligent early warning method for urban rail transit power supply system according to claim 1, characterized in that: The correction of the harmonic distortion rate influencing factor based on the environmental data includes: The ambient temperature and ambient humidity are taken as independent variables and marked as T and H respectively; the initial evaluation factor obtained after correction is taken as the dependent variable and marked as CP; The independent variables and dependent variables are fitted by polynomial fitting to construct the first revised model; Based on the first correction model, the harmonic distortion rate influencing factor is corrected to obtain the initial evaluation factor; The first correction model is specifically: CP=X[1+A1×ln(e^(|T-ZT| / ZT))+A2×ln(e^(|H-ZH| / ZH))]; where A1 and A2 are proportional adjustment coefficients, ZT is the standard temperature, and ZH is the standard humidity.

5. The intelligent early warning method for urban rail transit power supply system according to claim 1, characterized in that: The correction of the initial assessment factor based on the fundamental wave fluctuation data includes: The fundamental wave fluctuation data of the rail transit power supply system is collected in real time through the power quality analyzer; wherein the fundamental wave fluctuation data includes: fundamental wave current change value and fundamental wave voltage change value; The fundamental current change value is marked as I, the fundamental voltage change value is marked as V; Based on the fundamental wave fluctuation data, a second correction model is constructed to correct the initial evaluation factor to obtain the target evaluation factor; The second correction model is specifically: MP=CP[1+B1×ln(e^(| I| / (| I|+1)))+B2×ln(e^(| V| / (| V|+1)))]; where MP is the target evaluation factor, B1 and B2 are proportional adjustment coefficients, and when When I>0, 0<B1<1, 0<B2<1; when When I<0, -1<B1<0, -1<B2<0.

6. The intelligent early warning method for urban rail transit power supply system according to claim 1, characterized in that: The calculation of the resonance sensitivity factor based on the harmonic power data includes: The current amplitude of each harmonic and the voltage amplitude of each harmonic are marked as Ih and Vh respectively; where h is the harmonic order; The network impedance spectrum of harmonics is obtained in real time based on frequency domain impedance measurement technology; wherein the frequency domain impedance measurement technology includes: small signal injection method or impedance frequency response reconstruction method; Obtain the impedance value corresponding to each harmonic based on the network impedance spectrum, and mark the impedance value corresponding to each harmonic as Zh; The resonance sensitivity value corresponding to each harmonic is calculated using the formula Yh=(Ih×Vh) / |Zh|; where Yh refers to the resonance sensitivity value corresponding to the hth harmonic; The resonance sensitivity factor corresponding to each harmonic is obtained by normalizing the resonance sensitivity value.

7. The intelligent early warning method for urban rail transit power supply system according to claim 1, characterized in that: The power supply system evaluation coefficient is calculated based on the target evaluation factor and the resonance sensitivity factor, including: Extract the target evaluation factor MP and the resonance sensitivity factor, and mark the resonance sensitivity factor as Gh; The power supply system evaluation coefficient is calculated using the formula P=L1×MP+L2×∑(wh×Gh); where P is the power supply system evaluation coefficient, L1 and L2 are weight coefficients, wh is the weight coefficient of each harmonic, and the summation range of ∑ is h.

8. The intelligent early warning method for urban rail transit power supply system according to claim 1, characterized in that: The determining whether to issue an early warning based on the power supply system evaluation coefficient includes: Determine whether the power supply system evaluation coefficient is greater than the preset evaluation coefficient threshold; if yes, generate an early warning message and send it to the client; if not, continue monitoring and judgment.

9. An intelligent early warning system for an urban rail transit power supply system, executing the intelligent early warning method for an urban rail transit power supply system according to any one of claims 1 to 8, characterized in that: include: Data collection module, data analysis module and early warning module; Data acquisition module: used to obtain harmonic data and environmental data of urban rail transit power supply system; Data analysis module: calculates harmonic distortion rate influencing factors based on distortion rate data; Correct the harmonic distortion rate influencing factors based on environmental data and initially evaluate the factors; The initial evaluation factor is modified based on the fundamental wave fluctuation data to obtain the target evaluation factor; and, calculating a resonance sensitivity factor based on the harmonic power data; The power supply system evaluation coefficient is calculated based on the target evaluation factor and the resonance sensitivity factor; Early warning module: determines whether to issue an early warning based on the power supply system evaluation coefficient.

10. The intelligent early warning system for urban rail transit power supply system according to claim 9, characterized in that: The data analysis module is communicated and / or electrically connected to the data acquisition module and the early warning module respectively.

Images