An intelligent integrated uninterruptible AC / DC power supply system for rail transit

Abstract

The present invention relates to the technical field of power supply for rail transit, and discloses an intelligent integrated uninterruptible AC / DC power supply system for rail transit, specifically comprising: an AC power distribution module, a DC charging module, an AC inverter power supply module, a communication power supply module, a battery pack module, and an integrated monitoring module; wherein, the present invention monitors the voltage in the power supply circuit in real time to determine the voltage status, wherein the voltage status includes normal voltage and abnormal voltage. When the voltage is determined to be abnormal, the abnormal voltage is further analyzed to calculate a voltage fault judgment value, and the degree of the voltage fault is judged based on the voltage fault judgment value, so that the voltage abnormality can be understood in a timely manner, and the degree of the fault can be judged by in-depth analysis and judgment, and a fault warning signal or a fault processing signal can be generated, so that the power supply system fault can be targeted and processed to ensure the normal operation of the rail transit system.

Description

Technical Field

[0001] The present invention relates to the technical field of power supplies for rail transit, and in particular to an intelligent integrated uninterruptible AC / DC power supply system for rail transit. Background Art

[0002] An integrated uninterruptible AC / DC power supply is a power supply system that integrates multiple functions, including a DC power supply, an AC uninterruptible power supply (UPS), an inverter power supply, and a DC conversion power supply. By sharing a unified battery pack and achieving unified monitoring and management, the system provides stable and reliable power support for various devices and systems.

[0003] However, the current fault monitoring methods of some existing power supply systems are relatively simple and cannot conduct in-depth analysis of the fault causes. When a fault occurs, the cause cannot be quickly narrowed down, and the troubleshooting time may be long, which has a great impact on the operational stability of rail transit.

[0004] In view of this, we proposed an intelligent integrated uninterruptible AC / DC power supply system for rail transit. Summary of the Invention

[0005] The object of the present invention is to provide an intelligent integrated uninterruptible AC / DC power supply system for rail transit to solve the problems in the above background.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An intelligent integrated uninterruptible AC / DC power supply system for rail transit, specifically comprising: an AC power distribution module, a DC charging module, an AC inverter power supply module, a communication power supply module, a battery pack module and an integrated monitoring module; wherein the integrated monitoring module comprises a voltage monitoring module, a fault judgment module, a power switching module and a fault analysis module; the voltage monitoring module: monitors the voltage of the power supply circuit in real time, obtains voltage data, processes the data, and evaluates the voltage status, wherein the voltage status includes generating a voltage abnormality signal; the fault judgment module: processes the abnormal voltage data based on the generated voltage abnormality signal, calculates a voltage fault judgment value, and evaluates the fault degree of the abnormal voltage; wherein the fault degree of the abnormal voltage includes generating a fault warning signal or generating a fault processing signal; the power switching module: switches to using a battery pack module for power supply based on the generated fault processing signal; the fault analysis module: obtains fault status data when the fault processing signal is generated, and calculates, based on historical data, a similarity evaluation value with the fault status data when the fault processing signal is generated in the historical data, locates the cause of the fault based on the similarity evaluation value, and obtains the target fault type.

[0008] As a further solution of the present invention: the process of generating the voltage abnormality signal is:

[0009] Obtain real-time voltage data in the circuit, establish a two-dimensional model with time as the X-axis and voltage as the Y-axis, substitute the real-time voltage into the two-dimensional model, and draw a real-time voltage curve graph;

[0010] Taking the maximum and minimum values ​​of the voltage threshold range as standard values, draw two reference lines parallel to the X-axis, namely the upper reference line and the lower reference line;

[0011] Mark the upper side of the upper baseline and the lower side of the lower baseline as abnormal areas;

[0012] When the real-time voltage is in an abnormal area, a voltage abnormality signal is generated.

[0013] As a further solution of the present invention: the process of generating a fault warning signal or generating a fault processing signal is:

[0014] Obtaining a voltage fault judgment value, and comparing the voltage fault judgment value with a voltage fault judgment threshold;

[0015] If the voltage fault judgment value is less than the voltage fault judgment threshold, a fault warning signal is generated;

[0016] If the voltage fault judgment value is greater than or equal to the voltage fault judgment threshold, a fault processing signal is generated.

[0017] As a further solution of the present invention: the process of obtaining the voltage fault judgment value is as follows:

[0018] Based on the voltage anomaly signal generated above, the duration of the abnormal area is obtained, and the ratio of the duration of the abnormal area to the maximum duration of the abnormality is calculated to obtain the abnormal duration deviation ratio;

[0019] Obtain the voltage extreme value in the abnormal area, calculate the difference between the voltage extreme value and the voltage standard value, calculate the ratio of the absolute value of the difference to the voltage standard value, and obtain the abnormal deviation degree ratio;

[0020] The voltage fault judgment value is obtained by multiplying the abnormal duration deviation ratio and the abnormal deviation degree ratio.

[0021] As a further solution of the present invention: the process of obtaining the similarity evaluation value is as follows:

[0022] Obtain real-time fault status values ​​and historical fault status values;

[0023] Mark the historical fault status value as the reference fault status value, and mark the real-time fault status value as the comparison fault status value;

[0024] The difference between the comparison fault state value and the reference fault state value is calculated to obtain the absolute value of the difference, and the ratio of the absolute value of the difference to the comparison fault state value is calculated to obtain the similarity evaluation value.

[0025] As a further solution of the present invention: the process of obtaining the real-time fault status value and the historical fault status value is as follows:

[0026] Acquiring fault status data, wherein the fault status data includes a voltage fault judgment value, an abnormal voltage mean deviation ratio, and an abnormal voltage standard deviation;

[0027] Substitute into the formula GZ = a1*PD + a2*PC + a3*BZ to calculate the real-time fault status value GZ, where PD represents the voltage fault judgment value, PC represents the abnormal voltage mean deviation ratio, BZ represents the abnormal voltage standard deviation, and a1, a2, and a3 are preset proportional coefficients;

[0028] Extracting several groups of fault records when the fault processing signal is generated in the historical data, wherein the fault records include the fault status data corresponding to the fault processing signal generated in the historical data, and are marked as historical fault status data;

[0029] The historical fault status value is calculated by extracting the historical fault status data.

[0030] As a further solution of the present invention: the process of acquiring the fault status data is as follows:

[0031] Fault status data includes voltage fault judgment value, abnormal voltage mean deviation ratio and abnormal voltage standard deviation;

[0032] Obtaining a voltage fault judgment value corresponding to when a fault processing signal is generated;

[0033] Obtaining the time point when the abnormal area starts and the time point when the fault processing signal is generated, marking the time point when the abnormal area starts as the starting time point of the analysis period, and marking the time point when the fault processing signal is generated as the end time point of the analysis period;

[0034] The voltage data of the analysis period are summed and averaged to obtain the voltage mean value of the analysis period, the voltage mean value is calculated to be different from the voltage standard value to obtain the absolute value of the difference, the absolute value of the difference is processed with the voltage standard value to obtain the abnormal voltage mean deviation ratio;

[0035] Substitute the voltage data of the analysis period into the standard deviation formula to obtain the abnormal voltage standard deviation.

[0036] As a further solution of the present invention: the target fault type acquisition process is:

[0037] Obtain the maximum value ratio of individual values, and compare the maximum value ratio of individual values ​​with the number ratio threshold;

[0038] If the maximum value ratio of individual values ​​is greater than or equal to the number ratio threshold, it is marked as the target fault type;

[0039] If the maximum value ratio of individual values ​​is less than the number ratio threshold, further analysis is required.

[0040] As a further solution of the present invention: the process of obtaining the maximum value ratio of individual values ​​is as follows:

[0041] Extract the minimum value in the similarity evaluation value data, mark the corresponding reference fault state value as a similar value, obtain the fault cause corresponding to the similar value and the number of similar values;

[0042] Similar values ​​with the same fault cause are grouped into the same cause type, the number of values ​​for each same cause type is obtained, and the maximum value and the corresponding fault type are extracted;

[0043] Calculate the ratio of the maximum individual value to the number of similar values ​​to obtain the proportion of the maximum individual value.

[0044] As a further solution of the present invention: the process of further analysis includes:

[0045] The fault causes corresponding to similar values ​​in the historical data are classified into the same type of faults, the fault status values ​​of the same type of faults are obtained, and all the fault status values ​​of the same type of faults are marked as the same group of calculation data to obtain multiple groups of calculation data;

[0046] The fault state values ​​in the same group of calculated data are summed and averaged to obtain the fault state mean; the fault state mean corresponding to each group of calculated data is respectively subtracted from the comparison fault state mean to obtain the fault state deviation value;

[0047] The minimum value of the fault state deviation values ​​is extracted to obtain the fault type corresponding to the minimum value of the fault state deviation values, and the fault type is the target fault type.

[0048] Beneficial effects of the present invention:

[0049] (1) The present invention monitors the voltage in the power supply circuit in real time to determine the voltage status, wherein the voltage status includes normal voltage and abnormal voltage. When the voltage is determined to be abnormal, the abnormal voltage is further analyzed to calculate the voltage fault judgment value. The degree of the voltage fault is judged based on the voltage fault judgment value, thereby timely understanding the voltage abnormality and generating a fault warning signal or a fault processing signal by in-depth analysis and judgment of the degree of the fault. The power supply system fault can then be targeted to ensure the normal operation of the rail transit system.

[0050] (2) The present invention obtains the fault status data corresponding to when the fault processing signal is generated, and simultaneously obtains the historical fault status data corresponding to when the fault processing signal is generated in the historical data, calculates the fault status value based on the obtained data, and calculates the similarity evaluation value based on the calculated real-time fault status value and the historical fault status value, extracts the minimum value in the similarity evaluation value, obtains the corresponding fault cause and individual value, extracts the individual value maximum value and the corresponding fault type, calculates the individual value maximum value ratio, and compares it with the individual value ratio threshold value. If the individual value maximum value ratio is greater than or equal to the individual value ratio threshold value, it is marked as the target fault type. If the individual value maximum value ratio is less than the individual value ratio threshold value, further analysis is required based on the historical data. Therefore, according to the above analysis, when generating the fault processing signal, the scope of the fault cause can be quickly narrowed down, the time for judging the fault cause can be reduced, and the fault processing can be carried out more quickly, thereby increasing the stability and continuity of rail transit operation and reducing the impact caused by the long fault investigation time.

[0051] (3) The present invention realizes the intelligent integration of the rail transit power supply system by highly integrating multiple key components such as the AC distribution unit, DC charging module, AC inverter power module, communication power module, battery pack module and integrated monitoring module into one system. At the same time, the battery pack module equipped in the system serves as a backup power supply. When the external power supply fails or is interrupted, the battery pack can quickly take over the power supply task and provide continuous and stable power support for the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The present invention will be further described below with reference to the accompanying drawings.

[0053] Figure 1 This is a schematic diagram of an integrated monitoring module in an intelligent integrated uninterruptible AC / DC power supply system for rail transit according to the present invention;

[0054] Figure 2 This is a flow chart of a fault judgment module in an intelligent integrated uninterruptible AC / DC power supply system for rail transit in the present invention. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0056] Example 1

[0057] See also Figure 1 - Figure 2 As shown, the present invention is an intelligent integrated uninterruptible AC / DC power supply system for rail transit, which specifically includes: an AC power distribution module, a DC charging module, an AC inverter power supply module, a communication power supply module, a battery pack module and an integrated monitoring module;

[0058] For example, the AC power distribution module is responsible for distributing the external AC power input to provide a stable and reliable AC power supply to each module in the system;

[0059] DC charging module: converts AC power into DC power for charging the battery pack and may also directly power some DC loads;

[0060] AC inverter power module: converts DC power into AC power to support devices that require AC power;

[0061] Communication power module: provides stable and reliable power supply for the communication system to ensure the normal operation of communication equipment;

[0062] Battery module: As a backup power source, it provides power support for the entire system when the external power supply fails or is interrupted, ensuring uninterrupted operation of the system;

[0063] Integrated monitoring module: performs real-time monitoring, fault diagnosis and analysis, and power switching management to ensure efficient and stable operation of the system;

[0064] The core technology of this embodiment is: the present invention realizes the intelligent integration of the rail transit power supply system by highly integrating multiple key components such as the AC distribution unit, DC charging module, AC inverter power module, communication power module, battery pack module and integrated monitoring module into one system. At the same time, the battery pack module equipped in the system serves as a backup power supply. When the external power supply fails or is interrupted, the battery pack can quickly take over the power supply task and provide continuous and stable power support for the entire system.

[0065] Example 2

[0066] Based on the above embodiments, the present invention is an intelligent integrated uninterruptible AC / DC power supply system for rail transit, wherein the integrated monitoring module includes:

[0067] Voltage monitoring module: monitors the voltage of the power supply circuit in real time, obtains voltage data, processes it, and evaluates the voltage status;

[0068] In some embodiments, real-time voltage data in the circuit is acquired, a two-dimensional model is established with time as the X-axis and voltage as the Y-axis, and the real-time voltage is substituted into the two-dimensional model to draw a real-time voltage curve graph;

[0069] Taking the maximum and minimum values ​​of the voltage threshold range as standard values, draw two reference lines parallel to the X-axis, namely the upper reference line and the lower reference line;

[0070] Mark the upper part of the upper baseline and the lower part of the lower baseline as abnormal areas, and mark the lower part of the upper baseline and the upper part of the baseline as normal areas;

[0071] The maximum and minimum values ​​of the voltage threshold range are set by those skilled in the art based on experience;

[0072] When the real-time voltage is in the abnormal area, it means that the current voltage is in an abnormal state and a voltage abnormality signal is generated;

[0073] When the real-time voltage is in the normal range, it means that the current voltage is in a normal state and a voltage normal signal is generated;

[0074] Fault judgment module: Based on the generated voltage abnormality signal, it processes the abnormal voltage data, calculates the voltage fault judgment value, and evaluates the fault degree of the abnormal voltage;

[0075] In some embodiments, based on the voltage anomaly signal generated above, the duration of the abnormal region is obtained, and the ratio of the duration of the abnormal region to the maximum duration of the abnormality is calculated to obtain an abnormal duration deviation ratio;

[0076] The maximum duration of abnormality is set by those skilled in the art based on the summary of multiple historical experimental data;

[0077] Obtain the voltage extreme value in the abnormal area, calculate the difference between the voltage extreme value and the voltage standard value, calculate the ratio of the absolute value of the difference to the voltage standard value, and obtain the abnormal deviation degree ratio;

[0078] It should be explained that if the abnormal area is above the upper baseline, the voltage extreme value of the abnormal area is obtained as the maximum voltage, the maximum voltage is calculated as the difference between the maximum voltage and the standard voltage, and the absolute value of the difference is calculated as the ratio of the difference to the standard voltage to obtain the abnormal deviation degree ratio;

[0079] If the abnormal area is below the lower reference, the voltage extreme value of the abnormal area is obtained as the minimum voltage value, the difference between the minimum voltage value and the standard voltage value is calculated, and the absolute value of the difference is calculated by ratio with the standard voltage value to obtain the abnormal deviation degree ratio;

[0080] The voltage standard value is the average of the maximum and minimum values ​​of the voltage threshold range;

[0081] The voltage fault judgment value is obtained by multiplying the abnormal duration deviation ratio and the abnormal deviation degree ratio;

[0082] It should be explained that the voltage fault judgment value is calculated by the abnormal duration deviation ratio and the abnormal deviation degree ratio. That is, when the abnormal duration deviation ratio is larger, the abnormal duration is longer and the voltage is more abnormal. When the abnormal deviation degree ratio is larger, the deviation degree between the abnormal voltage extreme value and the voltage standard value is greater and the voltage is more abnormal.

[0083] Obtain a voltage fault judgment value, and compare the voltage fault judgment value with a voltage fault judgment threshold, wherein the voltage fault judgment threshold is a critical value used to judge the fault degree of abnormal voltage and is set by those skilled in the art based on historical experimental data;

[0084] If the voltage fault judgment value is less than the voltage fault judgment threshold, it means that the duration of generating the voltage abnormality signal and the degree of voltage extreme value deviation are small, the fault severity is low, and a fault warning signal is generated;

[0085] If the voltage fault judgment value is greater than or equal to the voltage fault judgment threshold, it means that the duration of generating the voltage abnormality signal and the degree of deviation of the voltage extreme value are large, the fault severity is high, and a fault processing signal is generated;

[0086] The core technologies of the voltage monitoring module and fault diagnosis module are as follows: first, by real-time monitoring of the voltage in the power supply circuit, the voltage status is determined, where the voltage status includes normal voltage and abnormal voltage. When the voltage is determined to be abnormal, the abnormal voltage is further analyzed to calculate the voltage fault judgment value. Based on the voltage fault judgment value, the degree of the voltage fault is judged. This allows timely understanding of the voltage anomaly. Through in-depth analysis and judgment of the degree of the fault, a fault warning signal or fault processing signal is generated, and then the power system fault can be targeted and processed to ensure the normal operation of the rail transit system.

[0087] Power switching module: performs power switching based on the generated fault processing signal;

[0088] In some embodiments, when a high fault level signal is generated, the battery pack module is switched to be used for power supply, thereby ensuring the continuity of power supply;

[0089] Example 3

[0090] Based on the above embodiments, the present invention is an intelligent integrated uninterruptible AC / DC power supply system for rail transit, wherein the integrated monitoring module further comprises:

[0091] Fault analysis module: obtains the fault status data when the fault processing signal is generated, and calculates the similarity evaluation value of the fault status data when the fault processing signal is generated in the historical data based on the historical data. Based on the similarity evaluation value, the cause of the fault is located and the target fault type is obtained;

[0092] Among them, the fault status data includes voltage fault judgment value, abnormal voltage mean deviation ratio and abnormal voltage standard deviation;

[0093] In some embodiments, obtaining a voltage fault judgment value corresponding to when a fault processing signal is generated;

[0094] Obtaining the time point when the abnormal area starts and the time point when the fault processing signal is generated, marking the time point when the abnormal area starts as the starting time point of the analysis period, and marking the time point when the fault processing signal is generated as the end time point of the analysis period;

[0095] The voltage data of the analysis period are summed and averaged to obtain the voltage mean value of the analysis period, the voltage mean value is calculated to be different from the voltage standard value to obtain the absolute value of the difference, the absolute value of the difference is processed with the voltage standard value to obtain the abnormal voltage mean deviation ratio;

[0096] Substitute the voltage data of the analysis period into the standard deviation formula to obtain the abnormal voltage standard deviation;

[0097] Substitute into the formula GZ = a1*PD + a2*PC + a3*BZ to calculate the real-time fault status value GZ, where PD represents the voltage fault judgment value, PC represents the abnormal voltage mean deviation ratio, BZ represents the abnormal voltage standard deviation, and a1, a2, and a3 are preset proportional coefficients;

[0098] Extracting several groups of fault records when the fault processing signal is generated in the historical data, wherein the fault records include the fault status data corresponding to the fault processing signal generated in the historical data, and are marked as historical fault status data;

[0099] Calculate historical fault status values ​​through the extracted historical fault status data;

[0100] Mark the historical fault status value as the reference fault status value, and mark the real-time fault status value as the comparison fault status value;

[0101] Calculate the difference between the comparison fault state value and the reference fault state value to obtain the absolute value of the difference, and calculate the ratio of the absolute value of the difference to the comparison fault state value to obtain a similarity evaluation value;

[0102] It should be explained that the similarity evaluation value is calculated by the difference between the compared fault state value and the reference fault state value, that is, the smaller the absolute value of the difference, the higher the similarity between the compared fault state value and the reference fault state value;

[0103] Extract the minimum value in the similarity evaluation value data, mark the corresponding reference fault state value as a similar value, obtain the fault cause corresponding to the similar value and the number of similar values;

[0104] Similar values ​​with the same fault cause are grouped into the same cause type, the number of values ​​for each same cause type is obtained, and the maximum value and the corresponding fault type are extracted;

[0105] Calculate the ratio of the maximum individual value to the individual value of similar values ​​to obtain the ratio of the maximum individual value;

[0106] Compare the maximum value of the number of proportions with the number of proportions threshold, where the proportion threshold is obtained by those skilled in the art based on historical experimental data;

[0107] If the maximum value ratio of individual values ​​is greater than or equal to the number ratio threshold, it means that the fault type has a higher relative frequency among all the fault types corresponding to similar values, and is marked as the target fault type;

[0108] If the proportion of the maximum individual value is less than the threshold value of the number proportion, it means that the relative frequency of this fault type is not high among all the fault types corresponding to similar values, that is, it may not be the main cause of the fault and further analysis is required;

[0109] The fault causes corresponding to similar values ​​in the historical data are classified into the same type of faults, the fault status values ​​of the same type of faults are obtained, and all the fault status values ​​of the same type of faults are marked as the same group of calculation data to obtain multiple groups of calculation data;

[0110] The fault state values ​​in the same group of calculated data are summed and averaged to obtain the fault state mean;

[0111] The difference between the fault state mean value corresponding to each set of calculated data and the comparison fault state mean value is calculated to obtain the fault state deviation value;

[0112] Extract the minimum value of the fault state deviation value, and obtain the fault type corresponding to the minimum value of the fault state deviation value, and then the fault type is the target fault type;

[0113] The core technology of the fault analysis module is: this module mainly analyzes the fault type, first obtains the fault status data corresponding to the generation of the fault processing signal, and at the same time obtains the historical fault status data corresponding to the generation of the fault processing signal in the historical data, calculates the fault status value based on the obtained data, and calculates the similarity evaluation value based on the calculated real-time fault status value and the historical fault status value, extracts the minimum value in the similarity evaluation value, obtains the corresponding fault cause and individual value, extracts the individual value maximum and the corresponding fault type, calculates the individual value maximum ratio, and compares it with the individual value ratio threshold. If the individual value maximum ratio is greater than or equal to the number ratio threshold, it is marked as the target fault type. If the individual value maximum ratio is less than the number ratio threshold, further analysis is required based on the historical data to obtain the target fault type, so that according to the above analysis, when generating the fault processing signal, the scope of the fault cause can be quickly narrowed down, the time for judging the fault cause can be reduced, and the fault processing can be carried out faster, thereby increasing the stability and continuity of rail transit operation and reducing the impact caused by the long fault troubleshooting time.

[0114] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent integrated uninterruptible AC / DC power supply system for rail transit, characterized in that: Specifically include: AC power distribution module, DC charging module, AC inverter power module, communication power module, battery pack module and integrated monitoring module; Among them, the integrated monitoring module includes a voltage monitoring module, a fault judgment module, a power switching module and a fault analysis module; Voltage monitoring module: monitors the voltage of the power supply circuit in real time, obtains voltage data, processes it, and evaluates the voltage status, including generating a voltage anomaly signal; Fault judgment module: Based on the generated voltage abnormality signal, it processes the abnormal voltage data, calculates the voltage fault judgment value, and evaluates the fault degree of the abnormal voltage; The fault degree of the abnormal voltage includes generating a fault warning signal or generating a fault processing signal; Power switching module: based on the generated fault processing signal, switches to the battery pack module for power supply; Fault analysis module: obtains the fault status data when the fault processing signal is generated, and calculates the similarity evaluation value of the fault status data when the fault processing signal is generated in the historical data based on the historical data. Based on the similarity evaluation value, the cause of the fault is located and the target fault type is obtained; The process of obtaining similar evaluation values ​​is as follows: Acquiring fault status data, wherein the fault status data includes a voltage fault judgment value, an abnormal voltage mean deviation ratio, and an abnormal voltage standard deviation; Substitute into the formula , calculate the real-time fault status value GZ, where PD represents the voltage fault judgment value, PC represents the abnormal voltage mean deviation ratio, BZ represents the abnormal voltage standard deviation, and a1, a2, and a3 are preset proportional coefficients; Extracting several groups of fault records when the fault processing signal is generated in the historical data, wherein the fault records include the fault status data corresponding to the fault processing signal generated in the historical data, and are marked as historical fault status data; Calculate historical fault status values ​​through the extracted historical fault status data; Mark the historical fault status value as the reference fault status value, and mark the real-time fault status value as the comparison fault status value; The difference between the comparison fault state value and the reference fault state value is calculated to obtain the absolute value of the difference, and the ratio of the absolute value of the difference to the comparison fault state value is calculated to obtain the similarity evaluation value.

2. The intelligent integrated uninterruptible AC / DC power supply system for rail transit according to claim 1, characterized in that: The process of generating voltage anomaly signal is as follows: Obtain real-time voltage data in the circuit, establish a two-dimensional model with time as the X-axis and voltage as the Y-axis, substitute the real-time voltage into the two-dimensional model, and draw a real-time voltage curve graph; Taking the maximum and minimum values ​​of the voltage threshold range as standard values, draw two reference lines parallel to the X-axis, namely the upper reference line and the lower reference line; Mark the upper side of the upper baseline and the lower side of the lower baseline as abnormal areas; When the real-time voltage is in an abnormal area, a voltage abnormality signal is generated.

3. The intelligent integrated uninterruptible AC / DC power supply system for rail transit according to claim 1, characterized in that: The process of generating a fault warning signal or generating a fault processing signal is as follows: Obtaining a voltage fault judgment value, and comparing the voltage fault judgment value with a voltage fault judgment threshold; If the voltage fault judgment value is less than the voltage fault judgment threshold, a fault warning signal is generated; If the voltage fault judgment value is greater than or equal to the voltage fault judgment threshold, a fault processing signal is generated.

4. The intelligent integrated uninterruptible AC / DC power supply system for rail transit according to claim 3, characterized in that: The process of obtaining the voltage fault judgment value is as follows: Based on the voltage anomaly signal generated above, the duration of the abnormal area is obtained, and the ratio of the duration of the abnormal area to the maximum duration of the abnormality is calculated to obtain the abnormal duration deviation ratio; Obtain the voltage extreme value in the abnormal area, calculate the difference between the voltage extreme value and the voltage standard value, calculate the ratio of the absolute value of the difference to the voltage standard value, and obtain the abnormal deviation degree ratio; The voltage fault judgment value is obtained by multiplying the abnormal duration deviation ratio and the abnormal deviation degree ratio.

5. The intelligent integrated uninterruptible AC / DC power supply system for rail transit according to claim 1, characterized in that: The process of acquiring fault status data is as follows: Fault status data includes voltage fault judgment value, abnormal voltage mean deviation ratio and abnormal voltage standard deviation; Obtaining a voltage fault judgment value corresponding to when a fault processing signal is generated; Obtaining the time point when the abnormal area starts and the time point when the fault processing signal is generated, marking the time point when the abnormal area starts as the starting time point of the analysis period, and marking the time point when the fault processing signal is generated as the end time point of the analysis period; The voltage data of the analysis period are summed and averaged to obtain the voltage mean value of the analysis period, the voltage mean value is calculated to be different from the voltage standard value to obtain the absolute value of the difference, the absolute value of the difference is processed with the voltage standard value to obtain the abnormal voltage mean deviation ratio; Substitute the voltage data of the analysis period into the standard deviation formula to obtain the abnormal voltage standard deviation.

6. The intelligent integrated uninterruptible AC / DC power supply system for rail transit according to claim 1, characterized in that: The process of obtaining the target fault type is as follows: Obtain the maximum value ratio of individual values, and compare the maximum value ratio of individual values ​​with the number ratio threshold; If the maximum value ratio of individual values ​​is greater than or equal to the number ratio threshold, it is marked as the target fault type; If the maximum value ratio of individual values ​​is less than the number ratio threshold, further analysis is required.

7. The intelligent integrated uninterruptible AC / DC power supply system for rail transit according to claim 6, characterized in that: The process of obtaining the maximum value ratio of each value is as follows: Extract the minimum value in the similarity evaluation value data, mark the corresponding reference fault state value as a similar value, obtain the fault cause corresponding to the similar value and the number of similar values; Group similar values ​​with the same fault cause into the same cause type, obtain the number of values ​​for each same cause type, and extract the maximum value and the corresponding fault type; Calculate the ratio of the maximum individual value to the number of similar values ​​to obtain the proportion of the maximum individual value.

8. The intelligent integrated uninterruptible AC / DC power supply system for rail transit according to claim 6, characterized in that: The further analysis process includes: The fault causes corresponding to similar values ​​in the historical data are summarized as the same type of faults, the fault status values ​​of the same type of faults are obtained, and all the fault status values ​​of the same type of faults are marked as the same group of calculation data to obtain multiple groups of calculation data; The fault state values ​​in the same group of calculated data are summed and averaged to obtain the fault state mean; The fault state mean corresponding to each set of calculated data is calculated separately from the comparison fault state mean to obtain the fault state deviation value; The minimum value of the fault state deviation values ​​is extracted to obtain the fault type corresponding to the minimum value of the fault state deviation values, and the fault type is the target fault type.

Images