Intelligent operation and maintenance method and system for 24-pulse rectifier of subway power supply system

Abstract

The present invention relates to a method and system for intelligent operation and maintenance of 24-pulse rectifiers in a subway power supply system. In step S1, the real-time junction temperature data of all semiconductor devices in all 24-pulse rectifiers of the entire subway line are collected online; in step S2, the real-time data obtained by S1 is classified according to the mean, variance, and median to obtain a classification result B; in step S3, according to the classification result B, a maintenance conclusion of the 24-pulse rectifier is formed and an operation prompt is given; according to the life cycle regression network C, the entire rectifier cabinet is prompted to be scrapped; thereby forming intelligent operation and maintenance of the power supply rectifier cabinet throughout its life cycle, and then the process is continuously executed in a loop starting from step S1. The method and system provide support for the intelligent operation and maintenance of the rectifier, and provide support for big data analysis and processing of the rectifier and the device throughout its life cycle based on the real-time status data of the rectifier.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent operation and maintenance, and relates to an intelligent operation and maintenance method and system for a 24-pulse rectifier of a subway power supply system. Background Art

[0002] Subway travel has become an important means to ease public transportation in large cities, and the subway power supply system is a key system in the subway field. In 2020, a total of 30 subway rail transit lines in 22 cities across the country were put up for tender, with a service line mileage of 891.48 kilometers; according to preliminary forecasts from the Urban Rail Transit Network, in 2021, 38 subway rail transit lines in 20 cities in China were put up for tender, with a service line mileage of 1,066.85 kilometers.

[0003] After years of high-speed construction, the scale and volume of subway operating lines and subway power supply equipment are huge, the service life increases, and the failure rate increases accordingly, which can easily cause safety hazards such as vehicle suspension in tunnels and excessive passenger flow in stations. In this case, it has become an urgent problem to establish a large-scale networked power supply intelligent operation and maintenance system that integrates four core functions, including real-time perception and early warning of the status of key equipment in the power supply system, full life management, intelligent business process drive, and expert system diagnosis and analysis, to ensure the safety, reliability and economy of the power supply system operation.

[0004] The intelligent semiconductor diode in this patent application is described in detail in the prior application with application number 202110221049X and patent name "An intelligent semiconductor device for a subway power supply 24-pulse rectifier cabinet". An intelligent semiconductor device for a subway power supply 24-pulse rectifier cabinet includes a tube shell seat and a tube shell cover. A tube core and a silver sheet are arranged on the tube shell seat in sequence, and positioning rings are arranged at both ends of the tube core. The tube shell cover is located on the tube shell seat, and the two are sealed and connected to form a closed cavity, and the closed cavity is filled with inert protective gas; an installation hole is opened on the tube shell cover, and a temperature sensor is embedded in the installation hole to realize state recognition and digitization of the semiconductor diode device during operation, forming an intelligent semiconductor device.

[0005] Traditional subway power supply 24-pulse rectifiers have the ability to protect against abnormal conditions such as overcurrent and overvoltage, but do not have the real-time status perception function during operation, and cannot accurately detect the rectifier process status and manage the entire life cycle. Routine manual inspections cannot accurately identify and judge, which poses a hidden danger to the safe operation of the subway power supply system. Summary of the invention

[0006] The purpose of the present invention is to overcome the above-mentioned shortcomings of the prior art and to provide an intelligent operation and maintenance method for a rectifier cabinet throughout its life cycle.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] An intelligent operation and maintenance method for a 24-pulse rectifier of a subway power supply system, characterized in that it comprises the following steps:

[0009] Step S1, collect the real-time junction temperature data of all semiconductor devices in all 24-pulse rectifiers of the entire subway line online to obtain a real-time data set (i=0, 1, 2, ..., n, i is the equipment number, j=0, 1, 2, ..., n, j is the number of collections, once per minute), and each set of collected data is stored in the historical database for management to form data for the entire life cycle;

[0010] Step S2, based on the real-time data obtained in S1 The mean, variance and median of are used for classification to obtain the classification result B;

[0011] And real-time data Use the support vector regression SVR algorithm for training to generate a diode life cycle regression network, and obtain a life cycle regression network C; perform sudden fault warning on the data collected at the current moment according to the classification result B, and predict the service life of the device according to the life cycle regression network C;

[0012] Step S3, based on the classification result B, a maintenance conclusion of the 24-pulse rectifier is formed and an operation prompt is given; based on the life cycle regression network C, the entire rectifier cabinet is prompted to be scrapped; thereby forming intelligent operation and maintenance of the power supply rectifier cabinet throughout its life cycle, and then the process is continuously executed in a loop starting from step S1.

[0013] Furthermore, in step S1, the junction temperature data of all semiconductor devices in the 24-pulse rectifier are collected online in real time through the intelligent semiconductor diode.

[0014] Furthermore, the real-time device temperature data in step S1 includes:

[0015] Temperature value of a single diode on a 24-pulse rectifier;

[0016] The average temperature of three semiconductor diodes on the same half-bridge arm of a 24-pulse rectifier;

[0017] The average temperature value of all six half-bridge legs of the 24-pulse rectifier.

[0018] Furthermore, the data set A in step S2 specifically includes the following data groups:

[0019] The temperature values ​​of all individual diodes, a total of 18 data, are defined as

[0020] The average temperature of the three semiconductor diodes on the same half-bridge arm is defined as the half-bridge temperature of the half-bridge arm. There are 6 data in total, defined as

[0021] The average temperature of the six half-bridge arms is defined as the real-time temperature of the 24-pulse rectifier.

[0022] Furthermore, the data set B in step S2 specifically includes the following data groups:

[0023] Average safe temperature of a single diode Median safe temperature Mean maintenance alarm temperature Median maintenance alarm temperature

[0024] Average safety temperature of a single half-bridge Median safe temperature Mean maintenance alarm temperature Median maintenance alarm temperature

[0025] The six half-bridge temperatures are averaged to form the real-time temperature of the rectifier, and the average value defines the safe temperature Median safe temperature Mean maintenance alarm temperature Median maintenance alarm temperature

[0026] 110% of the mean is the mean safety temperature, 110% of the median is the median safety temperature, 120% of the mean is the mean maintenance alarm temperature, and 120% of the median is the median maintenance alarm temperature.

[0027] Furthermore, the calculation method in step S2 is:

[0028] Real-time data obtained based on S1 Calculate the average value μ and variance s of all real-time junction temperature data of a single diode, a single half bridge, and six half bridges in turn. 2 :

[0029]

[0030]

[0031] According to the obtained mean μ and variance s 2 ,Combined with the data median P, it is jointly determined whether the diode object currently being detected is in a stable working state;

[0032] Compare real-time data one by one The individual junction temperature data and the average value μ and median value P are:

[0033] If the junction temperature is not higher than the mean and median safety temperatures at the same time, and the variance is less than 10, the device is in normal condition;

[0034] If the junction temperature is not higher than the mean and median safety temperatures at the same time, and the variance is greater than 10; or if one of the mean and median is within the range from its safety temperature to the maintenance alarm temperature, the device is in a warning state;

[0035] If the junction temperature is within the range of safety temperature to maintenance alarm temperature at the same time; or one of the mean and median exceeds the maintenance alarm temperature, it is in maintenance state;

[0036] The real-time collected data is classified according to the classification result B to determine the equipment status.

[0037] Furthermore, the data set A is:

[0038]

[0039] An intelligent operation and maintenance system for a 24-pulse rectifier of a subway power supply system, characterized in that the system comprises:

[0040] The acquisition module is used for online and offline acquisition of the real-time status device temperature data in the 24-pulse rectifier;

[0041] The storage module is used to store the collected data into the historical database for management;

[0042] An analysis module is used to perform calculation and analysis on each set of collected data;

[0043] The early warning module provides operation and maintenance prompts such as normal equipment, equipment maintenance, equipment repair, and whole cabinet update based on analysis results.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention is based on an intelligent temperature-measurable diode and aims at a key 24-pulse rectifier in a subway power supply system, and proposes an intelligent operation and maintenance method. The method adopts intelligent semiconductor devices to realize real-time measurement, identification and recording of reliability data of rectifiers and devices during operation; combines the temperature parameters of semiconductor devices to realize the digitized definition of the reliability of rectifiers and devices throughout their life cycle; based on an intelligent temperature-measurable diode, the present invention aims at a key 24-pulse rectifier in a subway power supply system, and obtains the real-time status data of the rectifier, so as to provide support for the intelligent operation and maintenance of the rectifier; based on the real-time status data of the rectifier, it provides support for big data analysis and processing of the rectifier and devices throughout their life cycle, which increases the measurement requirements and difficulty.

[0046] Other features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are incorporated in and constitute a part of this specification and, together with the description, serve to explain the principles of the present invention.

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0049] Figure 1 It is a flowchart of the intelligent operation and maintenance method of the 24-pulse rectifier of the subway power supply system proposed by the present invention;

[0050] Figure 2 This is a schematic diagram of the subway power supply system;

[0051] Figure 3 It is the principle diagram of the intelligent rectifier proposed by the present invention;

[0052] Figure 4 is a schematic diagram of visualization results of a single data collection in executing step S1 in an embodiment of the present invention;

[0053] Figure 5 It is a schematic diagram of the full life cycle junction temperature prediction result in executing step S2 in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices consistent with some aspects of the present invention as detailed in the appended claims.

[0055] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0056] like Figure 1-5 As shown, the present invention mainly proposes an intelligent operation and maintenance method for the key 24-pulse rectifier in the subway power supply system. The specific steps are:

[0057] Step S1, collect the real-time junction temperature data of all semiconductor devices in all 24-pulse rectifiers of the entire subway line online to obtain a real-time data set (i=0, 1, 2, ..., n, i is the device number, j=0, 1, 2, ..., n, j is the number of collections, once per minute), and each group of collected data is stored in a historical database for management to form data of the entire life cycle; in the step S1, the junction temperature data of all semiconductor devices in the 24-pulse rectifier are collected online in real time through the intelligent semiconductor diode.

[0058] The data set A is:

[0059]

[0060] The real-time device temperature data in step S1 includes:

[0061] Temperature value of a single diode on a 24-pulse rectifier;

[0062] The average temperature of three semiconductor diodes on the same half-bridge arm of a 24-pulse rectifier;

[0063] The average temperature value of the average temperature values ​​of all six half-bridge legs of the 24-pulse rectifier;

[0064] Step S2, based on the real-time data obtained in S1 The mean, variance and median of are used for classification to obtain the classification result B;

[0065]

[0066] And real-time data Use the support vector regression SVR algorithm for training to generate a diode life cycle regression network, and obtain a life cycle regression network C; perform sudden fault warning on the data collected at the current moment according to the classification result B, and predict the service life of the device according to the life cycle regression network C;

[0067] The calculation method in step S2 is:

[0068] Real-time data obtained based on S1 Calculate the average value μ and variance s of all real-time junction temperature data of a single diode, a single half bridge, and six half bridges in turn. 2 :

[0069]

[0070]

[0071] According to the obtained mean μ and variance s 2 ,Combined with the data median P, it is jointly determined whether the diode object currently being detected is in a stable working state;

[0072] Compare real-time data one by one The individual junction temperature data and the average value μ and median value P are:

[0073] If the junction temperature is not higher than the mean and median safety temperatures at the same time, and the variance is less than 10, the device is in normal condition;

[0074] If the junction temperature is not higher than the mean and median safety temperatures at the same time, and the variance is greater than 10; or if one of the mean and median is within the range from its safety temperature to the maintenance alarm temperature, the device is in a warning state;

[0075] If the junction temperature is within the range of safety temperature to maintenance alarm temperature at the same time; or one of the mean and median exceeds the maintenance alarm temperature, it is in maintenance state;

[0076] like Figure 4 As shown, visualizing the results makes it easier to see the location of the problematic device.

[0077] Then, the diode working time and the obtained junction temperature measurement results are used as input and output, and the SVR regression algorithm is used for prediction. Let the required hyperplane be f(a)

[0078] f(a)=<w,a> +b

[0079] The distance from a point to the hyperplane is d

[0080]

[0081] Minimize That is converted into an optimization problem:

[0082] min 1 / 2||w|| 2

[0083] The constraints are

[0084] |<w,a> +by|≤ε

[0085] According to the classification results, the data fault warning is classified and the life cycle is predicted according to the life cycle regression network, such as Figure 5 As shown in Figure 1, the junction temperature regression prediction of a device in the data set over a 15-year period can be used to predict other devices.

[0086] The real-time collected data is classified according to the classification result B to determine the equipment status.

[0087] The data set A in step S2 specifically includes the following data groups:

[0088] The temperature values ​​of all individual diodes, a total of 18 data, are defined as

[0089] The average temperature of the three semiconductor diodes on the same half-bridge arm is defined as the half-bridge temperature of the half-bridge arm. There are 6 data in total, defined as

[0090] The average temperature of the six half-bridge arms is defined as the real-time temperature of the 24-pulse rectifier.

[0091] The data set B in step S2 specifically includes the following data groups:

[0092] Average safe temperature of a single diode Median safe temperature Mean maintenance alarm temperature Median maintenance alarm temperature

[0093] Average safety temperature of a single half-bridge Median safe temperature Mean maintenance alarm temperature Median maintenance alarm temperature

[0094] The six half-bridge temperatures are averaged to form the real-time temperature of the rectifier, and the average value defines the safe temperature Median safe temperature Mean maintenance alarm temperature Median maintenance alarm temperature

[0095] 110% of the mean is the mean safety temperature, 110% of the median is the median safety temperature, 120% of the mean is the mean maintenance alarm temperature, and 120% of the median is the median maintenance alarm temperature.

[0096] Step S3, according to the mean value μ and variance s obtained in S2 2 , forming conclusions such as the overall condition of the 24-pulse rectifier is good, the semiconductor diode device is overhauled and maintained, the half-bridge arm components are overhauled and maintained, and the overall overhaul and maintenance of the rectifier cabinet, and prompting operations; according to the regression network prediction results, prompting the entire rectifier cabinet to be scrapped; thus forming intelligent operation and maintenance of the power supply rectifier cabinet throughout its life cycle. Step S3 is specifically as follows:

[0097] When all real-time data are within the safety threshold or safety range, the device is normal, the bridge arm is normal, and the rectifier cabinet is normal;

[0098] When real-time data exceeds the safe temperature or the safe temperature range, the system issues an alarm and requires maintenance inspection;

[0099] When real-time data exceeds the maintenance alarm temperature or maintenance alarm range, the system will issue an alarm to require system disconnection and maintenance;

[0100] After the rectifier cabinet has experienced more than ten years of normal operation, combined with the data changes over the entire life cycle, when the real-time temperature of the device, the real-time temperature of the bridge arm, and the real-time temperature of the rectifier cabinet (any one of them is satisfied) changes from a gradual and smooth linear increase to a steep exponential increase, the system prompts the entire rectifier cabinet to be scrapped and updated.

[0101] Then, the process is continuously executed in a loop starting from step S1.

[0102] The present invention is based on an intelligent temperature-measurable diode and aims at a key 24-pulse rectifier in a subway power supply system, and proposes an intelligent operation and maintenance method. The method adopts intelligent semiconductor devices to realize real-time measurement, identification and recording of reliability data of rectifiers and devices during operation; combines the temperature parameters of semiconductor devices to realize the digitized definition of the reliability of rectifiers and devices throughout their life cycle; based on an intelligent temperature-measurable diode, the present invention aims at a key 24-pulse rectifier in a subway power supply system, and obtains the real-time status data of the rectifier, so as to provide support for the intelligent operation and maintenance of the rectifier; based on the real-time status data of the rectifier, it provides support for big data analysis and processing of the rectifier and devices throughout their life cycle, which increases the measurement requirements and difficulty.

[0103] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention.

[0104] It should be understood that the present invention is not limited to what has been described above and that various modifications and changes may be made without departing from its scope. The scope of the present invention is limited only by the appended claims.

Claims

1. An intelligent operation and maintenance method for a 24-pulse rectifier in a subway power supply system, characterized in that: The following steps are involved: Step S1, collect the real-time junction temperature data of all semiconductor devices in all 24-pulse rectifiers of the entire subway line online to obtain a real-time data set A, and store each set of collected data in a historical database for management to form data of the entire life cycle; Step S2, calculating the mean, variance, and median of the real-time data set A obtained in S1 and classifying it to obtain a classification result B; The real-time data set A is trained using the support vector regression SVR algorithm to generate a diode life cycle regression network, and a life cycle regression network C is obtained; According to the classification result B, the data collected at the current moment is warned of sudden failures, and the service life of the device is predicted according to the life cycle regression network C; Step S3: Based on the classification result B, a maintenance conclusion of the 24-pulse rectifier is formed and an operation prompt is given; based on the life cycle regression network C, the entire rectifier cabinet is prompted to be scrapped; thus, intelligent operation and maintenance of the power supply rectifier cabinet is formed within the entire life cycle, and then the process is continuously executed in a loop starting from step S1; The real-time data set A in step S1 specifically includes the following data sets: The temperature values ​​of all individual diodes on the 24-pulse rectifier, a total of 18 data, are defined as Where: j is the number of acquisitions, which is once per minute; The average temperature of the three semiconductor diodes on the same half-bridge arm is defined as the half-bridge temperature of the half-bridge arm. There are 6 data in total, defined as The average temperature of the six half-bridge arms is defined as the real-time temperature of the 24-pulse rectifier. One data is defined as The classification result B in step S2 specifically includes the following data groups: Average safe temperature of a single diode Median safe temperature Mean maintenance alarm temperature Median maintenance alarm temperature Average safe temperature of a single half-bridge arm Median safe temperature Mean maintenance alarm temperature Median maintenance alarm temperature Average safe temperature of rectifier Median safe temperature Mean maintenance alarm temperature Median maintenance alarm temperature 110% of the mean is the mean safety temperature, 110% of the median is the median safety temperature, 120% of the mean is the mean maintenance alarm temperature, and 120% of the median is the median maintenance alarm temperature; The calculation method in step S2 is: According to the real-time data set A obtained by S1, the average value μ and variance s of all real-time junction temperature data of a single diode, a single half-bridge, and a rectifier are calculated in turn. 2 ; According to the obtained mean μ and variance s 2 ,Combined with the data median P, it is jointly determined whether the diode object currently being detected is in a stable working state; Compare the junction temperature data in the real-time data set A with the average value μ and the median value P in turn: If the junction temperature is not higher than the mean and median safety temperatures at the same time, and the variance is less than 10, the device is in normal condition; If the junction temperature is not higher than the mean and median safety temperatures at the same time, and the variance is greater than 10; or if one of the mean and median is within the range from its safety temperature to the maintenance alarm temperature, the device is in a warning state; If the junction temperature is within the range of safety temperature to maintenance alarm temperature at the same time; or one of the mean and median exceeds the maintenance alarm temperature, it is in maintenance state; The real-time collected data is classified according to the classification result B to determine the equipment status.

2. An intelligent operation and maintenance system based on the intelligent operation and maintenance method of a 24-pulse rectifier in a subway power supply system according to claim 1, characterized in that: The system comprises: The acquisition module is used for online and offline acquisition of the real-time status device temperature data in the 24-pulse rectifier; The storage module is used to store the collected data into the historical database for management; An analysis module is used to perform calculation and analysis on each set of collected data; The early warning module provides maintenance reminders for normal equipment, equipment maintenance, equipment repair, and whole cabinet update based on analysis results.

Images