Train operation intelligent protection system based on data processing

Abstract

The invention relates to the technical field of data processing, in particular to a train operation intelligent protection system based on data processing, which comprises a signal storage module, a data prediction module, a transverse comparison module, a longitudinal comparison module and an intelligent protection module, wherein the transverse comparison module is used for determining a real-time temperature time-domain graph and a historical temperature time-domain graph so as to respectively determine a real-time temperature fluctuation value and a historical temperature fluctuation value of each traction motor, and determining a motor characterization state according to the real-time temperature fluctuation value and the historical temperature fluctuation value; the longitudinal comparison module performs early warning on the real-time temperature data of each traction motor and determines a real-time characterization state; the intelligent protection module obtains real-time network voltage data, real-time direct current data and real-time total traction energy consumption according to the real-time representation state of the traction motor so as to determine the fault level of the traction motor and formulate a protection strategy; according to the invention, full-chain intelligent protection from temperature fluctuation trend analysis to multistage fault response is realized, and the safety, reliability and operation efficiency of a traction system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an intelligent train operation protection system based on data processing. Background Art

[0002] The current protection technology of subway traction motors mainly focuses on grounding protection, overvoltage and overcurrent protection, vibration protection and daily maintenance. First, grounding protection is an important measure to ensure the safe operation of traction motors. By optimizing the grounding system design of subway vehicles, such as setting protective grounding resistors and grounding devices, the risk of electrocorrosion of traction motor bearings can be effectively reduced to ensure the reliable operation of the equipment. Secondly, in response to the overvoltage and overcurrent problems of traction motors, the subway system can trigger the protection mechanism in time when abnormal conditions are detected to avoid motor damage by optimizing the control strategy and improving the protection logic. In addition, in order to reduce the impact of vibration on traction motors during transportation, a variety of protection status measures have been proposed. By arranging sensors at the motor shaft end, the vibration load is monitored and reduced, thereby protecting the motor bearings. Finally, daily maintenance is also an important part of traction motor protection, including regular cleaning, inspection of motor ventilation filters, lubrication of bearings, and monitoring of voltage and current. These measures help to detect and deal with potential problems in a timely manner and extend the service life of the motor.

[0003] Chinese patent announcement number CN113687226B discloses a method for identifying a phase-loss fault in an asynchronous motor of an urban rail vehicle-controlled traction inverter, comprising the following steps: S1: sampling the three-phase current of the asynchronous motor stator within a sampling period T; S2: calculating the effective value of the current of the three phases within the sampling period T; S3: comparing and judging the effective values of the three-phase current to determine the stator path of the asynchronous motor with a phase loss; S4: extracting the first phase whose deviation exceeds the set threshold, which is the stator path of the asynchronous motor with a phase-loss fault; This invention addresses the problem that it is difficult to accurately identify a phase loss in one motor of an urban rail asynchronous vehicle-controlled traction inverter, proposes a highly reliable fault diagnosis method, establishes a corresponding mathematical analysis model, and by introducing the parameters and operating conditions of the motor, outputs the deviation between the effective value of the current of the fault path and the normal stator path to determine the final phase-loss protection value. The algorithm of the present invention is simple, the accuracy of phase-loss identification is high, and it has broad industrial prospects. It can be seen that the existing technology has the following problems:

[0004] Traditional trains do not consider the operation consistency analysis of multiple traction motors and analyze the traction motors separately based on the consistency analysis results, which leads to problems such as fault classification and rough protection strategies. Summary of the Invention

[0005] To this end, the present invention provides a data processing-based intelligent train operation protection system to overcome the problem in the prior art that traditional trains do not consider the consistency analysis of multiple traction motor operations and analyze the traction motors separately based on the consistency analysis results, resulting in extensive fault classification and protection strategies. The system solves the technical problems of existing train traction motor monitoring systems in terms of real-time performance (short-term data window), consistency of multi-motor operation (horizontal comparison), single motor temperature anomaly warning (vertical comparison), fault classification protection (multi-dimensional analysis of power supply and energy consumption), and redundant system collaborative control (standby inverter switching), realizing full-chain intelligent protection from temperature fluctuation trend analysis to multi-level fault response, and improving the safety, reliability and operational efficiency of the traction system.

[0006] To achieve the above objectives, the present invention provides a train operation intelligent protection system based on data processing, comprising:

[0007] A signal storage module includes a data storage unit for obtaining historical temperature data of each traction motor and a signal display unit for displaying a plurality of real-time data, wherein the real-time data includes real-time temperature data, real-time grid voltage data, real-time DC data, and real-time total traction energy consumption;

[0008] a data prediction module connected to the signal storage module, configured to determine predicted temperature data based on historical temperature data of each traction motor;

[0009] a horizontal comparison module connected to the signal storage module, configured to determine a corresponding temperature time domain graph based on the historical temperature data of each traction motor to determine a real-time temperature time domain graph and a historical temperature time domain graph, and to respectively determine a real-time temperature fluctuation value and a historical temperature fluctuation value of each traction motor to determine a motor characterization state;

[0010] a longitudinal comparison module, connected to the signal storage module, the data prediction module, and the transverse comparison module, respectively, for obtaining motor characterization states and determining whether to issue an early warning for the corresponding traction motor based on the real-time temperature data and the predicted temperature data of each traction motor, so as to determine the real-time characterization state of the corresponding traction motor based on the relationship between the real-time temperature data of each traction motor and the temperature threshold;

[0011] an intelligent protection module, connected to the signal storage module, the horizontal comparison module, and the vertical comparison module, respectively, for acquiring real-time grid voltage data, real-time DC data, and real-time total traction energy consumption based on the real-time characterization status of the traction motor, so as to determine a fault level of the traction motor and formulate a protection strategy based on the fault level;

[0012] The protection strategy includes reducing output power, switching to a standby traction inverter, and cutting off traction of the corresponding traction inverter.

[0013] Furthermore, the data prediction module trains a neural network model based on historical temperature data of a single traction motor, and inputs real-time operating condition data related to the traction motor into the trained neural network model to determine predicted temperature data of the corresponding traction motor.

[0014] Furthermore, the horizontal comparison module determines a corresponding real-time temperature time domain graph according to the current time point, and determines a historical temperature time domain graph according to the temperature time domain graph and the real-time temperature time domain graph, so as to determine a real-time temperature fluctuation value and a historical temperature fluctuation value according to the real-time temperature time domain graph and the historical temperature time domain graph, respectively, and determines a motor characterization state according to the real-time temperature fluctuation value and the historical temperature fluctuation value of each traction motor;

[0015] The motor characterization state includes a consistent operation state and an abnormal operation state.

[0016] Furthermore, the horizontal comparison module determines the average temperature difference based on the temperature difference between any two adjacent extreme points of the temperature time domain diagram, determines the maximum temperature difference based on the maximum temperature and minimum temperature of the temperature time domain diagram, and determines the temperature fluctuation value based on the ratio of the average temperature difference to the maximum temperature difference.

[0017] Furthermore, the horizontal comparison module determines a motor characterization value of the corresponding traction motor based on a ratio of the real-time temperature fluctuation value to the historical temperature fluctuation value of the single traction motor, and determines a motor characterization state according to the motor characterization value of each traction motor;

[0018] Among them, the motor characterization value of each traction motor in the consistent operating state does not exceed the preset characterization value.

[0019] Furthermore, the longitudinal comparison module determines to issue an early warning to the corresponding traction motor based on the result of the determination of the consistent operation state and according to the magnitude relationship that the real-time temperature data of any traction motor is greater than the predicted temperature data.

[0020] Furthermore, the longitudinal comparison module determines that the real-time characteristic state of the corresponding traction motor is a fault state based on the judgment result of the early warning of the traction motor and the magnitude relationship between the real-time temperature data of the corresponding traction motor and the temperature threshold;

[0021] The real-time characterization state includes a fault state and a normal state.

[0022] Furthermore, the intelligent protection module obtains real-time grid voltage data, real-time DC data and real-time total traction energy consumption based on the determination result that the traction motor is in a fault state.

[0023] Furthermore, the intelligent protection module determines the corresponding fault level according to whether the real-time grid voltage data, real-time DC data and real-time total traction energy consumption meet the first condition, the second condition or the third condition and formulates a protection strategy according to the fault level.

[0024] Furthermore, the intelligent protection module includes a condition comparison unit for determining whether the real-time grid voltage data, the real-time DC data, and the real-time total traction energy consumption meet any one of the first condition, the second condition, or the third condition;

[0025] The first condition is that the total traction energy consumption is within a preset range, and there is a deviation in the real-time grid voltage data or the real-time DC data;

[0026] The second condition is that the total traction energy consumption is within a preset range, and there is a deviation between the real-time grid voltage data and the real-time DC data;

[0027] The third condition is that the total traction energy consumption exceeds a preset range.

[0028] Compared with the existing technology, the beneficial effect of the present invention is that the train operation intelligent protection system provided by the present invention realizes early warning, precise positioning and hierarchical treatment of traction motor faults through multi-dimensional data monitoring (historical / real-time temperature, grid voltage, DC, energy consumption), intelligent prediction (neural network temperature prediction), lateral (differences between motors) and longitudinal (real-time / predicted comparison) state analysis, combined with hierarchical fault judgment (level one, level two, level three) and dynamic protection strategy, significantly improving the safety (avoiding overheating / short-circuit accidents), reliability (redundant switching to ensure continuous operation) and economy (reducing unplanned downtime and maintenance costs) of train operation. At the same time, it optimizes the energy efficiency of the traction system through data-driven intelligent decision-making, providing an efficient solution for the intelligent operation and maintenance of rail transit.

[0029] Furthermore, the horizontal comparison module accurately determines the motor's operating status by monitoring the temperature changes of the traction motor in real time and performing comparative analysis based on historical data. It can not only quickly identify motors with abnormal operation, but also effectively distinguish faulty motors, providing strong support for the safe operation of trains. At the same time, this module ensures the real-time and accuracy of monitoring by reasonably setting the preset duration and characterization value range, thereby improving the reliability of train operation and maintenance efficiency.

[0030] Furthermore, the train longitudinal comparison module dynamically compares real-time temperature data with predicted temperature data, combined with the safety boundary design of temperature thresholds, to achieve accurate early warning and fault determination of the temperature status of individual traction motors. This module can effectively identify temperature anomalies that exceed expectations and avoid system failures caused by overheating of a single motor. At the same time, it clearly defines the normal state and reduces interference from misjudgments, providing hierarchical temperature safety protection for the train traction system, improving the safety and reliability of motor operation and targeted maintenance. It ensures that early warnings are triggered at the early stage of temperature anomalies, preventing fault escalation and ensuring the continuous and stable operation of the train.

[0031] Furthermore, the intelligent protection module builds a hierarchical response system of "fault level-protection strategy" by integrating multi-dimensional analysis of real-time grid voltage data, DC data and total traction energy consumption, achieving full scenario coverage from local power supply anomalies to serious motor failure: Level 1 faults alleviate short-term overloads by reducing power, Level 2 faults use redundant design to switch to the backup inverter to ensure continuous operation, and Level 3 faults decisively remove the faulty unit to prevent the spread of disasters; this module quantifies the fault hazards in the dual dimensions of power supply stability and load health, and combines a progressive protection strategy to improve the fault tolerance, operation continuity and safety of the traction system. At the same time, through precise fault location and hierarchical handling, it reduces maintenance costs, avoids operational interruptions caused by excessive protection, and provides an intelligent, multi-level active safety barrier for the train traction system. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a connection diagram of the train operation intelligent protection system based on data processing according to an embodiment of the present invention;

[0033] Figure 2 This is a workflow diagram of the horizontal comparison module according to an embodiment of the present invention;

[0034] Figure 3 This is a workflow diagram of the vertical comparison module according to an embodiment of the present invention;

[0035] Figure 4 This is a workflow diagram of the intelligent protection module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0037] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0038] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0039] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0040] See also Figure 1 As shown in FIG, it is a connection diagram of a train operation intelligent protection system based on data processing according to an embodiment of the present invention. An embodiment of the present invention provides a train operation intelligent protection system based on data processing, comprising:

[0041] The signal storage module includes a data storage unit for acquiring historical temperature data of each traction motor and a signal display unit for displaying a plurality of real-time data, wherein the real-time data includes real-time temperature data, real-time grid voltage data, real-time DC data, and real-time total traction energy consumption. It is understood that the acquisition and storage of temperature data, grid voltage data, DC data, and total traction energy consumption data in subway trains are existing technologies and have been applied, so they will not be described in detail.

[0042] a data prediction module connected to the signal storage module and configured to determine predicted temperature data based on the historical temperature data of each traction motor; it is understood that the historical temperature data of each traction motor is used to train a neural network model, and then the trained neural network model is input with current train operation data to determine the predicted temperature data in real time;

[0043] a horizontal comparison module connected to the signal storage module, for determining a corresponding temperature time domain diagram based on the historical temperature data of each traction motor to determine a real-time temperature time domain diagram and a historical temperature time domain diagram, and respectively determining the real-time temperature fluctuation value and the historical temperature fluctuation value of each traction motor to determine the motor characterization state; it can be understood that the temperature time domain diagram is composed of the real-time temperature time domain diagram and the historical temperature time domain diagram; the horizontal comparison module is used to determine the degree of difference between each traction motor to understand the overall state of each traction motor in the subway train (recorded as the motor characterization state); if the degree of difference between each traction motor is relatively small, the motor characterization state is determined to be an operating consistent state; if the degree of difference between one or more traction motors is relatively large, the motor characterization state is determined to be an operating abnormal state; in the case of an abnormal operating state, the abnormal traction motor can be directly locked and corresponding protective measures can be taken for it; in implementation, the degree of difference is determined by comparing the ratio of the real-time temperature fluctuation value of each traction motor to the corresponding historical temperature fluctuation value;

[0044] a longitudinal comparison module, connected to the signal storage module, the data prediction module, and the transverse comparison module, respectively, for obtaining motor characterization states and determining whether to issue a warning for the corresponding traction motor based on the real-time temperature data and the predicted temperature data of each traction motor, thereby determining the real-time characterization state of the corresponding traction motor based on the relationship between the real-time temperature data of each traction motor and the temperature threshold. It is understood that the longitudinal comparison module determines the real-time state (referred to as the real-time characterization state) of each traction motor based on the historical data of each traction motor;

[0045] In practice, the status of each motor is determined only after the horizontal comparison module confirms that the differences between the motors are small (i.e., they are operating in a consistent state), to avoid situations where all motors are abnormal at the same time or a single motor is different from its historical operating condition;

[0046] An intelligent protection module is connected to the signal storage module, the horizontal comparison module and the vertical comparison module respectively, and is used to obtain real-time grid voltage data, real-time DC data and real-time total traction energy consumption according to the real-time characterization state of the traction motor, so as to determine the fault level of the traction motor and formulate a protection strategy according to the fault level; it can be understood that the traction motor and the traction inverter are the core components of the rail transit traction transmission system, and the relationship between the two is as follows: (1) Energy conversion relationship: The traction inverter is responsible for converting the DC power of the intermediate DC circuit into three-phase AC power with controllable voltage and frequency to provide power for the traction motor; the traction motor converts electrical energy into mechanical energy (traction working condition) or mechanical energy into electrical energy (regenerative braking working condition) to drive the wheelset or realize energy recovery; (2) Control relationship: The traction inverter adjusts the output current and frequency according to the control instruction to accurately control the operating state of the traction motor, and the real-time feedback of the traction motor (such as temperature, speed, current) is used for closed-loop control of the inverter to ensure stable operation of the system; therefore, when the traction motor is abnormal, the traction inverter needs to be adjusted to protect the operation of the subway train;

[0047] The protection strategy includes reducing output power, switching to a standby traction inverter, and cutting off traction of the corresponding traction inverter.

[0048] It can be understood that the intelligent train operation protection system provided by the embodiment of the present invention breaks through the single parameter threshold limitation of traditional train protection through the full-chain design of "data monitoring-intelligent prediction-multi-dimensional comparison-grading protection", and realizes the active prevention, precise disposal and energy efficiency optimization of traction system faults: (1) dual state evaluation integrating horizontal (between motors) and vertical (real-time-history) comparison; (2) deep coupling of temperature prediction and multi-parameter fault classification based on neural network; (3) hierarchical protection strategy of dynamic adjustment of traction inverter, which ultimately improves the three dimensions of safety, reliability and economy, and provides an integrated "measurement-judgment-control" solution for intelligent rail transit.

[0049] Specifically, the data prediction module trains a neural network model based on the historical temperature data of a single traction motor, and inputs real-time operating condition data related to the traction motor into the trained neural network model to determine the predicted temperature data of the corresponding traction motor.

[0050] It is understandable that when training the neural network model, it is also necessary to input the operating condition data corresponding to each historical temperature data to better train the neural network model. It is understandable that the historical temperature data contains the temperature change law of the motor under different operating conditions. The neural network has a strong nonlinear mapping ability and can learn these complex laws to establish a relationship model between the operating condition and the temperature. In implementation, accurately predicting the temperature of the traction motor is of great significance to ensuring the safe operation of the motor and optimizing the maintenance plan. By inputting real-time operating condition data, the predicted temperature of the motor can be obtained in time, and measures can be taken in advance to avoid overheating failures.

[0051] In practice, the working condition data related to the traction motor usually include the following categories: (1) Electrical parameters: ① Current: The current of the traction motor directly reflects its load condition; the larger the current, the greater the heat generated by the motor. Therefore, the current is one of the important factors affecting the motor temperature; ② Voltage: The voltage at both ends of the motor will affect the motor's operating efficiency and power consumption and thus affect the temperature. Unstable voltage may cause the motor to be overloaded or overheated; ③ Power: Power is the product of current and voltage, which comprehensively reflects the working intensity of the motor; at different power levels, the heating condition of the motor will also be different; (2) Mechanical parameters: ① Speed: The speed of the motor is closely related to the load and heat dissipation conditions; when running at high speed, the friction loss and ventilation loss of the motor will increase, resulting in an increase in temperature; while at low speed or no load, the temperature is relatively low; ② Torque: Torque is the rotational force output by the motor and is proportional to the load size. A larger torque means that the motor needs to overcome a greater resistance, thereby generating more heat; (3) Environmental parameters: ① Ambient temperature: The temperature of the surrounding environment will affect the heat dissipation effect of the motor. In a high temperature environment, the heat dissipation speed of the motor will slow down, which will easily lead to temperature rise; in a low temperature environment, the heat dissipation is relatively fast; ② Humidity: Humidity will affect the insulation performance and heat dissipation efficiency of the motor. A high humidity environment may cause the insulation of the motor to get damp, increase the risk of leakage, and also reduce the heat dissipation efficiency; ③ Ventilation conditions: Good ventilation can take away the heat generated by the motor and reduce the temperature. Ventilation parameters such as ventilation volume and wind speed are crucial for accurately predicting the motor temperature; (4) Operating status parameters: ① Operating time: The longer the motor runs continuously, the more heat it accumulates and the temperature will rise accordingly; ② Number of starts / stops: Frequent starts and stops will cause the motor to withstand a large current shock, resulting in large temperature fluctuations. Statistical information on the number of starts / stops can help predict the temperature changes of the motor in different operating stages; the above operating condition data can be directly obtained from the signal display unit of the subway train.

[0052] See also Figure 2, which is a workflow diagram of the horizontal comparison module according to an embodiment of the present invention. Specifically, the horizontal comparison module determines a corresponding real-time temperature time domain graph based on the current time point, and determines a historical temperature time domain graph based on the temperature time domain graph and the real-time temperature time domain graph, thereby determining a real-time temperature fluctuation value and a historical temperature fluctuation value based on the real-time temperature time domain graph and the historical temperature time domain graph, respectively, and determining a motor characterization state based on the real-time temperature fluctuation value and the historical temperature fluctuation value of each traction motor;

[0053] The motor characterization state includes a consistent operation state and an abnormal operation state.

[0054] In implementation, the temperature time domain graph within a preset time period before the current time point (usually less than 10 minutes, if the preset time period is too long, it will affect the real-time performance of the motor state, preferably set to 6 minutes) is determined as the real-time temperature time domain graph, and the part of the temperature time domain graph other than the real-time temperature time domain graph is determined as the historical temperature time domain graph; it can be understood that as the current temperature continues to change, the real-time temperature time domain graph and the historical temperature time domain graph also change accordingly.

[0055] Specifically, the horizontal comparison module determines the average temperature difference based on the temperature difference between any two adjacent extreme points in the temperature time domain diagram, determines the maximum temperature difference based on the maximum temperature and minimum temperature of the temperature time domain diagram, and determines the temperature fluctuation value based on the ratio of the average temperature difference to the maximum temperature difference.

[0056] It can be understood that the horizontal comparison module determines the average real-time temperature difference based on the temperature difference between any two adjacent extreme points in the real-time temperature time domain diagram, determines the maximum real-time temperature difference based on the maximum temperature and minimum temperature of the real-time temperature time domain diagram, and determines the real-time temperature fluctuation value based on the ratio of the average real-time temperature difference to the maximum real-time temperature difference; the horizontal comparison module determines the average historical temperature difference based on the temperature difference between any two adjacent extreme points in the historical temperature time domain diagram, determines the maximum historical temperature difference based on the maximum temperature and minimum temperature of the historical temperature time domain diagram, and determines the historical temperature fluctuation value based on the ratio of the average historical temperature difference to the maximum historical temperature difference.

[0057] Specifically, the horizontal comparison module determines the motor characterization value of the corresponding traction motor based on the ratio of the real-time temperature fluctuation value and the historical temperature fluctuation value of the single traction motor, and determines the motor characterization state according to the motor characterization value of each traction motor;

[0058] Among them, the motor characterization value of each traction motor in the consistent operation state does not exceed (that is, is less than or equal to) the preset characterization value.

[0059] It can be understood that the motor characterization value = real-time temperature fluctuation value ÷ historical temperature fluctuation value. The closer the motor characterization value is to 1, the closer the real-time temperature fluctuation value and the historical temperature fluctuation value are, that is, the change state of the real-time temperature and the historical temperature are similar. Among them, when the motor characterization value is less than 1, it means that the temperature state of the motor is more stable than the historical state. When the motor characterization value is greater than 1, it means that the temperature state of the motor is more unstable than the historical state. Therefore, in implementation, the preset characterization value ∈(1,1.2], preferably the preset characterization value is 1.1.

[0060] In implementation, if the motor characterization value of any traction motor is greater than the preset characterization value, it means that the current motor characterization state is an abnormal operation state, and the real-time characterization state of the traction motor that exceeds the preset characterization value is determined to be a fault state.

[0061] It is understandable that the horizontal comparison module ensures real-time performance through short-cycle data updates (6 minutes) to adapt to the dynamic needs of high-speed train operation; quantitative analysis based on extreme points and temperature differences avoids noise interference and captures true temperature fluctuation characteristics; horizontal comparison of multiple motor states ensures the consistency of the overall system operation and prevents the spread of local faults; preventive maintenance reduces downtime, extends motor life, and reduces operating costs.

[0062] See also Figure 3 , which is a workflow diagram of the longitudinal comparison module according to an embodiment of the present invention. Specifically, based on the determination result of the consistent operating state, the longitudinal comparison module determines whether to issue a warning for the corresponding traction motor if the real-time temperature data of any traction motor is greater than the predicted temperature data. It is understood that based on the determination result of the consistent operating state, the longitudinal comparison module determines whether to issue a warning for the corresponding traction motor if the real-time temperature data of any traction motor is less than or equal to the predicted temperature data. In practice, for traction motors for which no warning is issued, their real-time representation state is normal.

[0063] Specifically, the longitudinal comparison module determines that the real-time characterization state of the corresponding traction motor is a fault state based on the judgment result of the early warning of the traction motor and the magnitude relationship between the real-time temperature data of the corresponding traction motor and the temperature threshold;

[0064] The real-time characterization state includes a fault state and a normal state.

[0065] In implementation, the predicted temperature data should be less than the temperature threshold, and the predicted temperature data should be within the normal temperature range (which should be indicated in the safety manual of the traction motor when the traction motor undergoes factory testing). The temperature threshold is usually less than the maximum temperature of the traction motor during the design stage; in implementation, it is usually set to 80% to 90% of the design maximum temperature.

[0066] See also Figure 4 , which is a flowchart of the intelligent protection module according to an embodiment of the present invention. Specifically, the intelligent protection module obtains real-time grid voltage data, real-time DC data, and real-time total traction energy consumption based on the result of determining that the traction motor is in a fault state.

[0067] It is understandable that the traction motor is in a fault state and a judgment result can be obtained in the horizontal comparison module when the motor characterization state is an abnormal operation state, or a judgment result can be obtained in the vertical comparison module when the motor characterization state is a consistent operation state in the horizontal comparison module.

[0068] Specifically, the intelligent protection module determines the corresponding fault level according to whether the real-time grid voltage data, real-time DC data and real-time total traction energy consumption meet the first condition, the second condition or the third condition and formulates a protection strategy according to the fault level, including:

[0069] Based on the determination that the real-time grid voltage data, real-time DC data, and real-time total traction energy consumption meet the first condition, the fault level is determined to be a level 1 fault, and a protection strategy is formulated to reduce output power. It is understandable that if the total traction energy consumption is within the preset range (normal load), but a single deviation exists in the grid voltage or DC data (such as a grid voltage fluctuation exceeding a threshold or a DC current zero drift), it may cause a short-term overload or abnormal heat dissipation of the motor, but does not affect the overall energy consumption. In this case, it is only necessary to reduce the output power to reduce the motor load and heat generation, and avoid further deterioration of the power supply system (such as preventing overcurrent caused by voltage deviation).

[0070] Based on the determination that the real-time grid voltage data, real-time DC data, and real-time total traction energy consumption meet the second condition, the fault level is determined to be a level 2 fault, and a protection strategy is formulated to switch to the backup traction inverter. It is understandable that the total traction energy consumption is within the preset range (normal load), but the grid voltage and DC data are both deviated (the grid voltage continues to fluctuate and the DC current is abnormal), indicating that the grid voltage is unstable and the DC link is faulty, possibly due to unstable input from the current traction inverter, which threatens the reliable operation of the motor. At this time, switching to the backup inverter avoids the power supply risk of the faulty inverter, that is, utilizing a redundant design to ensure continuous operation of the motor (it is necessary to ensure that the backup system is normal).

[0071] According to the judgment result that the real-time grid voltage data, real-time DC data and real-time total traction energy consumption meet the third condition, the fault level is determined to be a level 3 fault, and a protection strategy is formulated to cut off the traction of the traction inverter at the corresponding position; it can be understood that the total traction energy consumption exceeds the preset range, that is, the energy consumption exceeds the limit, indicating that the motor load is too high (such as mechanical jamming, winding short circuit) or the efficiency drops sharply (such as cooling system failure), and continued operation will lead to severe overheating or device damage; at this time, the traction of the faulty inverter should be cut off and sent back to the warehouse for processing to avoid the spread of the fault (such as preventing short circuit from causing fire or damaging other equipment).

[0072] It can be understood that the grid voltage data reflects the stability of the external power supply system (such as grid voltage fluctuations and deviations); the DC data reflects the status of the intermediate DC link of the traction system (such as current deviation and zero drift); and the total traction energy consumption reflects the load intensity and energy consumption efficiency of the traction motor (directly related to motor heating and torque output). Therefore, the fault level of the faulty traction motor can be determined based on these three real-time data.

[0073] Specifically, the intelligent protection module includes a condition comparison unit for determining whether the real-time grid voltage data, the real-time DC data, and the real-time total traction energy consumption meet any one of the first condition, the second condition, or the third condition;

[0074] The first condition is that the total traction energy consumption is within a preset range, and there is a deviation in the real-time grid voltage data or the real-time DC data;

[0075] The second condition is that the total traction energy consumption is within a preset range, and there is a deviation between the real-time grid voltage data and the real-time DC data;

[0076] The third condition is that the total traction energy consumption exceeds a preset range.

[0077] In implementation: Level 1 fault is an abnormality in a single power supply parameter (grid voltage or DC), while energy consumption is normal, that is, a local slight abnormality; Level 2 fault is an abnormality in two power supply parameters (grid voltage and DC), while energy consumption is normal, that is, multiple abnormalities in the power supply system; Level 3 fault is energy consumption exceeding the limit (regardless of whether the power supply parameters are abnormal), which means that the motor load or efficiency has seriously deteriorated.

[0078] It can be understood that power supply stability (grid voltage / DC deviation) reflects the reliability of external input and intermediate links; load rationality (energy consumption) directly reflects the health of the motor's operating status; the fault conditions in the present invention are gradually upgraded from "local abnormality-system abnormality-serious failure" according to the severity of the fault.

[0079] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0080] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A train operation intelligent protection system based on data processing, characterized in that: include: A signal storage module includes a data storage unit for obtaining historical temperature data of each traction motor and a signal display unit for displaying a plurality of real-time data, wherein the real-time data includes real-time temperature data, real-time grid voltage data, real-time DC data, and real-time total traction energy consumption; a data prediction module connected to the signal storage module, configured to determine predicted temperature data based on historical temperature data of each traction motor; a horizontal comparison module connected to the signal storage module, configured to determine a corresponding temperature time domain graph based on the historical temperature data of each traction motor to determine a real-time temperature time domain graph and a historical temperature time domain graph, and to respectively determine a real-time temperature fluctuation value and a historical temperature fluctuation value of each traction motor to determine a motor characterization state; a longitudinal comparison module, connected to the signal storage module, the data prediction module, and the transverse comparison module, respectively, for obtaining motor characterization states and determining whether to issue an early warning for the corresponding traction motor based on the real-time temperature data and the predicted temperature data of each traction motor, so as to determine the real-time characterization state of the corresponding traction motor based on the relationship between the real-time temperature data of each traction motor and the temperature threshold; an intelligent protection module, connected to the signal storage module, the horizontal comparison module, and the vertical comparison module, respectively, for acquiring real-time grid voltage data, real-time DC data, and real-time total traction energy consumption based on the real-time characterization status of the traction motor, so as to determine a fault level of the traction motor and formulate a protection strategy based on the fault level; The protection strategy includes reducing output power, switching to a standby traction inverter, and cutting off traction of the corresponding traction inverter.

2. The train operation intelligent protection system based on data processing according to claim 1 is characterized in that: The data prediction module trains a neural network model based on historical temperature data of a single traction motor, and inputs real-time operating condition data related to the traction motor into the trained neural network model to determine predicted temperature data of the corresponding traction motor.

3. The train operation intelligent protection system based on data processing according to claim 1 is characterized in that: The horizontal comparison module determines a corresponding real-time temperature time domain graph according to a current time point, and determines a historical temperature time domain graph according to the temperature time domain graph and the real-time temperature time domain graph, so as to determine a real-time temperature fluctuation value and a historical temperature fluctuation value according to the real-time temperature time domain graph and the historical temperature time domain graph, respectively, and determines a motor characterization state according to the real-time temperature fluctuation value and the historical temperature fluctuation value of each traction motor; The motor characterization state includes a consistent operation state and an abnormal operation state.

4. The train operation intelligent protection system based on data processing according to claim 3 is characterized in that: The horizontal comparison module determines the average temperature difference based on the temperature difference between any two adjacent extreme points of the temperature time domain diagram, determines the maximum temperature difference based on the maximum temperature and the minimum temperature of the temperature time domain diagram, and determines the temperature fluctuation value based on the ratio of the average temperature difference to the maximum temperature difference.

5. The train operation intelligent protection system based on data processing according to claim 3 is characterized in that: The horizontal comparison module determines a motor characterization value of a corresponding traction motor based on a ratio of a real-time temperature fluctuation value to a historical temperature fluctuation value of a single traction motor, and determines a motor characterization state according to the motor characterization value of each traction motor; Among them, the motor characterization value of each traction motor in the consistent operating state does not exceed the preset characterization value.

6. The train operation intelligent protection system based on data processing according to claim 1 is characterized in that: The longitudinal comparison module determines to issue an early warning to the corresponding traction motor based on the result of the determination of the consistent operation state and the magnitude relationship that the real-time temperature data of any traction motor is greater than the predicted temperature data.

7. The train operation intelligent protection system based on data processing according to claim 1 is characterized in that: The longitudinal comparison module determines that the real-time characteristic state of the corresponding traction motor is a fault state based on the judgment result of the early warning of the traction motor and the magnitude relationship between the real-time temperature data of the corresponding traction motor and the temperature threshold; The real-time characterization state includes a fault state and a normal state.

8. The train operation intelligent protection system based on data processing according to claim 1 is characterized in that: The intelligent protection module obtains real-time grid voltage data, real-time DC data and real-time total traction energy consumption according to the result of determining that the traction motor is in a fault state.

9. The train operation intelligent protection system based on data processing according to claim 1 is characterized in that: The intelligent protection module determines the corresponding fault level according to the real-time grid voltage data, real-time DC data and real-time total traction energy consumption meeting the first condition, the second condition or the third condition and formulates a protection strategy according to the fault level.

10. The train operation intelligent protection system based on data processing according to claim 9 is characterized in that: The intelligent protection module includes a condition comparison unit for determining whether the real-time grid voltage data, the real-time DC data, and the real-time total traction energy consumption meet any one of the first condition, the second condition, or the third condition; The first condition is that the total traction energy consumption is within a preset range, and there is a deviation in the real-time grid voltage data or the real-time DC data; The second condition is that the total traction energy consumption is within a preset range, and there is a deviation between the real-time grid voltage data and the real-time DC data; The third condition is that the total traction energy consumption exceeds a preset range.

Images