High-speed rail lighting fault prediction method and system

Abstract

The invention relates to the technical field of data processing, and discloses a high-speed rail lighting fault prediction method and system, and the system comprises a multi-dimensional collection module and an intelligent prediction module. According to the high-speed rail lighting fault prediction method and system, a multi-dimensional acquisition module is connected with a high-speed rail lighting system and a sensing device, management data of all lamps, operation data of all electrical circuits and environment sensing data of all carriages are obtained and classified to form a data set, an intelligent prediction module analyzes the use state of each lamp, and the intelligent prediction module is used for predicting the lighting fault of the high-speed rail. A corresponding fatigue coefficient is generated, then a fixed monitoring period, a temperature threshold value, a humidity threshold value, a frequency threshold value and an amplitude threshold value are set, the fluctuation trend of each electrical circuit and the environment change trend of each carriage are analyzed, a corresponding fluctuation coefficient and an environment data set are generated, and the multi-dimensional prevention capability is high. The risk of lamp fatigue damage, the risk of electrical circuit fault and the risk of lamp fault damage are evaluated, corresponding management suggestions are output, and the intelligent prediction management efficiency is high.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a high-speed rail lighting fault prediction method and system. Background Art

[0002] High-speed rail lamps are special lighting equipment designed for high-speed rail carriages. They not only provide necessary lighting for passengers and staff, but also have multiple functions to adapt to the special environment of high-speed rail operation. High-speed rail lamps include design features such as energy saving and high efficiency, uniform lighting, durability and reliability, and easy maintenance. LED technology is usually used, which has lower energy consumption and higher brightness than traditional lamps, and can effectively save energy. The lamp design ensures that all light is evenly distributed in the carriage, avoiding glare or shadows, and creating a comfortable visual environment for passengers. In addition, considering the high-frequency vibration and extreme temperature changes of high-speed rail operation, high-speed rail lamps must also have good shock resistance and durability, easy installation and disassembly, and convenient daily maintenance and troubleshooting. The types of high-speed rail lamps include but are not limited to top lighting, reading lights, emergency lighting and identification lights. Top lighting is installed on the top of the carriage and provides the main lighting function. Each seat is equipped with a reading light to facilitate passengers to read books or use electronic devices. In emergency situations, such as power outages or disasters, the emergency lighting system will be activated immediately to ensure the safety of passengers. Identification lights are used to indicate important locations such as emergency exits and carriage connections. Modern high-speed rail lighting systems are often equipped with intelligent control functions, which can automatically adjust the brightness according to the ambient light, or achieve remote monitoring and management through a central control system. This not only improves lighting efficiency, but also increases convenience of use.

[0003] At present, traditional high-speed rail lighting fault prediction methods often rely on manual inspections and limited sensor data. The information collected is of a single dimension and the data basis is not comprehensive enough, which easily leads to low accuracy of fault prediction results. Lighting failures may be caused by multiple faults such as short circuits, open circuits, and leakage of electrical components at the same time, or they may be the result of multiple factors such as damage to the mechanical structure of the lighting equipment and aging of optical components. Only analyzing a single factor cannot fully consider the relationship and influence between various factors, and the prediction effect is poor in the face of complex faults. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides a high-speed rail lighting fault prediction method and system, which has the advantages of high multi-dimensional analysis accuracy and high intelligent prediction management efficiency, and solves the problems that the data basis of traditional high-speed rail lighting fault prediction methods is not comprehensive enough and the prediction effect of complex faults is poor.

[0006] (II) Technical solution

[0007] To achieve the above object, the present invention provides the following technical solution: a high-speed railway lighting fault prediction method, comprising the following steps:

[0008] Step 1: Connect the high-speed rail lighting system and sensor devices through the network to obtain the management data of all lamps, the operation data of all electrical lines and the environmental sensor data of all carriages, and classify them into lamp data sets, operation data sets and environmental data sets;

[0009] Step 2: Analyze the usage status of each lamp based on the lamp data set and generate the corresponding fatigue coefficient ;

[0010] Step 3: Set a fixed-duration monitoring cycle and fixed range temperature thresholds , humidity threshold , frequency threshold , Amplitude Threshold , combined with the operation data set and the environmental data set, analyze the fluctuation trend of each electrical line and the environmental change trend of each carriage, and generate the corresponding fluctuation coefficient and Environmental Data Group ;

[0011] Step 4: Set a fixed range of fatigue thresholds and fluctuation threshold , combined with the fatigue coefficient , volatility coefficient and Environmental Data Group , assess the risk of lamp fatigue damage, the risk of electrical circuit failure, and the risk of lamp failure damage, and output corresponding management recommendations.

[0012] Preferably, in step 1, the expression of the lamp data set is , to Indicates the first to The management data of each lamp includes luminous flux, color temperature, power factor, cumulative working time, cumulative number of switches, cumulative number of faults, connection lines and car positions. Indicates the protection level of a single luminaire.

[0013] Preferably, in step 1, the expression of the running data set is , to Indicates the first to the The operating data of the electrical lines include voltage, current, cumulative fault times and car position. Indicates the total number of lamps connected to a single electrical circuit.

[0014] Preferably, in step 1, the expression of the environmental data set is , Indicates the temperature in a single compartment environment. Indicates the humidity in a single compartment environment. represents the vibration frequency of a single carriage, represents the vibration amplitude of a single carriage, Indicates the car number.

[0015] Preferably, in step 2, the fatigue coefficient The calculation process is as follows:

[0016] According to the lamp data set, extract the management data of each lamp, and The luminous flux of each lamp is marked as , will The color temperature of the lamp is marked as , will The power factor of each lamp is marked as , will The accumulated working time of each lamp is marked as , will The cumulative number of switching times of each lamp is marked as , will The cumulative number of failures of each lamp is marked as ;

[0017]

[0018] In the formula, Indicates the rated value of the luminous flux of the lamp. Represents the weight of the ratio of luminous flux to rated value, Indicates the rated value of the color temperature of the lamp. Indicates the absolute difference between the color temperature and the rated value. Represents the weight for the absolute difference in color temperature, Indicates the rated value of the lamp power factor. Represents the weight of the ratio of power factor to rated value, Indicates the switching frequency of the lamp, represents the weight for the switching frequency, Indicates the failure frequency of the lamp, represents the weight for the fault frequency, , , , and are constants, and , Indicates according to , , , and Weight, calculate the Fatigue coefficient of each lamp .

[0019] Preferably, in step 3, the fluctuation coefficient The calculation process is as follows:

[0020] Extract monitoring cycles based on the running data set within, no. The operation data of electrical lines, among which The connection line of each lamp is electrical lines;

[0021] The first The voltage of the electrical circuit is marked , will The current of the electrical circuit is marked as , will The cumulative number of faults of the electrical lines is marked as , will The total number of lamps connected to the electrical circuit is marked as ;

[0022]

[0023] In the formula, Indicates monitoring cycle within, no. The voltage change of an electrical line, represents the weight for the voltage change, Indicates monitoring cycle within, no. The change in current in an electrical line, represents the weight for the current change, Represents the weight of the cumulative number of faults for electrical lines, Represents the weight of the total number of electrical circuit lamps, , , and are constants, and , Indicates according to , , and Weight, calculate the monitoring period within, no. The fluctuation coefficient of the electrical line .

[0024] Preferably, in step 3, the environmental data set The calculation process is as follows:

[0025] Extract monitoring cycles based on environmental data sets within, no. The environmental sensor data of the carriage, among which The carriage number of the carriage is , No. The lamp and The electrical lines are all installed in Inside the carriage;

[0026]

[0027] In the formula, and Indicates the temperature threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Temperature in the compartment environment versus temperature threshold , and Indicates humidity threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Humidity in the compartment environment vs. humidity threshold , and Indicates frequency threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Vibration frequency of the carriage compared to the frequency threshold , and Indicates the amplitude threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Vibration amplitude of the carriage compared to the amplitude threshold , Indicates monitoring cycle within, no. Environmental data set for the carriage.

[0028] Preferably, in step 4, the fatigue coefficient Exceeding fatigue threshold , it indicates that the risk of lamp fatigue damage is high, and it is recommended to replace the aging lamp in time.

[0029] Preferably, in step 4, the coefficient of fluctuation Exceeding the volatility threshold When the risk of electrical line failure is high, it is recommended to conduct inspection and maintenance in time. When any value exceeds the threshold range, it means that the car environment changes drastically and the risk of lamp failure and damage is high. Timely inspection and maintenance are recommended.

[0030] A high-speed rail lighting fault prediction system, comprising a multi-dimensional acquisition module and an intelligent prediction module;

[0031] The multi-dimensional acquisition module is composed of a lighting data unit, an electrical data unit and an environmental data unit. The lighting data unit is connected to the high-speed rail lighting system through a network to collect a lamp data set, and the lamp data set includes management data of all lamps. The electrical data unit is connected to the high-speed rail lighting system through a network to collect an operation data set, and the operation data set includes operation data of all electrical lines. The environmental data unit is connected to the sensor device through a network to collect an environmental data set, and the environmental data set includes environmental sensor data of all carriages.

[0032] The intelligent prediction module consists of a fatigue analysis unit, a monitoring analysis unit and an evaluation management unit. The fatigue analysis unit analyzes the usage status of each lamp according to the lamp data set and generates a corresponding fatigue coefficient. The monitoring and analysis unit is provided with a monitoring cycle of fixed duration. and fixed range temperature thresholds , humidity threshold , frequency threshold , Amplitude Threshold , combined with the operation data set and the environmental data set, analyze the fluctuation trend of each electrical line and the environmental change trend of each carriage, and generate the corresponding fluctuation coefficient and Environmental Data Group The assessment management unit is set with a fixed range of fatigue thresholds and fluctuation threshold , combined with the fatigue coefficient , volatility coefficient and Environmental Data Group , assess the risk of lamp fatigue damage, the risk of electrical circuit failure, and the risk of lamp failure damage, and output corresponding management recommendations.

[0033] Compared with the prior art, the present invention provides a high-speed rail lighting fault prediction method and system, which has the following beneficial effects:

[0034] 1. The present invention connects the high-speed rail lighting system and the sensor device through a multi-dimensional acquisition module to obtain the management data of all lamps, the operation data of all electrical lines and the environmental sensor data of all carriages, and classifies them into lamp data sets, operation data sets and environmental data sets. The intelligent prediction module analyzes the usage status of each lamp based on the lamp data sets and generates the corresponding fatigue coefficient , directly reflects the working efficiency of the lamp. The higher the value, the faster the working efficiency of the lamp decreases. Set a fixed monitoring period and fixed range temperature thresholds , humidity threshold , frequency threshold , Amplitude Threshold , combined with the operation data set and the environmental data set, analyze the fluctuation trend of each electrical line and the environmental change trend of each carriage, and generate the corresponding fluctuation coefficient and Environmental Data Group , multi-dimensional analysis has high accuracy.

[0035] 2. The present invention sets a fixed-duration monitoring cycle through an intelligent prediction module and fixed range temperature thresholds , humidity threshold , frequency threshold , Amplitude Threshold , combined with the operation data set and the environmental data set, analyze the fluctuation trend of each electrical line and the environmental change trend of each carriage, and generate the corresponding fluctuation coefficient and Environmental Data Group , multi-dimensional analysis has high accuracy, and the assessment management unit sets a fixed range of fatigue thresholds and fluctuation threshold , combined with the fatigue coefficient , volatility coefficient and Environmental Data Group , assess the risk of lamp fatigue damage, the risk of electrical circuit failure, and the risk of lamp failure damage, and output corresponding management suggestions, with high efficiency of intelligent predictive management. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a step diagram of the method of the present invention;

[0037] Figure 2 Schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0039] Since traditional high-speed rail lighting fault prediction methods often rely on manual inspections and limited sensor data, the information collected is of a single dimension and the data foundation is not comprehensive enough, which easily leads to low accuracy of fault prediction results. Lighting failures may be caused by multiple faults such as short circuit, open circuit, leakage of electrical components, or the result of multiple factors such as mechanical structure damage and aging of optical components of lighting equipment. Only analyzing a single factor cannot fully consider the relationship and influence between various factors, and the prediction effect is not good in the face of complex faults. Therefore, a high-speed rail lighting fault prediction method and system are provided. Please refer to Figure 1-Figure 2 , a high-speed railway lighting fault prediction method, comprising the following steps:

[0040] Step 1: Connect the high-speed rail lighting system and sensor devices through the network to obtain the management data of all lamps, the operation data of all electrical lines and the environmental sensor data of all carriages, and classify them into lamp data sets, operation data sets and environmental data sets;

[0041] The expression of the lamp data set is , to Indicates the first to The management data of each lamp includes luminous flux, color temperature, power factor, cumulative working time, cumulative number of switches, cumulative number of faults, connection lines and car positions. Indicates the protection level of a single luminaire;

[0042] The expression for running the data set is , to Indicates the first to the The operating data of the electrical lines include voltage, current, cumulative fault times and car position. Indicates the total number of lamps connected to a single electrical circuit;

[0043] The expression of the environment dataset is , Indicates the temperature in a single compartment environment. Indicates the humidity in a single compartment environment. represents the vibration frequency of a single carriage, represents the vibration amplitude of a single carriage, Indicates the carriage number;

[0044] Step 2: Analyze the usage status of each lamp based on the lamp data set and generate the corresponding fatigue coefficient , the calculation process is as follows:

[0045] According to the lamp data set, extract the management data of each lamp, and The luminous flux of each lamp is marked as , will The color temperature of the lamp is marked as , will The power factor of each lamp is marked as , will The accumulated working time of each lamp is marked as , will The cumulative number of switching times of each lamp is marked as , will The cumulative number of failures of each lamp is marked as ;

[0046]

[0047] In the formula, Indicates the rated value of the luminous flux of the lamp. Represents the weight of the ratio of luminous flux to rated value, Indicates the rated value of the color temperature of the lamp. Indicates the absolute difference between the color temperature and the rated value. Represents the weight for the absolute difference in color temperature, Indicates the rated value of the lamp power factor. Represents the weight of the ratio of power factor to rated value, Indicates the switching frequency of the lamp, represents the weight for the switching frequency, Indicates the failure frequency of the lamp, represents the weight for the fault frequency, , , , and are constants, and , Indicates according to , , , and Weight, calculate the Fatigue coefficient of each lamp , fatigue coefficient It directly reflects the working efficiency of the lamp. The higher the value, the faster the working efficiency of the lamp decreases, and the planned maintenance reminder should be triggered in time.

[0048] Step 3: Set a fixed-duration monitoring cycle and fixed range temperature thresholds , humidity threshold , frequency threshold , Amplitude Threshold , combined with the operation data set and the environmental data set, analyze the fluctuation trend of each electrical line and the environmental change trend of each carriage, and generate the corresponding fluctuation coefficient and Environmental Data Group ;

[0049] Volatility The calculation process is as follows:

[0050] Extract monitoring cycles based on the running data set within, no. The operation data of electrical lines, among which The connection line of each lamp is electrical lines;

[0051] The first The voltage of the electrical circuit is marked , will The current of the electrical circuit is marked as , will The cumulative number of faults of the electrical lines is marked as , will The total number of lamps connected to the electrical circuit is marked as ;

[0052]

[0053] In the formula, Indicates monitoring cycle within, no. The voltage change of an electrical line, represents the weight for the voltage change, Indicates monitoring cycle within, no. The change in current in an electrical line, represents the weight for the current change, Represents the weight of the cumulative number of faults for electrical lines, Represents the weight of the total number of electrical circuit lamps, , , and are constants, and , Indicates according to , , and Weight, calculate the monitoring period within, no. The fluctuation coefficient of the electrical line , coefficient of fluctuation The higher the value, the worse the performance stability of the electrical circuit is, which is prone to overheating or short circuit risks, and emergency protection should be triggered in time;

[0054] Environmental Data Group The calculation process is as follows:

[0055] Extract monitoring cycles based on environmental data sets within, no. The environmental sensor data of the carriage, among which The carriage number of the carriage is , No. The lamp and The electrical lines are all installed in Inside the carriage;

[0056]

[0057] In the formula, and Indicates the temperature threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Temperature in the compartment environment versus temperature threshold , and Indicates humidity threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Humidity in the compartment environment vs. humidity threshold , and Indicates frequency threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Vibration frequency of the carriage compared to the frequency threshold , and Indicates the amplitude threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Vibration amplitude of the carriage compared to the amplitude threshold , Indicates monitoring cycle within, no. Environmental data set of the carriages. Abnormal environmental factors will have a negative impact on the performance of lamps, thus failing to ensure the safety and comfort of high-speed rail operations. When emergency lighting fails, it may hinder emergency evacuation, and lamp shedding may also cause secondary damage.

[0058] Step 4: Set a fixed range of fatigue thresholds and fluctuation threshold , combined with the fatigue coefficient , volatility coefficient and Environmental Data Group , assess the risk of lamp fatigue damage, the risk of electrical circuit failure, and the risk of lamp failure damage, fatigue coefficient Exceeding fatigue threshold When the lamp is at a high risk of fatigue damage, it is recommended to replace the aging lamps in time and perform preventive maintenance, which is conducive to advancing the fault detection time from "after-the-fact repair" to "several hours to several days before the fault". Exceeding the volatility threshold When the number of faults is high, it indicates that the risk of electrical line failure is high. It is recommended to conduct timely inspection and maintenance to reduce the cost of manual inspection and avoid passenger complaints or operational delays caused by lighting failure. When any value exceeds the threshold range, it means that the car environment changes drastically and the risk of lamp failure and damage is high. Timely inspection and maintenance are recommended to help managers quickly locate the cause of lamp damage.

[0059] A high-speed rail lighting fault prediction system, comprising a multi-dimensional acquisition module and an intelligent prediction module;

[0060] The multi-dimensional acquisition module consists of a lighting data unit, an electrical data unit, and an environmental data unit. The lighting data unit is connected to the high-speed rail lighting system through the network to collect lamp data sets, which include management data of all lamps. The electrical data unit is connected to the high-speed rail lighting system through the network to collect operation data sets, which include operation data of all electrical lines. The environmental data unit is connected to the sensor device through the network to collect environmental data sets, which include environmental sensor data of all carriages.

[0061] The intelligent prediction module consists of a fatigue analysis unit, a monitoring analysis unit, and an evaluation management unit. The fatigue analysis unit analyzes the usage status of each lamp based on the lamp data set and generates the corresponding fatigue coefficient. The monitoring and analysis unit is set with a fixed-length monitoring cycle. and fixed range temperature thresholds , humidity threshold , frequency threshold , Amplitude Threshold , combined with the operation data set and the environmental data set, analyze the fluctuation trend of each electrical line and the environmental change trend of each carriage, and generate the corresponding fluctuation coefficient and Environmental Data Group , multi-dimensional analysis has high accuracy, and the assessment management unit sets a fixed range of fatigue thresholds and fluctuation threshold , combined with the fatigue coefficient , volatility coefficient and Environmental Data Group , assess the risk of lamp fatigue damage, the risk of electrical circuit failure, and the risk of lamp failure damage, and output corresponding management suggestions, with high efficiency of intelligent predictive management.

[0062] Embodiment 1:

[0063] In this embodiment, the LED flat panel lamp on the top of the high-speed rail carriage is selected as the experimental object. After testing, the luminous flux of the lamp is 800 lumens, the color temperature is 3500K, the power factor is 0.5, the cumulative working time is 1000 hours, the cumulative number of switches is 100 times, the cumulative number of failures is 5 times, and the fatigue coefficient of the lamp is The calculation process is as follows:

[0064]

[0065]

[0066] In the formula, Indicates the rated value of the luminous flux of the lamp. Represents the weight of the ratio of luminous flux to rated value, Indicates the rated value of the color temperature of the lamp. Indicates the absolute difference between the color temperature and the rated value. Represents the weight for the absolute difference in color temperature, Indicates the rated value of the lamp power factor. Represents the weight of the ratio of power factor to rated value, Indicates the switching frequency of the lamp, represents the weight for the switching frequency, Indicates the failure frequency of the lamp, represents the weight for the fault frequency, , , , and are constants, and ,according to , , , and Weight, calculate the fatigue coefficient of the lamp for .

[0067] Embodiment 2:

[0068] In this embodiment, the electrical circuit connected to the luggage rack light in the high-speed rail carriage is selected as the experimental object. After testing, the voltage change of the electrical circuit is 5V, the current change is 2A, the cumulative number of failures is 3 times, the total number of connected lamps is 10, and the fluctuation coefficient of the electrical circuit is The calculation process is as follows:

[0069]

[0070]

[0071] In the formula, represents the weight for the voltage change, represents the weight for the current change, Represents the weight of the cumulative number of faults for electrical lines, Represents the weight of the total number of electrical circuit lamps, , , and are constants, and ,according to , , and Weight, calculate the fluctuation coefficient of the electrical line within one hour for .

[0072] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A high-speed railway lighting fault prediction method, characterized by: The following steps are involved: Step 1: Connect the high-speed rail lighting system and sensor devices through the network to obtain the management data of all lamps, the operation data of all electrical lines and the environmental sensor data of all carriages, and classify them into lamp data sets, operation data sets and environmental data sets; Step 2: Analyze the usage status of each lamp based on the lamp data set and generate the corresponding fatigue coefficient ; Step 3: Set a fixed-duration monitoring cycle and fixed range temperature thresholds , humidity threshold , frequency threshold , Amplitude Threshold , combined with the operation data set and the environmental data set, analyze the fluctuation trend of each electrical line and the environmental change trend of each carriage, and generate the corresponding fluctuation coefficient and Environmental Data Group ; Step 4: Set a fixed range of fatigue thresholds and fluctuation threshold , combined with the fatigue coefficient , volatility coefficient and Environmental Data Group , assess the risk of lamp fatigue damage, the risk of electrical circuit failure, and the risk of lamp failure damage, and output corresponding management recommendations.

2. A high-speed railway lighting fault prediction method according to claim 1, characterized in that: In step 1, the expression of the lamp data set is: , to Indicates the first to The management data of each lamp includes luminous flux, color temperature, power factor, cumulative working time, cumulative number of switches, cumulative number of faults, connection lines and car positions. Indicates the protection level of a single luminaire.

3. A high-speed railway lighting fault prediction method according to claim 2, characterized in that: In step 1, the expression for running the data set is: , to Indicates the first to the The operating data of the electrical lines include voltage, current, cumulative fault times and car position. Indicates the total number of lamps connected to a single electrical circuit.

4. A high-speed railway lighting fault prediction method according to claim 3, characterized in that: In step 1, the expression of the environmental data set is: , Indicates the temperature in a single compartment environment. Indicates the humidity in a single compartment environment. represents the vibration frequency of a single carriage, represents the vibration amplitude of a single carriage, Indicates the car number.

5. A high-speed railway lighting fault prediction method according to claim 4, characterized in that: In the step 2, the fatigue coefficient The calculation process is as follows: According to the lamp data set, extract the management data of each lamp, and The luminous flux of a lamp is marked as , will The color temperature of the lamp is marked as , will The power factor of each lamp is marked as , will The accumulated working time of each lamp is marked as , will The cumulative number of switching times of each lamp is marked as , will The cumulative number of failures of each lamp is marked as ; In the formula, Indicates the rated value of the luminous flux of the lamp. Represents the weight of the ratio of luminous flux to rated value, Indicates the rated value of the color temperature of the lamp. Indicates the absolute difference between the color temperature and the rated value. Represents the weight for the absolute difference in color temperature, Indicates the rated value of the lamp power factor. Represents the weight of the ratio of power factor to rated value, Indicates the switching frequency of the lamp, represents the weight for the switching frequency, Indicates the failure frequency of the lamp, represents the weight for the fault frequency, , , , and are constants, and , Indicates according to , , , and Weight, calculate the Fatigue coefficient of each lamp .

6. A high-speed railway lighting fault prediction method according to claim 5, characterized in that: In step 3, the coefficient of fluctuation The calculation process is as follows: Extract monitoring cycles based on the running data set within, no. The operation data of electrical lines, among which The connection line of each lamp is electrical lines; The first The voltage of the electrical circuit is marked , will The current of the electrical circuit is marked as , will The cumulative number of faults of the electrical lines is marked as , will The total number of lamps connected to the electrical circuit is marked as ; In the formula, Indicates monitoring cycle within, no. The voltage change of an electrical line, represents the weight for the voltage change, Indicates monitoring cycle within, no. The change in current in an electrical line, represents the weight for the current change, Represents the weight of the cumulative number of faults for electrical lines, Represents the weight of the total number of electrical circuit lamps, , , and are constants, and , Indicates according to , , and Weight, calculate the monitoring period within, no. The fluctuation coefficient of the electrical line .

7. A high-speed railway lighting fault prediction method according to claim 6, characterized in that: In step 3, the environmental data set The calculation process is as follows: Extract monitoring cycles based on environmental data sets within, no. The environmental sensor data of the carriage, among which The carriage number of the carriage is , No. The lamp and The electrical lines are all installed in Inside the carriage; In the formula, and Indicates the temperature threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Temperature in the compartment environment versus temperature threshold , and Indicates humidity threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Humidity in the compartment environment vs. humidity threshold , and Indicates frequency threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Vibration frequency of the carriage compared to the frequency threshold , and Indicates the amplitude threshold The minimum and maximum values ​​in Indicates that the monitoring cycle within, no. Vibration amplitude of the carriage compared to the amplitude threshold , Indicates monitoring cycle within, no. Environmental data set for the carriage.

8. A high-speed railway lighting fault prediction method according to claim 7, characterized in that: Step 4: Fatigue coefficient Exceeding fatigue threshold , it indicates that the risk of lamp fatigue damage is high, and it is recommended to replace the aging lamp in time.

9. A high-speed railway lighting fault prediction method according to claim 8, characterized in that: Step 4: Fluctuation coefficient Exceeding the volatility threshold When the risk of electrical line failure is high, it is recommended to conduct inspection and maintenance in time. When any value exceeds the threshold range, it means that the car environment changes drastically and the risk of lamp failure and damage is high. Timely inspection and maintenance are recommended.

10. A high-speed railway lighting fault prediction system, applied to a high-speed railway lighting fault prediction method as claimed in any one of claims 1 to 9, characterized in that: Including multi-dimensional acquisition module and intelligent prediction module; The multi-dimensional acquisition module is composed of a lighting data unit, an electrical data unit and an environmental data unit. The lighting data unit is connected to the high-speed rail lighting system through a network to collect a lamp data set, and the lamp data set includes management data of all lamps. The electrical data unit is connected to the high-speed rail lighting system through a network to collect an operation data set, and the operation data set includes operation data of all electrical lines. The environmental data unit is connected to the sensor device through a network to collect an environmental data set, and the environmental data set includes environmental sensor data of all carriages. The intelligent prediction module consists of a fatigue analysis unit, a monitoring analysis unit and an evaluation management unit. The fatigue analysis unit analyzes the usage status of each lamp according to the lamp data set and generates a corresponding fatigue coefficient. The monitoring and analysis unit is provided with a monitoring cycle of fixed duration. and fixed range temperature thresholds , humidity threshold , frequency threshold , Amplitude Threshold , combined with the operation data set and the environmental data set, analyze the fluctuation trend of each electrical line and the environmental change trend of each carriage, and generate the corresponding fluctuation coefficient and Environmental Data Group The assessment management unit is set with a fixed range of fatigue thresholds and fluctuation threshold , combined with the fatigue coefficient , volatility coefficient and Environmental Data Group , assess the risk of lamp fatigue damage, the risk of electrical circuit failure, and the risk of lamp failure damage, and output corresponding management recommendations.

Images