High-speed rail pantograph infrared thermal image intelligent monitoring system

Abstract

The invention discloses a high-speed rail pantograph infrared thermal image intelligent monitoring system, which relates to the technical field of intelligent monitoring, and comprises the following steps: determining a monitoring target and carrying out data acquisition to obtain infrared thermal image data; performing heat map analysis and anomaly detection according to the infrared thermal image data to obtain a heat map analysis result; generating a fault early warning model by using a machine learning algorithm according to a heat map analysis result; performing real-time fault diagnosis and decision support according to the fault early warning model to obtain a fault diagnosis result; generating a system optimization and maintenance suggestion according to the fault diagnosis result; performing equipment maintenance and performance improvement according to the system optimization and maintenance suggestion to obtain a maintenance result; and performing long-term monitoring and intelligent decision making according to a maintenance result. According to the efficiency of the genetic algorithm in multi-objective optimization, the accuracy of equipment fault early warning and the rationality of a maintenance strategy are improved, the operation efficiency and safety of equipment are improved, and long-term stable operation of the high-speed rail pantograph is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to an infrared thermal imaging intelligent monitoring system for a high-speed railway pantograph. Background Art

[0002] The high-speed railway pantograph is a key component in the high-speed railway power supply system. Its main function is to provide power supply through contact with the overhead line. Since the pantograph needs to operate under high speed, high voltage, vibration and complex environmental conditions, the health monitoring and fault warning of its operating status are particularly important. Traditional pantograph fault diagnosis mostly relies on manual inspections and detection methods based on single parameters. These methods are not only inefficient, but also difficult to accurately warn in complex environments.

[0003] With the development of technology, infrared thermal imaging technology has gradually become an important means of pantograph fault monitoring due to its non-contact, high-efficiency and real-time characteristics. Through infrared thermal imaging technology, the temperature distribution of the pantograph can be monitored in real time, and abnormal heating points that may exist can be detected, which provides valuable information for fault warning. However, relying solely on infrared thermal image analysis still has certain limitations, especially in the face of complex pantograph operating environments (such as temperature, humidity, vibration and other factors). How to accurately determine the risk of equipment failure and reasonably arrange maintenance strategies are still problems that need to be solved in current technology.

[0004] 1. In the prior art, genetic algorithms have limitations in multi-objective optimization: genetic algorithms usually require a large amount of computing resources for global optimization, and when faced with complex environmental factors (such as temperature, humidity, vibration, etc.), the optimization process may be difficult to find the global optimal solution within a reasonable time. In addition, the search process of genetic algorithms may easily fall into local optimality, resulting in the final maintenance strategy being unable to adapt to changes in the dynamic environment in some cases.

[0005] 2. In existing technologies, reinforcement learning has shortcomings in real-time adjustment: Traditional RL methods may find it difficult to make effective decisions in real time in large-scale state spaces, especially when faced with multiple objective optimizations such as equipment failure risk, energy efficiency requirements, and maintenance costs. How to balance these objectives and quickly adapt to the changing environment remains a problem that needs to be solved. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a high-speed railway pantograph infrared thermal imaging intelligent monitoring system to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides a high-speed railway pantograph infrared thermal imaging intelligent monitoring system, comprising the following steps: S1. Determine the monitoring target and collect data to obtain infrared thermal imaging data; S2. Perform thermal map analysis and anomaly detection based on infrared thermal imaging data to obtain thermal map analysis results; S3. Generate a fault warning model using a machine learning algorithm based on the heat map analysis results; S4. Perform real-time fault diagnosis and decision support based on the fault warning model to obtain fault diagnosis results; S5. Generate system optimization and maintenance suggestions based on fault diagnosis results; S6. Perform equipment maintenance and performance improvement according to system optimization and maintenance suggestions to obtain maintenance results; S7. Conduct long-term monitoring and intelligent decision-making based on maintenance results.

[0008] To further optimize the technical solution, the determining of monitoring targets and data collection in S1 includes: Analyze the working environment, operation mechanism and failure mode of the equipment, determine the objectives of the monitoring system, use infrared thermal imaging technology, conduct real-time temperature monitoring, and collect infrared thermal imaging data.

[0009] To further optimize the technical solution, the heat map analysis and anomaly detection in S2 include: Image processing technology is used to process and analyze infrared thermal imaging data, identify temperature changes in the pantograph area, and detect potential abnormal hotspots, fault risks, and fault types.

[0010] To further optimize the technical solution, the real-time fault diagnosis and decision support in S4 includes: By using the fault warning model and combining multiple data sources to perform multi-dimensional fault diagnosis, the potential fault types of the equipment can be identified and maintenance plans can be given.

[0011] To further optimize the technical solution, the system optimization and maintenance suggestion generation in S5 includes: Genetic algorithms are used to analyze equipment failure types, historical maintenance records, and operating data to generate system optimization and maintenance recommendations, which are continuously optimized through a feedback mechanism.

[0012] To further optimize the technical solution, the genetic algorithm includes: Fitness function: ; in: : , indicating equipment parameters, including voltage and maintenance interval; : , represents environmental factors, including temperature, humidity, and vibration frequency; : The kth objective function, including failure risk, energy efficiency, and maintenance cost functions; : Weight coefficient, set according to actual conditions; : The fitness of the maintenance strategy; Genetic Operations: Selection: Select the maintenance strategy with the highest fitness based on the function; Crossover: Crossover two different maintenance strategies to create a new generation strategy; Mutation: Explore new maintenance strategies through small random changes.

[0013] To further optimize this technical solution, the equipment maintenance and performance improvement in S6 include: Reinforcement learning technology is used to adjust the control strategy in real time according to system optimization and maintenance suggestions and equipment status, and continuous optimization is achieved through real-time feedback to ensure long-term and stable operation of the equipment.

[0014] To further optimize this technical solution, the reinforcement learning technology includes: Reward function: ; in: : State space , including equipment parameters and environmental factors; : Action Space , is the i-th action, including current regulation, temperature control, and vibration regulation; : Failure risk function, the lower the failure probability, the smaller the failure probability; :Equipment energy efficiency is improved, which is obtained based on the difference before and after optimization; : Changes in equipment maintenance costs, obtained based on the difference before and after optimization; : Weight coefficient, set according to actual situation; Q value update formula: Find the optimal strategy based on the maximum Q value; ; in: : Current state and actions taken; : Reward function, when performing actions Get Status Immediate rewards after : Discount factor, which indicates the degree of reward attenuation and is set according to actual conditions; : Learning rate, controls the learning speed and is set according to actual conditions; : The maximum Q value among all actions in the next state.

[0015] To further optimize this technical solution, the long-term monitoring and intelligent decision-making in S7 include: In long-term operation, the working status of the pantograph can be monitored in real time, intelligent decisions can be made based on historical data, the maintenance cycle, warning threshold and resource allocation of the equipment can be automatically adjusted, and deep reinforcement learning technology can be used to continuously optimize and adjust the decisions.

[0016] To further optimize this technical solution, the functional modules of the high-speed railway pantograph infrared thermal imaging intelligent monitoring system include: Thermal image acquisition module; data analysis and processing module; fault warning module; suggestion generation module; equipment maintenance module; monitoring and intelligent decision-making module.

[0017] In a second aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of a high-speed railway pantograph infrared thermal imaging intelligent monitoring system as described in the first aspect of the present invention are implemented.

[0018] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of a high-speed railway pantograph infrared thermal imaging intelligent monitoring system as described in the first aspect of the present invention are implemented.

[0019] Compared with the prior art, the present invention provides a high-speed railway pantograph infrared thermal imaging intelligent monitoring system, which has the following beneficial effects: The high-speed railway pantograph infrared thermal imaging intelligent monitoring system combines the fault risk function with environmental factors and introduces a dynamic adjustment mechanism based on environmental changes, so that the genetic algorithm can provide a global optimization solution more accurately in a dynamic and complex environment in multi-objective optimization, thereby improving the efficiency of multi-objective optimization.

[0020] Genetic algorithms can also update equipment maintenance strategies in real time through a dynamic feedback mechanism, thereby avoiding local optimal problems in complex environments, improving the accuracy of equipment failure warnings, and the rationality of maintenance strategies.

[0021] Combining genetic algorithms and deep reinforcement learning, through comprehensive analysis of multiple factors such as equipment operating status, environmental data and maintenance costs, this system can quickly respond to environmental changes in real-time adjustments and adaptively optimize the operating status of the equipment, thereby improving the operating efficiency and safety of the equipment and ensuring the long-term stable operation of the high-speed rail pantograph. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic diagram of the process of a high-speed railway pantograph infrared thermal imaging intelligent monitoring system proposed by the present invention; Figure 2 A schematic diagram of the flow of a genetic algorithm for a high-speed railway pantograph infrared thermal imaging intelligent monitoring system proposed by the present invention; Figure 3 A schematic diagram of the flow of a reinforcement learning algorithm for a high-speed railway pantograph infrared thermal imaging intelligent monitoring system proposed by the present invention; Figure 4 A schematic diagram of the process flow of a deep reinforcement learning algorithm for a high-speed railway pantograph infrared thermal imaging intelligent monitoring system proposed by the present invention; Figure 5 This is a module schematic diagram of a high-speed railway pantograph infrared thermal imaging intelligent monitoring system proposed by the present invention. DETAILED DESCRIPTION

[0024] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0025] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0026] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0027] Embodiment 1: Reference Figure 1 to Figure 4 , which is the first embodiment of the present invention, provides a high-speed railway pantograph infrared thermal imaging intelligent monitoring system, comprising the following steps: S1. Determine the monitoring target and collect data to obtain infrared thermal imaging data.

[0028] In this embodiment, determining the monitoring target and collecting data includes: Analyze the working environment, operation mechanism and possible failure modes of the high-speed rail pantograph, and determine the goals of the monitoring system, including: real-time monitoring of the contact between the pantograph and the contact network, local hot spots, temperature rise trends of the equipment and abnormal temperature changes, and use infrared thermal imaging technology to monitor the temperature of the pantograph area in real time through a high-resolution infrared thermal imager to collect infrared thermal imaging data. The infrared thermal imager will be installed in a fixed position to ensure coverage of all working areas of the pantograph. The system needs to consider the accuracy, resolution, high temperature resistance and vibration resistance of the instrument to ensure its stable operation in the complex environment of the high-speed rail. In addition, the acquisition module should also have an automatic calibration function to ensure continuous and accurate data collection and analysis.

[0029] S2. Perform thermal map analysis and anomaly detection based on the infrared thermal imaging data to obtain thermal map analysis results.

[0030] In this embodiment, heat map analysis and anomaly detection include: Image processing technology is used to process and analyze infrared thermal imaging data to identify temperature changes in the pantograph area and detect potential abnormal hot spots, fault risks and fault types. Image processing algorithms can detect temperature gradients in thermal imaging images and identify abnormal areas (such as local overheating). By analyzing the temperature change trends in the thermal map, the system can determine whether there is poor contact, equipment damage or other fault risks. This process will combine historical data to analyze the patterns of different temperature changes to identify potential fault types. For example, local overheating may indicate poor contact between the overhead contact and the pantograph or an electrical fault inside the equipment. In this step, the system needs to have efficient and real-time image processing capabilities to quickly respond to temperature changes in high-speed rail operation and ensure that any possible equipment failures are detected in a timely manner.

[0031] S3. Based on the heat map analysis results, a fault warning model is generated using a machine learning algorithm.

[0032] In this embodiment, a support vector machine (SVM) is used to learn historical thermal imaging data and establish an equipment failure warning model. By classifying different temperature change patterns, SVM can identify and classify each type of abnormal temperature change, thereby predicting potential failure risks. The fault warning model outputs a real-time warning signal to determine whether there is a failure risk based on the temperature change and historical operating data of the equipment. For example, a continuous temperature increase may indicate an electrical component failure or mechanical wear. The output of the model will help operators take timely measures to prevent failures. In order to improve the accuracy of the model, the system will conduct multiple training and verifications to optimize the warning model and reduce the false alarm rate. Ultimately, the warning model will be able to issue an alarm in advance before the equipment becomes abnormal, thereby effectively reducing the risks in high-speed rail operation.

[0033] S4. Perform real-time fault diagnosis and decision support based on the fault warning model to obtain fault diagnosis results.

[0034] In this embodiment, real-time fault diagnosis and decision support include: By using the fault warning model and combining multiple data sources (such as temperature, vibration, current, etc.) to perform multi-dimensional fault diagnosis, the potential fault types of the equipment can be identified and maintenance plans can be given, so as to identify potential faults in high-speed rail operation in advance, provide timely and effective maintenance decision support, prevent the expansion of faults, and ensure the safety and normal operation of high-speed rail.

[0035] S5. Generate system optimization and maintenance suggestions based on fault diagnosis results.

[0036] In this embodiment, the system optimization and maintenance suggestion generation includes: Genetic algorithms are used to analyze equipment failure types, historical maintenance records, and operating data to generate system optimization and maintenance recommendations, which are continuously optimized through feedback mechanisms. For example, genetic algorithms can recommend optimizing contact pressure, adjusting heat dissipation equipment, or regularly testing electrical components based on the specific failure type of the pantograph. Through intelligent maintenance strategies, the system can reduce the frequency of failures, extend the service life of equipment, and improve operating efficiency.

[0037] Furthermore, the genetic algorithm comprises: Fitness function: ; in: : , indicating equipment parameters, including voltage and maintenance interval; : , represents environmental factors, including temperature, humidity, and vibration frequency; : The kth objective function, including failure risk, energy efficiency, and maintenance cost functions; : Weight coefficient, set according to actual situation; : The fitness of the maintenance strategy, the higher the fitness, the better the strategy; Specifically define the following objective function: Failure risk function: This function evaluates the probability of equipment failure under different maintenance strategies; ; in, are the temperature and voltage parameters of the ith maintenance strategy, is the maximum allowable temperature and optimal voltage of the device, is a constant that controls the tolerance of temperature and voltage, is the weight coefficient. This objective function calculates the risk of equipment failure under a given maintenance plan. The probability of failure increases as the equipment temperature and voltage deviate from the optimal value. Energy efficiency function: This function evaluates the energy consumption of the equipment under different maintenance strategies, with the goal of minimizing the energy consumption of the equipment; ; in, are the ambient temperature and the vibration frequency, is the energy efficiency coefficient, which indicates the impact of different factors on energy efficiency; Maintenance cost function: This function evaluates the total cost of maintenance decisions, including labor costs, equipment repair costs, etc. The goal is to minimize the economic cost of maintenance; ; in, is the cost coefficient of the maintenance decision, is the execution strength of the maintenance decision, is the influence coefficient of ambient humidity on the equipment; Genetic Operations: Selection: Select the maintenance strategy with the highest fitness based on the function; Crossover: Crossover two different maintenance strategies to create a new generation strategy; Mutation: Explore new maintenance strategies through small random changes.

[0038] Genetic Algorithm uses: Initialize the population: First, generate the initial population based on the initial maintenance status of the equipment (such as temperature, current, etc.) and environmental factors (such as temperature, humidity, vibration, etc.).

[0039] Calculate fitness: Use the fitness function above to calculate the fitness of each individual (maintenance scheme).

[0040] Selection, crossover, and mutation: Perform genetic operations to generate new maintenance strategies.

[0041] Set termination conditions: When the fitness function reaches the preset threshold, or the evolution reaches a certain number of generations, the algorithm stops and outputs the best maintenance strategy.

[0042] Through this optimization process, the genetic algorithm can adaptively optimize the equipment maintenance cycle and strategy in a dynamically changing environment and complex equipment failure modes to ensure the long-term stable operation of the equipment.

[0043] S6. Perform equipment maintenance and performance improvement according to system optimization and maintenance recommendations to obtain maintenance results.

[0044] In this embodiment, equipment maintenance and performance improvement include: Reinforcement learning technology is used to adjust the control strategy in real time according to system optimization and maintenance suggestions and equipment status, and continuous optimization is achieved through real-time feedback to ensure long-term stable operation of the equipment. In actual operation, the system simulates different maintenance plans, automatically selects the most appropriate operation strategy, and continuously optimizes through feedback mechanisms. For example, the system can adjust the current output or the contact angle between the pantograph and the contact network according to real-time temperature and pressure data, thereby reducing the risk of failure. Reinforcement learning can adapt to changes in the high-speed rail operating environment in real time, and continuously optimize the maintenance effect in actual applications, improving the system's adaptive ability and decision-making efficiency.

[0045] Furthermore, the reinforcement learning technology includes: Reward function: ; in: : State space , including equipment parameters and environmental factors; : Action Space , is the i-th action, including current regulation, temperature control, and vibration regulation; : Failure risk function, the lower the failure probability, the smaller the failure probability; :Equipment energy efficiency is improved, which is obtained based on the difference before and after optimization; : Changes in equipment maintenance costs, obtained based on the difference before and after optimization; : Weight coefficient, set according to actual situation; Q value update formula: Find the optimal strategy based on the maximum Q value; ; in: : Current state and actions taken; : Reward function, when performing actions Get Status Immediate rewards after : Discount factor, which indicates the degree of reward attenuation and is set according to actual conditions; : Learning rate, controls the learning speed and is set according to actual conditions; : The maximum Q value among all actions in the next state.

[0046] Steps: Initialize the Q value table: Initialize the Q value of all state-action pairs. The initial value can be set to zero or initialized according to the genetic algorithm optimization scheme.

[0047] Action selection: Based on the current state and Q-value table, an action is selected using the ε-greedy strategy, that is, the optimal action is selected with a certain probability (greedy), and the remaining probability is selected as a random action (exploration).

[0048] Execute actions and get rewards: After selecting an action, the reward is calculated based on the device's operation and environmental feedback.

[0049] Update Q-value: Update the Q-value of the state-action pair according to the Q-value update formula of Q-learning.

[0050] Repeat iteration: Repeat the above steps until the Q value converges and the optimal device operation strategy is found.

[0051] S7. Conduct long-term monitoring and intelligent decision-making based on maintenance results.

[0052] In this embodiment, long-term monitoring and intelligent decision-making include: In long-term operation, the system monitors the working status of the pantograph in real time, makes intelligent decisions based on historical data, automatically adjusts the equipment maintenance cycle, warning threshold and resource allocation, and uses deep reinforcement learning technology to continuously optimize and adjust decisions. Through this intelligent long-term monitoring and decision-making, the system can not only effectively increase the service life of the equipment, but also continuously optimize during the operation of the high-speed rail, reduce the frequency of failures, and ensure the safety and efficient operation of the high-speed rail.

[0053] Deep reinforcement learning technology: Use deep neural networks to approximate the Q-value function to cope with more complex state spaces and high-dimensional problems; Deep Q-value function: : State space , including equipment parameters and environmental factors; : Action Space , is the i-th action, including current regulation, temperature control, and vibration regulation; Defining the deep Q-value function As the device is in state Take action The expected return after are the weights of the neural network: ; in, It is a deep neural network, and the input of the network is a state-action pair , the output is Q value; Reward function: Same as the reward function in reinforcement learning: ; Q value update and deep learning training: ; in, is the Q value output by the current neural network, is the parameter of the target network, used to calculate the target Q value, is the learning rate, which controls the learning speed and is set according to the actual situation. is the discount factor, which indicates the degree of reward attenuation and is set according to actual conditions. is the reward function, is the maximum Q value of the target network in the next state; Through this updating method, the deep neural network gradually approaches the optimal Q value, so that it can choose the best action in a given state; Steps: Initialize network parameters: Initialize deep neural network and target network , and set relevant parameters (such as learning rate , Discount Factor wait).

[0054] State and action sampling: Get the current state from the environment , and select an action according to the ε-greedy strategy, that is, the optimal action is selected with a certain probability (greedy), and the remaining probabilities are randomly explored.

[0055] Perform actions and get rewards: Perform the selected actions and get rewards based on device operation and environmental feedback.

[0056] Update Q value: Use the deep Q value update formula to adjust the weights of the current network, calculate the new Q value, and update the parameters of the target network.

[0057] Repeated iteration: Through multiple iterations, the deep neural network can continue to learn and gradually approach the optimal strategy.

[0058] Embodiment 2: Reference Figure 5 , which is the second embodiment of the present invention, and provides a high-speed railway pantograph infrared thermal imaging intelligent monitoring system, including the following functional modules: Thermal imaging acquisition module: used to collect thermal imaging data in real time; Data analysis and processing module: used to analyze and process the collected infrared thermal imaging data through image processing technology; Fault warning module: used to predict potential fault risks, output real-time warning signals, and issue alarms before equipment abnormalities occur; Suggestion generation module: used to provide maintenance personnel with repair suggestions based on specific fault types and continuously optimize maintenance strategies based on the actual performance of the equipment; Equipment maintenance module: used to adjust its working strategy according to the equipment status and real-time feedback to ensure the long-term stable operation of the equipment; Monitoring and intelligent decision-making module: used for long-term monitoring of equipment and making intelligent decisions based on historical data, automatically adjusting the equipment's maintenance cycle, warning thresholds, and resource allocation to ensure the stability and safety of the equipment in the long-term operation of high-speed rail.

[0059] Embodiment three: This embodiment also provides a computer device, which is suitable for a high-speed railway pantograph infrared thermal imaging intelligent monitoring system, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a high-speed railway pantograph infrared thermal imaging intelligent monitoring system as proposed in the above embodiment.

[0060] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, an infrared thermal imaging intelligent monitoring system for high-speed railway pantographs as proposed in the above embodiment is implemented.

[0061] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0062] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0063] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0064] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0065] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0066] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A high-speed railway pantograph infrared thermal imaging intelligent monitoring system, characterized in that: The following steps are involved: S1. Determine the monitoring target and collect data to obtain infrared thermal imaging data; S2. Perform thermal map analysis and anomaly detection based on infrared thermal imaging data to obtain thermal map analysis results; S3. Generate a fault warning model using a machine learning algorithm based on the heat map analysis results; S4. Perform real-time fault diagnosis and decision support based on the fault warning model to obtain fault diagnosis results; S5. Generate system optimization and maintenance suggestions based on fault diagnosis results; S6. Perform equipment maintenance and performance improvement according to system optimization and maintenance suggestions to obtain maintenance results; S7. Conduct long-term monitoring and intelligent decision-making based on maintenance results.

2. According to claim 1, a high-speed railway pantograph infrared thermal imaging intelligent monitoring system is characterized in that: Determining the monitoring target and collecting data in S1 includes: Analyze the working environment, operation mechanism and failure mode of the equipment, determine the objectives of the monitoring system, use infrared thermal imaging technology, conduct real-time temperature monitoring, and collect infrared thermal imaging data.

3. According to claim 1, a high-speed railway pantograph infrared thermal imaging intelligent monitoring system is characterized in that: The heat map analysis and anomaly detection in S2 include: Image processing technology is used to process and analyze infrared thermal imaging data, identify temperature changes in the pantograph area, and detect potential abnormal hotspots, fault risks, and fault types.

4. The high-speed railway pantograph infrared thermal imaging intelligent monitoring system according to claim 1 is characterized in that: The real-time fault diagnosis and decision support in S4 includes: By using the fault warning model and combining multiple data sources to perform multi-dimensional fault diagnosis, the potential fault types of the equipment can be identified and maintenance plans can be given.

5. The high-speed railway pantograph infrared thermal imaging intelligent monitoring system according to claim 1 is characterized in that: The system optimization and maintenance suggestion generation in S5 includes: Genetic algorithms are used to analyze equipment failure types, historical maintenance records, and operating data to generate system optimization and maintenance recommendations, which are continuously optimized through a feedback mechanism.

6. The high-speed railway pantograph infrared thermal imaging intelligent monitoring system according to claim 5 is characterized in that: The genetic algorithm comprises: Fitness function: ； in: : , indicating equipment parameters, including voltage and maintenance interval; : , represents environmental factors, including temperature, humidity, and vibration frequency; : The kth objective function, including failure risk, energy efficiency, and maintenance cost functions; : Weight coefficient, set according to actual conditions; : The fitness of the maintenance strategy, the higher the fitness, the better the strategy; Genetic Operations: Selection: Select the maintenance strategy with the highest fitness based on the function; Crossover: Crossover two different maintenance strategies to create a new generation strategy; Mutation: Explore new maintenance strategies through small random changes.

7. The high-speed railway pantograph infrared thermal imaging intelligent monitoring system according to claim 1 is characterized in that: The equipment maintenance and performance improvement in S6 include: Reinforcement learning technology is used to adjust the control strategy in real time according to system optimization and maintenance suggestions and equipment status, and continuous optimization is achieved through real-time feedback to ensure long-term and stable operation of the equipment.

8. The high-speed railway pantograph infrared thermal imaging intelligent monitoring system according to claim 7 is characterized in that: The reinforcement learning technology includes: Reward function: ； in: : State space , including equipment parameters and environmental factors; : Action Space , is the i-th action, including current regulation, temperature control, and vibration regulation; : Failure risk function, the lower the failure probability, the smaller the failure probability; :Equipment energy efficiency is improved, which is obtained based on the difference before and after optimization; : Changes in equipment maintenance costs, obtained based on the difference before and after optimization; : Weight coefficient, set according to actual conditions; Q value update formula: Find the optimal strategy based on the maximum Q value; ； in: : Current state and actions taken; : Reward function, when performing actions Get Status Immediate rewards after : Discount factor, which indicates the degree of reward attenuation and is set according to actual conditions; : Learning rate, controls the learning speed and is set according to actual conditions; : The maximum Q value among all actions in the next state.

9. The high-speed railway pantograph infrared thermal imaging intelligent monitoring system according to claim 1 is characterized in that: The long-term monitoring and intelligent decision-making in S7 include: In long-term operation, the working status of the pantograph can be monitored in real time, intelligent decisions can be made based on historical data, the maintenance cycle, warning threshold and resource allocation of the equipment can be automatically adjusted, and deep reinforcement learning technology can be used to continuously optimize and adjust the decisions.

10. The high-speed railway pantograph infrared thermal imaging intelligent monitoring system according to claim 1 is characterized in that: The functional modules of the high-speed railway pantograph infrared thermal imaging intelligent monitoring system include: Thermal image acquisition module; data analysis and processing module; fault warning module; suggestion generation module; equipment maintenance module; monitoring and intelligent decision-making module.

Images