Railway annunciator operation state health assessment method, device, equipment and medium

Abstract

The embodiment of the invention relates to the field of railway signal equipment health monitoring, and discloses a railway signal machine operation state health assessment method, device and equipment and a medium, and the method comprises the steps: receiving the monitoring data of a railway signal machine in real time; performing data processing on the received monitoring data of the railway annunciator to obtain key feature data capable of reflecting the operation condition and the health condition of the railway annunciator; inputting the obtained key feature data into a pre-constructed railway signal machine operation health assessment model to obtain an output result of the model, the output result of the model being an assessment score corresponding to each preset health level; and according to an output result of the model, determining the health level with the maximum evaluation score as a final operation health evaluation result of the railway annunciator. According to the invention, the application state health of the railway annunciator can be automatically and accurately evaluated.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of railway signal equipment health monitoring, and in particular to a railway signal equipment operating status health assessment method, device, equipment and medium. Background Art

[0002] Railway signal machines are important components of the railway transportation system, and their operating health is directly related to the safety and efficiency of railway operations. However, railway signal machines are easily affected by various outdoor factors. Their operating health is not only related to the status of the railway signal machines themselves, but also affected by many uncertain factors such as outdoor and indoor factors. At present, the operation and maintenance mode of signal machines is still mainly planned maintenance and fault repair. Planned maintenance requires the formulation of maintenance plans every year, which increases maintenance costs, while fault repair affects transportation safety and railway service quality.

[0003] In order to better ensure the stable and efficient operation of railways, there is an urgent need for a method that can perform near real-time or even real-time health assessment of the operating status of railway signal machines. Summary of the invention

[0004] The object of the present invention is to provide at least a method, device, equipment and medium for evaluating the health of railway signal operation status.

[0005] In order to solve the above-mentioned current railway signal machine technical problems, at least one embodiment of the present application further provides a railway signal machine operation status health assessment method, comprising:

[0006] Receive monitoring data of railway signal machines in real time, wherein the monitoring data includes operation data, environmental factor data and historical fault records of the railway signal machines;

[0007] Processing the received monitoring data of the railway signal to obtain key characteristic data that can reflect the operating status and health status of the railway signal;

[0008] Inputting the obtained key feature data into a pre-built railway signal operation health assessment model to obtain an output result of the model, wherein the output result of the model is an assessment score corresponding to each preset health level;

[0009] According to the output result of the model, the health level with the largest evaluation score is determined as the final operation health evaluation result of the railway signal.

[0010] In some optional embodiments, constructing the railway signal operation status health assessment model includes:

[0011] Build a GRU neural network model;

[0012] Acquire historical monitoring data of railway signal machines, wherein the historical monitoring data includes operation data, environmental factor data and historical fault records of railway signal machines;

[0013] Processing the acquired historical monitoring data of the railway signal to obtain key characteristic data that can reflect the operating status and health status of the railway signal;

[0014] The GRU neural network model is trained based on the key feature data, and the trained GRU neural network model is used as the railway signal operation health assessment model.

[0015] In some optional embodiments, the model structure of the GRU neural network model includes an input layer, two GRU layers, two fully connected layers and an output layer.

[0016] In some optional embodiments, the data processing of the received monitoring data of the railway signal to obtain key characteristic data that can reflect the operating status and health status of the railway signal includes:

[0017] Performing data preprocessing on the monitoring data of the railway signal;

[0018] Extracting features from the monitoring data of the railway signal after data preprocessing to obtain key feature data that can reflect the operating status and health status of the railway signal;

[0019] The extracted key features are screened using a feature selection algorithm to remove redundant features and irrelevant features in the key features to obtain final key feature data.

[0020] In some optional embodiments, the key feature data include the development frequency of the railway signal, the cumulative number of current alarms, the cumulative number of voltage alarms, the cumulative number of lumen alarms and the cumulative number of maintenance times of various maintenance levels, as well as the time when the railway signal is officially put into use and the life time of the railway signal issued by the manufacturer.

[0021] In some optional embodiments, the real-time receiving of monitoring data of a railway signal machine includes:

[0022] The monitoring data of the railway signal machine is received in real time through a message queue, wherein the ID number of each railway signal machine is used as the key value of the message queue, and the monitoring data of the railway signal machine is used as the value of the message queue.

[0023] In some optional embodiments, the method for evaluating the operating status of a railway signal machine further includes: setting a unique timestamp for each piece of monitoring data of the railway signal machine received by the message queue.

[0024] At least one embodiment of the present application further provides a railway signal operation status health assessment device, comprising:

[0025] An acquisition module, used for receiving monitoring data of a railway signal in real time, wherein the monitoring data includes operation data, environmental factor data and historical fault records of the railway signal;

[0026] A processing module, used for processing the received monitoring data of the railway signal machine to obtain key characteristic data that can reflect the operation status and health status of the railway signal machine;

[0027] An evaluation module, used for inputting the obtained key feature data into a pre-built railway signal operation health evaluation model to obtain an output result of the model, wherein the output result of the model is an evaluation score corresponding to each preset health level;

[0028] The analysis module is used to determine the health level with the largest evaluation score as the final operation health evaluation result of the railway signal according to the output result of the model.

[0029] At least one embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned railway signal machine operating status health assessment method.

[0030] At least one embodiment of the present application further provides a computer-readable storage medium storing a computer program, which implements the above-mentioned railway signal operation status health assessment method when executed by a processor.

[0031] The embodiments of the present application provide a method, device, equipment and medium for evaluating the operating status of a railway signal machine. The method receives the monitoring data of the railway signal machine in real time, and the monitoring data includes the operating data, environmental factor data and historical fault records of the railway signal machine. The received monitoring data of the railway signal machine is processed to obtain key feature data that can reflect the operating status and health status of the railway signal machine. The key feature data is then input into a pre-built railway signal machine operating health evaluation model to obtain the output result of the model, and the output result of the model is the evaluation score corresponding to each preset health level. Finally, according to the output result of the model, the health level with the largest evaluation score is determined as the final operating health evaluation result of the railway signal machine. This realizes the automatic and accurate evaluation of the operating status of the railway signal machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] One or more embodiments are exemplarily described by the pictures in the corresponding drawings, and these exemplary descriptions do not constitute limitations on the embodiments.

[0033] Figure 1 is a flow chart of a method for evaluating the operating status of a railway signal machine provided by an embodiment of the present application;

[0034] Figure 2 is a schematic diagram of the network structure of a GRU provided by an embodiment of the present application;

[0035] Figure 3 It is a schematic diagram of the model structure of a GRU neural network model provided by an embodiment of the present application;

[0036] Figure 4 is a structural schematic diagram of a railway signal operation status health assessment device provided by another embodiment of the present application;

[0037] Figure 5 It is a flowchart of a railway signal operating status health assessment method provided by another embodiment of the present application. DETAILED DESCRIPTION

[0038] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the present application, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented. The division of the following embodiments is for the convenience of description, and the specific implementation of the present application should not be construed as any limitation, and the various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0039] In order to facilitate understanding of the embodiments of the present application, the relevant contents about the method for evaluating the health level of the operating status of railway signal machines are first introduced here.

[0040] The traditional method for evaluating the health level of railway signal operation status is manual inspection. It mostly relies on manual inspection and experience judgment, which is not only inefficient, but also easily affected by human factors, making it difficult to accurately evaluate the health status of railway signal.

[0041] In order to solve the technical problems that the above-mentioned traditional railway signal operation status health level assessment method is inefficient, easily affected by human factors, and difficult to accurately assess the health status of railway signals, the present invention proposes a railway signal operation status health assessment method. The implementation details of the railway signal operation status health assessment method of this embodiment are specifically described below. The following content is only the implementation details provided for ease of understanding and is not necessary for the implementation of this solution.

[0042] Embodiment 1:

[0043] The railway signal machine operation status health assessment method of this embodiment can be applied to electronic devices with communication, computing and data storage capabilities. The specific process can be as follows: Figure 1 As shown, including:

[0044] Step S11, receiving monitoring data of the railway signal in real time, wherein the monitoring data includes operation data, environmental factor data and historical fault records of the railway signal.

[0045] Specifically, the monitoring data of the railway signal can be collected through sensors or monitoring equipment. The operation data of the railway signal includes but is not limited to data such as voltage, current, luminance, signal sending and receiving status, power-on status, response time, etc. The environmental factor data of the railway signal includes external factors such as weather conditions, temperature changes, humidity changes, etc. that may affect the operation of the railway signal. The historical fault records of the railway signal include information such as the number of fault alarms, fault occurrence time, fault type, maintenance records, etc.

[0046] For example, the monitoring data of the railway signal machine is received in real time through a message queue, and a unique timestamp is set for each piece of monitoring data of the railway signal machine received by the message queue. The ID number of each railway signal machine is used as the key value of the message queue, and the monitoring data of the railway signal machine is used as the value of the message queue.

[0047] Step S12, processing the received monitoring data of the railway signal to obtain key characteristic data that can reflect the operating status and health status of the railway signal.

[0048] In some embodiments, step S12 includes:

[0049] Step S121, performing data preprocessing on the monitoring data of the railway signal.

[0050] Specifically, the historical monitoring data of the railway signal lights obtained are cleaned, standardized and normalized to eliminate noise and outliers in the data, and feature calculations are performed, such as mean, maximum, minimum, variance, deviation, discreteness, integral and other features.

[0051] Step S122, extracting features from the monitoring data of the railway signal after data preprocessing, and obtaining key feature data that can reflect the operating status and health status of the railway signal.

[0052] For example, the key characteristic data include the development frequency of the railway signal, the cumulative number of current alarms (such as the number of first-level current alarms and the number of second-level current alarms), the cumulative number of voltage alarms (such as the number of first-level voltage alarms and the number of second-level voltage alarms), the cumulative number of lumen alarms and the cumulative number of maintenance times of various maintenance levels (such as the number of major, medium and minor maintenance times of the railway signal recently), the time when the railway signal was officially put into use and the life time of the railway signal issued by the manufacturer, etc., which are characteristic data that can reflect the operating status and health status of the railway signal.

[0053] Step S123, using a feature selection algorithm to screen the extracted key features to remove redundant features and irrelevant features in the key features to obtain final key feature data.

[0054] Specifically, by using a feature selection algorithm to screen the extracted key features to remove redundant features and irrelevant features in the key features, the accuracy and efficiency of the evaluation can be improved.

[0055] Step S13, input the obtained key feature data into a pre-built railway signal machine operation health assessment model to obtain the output result of the model. The output result of the model is the assessment score corresponding to each preset health level.

[0056] In some embodiments, the process of constructing the railway signal operation status health assessment model includes:

[0057] Step 1: Build a GRU (Gated Recurrent Unit) deep network model.

[0058] GRU is one of the most commonly used network structures in recurrent neural networks (RNNs) and one of the most common structural units in time series prediction. Figure 2 As shown, Figure 2 In the above code, Sigmoldσ represents the activation function, and tanh refers to the hyperbolic tangent function. GRU introduces the update gate and reset gate to control the flow of information, thereby solving the problems of gradient vanishing and gradient exploding, and can more effectively handle the problems of long-term dependency and short-term memory. Compared with traditional RNN, the advantage of GRU is that it can more effectively process long sequence data and alleviate the problem of gradient vanishing. At the same time, because GRU usually has fewer parameters than LSTM (Long Short-Term Memory), it is simpler.

[0059] Specifically, the deep learning framework Pytorch is used to build a GRU neural network model. By adjusting the number of structural layers, the number of neurons in each layer, the activation function and the training strategy of the GRU neural network model, the GRU neural network model can learn and memorize the potential long-term dependencies and short-term memory relationships of the railway signal data. Specifically, according to the characteristics and evaluation requirements of the input data of the GRU neural network model, a suitable GRU network structure is designed, including the number of network layers, the number of neurons in each layer, etc. And the model parameters are set: including hyperparameters such as learning rate, batch size, and number of iterations, so as to adjust the model performance during the training process.

[0060] In some examples, the model structure of the GRU neural network model is as follows Figure 3 As shown, it includes an input layer, two GRU layers, two fully connected layers and an output layer. Finally, the GRU neural network model outputs a three-dimensional vector, which respectively represents the scores of the three health levels of health, attention and disease corresponding to the operating status of the railway signal. Select the cross entropy loss function, set the accuracy and recall evaluation indicators, and tune the model parameters by reasonably setting the training data set and the verification data set to improve the prediction performance of the model. Save the trained GRU neural network model to the computer memory.

[0061] Step 2: Obtain historical monitoring data of the railway signal light, wherein the historical monitoring data includes operation data, environmental factor data and historical fault records of the railway signal light.

[0062] Specifically, the operation data of the railway signal includes but is not limited to real-time monitoring data such as voltage, current, temperature, humidity, switch status, etc. The environmental factor data of the railway signal includes external factors such as weather conditions, temperature changes, humidity changes, etc. that may affect the operation of the railway signal. The historical fault records of the railway signal include information such as the number of fault alarms, fault occurrence time, fault type, maintenance records, etc.

[0063] Step three, processing the acquired historical monitoring data of the railway signal to obtain key feature data that can reflect the operating status and health status of the railway signal.

[0064] Specifically, the historical monitoring data of the railway signal lights obtained are cleaned, standardized and normalized to eliminate noise and outliers in the data. Feature calculations are also performed, such as mean, maximum, minimum, variance, deviation, discreteness, integral and other features, to provide a high-quality data set for subsequent model construction and training.

[0065] Step 4: Train the GRU neural network model based on the key feature data, and use the trained GRU neural network model as the railway signal operation health assessment model.

[0066] Specifically, the GRU neural network model is trained using the historical monitoring data, and the model parameters are optimized by the back propagation algorithm. During the training process, cross-validation, early stopping and other methods are used to prevent overfitting and improve the generalization ability of the GRU neural network model. The performance of the trained GRU neural network model is evaluated, including indicators such as accuracy, recall rate, and F1 value, to ensure that the GRU neural network model can accurately evaluate the operating health status of the railway signal machine.

[0067] Step S14, according to the output result of the model, determining the health level with the largest evaluation score as the final operation health evaluation result of the railway signal.

[0068] Specifically, according to the evaluation scores, the health level with the largest evaluation score is selected as the final operation health evaluation result of the railway signal. The final operation health evaluation result of the railway signal can be displayed by visualization means, so that railway staff can intuitively understand the health status of the railway signal and take corresponding maintenance measures.

[0069] During the specific use of the GRU neural network model, in order to improve the accuracy of model evaluation, the health status of the railway signal is continuously monitored, and the operational health evaluation results of the railway signal are updated in real time. The performance of the GRU neural network model is evaluated regularly, and the GRU neural network model is optimized and adjusted according to the performance evaluation results, such as adjusting the network structure of the GRU neural network model; the number of hidden neurons; adding a dropout layer (Dropout layer) to prevent overfitting; increasing data diversity through data enhancement techniques (such as data flipping, rotation, etc.) to improve the generalization ability of the model; standardizing or normalizing the data to accelerate the training process and improve model performance. Collect new fault data and maintenance records to update the model and improve the accuracy of the evaluation.

[0070] The railway signal machine operation status health assessment method provided in this embodiment receives the monitoring data of the railway signal machine in real time, and the monitoring data includes the operation data, environmental factor data and historical fault records of the railway signal machine; and processes the received monitoring data of the railway signal machine to obtain key feature data that can reflect the operation status and health status of the railway signal machine; and then inputs the obtained key feature data into the pre-built railway signal machine operation health assessment model to obtain the output result of the model, and the output result of the model is the assessment score corresponding to each preset health level; finally, according to the output result of the model, the health level with the largest assessment score is determined as the final operation health assessment result of the railway signal machine. Thereby, the automatic and accurate assessment of the operation status health of the railway signal machine is realized.

[0071] Embodiment 2:

[0072] Another embodiment of the present application relates to a railway signal machine operating status health assessment device. The implementation details of the railway signal machine operating status health assessment device of this embodiment are specifically described below. The following content is only for the convenience of understanding the implementation details provided, and is not necessary for the implementation of this solution. The schematic diagram of the railway signal machine operating status health assessment device of this embodiment can be as follows Figure 4 As shown, it includes an acquisition module 401, a processing module 402, an evaluation module 403 and an analysis module 404.

[0073] The acquisition module 401 is used to receive monitoring data of the railway signal in real time, and the monitoring data includes operation data, environmental factor data and historical fault records of the railway signal.

[0074] The processing module 402 is used to process the received monitoring data of the railway signal to obtain key characteristic data that can reflect the operating status and health status of the railway signal.

[0075] The evaluation module 403 is used to input the obtained key feature data into a pre-built railway signal operation health evaluation model to obtain the output result of the model, and the output result of the model is the evaluation score corresponding to each preset health level.

[0076] The analysis module 404 is used to determine the health level with the largest evaluation score as the final operation health evaluation result of the railway signal according to the output result of the model.

[0077] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0078] Embodiment three:

[0079] Based on the above embodiments, this embodiment provides an application example. The application example provided in this embodiment involves a railway signal operation status health assessment system, including a sensor or monitoring device for collecting data, a collection extension for receiving monitoring data of each railway signal, an edge station receiving data from each of the collection extensions, and a server.

[0080] A railway signal operation status health assessment method, the specific process is as follows Figure 5 As shown, the following steps are included:

[0081] Step 1: Data collection.

[0082] Through sensors or monitoring equipment, three main types of data are collected: (1) real-time operation data of railway signal machines, including but not limited to voltage, current, brightness, signal sending and receiving status, switch status, response time, etc. (2) historical operation data of railway signal machines, including switch status, fault records, working environment parameters, etc. of signal machines; (3) basic equipment parameter data of railway signal machines, such as production date, service life, warranty period, life span, and family quality history.

[0083] Step 2: The data collection extension collects the data uploaded by the sensors of each railway signal in real time.

[0084] The collection extension is based on an embedded PLC computer and uses the Linux embedded operating system to collect data uploaded by sensors of each railway signal in real time. One railway signal corresponds to one collection extension. Serial ports and CAN ports are used to realize hardware communication between sensors and collection extensions. For example, the collection extension has a built-in collector, and the collector communicates with the edge station controller through the network port. Since the distance between the collection extension and the edge station in the station is relatively long, a communication host is generally used as a relay between the collection extension and the edge station to realize communication between the collection extension and the edge station. As the communication control mechanism between the collection extension and the edge station, the edge station adopts a unified roll call control, and the collection extension transmits data back to the edge station through polling.

[0085] Step 3: The edge station receives data from each collection extension through the roll call control method and the network port, parses the received data at the physical level, and uploads the parsed data to the message queue. Each device ID is used as the key of the Kafka message, and the value is JSON format data. Each reported data corresponds to a unique timestamp.

[0086] Step 4: Message buffer layer.

[0087] Choose the mainstream message queue Kafka. The message queue Kafka can handle large amounts of data streams. It provides a buffer layer to temporarily store large amounts of real-time data generated by different data sources. This helps to cope with fluctuations in the speed of data sources and ensures the stability of data processing and analysis. The message queue Kafka provides high-throughput message transmission, allowing data to flow efficiently between various components. The message queue Kafka can also integrate data from multiple data sources to achieve data aggregation and aggregation. This buffering mechanism allows the data stream to be smoothly transmitted to the subsequent processing stage.

[0088] Step 5: Process the collected data using the Spark Structured Streaming real-time stream processing technology of big data.

[0089] Structured Streaming is a scalable and fault-tolerant stream processing engine on the Spark SQL engine. Its main features are fast, scalable, fault-tolerant, and end-to-end stream processing that is executed only once. It unifies the programming model of streams and batches, so that developers do not need to make additional considerations for stream and batch processing, and only need to write code using the same computing operations. In addition, Structured Streaming also supports processing logic based on event_time time windows, and implements end-to-end Exactly-Once semantics through mechanisms such as checkpoints and write-ahead logs. This fault-tolerant mechanism ensures that data is processed only once even in the event of a failure, thus avoiding the problem of data duplication or loss.

[0090] The Spark Structured Streaming real-time stream processing technology of big data is used to perform quasi-real-time or even real-time cleaning, standardization and normalization of monitoring data to eliminate noise and outliers in the data, and perform quasi-real-time feature calculations on the data, such as mean, maximum, minimum, variance, deviation, discreteness, integral and other features, to provide high-quality data sets for subsequent model construction and training. According to the operating characteristics and health assessment requirements of railway signal machines, key features are extracted from the preprocessed data. These features should be able to fully reflect the operating status and health status of railway signal machines. At the same time, feature selection algorithms are used to screen the extracted features, remove redundant and irrelevant features, and improve the accuracy and efficiency of the assessment.

[0091] The selected features include: the development frequency of the railway signal; the number of first and second level current alarms of the railway signal's voltage and current monitoring data, the number of first and second level voltage alarms of the railway signal; the number of lumen alarms of the railway signal; the number of major, medium and minor repairs of the railway signal in the past six months; the time the railway signal has been in use (referring to the time when the railway signal is officially put into use); and the life span of the railway signal issued by the manufacturer.

[0092] Step 6: Build a railway signal machine operation health assessment model, including: building a GRU neural network model, training and tuning the GRU neural network model.

[0093] The specific process of this step has been described in detail in the above embodiment and will not be repeated here.

[0094] Step 7: Signal health assessment and result presentation.

[0095] The data of the railway signal machine to be evaluated is input into the constructed railway signal machine operation health evaluation model to obtain the model output result. The output result of the model is the evaluation score of the railway signal machine at different pre-divided health levels, such as the evaluation scores of the three levels of health, attention, and disease. According to the evaluation score, the one with the largest score is selected as the final evaluation result of the equipment health level. The evaluation results are displayed by visual means, which makes it easier for railway staff to intuitively understand the health status of the signal machine and take corresponding maintenance measures. For example, for railway signal machines in poor health, maintenance personnel are notified in time to carry out maintenance to avoid failures.

[0096] Embodiment 4:

[0097] Another embodiment of the present application relates to an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the railway signal machine operating status health assessment method in the above-mentioned embodiments.

[0098] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0099] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0100] Embodiment five:

[0101] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0102] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as: ROM), random access memory (Random Access Memory, referred to as: RAM), disk or optical disk and other media that can store program codes.

[0103] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A method for evaluating the operating status of a railway signal, characterized in that: include: Receive monitoring data of railway signal machines in real time, wherein the monitoring data includes operation data, environmental factor data and historical fault records of the railway signal machines; Processing the received monitoring data of the railway signal to obtain key characteristic data that can reflect the operating status and health status of the railway signal; Inputting the obtained key feature data into a pre-built railway signal operation health assessment model to obtain an output result of the model, wherein the output result of the model is an assessment score corresponding to each preset health level; According to the output result of the model, the health level with the largest evaluation score is determined as the final operation health evaluation result of the railway signal.

2. The railway signal operation status health assessment method according to claim 1 is characterized in that: Constructing the railway signal operation status health assessment model, including: Build a GRU neural network model; Acquire historical monitoring data of railway signal machines, wherein the historical monitoring data includes operation data, environmental factor data and historical fault records of railway signal machines; Processing the acquired historical monitoring data of the railway signal to obtain key characteristic data that can reflect the operating status and health status of the railway signal; The GRU neural network model is trained based on the key feature data, and the trained GRU neural network model is used as the railway signal operation health assessment model.

3. The railway signal operation status health assessment method according to claim 2 is characterized in that: The model structure of the GRU neural network model includes an input layer, two GRU layers, two fully connected layers and an output layer.

4. The railway signal operation status health assessment method according to claim 1 is characterized in that: The data processing of the received monitoring data of the railway signal machine to obtain key characteristic data that can reflect the operating status and health status of the railway signal machine includes: Performing data preprocessing on the monitoring data of the railway signal; Extracting features from the monitoring data of the railway signal after data preprocessing to obtain key feature data that can reflect the operating status and health status of the railway signal; The extracted key features are screened using a feature selection algorithm to remove redundant features and irrelevant features in the key features to obtain final key feature data.

5. The railway signal operation status health assessment method according to claim 4 is characterized in that: The key characteristic data include the development frequency of the railway signal, the cumulative number of current alarms, the cumulative number of voltage alarms, the cumulative number of lumen alarms and the cumulative number of maintenance of various maintenance levels, as well as the time when the railway signal was officially put into use and the life time of the railway signal issued by the manufacturer.

6. The railway signal operation status health assessment method according to claim 1 is characterized in that: The real-time receiving of monitoring data of railway signal machines includes: The monitoring data of the railway signal machine is received in real time through a message queue, wherein the ID number of each railway signal machine is used as the key value of the message queue, and the monitoring data of the railway signal machine is used as the value of the message queue.

7. The railway signal operation status health assessment method according to claim 6 is characterized in that: Also includes: A unique timestamp is correspondingly set for each piece of monitoring data of the railway signal received by the message queue.

8. A railway signal machine operating status health assessment device, characterized in that: include: An acquisition module, used for receiving monitoring data of a railway signal in real time, wherein the monitoring data includes operation data, environmental factor data and historical fault records of the railway signal; A processing module, used for processing the received monitoring data of the railway signal machine to obtain key characteristic data that can reflect the operation status and health status of the railway signal machine; An evaluation module, used for inputting the obtained key feature data into a pre-built railway signal operation health evaluation model to obtain an output result of the model, wherein the output result of the model is an evaluation score corresponding to each preset health level; The analysis module is used to determine the health level with the largest evaluation score as the final operation health evaluation result of the railway signal according to the output result of the model.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the railway signal machine operating status health assessment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for evaluating the operating status of a railway signal machine according to any one of claims 1 to 7 is implemented.

Images