Subway operation state monitoring terminal

Abstract

The utility model relates to the technical field of metro operation monitoring, and discloses a metro operation state monitoring terminal which comprises a data acquisition module used for acquiring, preprocessing and storing operation data. The data processing unit is used for carrying out fusion and fault analysis on the processed operation data and evaluating the subway operation performance; the communication module is used for data transmission communication; the interaction module is used for workers to detect and interactively control the subway operation condition; the power supply management module is used for supplying power to each module; the intelligent monitoring of subway operation is realized, and the accuracy of real-time monitoring of the subway operation condition is improved.

Description

TECHNICAL FIELD

[0001] The utility model relates to the technical field of subway operation monitoring discloses a subway operation state monitoring terminal. BACKGROUND

[0002] With the increasing complexity of the subway operation monitoring system, the maintenance and repair costs of the equipment also increase accordingly. On the one hand, due to the large number of equipment types and high technical content, professional technical personnel are needed for maintenance and repair, and the labor cost is high. On the other hand, the supply and replacement cost of spare parts of some equipment is also high, which brings certain economic pressure to the operating unit. The subway operation environment is complex and changeable, such as electromagnetic interference, high temperature and humidity in the tunnel, etc. The performance and reliability of the monitoring terminal are put forward to higher requirements. At present, some monitoring equipment may have problems such as signal attenuation and data distortion in complex environment, which affects the monitoring effect and the normal operation of the system.

[0003] For example, the Chinese patent application with the publication number CN109050582B discloses a kind of train state intelligent monitoring method and system, method includes: PIS system receives the train operation information sent by TCMS, carries out automatic broadcast play, and the content played is uploaded to the vehicle state intelligent monitoring platform by vehicle-ground wireless communication;Vehicle state intelligent monitoring platform receives the broadcast content reported by the PIS system, obtains train operation state;From signal system, the actual running state of the train is acquired in real time;The train operation state reported by the PIS system is compared with the actual running state of the train acquired from the signal system in real time, to judge whether the running state of the train is normal or not. The present application can monitor the real-time running state of subway train in real time, and compare the signal source data of signal system, which can further deepen the monitoring of subway train state, facilitate the supervision of train operation state for subway operating company, discover fault in time and obtain the cause of fault, so as to solve the problem of fault.

[0004] The above-mentioned utility model mainly depends on PIS system to receive the train operation information sent by TCMS and to acquire the actual running state of the train from the signal system, and the data source is relatively narrow, which may not fully reflect the running state of subway train. For example, the temperature, vibration and other physical parameters of train key components, and the environmental parameters in the carriage cannot be directly acquired, and the specific method and process of data fusion are not described in detail, only the train operation state reported by PIS system is compared with the actual running state of the signal system, the depth and breadth of data fusion are limited, and it is difficult to fully tap the correlation between different data and potential value. UTILITY MODEL CONTENT

[0005] The purpose of this part is to outline some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part and the abstract of the specification and the title of the application in order to avoid obscuring the purpose of this part, the abstract of the specification and the title of the application, and such simplifications or omissions cannot be used to limit the scope of the application.

[0006] To solve the above technical problems, the main purpose of the present application is to provide a subway operation state monitoring terminal, comprising:

[0007] The data acquisition module comprises a sensor unit, a data preprocessing unit and a data caching unit, wherein the data preprocessing unit is used for preprocessing the collected operation data, and the data caching unit is used for temporarily storing the preprocessed data.

[0008] The data processing module comprises a data fusion unit, a fault diagnosis unit and a performance evaluation unit, wherein the data fusion unit is used for fusion processing of the preprocessed operation data, and the fault diagnosis unit is used for judging whether there is a hidden danger of failure in the subway.

[0009] The communication module comprises a 5G communication unit, a network management unit and a data encryption unit, wherein the 5G communication unit is used for establishing a 5G wireless connection, and the network management unit is used for real-time monitoring and management of the communication network.

[0010] The interactive module comprises a display screen, a voice unit and an operation unit, wherein the operation unit is used for connecting external storage devices, debugging devices and performing system upgrade and maintenance.

[0011] The power management module comprises a main power unit, a backup power unit and a power management unit, wherein the power management unit is used for dynamically adjusting power distribution according to the working state and power demand of each module of the terminal.

[0012] The data preprocessing unit comprises signal filtering and data correction.

[0013] The signal filtering is performed by digital filtering, and the collected sensor data is filtered and processed to filter out high-frequency noise signals and retain low-frequency effective signals of the subway operation state.

[0014] The data correction is performed according to the characteristics of the sensor and the known standard reference value.

[0015] As a preferred scheme of the subway operation state monitoring terminal of the present application, wherein:

[0016] The data fusion unit comprises multi-sensor data fusion and data fusion.

[0017] The multi-sensor data fusion adopts a Kalman filtering algorithm to fuse the measurement data from different sensors;

[0018] The data fusion method comprises

[0019] S1, a data fusion unit receives preprocessed subway multi-parameter data information;

[0020] S2, the data from each sensor is subjected to time synchronization processing to ensure that the data collected by different sensors is consistent in time;

[0021] S3, the time-synchronized sensor data is subjected to fusion calculation to obtain fused subway operation state data;

[0022] S4, the fused data is output to a fault diagnosis unit and a performance evaluation unit for further processing.

[0023] As a preferred scheme of the subway operation state monitoring terminal of the utility model, wherein:

[0024] The fault diagnosis unit constructs a subway fault diagnosis model based on a machine learning algorithm;

[0025] The performance evaluation unit establishes a subway performance evaluation index system.

[0026] As a preferred scheme of the subway operation state monitoring terminal of the utility model, wherein:

[0027] The 5G communication unit transmits subway operation information;

[0028] The network management unit comprises network state monitoring and network switching and optimization;

[0029] The data encryption unit encrypts the uploaded and downloaded operation data through subway data encryption.

[0030] As a preferred scheme of the subway operation state monitoring terminal of the utility model, wherein:

[0031] The multi-band antenna optimizes the 5G communication module;

[0032] The network management unit comprises network state monitoring and network switching and optimization;

[0033] The network state monitoring is used for monitoring the state of the 5G communication network in real time, including signal strength, signal-to-noise ratio, network delay and packet loss rate;

[0034] The network switching and optimization is used for optimizing the network switching mechanism.

[0035] The utility model has the advantages of:

[0036] The data fusion unit adopts a Kalman filtering algorithm for multi-sensor data fusion, can comprehensively utilize the advantages of different sensors, make up for the limitations of a single sensor, obtain more accurate and complete subway operation state data, the fault diagnosis unit can identify potential fault patterns and features through learning a large amount of historical operation data, and discover hidden faults in advance instead of responding after the fault occurs, the performance evaluation unit can quantitatively evaluate the overall performance of the subway vehicle from multiple dimensions, the network management unit can ensure the stability and reliability of network connection in a complex subway operation environment through real-time monitoring and optimization switching mechanism of the communication network. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical scheme of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor. Among them:

[0038] Figure 1 A subway operation state monitoring terminal according to the present application is shown in the figure;

[0039] Figure 2 A data fusion method of the subway operation state monitoring terminal according to the present application is shown in the figure;

[0040] Figure 3 A subway operation state monitoring terminal topology according to the present application is shown in the figure. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0042] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited by the specific embodiments disclosed below.

[0043] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. In this specification, "in one embodiment" does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0044] Embodiment One

[0045] As Figure 1 shown, a subway operation state monitoring terminal, comprising:

[0046] A data acquisition module, including a sensor unit, a data preprocessing unit, and a data cache unit, wherein the sensor unit is used to collect subway operation data, the data preprocessing unit is used to preprocess the collected operation data, and the data cache unit is used to temporarily store the preprocessed data;

[0047] Further, according to the subway operation state monitoring requirements, sensors with high precision, high reliability, and adaptability to complex subway environments are selected. For example, MEMS micro-electromechanical accelerometers are selected for acceleration sensors, which have the characteristics of small size, low power consumption, and high measurement accuracy, and can accurately measure the acceleration changes of the subway, which are used to judge the start, braking, and driving stability of the subway; PT100 platinum resistance temperature sensors are used for temperature sensors, which can accurately measure the temperature of key components such as motors, gearboxes, and braking systems, and have a wide measurement range and good stability, which can effectively monitor whether the working temperature of the equipment is abnormal; high-precision piezoelectric pressure sensors are selected for pressure sensors, which are used to monitor the pressure changes of the hydraulic braking system to ensure the normal operation of the braking system.

[0048] Considering the installation position of the sensor, it is ensured that the required operation data can be accurately collected. For example, the acceleration sensor is installed near the wheels of the subway chassis to better perceive the vibration and acceleration changes during the subway driving process; temperature sensors are installed in key heat generating parts such as motor windings, gear box shells, and brake discs; pressure sensors are installed on the key nodes of the brake pipeline;

[0049] Further, a reasonable layout scheme is designed for the sensors, so that the sensors are distributed in various key parts of the subway to form a comprehensive monitoring network. Industrial-grade sensor connection cables are used to ensure the stability and anti-interference of signal transmission. Shielded wires are used for connection cables, and grounding treatment is done to reduce the influence of external electromagnetic interference on sensor signals.

[0050] Further, an independent signal conditioning circuit is provided for each sensor to amplify, filter, and convert the weak signals output by the sensor, so that it can meet the input requirements of the data acquisition unit. For example, the signal conditioning circuit of the acceleration sensor amplifies and filters the analog voltage signal output by it to remove noise interference, and converts it into a digital signal format suitable for data acquisition unit acquisition;

[0051] The data preprocessing unit includes signal filtering and data correction;

[0052] Further, signal filtering uses digital filtering techniques, such as Finite Impulse Response (FIR) filter and Infinite Impulse Response (IIR) filter, to filter the collected sensor data. For high-frequency noise interference, a low-pass FIR filter is used to set the appropriate cutoff frequency, filter out high-frequency noise signals, and retain low-frequency effective signals of the subway running state. For example, for acceleration sensor data, a low-pass filter with a cutoff frequency of 100Hz can be set to remove high-frequency interference signals such as road bumps during subway travel, making the acceleration data more reflective of the overall motion state of the subway.

[0053] For specific frequency interference signals, such as 50Hz or 60Hz power frequency interference generated by the subway power supply system, a notch filter is used for targeted filtering. The notch filter can form a very deep attenuation band at a specific frequency, effectively suppressing the influence of power frequency interference on sensor data and improving data accuracy

[0054] Further, data correction calibrates the collected data according to the characteristics of the sensor and the known standard reference value. For example, for temperature sensors, calibration experiments are conducted at different temperature environments to obtain a calibration curve or calibration coefficient between the sensor output value and the actual temperature value. During data preprocessing, the calibration curve or calibration coefficient is used to correct the collected temperature data to make it closer to the true temperature value.

[0055] Further, regular calibration and maintenance of the sensor are also needed to update the calibration data to compensate for the performance drift of the sensor due to long-term use or environmental changes. Automatic calibration and manual calibration can be combined, with automatic calibration being performed automatically during system operation according to the preset calibration period and conditions, and manual calibration being performed by maintenance personnel when the sensor is replaced, repaired, or data anomalies are found.

[0056] The data buffer unit includes buffer capacity and buffer management strategy, and the appropriate data buffer capacity is designed according to the collection frequency of subway operation data, data type and network transmission capacity. For example, considering the collection of a large amount of sensor data such as acceleration, temperature, pressure, etc. during subway operation, and the possible network transmission delay or interruption, the data buffer capacity is set to 1GB or more. This can ensure that a sufficient amount of operation data can be temporarily stored for a long time during network failure or data transmission peak period, avoiding data loss.

[0057] Further, the cache management strategy adopts a first-in, first-out (FIFO) cache management strategy. When the cache area is full and new data needs to be stored, the earliest stored data is automatically deleted to make room for new data. At the same time, a marking and indexing mechanism for cache data is set up to facilitate the data processing module to quickly locate and read the required data. For example, a timestamp is added as a marker to each cache data block according to the time sequence of data collection, and an index table is established. Through the timestamp or data type information, the cache data can be quickly queried and extracted;

[0058] The cache data is monitored and managed in real time, and the usage and remaining capacity of the cache data are counted. When the cache data exceeds a certain threshold or the remaining cache capacity is insufficient, a warning message is sent in time to remind the system administrator or maintenance personnel to pay attention to the network transmission status or take appropriate data cleaning measures, such as prioritizing important data upload or adjusting data collection frequency, etc.

[0059] The communication module includes a 5G communication unit, a network management unit, and a data encryption unit. The 5G communication unit is used to establish a 5G wireless connection. The network management unit is used to monitor and manage the communication network in real time. The data encryption unit is used to encrypt the uploaded and downloaded operation data.

[0060] The 5G communication unit selects an industrial-grade 5G communication module, such as products from well-known brands such as Huawei and ZTE. It has high reliability, stability, and anti-interference ability, and can adapt to the complex electromagnetic environment and operating conditions of the subway. According to the 5G network frequency band and operator requirements in the area where the subway is located, the 5G communication module is configured accordingly to ensure smooth access to the 5G network. For example, in China, according to the allocation of 5G frequency bands by different operators, select 5G modules that support the corresponding frequency bands and set the correct network access parameters such as APN (Access Point Name), username, password, etc.

[0061] Further, the 5G communication module's antenna design is optimized, using high-gain, multi-band antennas to improve signal reception and transmission capabilities. The 5G antenna is installed on the top of the subway or in a suitable location on the vehicle body to ensure that the antenna can obtain good signal coverage. At the same time, antenna diversity technology is used to receive signals through multiple antennas and combine them for processing, further improving the reliability and stability of communication and reducing the impact of signal fading and interference on communication quality.

[0062] The network management unit includes network status monitoring and network switching and optimization.

[0063] Further, network state monitoring is used to monitor the state of the 5G communication network in real time, including signal strength, signal-to-noise ratio, network delay, packet loss rate and other parameters. By periodically sending probe data packets to the network and receiving the response information returned by the network, the performance indicators of the network are calculated. For example, an ICMP echo request data packet (ping packet) is sent to the 5G base station every 10 seconds, and the network delay is calculated according to the received response time; the number of data packets sent and the number of data packets not received in a certain period of time are counted to calculate the packet loss rate. The monitored network state information is displayed in real time on the display screen of the interactive module, so that the network personnel can timely understand the network status, and if the network state is abnormal, such as signal strength below threshold, packet loss rate too high or network delay too large, the network management unit will issue a warning information in time and take appropriate measures, the warning information can be voice alarm through the voice unit of the interactive module, and the detailed network abnormal information, including abnormal type, occurrence time, influence range, etc., is displayed on the display screen;

[0064] Further, network switching and optimization is used to optimize the network switching mechanism, when the 5G network fails or the signal quality seriously decreases, it automatically switches to the standby network, such as the Wi-Fi network inside the subway or the 4G network (as an emergency backup). During network switching, ensure the continuity and integrity of data transmission, avoid data loss. For example, before switching, the data not transmitted is cached, and after switching, the cached data is transmitted continuously. At the same time, the standby network is monitored and managed in real time to ensure the availability and stability of the standby network;

[0065] The data encryption unit encrypts the uploaded and downloaded operation data by subway data encryption algorithm, such as AES (Advanced Encryption Standard) and RSA (Asymmetric Encryption Algorithm). For a large amount of operation data, AES algorithm is used for fast encryption, which has the characteristics of fast encryption speed and high encryption efficiency, and can meet the real-time encryption needs of subway operation state monitoring data. For some key information, such as user authentication information and device key, RSA algorithm is used for encryption, which has higher security and can effectively prevent information leakage and tampering.

[0066] Encryption and decryption modules are deployed in terminal devices and subway control center respectively to ensure the confidentiality and integrity of data in transmission process. The encryption module encrypts the data before transmission, and the decryption module decrypts the data after reception. At the same time, a key management system is established to manage the encryption keys safely, and the keys are updated regularly to prevent data security problems caused by key leakage;

[0067] The interactive module includes a display screen, a voice unit and an operation unit, wherein the high-definition display screen is used to show the running state information of the subway, the voice unit is used to issue voice prompts and alarms, and the operation unit is used to connect external storage devices, debugging devices and perform system upgrade and maintenance.

[0068] The display screen is designed to be intuitive, clear and easy to operate, and adopts a graphical interface design method to show the running state information of the subway in various forms such as charts, graphs and texts. For example, the real-time position, speed, direction of travel and other information of the subway are displayed on the main interface, the position of the subway on the line is displayed in the form of map navigation, and the speed and direction are displayed in the form of dynamic pointers or numbers; the temperature, pressure and other parameters of key components are displayed in the form of instrument panels or column charts in real time, so that the operating personnel can understand the running state of the subway at a glance.

[0069] Further, the display screen is designed to have multiple page display functions, and multiple display pages are set according to different information display requirements, such as a running state page, a fault alarm page, a performance evaluation page and a historical data page. The operating personnel can switch between different pages through touch operation or operation buttons to view detailed information. For example, on the fault alarm page, all fault alarm information of the current subway is displayed, including fault type, occurrence position, alarm time, fault severity and the like, to prompt the operating personnel to pay attention in a prominent color and icon; on the historical data page, a function of querying and viewing historical running data is provided, such as the speed curve and temperature change curve of the subway in the past week or month, so as to facilitate the operating personnel to analyze data and troubleshoot faults;

[0070] As shown in Figure 3 a subway running state monitoring device topology,

[0071] The subway running state monitoring terminal includes an application layer, an analysis and decision layer, a preprocessing layer, a calculation layer and a foundation layer.

[0072] The application layer includes real-time report analysis, subway running analysis, subway running data analysis and fault diagnosis.

[0073] The analysis and decision layer includes data modeling, data calculation and data decision.

[0074] Further, the data modeling includes machine learning, deep learning and reinforcement learning.

[0075] The data calculation is model parallel computing.

[0076] The data decision includes real-time analysis of subway running data and subway situation analysis

[0077] The preprocessing layer includes data cleaning, data fusion and data desensitization;

[0078] The computing layer includes stream computing and batch computing;

[0079] The base layer is used to collect subway operation parameter data, including data collection, data storage and data management;

[0080] A subway operation state monitoring terminal topology also includes a subway monitoring platform, a subway task scheduling platform and a terminal operation status analysis;

[0081] The voice unit includes various voice prompts and alarm functions, and emits corresponding voice information according to different events and fault types. For example, when the subway starts, the voice unit emits the voice prompt “Subway starts, please fasten your seat belt”; when a fault is detected, different alarm voices are emitted according to the severity of the fault, such as the voice prompt “Please note that the subway has a minor fault, please check in time” for a minor fault, the voice alarm “The subway has a moderate fault, please take immediate action” for a moderate fault, and the voice alarm “The subway has a serious fault, please emergency brake and contact the maintenance personnel” for a serious fault.

[0082] Embodiment two

[0083] The data processing module includes a data fusion unit, a fault diagnosis unit and a performance evaluation unit, wherein the data fusion unit is used to perform fusion processing on the preprocessed operation data, the fault diagnosis unit is used to judge whether there is a fault hidden danger in the subway, and the performance evaluation unit is used to evaluate the overall performance of the subway;

[0084] Further, the data fusion unit includes multi-sensor data fusion and data fusion;

[0085] The multi-sensor data fusion adopts Kalman filtering algorithm for data fusion, and the measurement data from different sensors are fused and processed to obtain more accurate and comprehensive subway operation state estimation value. For example, the data of acceleration sensor and wheel speed sensor are fused, and Kalman filtering algorithm is used to estimate the speed and position of the subway. Kalman filtering algorithm can update the state estimation value in real time according to the uncertainty of sensor measurement data and the dynamic model of the system, so that the estimation result is closer to the true value.

[0086] For some sensor data with complementary properties, such as temperature sensor and infrared thermal imaging sensor data, a weighted average fusion algorithm is adopted. According to the accuracy, reliability and other factors of the sensor, different weights are assigned to each sensor data, and then the weighted sensor data is summed and averaged to obtain the fused temperature data. In this way, the advantages of different sensors can be fully utilized to improve the accuracy and reliability of temperature measurement

[0087] As Figure 2 shown, the data fusion method includes

[0088] S1, the data fusion unit receives the preprocessed subway multi-parameter data information;

[0089] S2, the data from each sensor is time synchronized to ensure that the data collected by different sensors is consistent in time;

[0090] The data is synchronized by aligning the time stamp or interpolating the data collected at different times to the same time reference;

[0091] S3, the time synchronized sensor data is fused and calculated to obtain the fused subway running state data;

[0092] The subway data that needs to be fused includes the comprehensive speed, position, attitude, comprehensive temperature and pressure of key components and other information of the subway;

[0093] S4, the fused data is output to the fault diagnosis unit and the performance evaluation unit for further processing;

[0094] Fault diagnosis model construction:

[0095] The fault diagnosis unit constructs a subway fault diagnosis model based on machine learning algorithm, collects a large amount of historical running data of the subway under normal operation and fault state, extracts and preprocesses the features of these data, and then trains the machine learning algorithm to establish the fault diagnosis model. The running data of the subway such as acceleration, speed, temperature and pressure are used as input features, and whether the subway has a fault and the fault type are used as output labels. Through training the neural network model, it can accurately judge whether the subway has a fault hidden danger and identify the fault type according to the input running data.

[0096] Further, the fault diagnosis model is updated and optimized regularly. With the continuous accumulation of subway running data and the change of operation environment, the fault characteristics and patterns may change. Incremental learning or online learning method is adopted to include new running data and fault cases into the model training, continuously adjust the parameters and structure of the model, and improve the accuracy and adaptability of the fault diagnosis model

[0097] The performance evaluation unit establishes a subway performance evaluation index system;

[0098] Embodiment three

[0099] Core computing module for processing subway running data;

[0100] The core computing module adopts a high-performance heterogeneous multi-core processor architecture, such as containing multiple ARM Cortex-A series cores and dedicated digital signal processor (DSP) cores. The ARM Cortex-A core is responsible for running the operating system, processing control logic, and interacting with other modules for general tasks such as data exchange, and its main frequency can reach 2.5GHz, with powerful computing power and rich instruction sets. The DSP core is specifically used to process a large number of digital signal processing tasks in the subway operation data, such as sensor data filtering, spectral analysis, and complex mathematical operations in data fusion algorithms, etc. The DSP core is optimized for digital signal processing, with efficient multiply-add operation units and fast data access channels, which can greatly improve the speed and efficiency of data processing.

[0101] Equipped with large-capacity cache (Cache) and memory. Adopt multi-level Cache structure, such as L1, L2 and L3 Cache, among which L3 Cache capacity can reach more than 8MB, used to store data and instructions frequently accessed by the processor, reducing the number of memory access, improving data reading speed. Memory uses DDR4 technology, capacity can be selected according to actual demand 8GB or higher, memory frequency can reach 3200MHz, to meet the demand of fast storage and reading of a large amount of data in the process of data processing. At the same time, use high-speed solid state disk (SSD) as external storage device, its read-write speed can reach more than 500MB / s, used to store a large amount of data such as historical data, fault records and performance evaluation report of subway operation, convenient for long-term preservation and subsequent analysis of data.

[0102] Data processing flow and algorithm implementation:

[0103] Data reception and preprocessing: the core computing module is connected with the data acquisition module through high-speed data bus, receiving raw data from various sensors. First, format conversion and verification are performed on the data, and different formats of data output by different sensors are uniformly converted into the standard format required for internal processing, and the integrity and correctness of the data are checked. For example, binary data collected by sensors are converted into floating-point or integer data, and the data is verified according to the checksum or CRC code to check whether errors occur in the transmission process. Then, the data is preliminarily filtered and denoised, using an adaptive filtering algorithm to adjust the filter parameters according to the real-time characteristics of the data, to remove high-frequency noise and outliers in the data and improve the quality of the data.

[0104] Data fusion and feature extraction: Apply model-based multi-sensor data fusion algorithms such as Extended Kalman Filter (EKF) or Unscented Kalman Filter (UKF) to fuse multi-source data from acceleration sensors, speed sensors, position sensors, temperature sensors, etc. to obtain more accurate and comprehensive running state information of metro vehicles, such as precise position, speed, attitude and health status of key components, etc. During the fusion process, feature extraction is also performed to extract key parameters that reflect the running state and fault characteristics of metro vehicles, such as vehicle vibration characteristics, temperature change trends, energy consumption characteristics, etc. These features will serve as important basis for subsequent fault diagnosis and performance evaluation. For example, by performing spectral analysis on acceleration sensor data, extract vibration amplitude and frequency characteristics in a specific frequency range to determine whether the vehicle has wheel imbalance, track irregularity, etc. Perform trend analysis on temperature sensor data to extract temperature rise rate, temperature fluctuation range, etc. to predict whether key components are at risk of overheating.

[0105] Fault diagnosis and prediction: Use artificial intelligence-based fault diagnosis methods such as Recurrent Neural Network (RNN) or Long Short-Term Memory Network (LSTM) models in deep learning to diagnose and predict faults based on extracted feature data. These models can learn feature patterns of metro vehicles under normal operation and fault conditions, and through training on a large amount of historical data, establish a fault diagnosis model. Input real-time feature data into the model, and the model outputs information such as fault type, location, severity and probability of occurrence. For example, use the LSTM model to analyze current, vibration and temperature feature data of the motor to predict whether the motor has winding short circuit, bearing wear and other faults, and issue an early warning to take timely maintenance measures to prevent further deterioration of the fault and improve the safety and reliability of metro operation.

[0106] Performance Evaluation and Optimization Suggestions: Based on the operation data of the subway vehicle and the preset performance evaluation index system, the overall performance of the vehicle is evaluated and calculated. Performance evaluation indicators include energy efficiency, braking performance, ride smoothness, comfort, and other aspects. For example, by integrating the speed, current, voltage, and other data of the vehicle, energy consumption data is obtained, and compared with the same type of vehicle or historical data to evaluate energy efficiency; according to the pressure, wheel speed, and braking distance of the braking system, braking performance indicators such as deceleration, braking response time, etc. are calculated; using acceleration sensor data to calculate the root mean square value (RMS) of the vehicle's acceleration during travel and the Sperling smoothness index to evaluate the ride smoothness; combined with temperature, humidity, noise, vibration, and other sensor data in the car and passenger feedback information, the comfort is evaluated comprehensively. According to the performance evaluation results, an optimization suggestion report is generated to provide decision-making basis for the subway operation management department, such as adjusting the train running speed curve to reduce energy consumption, optimizing the braking system parameters to improve braking performance, improving the car environment to improve comfort, etc.

[0107] Task Scheduling and Resource Management:

[0108] Real-time multi-task operating system (RTOS) such as VxWorks or QNX is used for task scheduling and resource management. The functions of the core computing module are divided into multiple tasks, such as data acquisition task, data processing task, fault diagnosis task, performance evaluation task, communication task, etc., each task has different priority and execution period. For example, the data acquisition task has high priority and short execution period (such as 10ms) to ensure that the latest sensor data can be obtained in time; the fault diagnosis task is executed immediately after data fusion, and its priority is also relatively high to discover potential faults in time; while the performance evaluation task can be executed once in a certain time interval (such as 1 minute), and its priority is relatively low. RTOS allocates processor resources according to the priority and execution period of each task to ensure that each task can be completed on time, improving the real-time performance and reliability of the system.

[0109] The RTOS is responsible for managing the system's memory resources, interrupt resources, and synchronization and communication between tasks. In terms of memory management, dynamic memory allocation and memory protection mechanisms are adopted, with memory space allocated dynamically according to task requirements, and memory access between different tasks prevented to improve memory utilization and system stability. For example, when a data processing task needs to process a large amount of data, the RTOS allocates sufficient memory space for it, and recycles the memory in time after the task is completed. In terms of interrupt management, various hardware interrupts are prioritized and processed to ensure that important interrupts can be responded to in a timely manner, such as sensor data ready interrupts, communication data reception interrupts, etc. In terms of synchronization and communication between tasks, mechanisms such as semaphores, message queues, shared memory, etc. are used to achieve data sharing and collaborative work between different tasks. For example, the data acquisition task sends the collected data to the data processing task through the message queue, and the data processing task notifies the fault diagnosis task and performance evaluation task of the results through the semaphore after completion, ensuring efficient and reliable data transmission and interaction between tasks

[0110] A comprehensive performance evaluation index system for the subway is established, including energy consumption indicators, braking performance indicators, ride smoothness indicators, comfort indicators, etc. For example, energy consumption indicators can be measured by calculating the power consumption or fuel consumption per unit of distance; braking performance indicators can be evaluated by braking distance, braking deceleration, braking stability, etc.; ride smoothness indicators can be represented by the standard deviation or root mean square value of subway acceleration; comfort indicators can be evaluated by considering factors such as temperature, humidity, noise, vibration, etc. inside the car.

[0111] Reasonable evaluation standards and weights are determined for each performance evaluation indicator, and the qualified range and importance of different performance indicators are formulated according to the design requirements of the subway, the operation specifications, and the needs of passengers. For example, braking performance indicators are crucial to the safety of subway operation, so they are given a higher weight; while comfort indicators have a relatively lower weight, but cannot be ignored to ensure a comfortable riding environment for passengers under the premise of safety.

[0112] The selection of core processing module architecture and parameter processing requires specific parameter design in the specific implementation mode. The above only provides one or more options, and does not represent fixed parameter setting and system design.

[0113] It is important to note that the construction and arrangement of the application shown in the various exemplary embodiments is illustrative only. Although only two embodiments have been described in detail in this disclosure, those skilled in the art who review the disclosure will readily appreciate that many modifications can be made to the embodiments without departing from the spirit of the described application, for example, the size, shape, and relative arrangement of the elements, the sizes, shapes, and proportions of the various elements, and the values of parameters (such as temperature, pressure, etc.), the mounting arrangements, the use of materials, colors, orientation, and the like can be changed as will occur to those skilled in the art. For example, the elements shown as integrally formed can be constructed of a number of separate elements, the position of elements can be reversed or otherwise varied, and the nature or number of elements or positions can be modified or changed. Accordingly, all such modifications are intended to be included within the scope of the present application. The order or sequence of any process or method steps can be varied or re-sequenced without departing from the spirit of the application. Any "means plus function" clauses are intended to cover the structures described herein as performing claimed functions and not only structural equivalents, but also equivalent structures. Other substitutions, modifications, changes, and omissions can be made in the design, operating conditions, and arrangement of the exemplary embodiments without departing from the scope of the present application. Accordingly, the present application is not limited to the particular embodiments described and illustrated herein, but extends to equivalents of which the skilled in the art will appreciate.

[0114] Furthermore, in order to provide a concise description of exemplary embodiments, not all features of an actual implementation can be described (i.e., those not pertinent to the best mode for carrying out the present application, or those that are self-explanatory).

[0115] It is to be understood that the development of the exemplary embodiments of this application can not be limited to the precise constructional arrangements shown in the drawings, and that various modifications can be made to the embodiments without departing from the spirit and scope of the application. For example, while specific embodiments have been described in detail, persons of ordinary skill in the art understanding that modifications can be made to the described embodiments and other embodiments can be used without departing from the inventive or discovery underlying this application without the use of the present disclosure will appreciate that the scope of the application is not limited to particular embodiments, and that work developed from the teaching hereof by others skilled in the art are to come within the purview of the application.

[0116] It should be noted that the above examples are intended to be illustrative only and not limiting of the technical solutions of the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that modifications can be made to the technical solutions of the present application without departing from the spirit and scope of the present application, and all such modifications should be included in the scope of the claims of the present application.

Claims

1. A subway operation status monitoring terminal, characterized in that, Comprise: Data acquisition module, including sensor unit, data preprocessing unit, data cache unit, wherein, the data preprocessing unit is used for the preprocessing of the collected operation data, and the data cache unit is used for temporarily storing the preprocessed data; Data processing module, including data fusion unit, fault diagnosis unit and performance evaluation unit, wherein, the data fusion unit is used for fusion processing of the preprocessed operation data, and the fault diagnosis unit is used for judging whether the subway exists hidden trouble; Communication module, including 5G communication unit, network management unit and data encryption unit, wherein, the 5G communication unit is used for establishing 5G wireless connection, and the network management unit is used for real-time monitoring and management of communication network; Interactive module, including display screen, voice unit and operation unit, wherein, the operation unit is used for connecting external storage device, debugging device and system upgrade maintenance; Power management module, including main power unit, standby power unit and power management unit, wherein, the power management unit is used for dynamically adjusting power distribution according to the working state and power demand of each module of the terminal.

2. The subway operation state monitoring terminal according to claim 1, wherein: The data preprocessing unit comprises signal filtering and data correction; Signal filtering is carried out by digital filtering to filter out high-frequency noise signals and retain low-frequency effective signals of the subway operation state; Data correction is carried out according to the characteristics of the sensor and the known standard reference value.

3. The subway operation state monitoring terminal according to claim 2, wherein: The data fusion unit comprises multi-sensor data fusion and data fusion; Multi-sensor data fusion adopts Kalman filtering algorithm to fuse the measurement data from different sensors; The data fusion method comprises, S1, the data fusion unit receives the preprocessed subway multi-parameter data information; S2, the data from each sensor is time-synchronized to ensure that the data collected by different sensors is consistent in time; S3, the time-synchronized sensor data is fused to obtain the fused subway operation state data; S4, the fused data is output to the fault diagnosis unit and the performance evaluation unit for further processing.

4. The subway operation state monitoring terminal according to claim 3, wherein: The fault diagnosis unit constructs a subway fault diagnosis model based on machine learning algorithm; The performance evaluation unit establishes a subway performance evaluation index system.

5. The subway operation state monitoring terminal according to claim 4, wherein: The 5G communication unit is used for transmitting subway operation information; The network management unit comprises network state monitoring and network switching and optimization; The data encryption unit encrypts the uploaded and downloaded operation data through subway data encryption.

6. The subway operation state monitoring terminal according to claim 5, wherein: The 5G communication module is optimized by multi-band antenna. The network management unit includes network state monitoring and network switching and optimization; The network state monitoring is used to monitor the state of the 5G communication network in real time, including signal strength, signal-to-noise ratio, network delay, and packet loss rate; The network switching and optimization is used to optimize the network switching mechanism.

Images