An intelligent equipment operation and maintenance method and system based on railway operation and maintenance

Abstract

The present invention relates to the field of intelligent railway operation and maintenance technology, specifically a method and system for intelligent equipment operation and maintenance based on railway operation and maintenance. The method comprises collecting multidimensional operation and maintenance perception data; performing data cleaning and adaptive multi-level encryption on the multidimensional operation and maintenance perception data, and transmitting the data to a master station using a dynamic transmission protocol switching algorithm; restoring and verifying the data quality of the security data packets received by the master station to obtain cleaned data with spatial correlation; utilizing satellite positioning technology and three-dimensional visualization technology to obtain a dynamic and interactive equipment operation and maintenance digital twin environment; and employing time series feature extraction and a multi-factor association analysis algorithm to identify potential equipment faults. The present invention improves the efficiency of railway equipment operation and maintenance through big data analysis technology.

Description

Technical Field

[0001] The present invention relates to the technical field of railway intelligent operation and maintenance, and in particular to an equipment intelligent operation and maintenance method and system based on railway operation and maintenance. Background Art

[0002] With the rapid expansion of railway networks and the increasing complexity of their operations, railway monitoring equipment is increasingly being used. Railway monitoring equipment includes temperature sensors, humidity sensors, smoke density sensors, and video cameras installed in equipment rooms along the railway. These devices provide online monitoring of temperature, humidity, smoke density, and environmental video in equipment rooms along the railway, ensuring the normal operation of servers and control rooms within the equipment rooms, thereby maintaining the smooth operation and dispatch of the railway system. However, the current maintenance of railway monitoring equipment relies primarily on regular manual inspections, which present several technical challenges. First, railway monitoring equipment is often distributed over a vast geographical area and is numerous, making manual inspections inefficient and costly. For example, on conventional railway lines, hundreds of kilometers of track contain numerous equipment rooms. Traditional inspection methods require significant manpower and resources, and are difficult to implement around-the-clock monitoring. Second, because railway lines often traverse diverse terrains, the network conditions of monitoring equipment in equipment rooms along the railway vary. For example, monitoring equipment located in plain areas often enjoys a better network environment, while monitoring equipment in mountainous areas often experiences a poorer and more volatile network environment. Another challenge that requires research is how to optimize data transmission based on the network environment in which the monitoring equipment resides and the attributes of the monitoring data. Thirdly, railway monitoring equipment may have potential faults during operation, and how to use monitoring data to identify potential faults is also a problem that needs to be studied.

[0003] Furthermore, with the development of modern information technologies such as the Internet of Things (IoT), big data, and artificial intelligence, railway equipment operation and maintenance technologies are also facing the need for upgrading. Research institutions and companies at home and abroad have begun exploring IoT-based equipment monitoring solutions, big data-based fault prediction models, and 3D visualization-based monitoring platforms. However, these technologies have yet to form a complete solution, facing challenges such as insufficient secure data transmission, inadequate analysis of environmental correlations, and low accuracy in identifying potential faults.

[0004] In summary, there is an urgent need for an intelligent equipment operation and maintenance method and system based on railway operation and maintenance to solve the above technical problems. Summary of the Invention

[0005] (1) Technical problems to be solved

[0006] The purpose of the present invention is to provide an intelligent operation and maintenance method and system for equipment based on railway operation and maintenance, so as to realize intelligent operation and maintenance and potential fault identification of railway monitoring equipment.

[0007] (2) Technical solution

[0008] To achieve the above objectives, the present invention provides an intelligent equipment operation and maintenance method based on railway operation and maintenance, the method comprising the following steps:

[0009] S1, collects multi-dimensional operation and maintenance perception data, including equipment environment data and operation status data; the equipment environment data includes temperature data, humidity data, smoke concentration data, and video image data; the operation status data includes equipment operation parameters, alarm information, and historical operation and maintenance records; the equipment operation parameters include equipment CPU usage.

[0010] S2, cleans the multi-dimensional operation and maintenance perception data, performs adaptive multi-level encryption according to the sensitivity level and importance of the data to obtain a security data packet, adopts a dynamic transmission protocol switching algorithm to transmit the security data packet to the main station according to the stability and bandwidth conditions of the network transmission link, restores the security data packet received by the main station and verifies the data quality to obtain cleaned data with spatial correlation.

[0011] S3, based on the cleaned data with spatial correlation, uses satellite positioning technology and three-dimensional visualization technology to obtain a dynamic and interactive equipment operation and maintenance digital twin environment.

[0012] S4 uses time series feature extraction and multi-factor association analysis algorithms to identify potential equipment faults based on pre-set historical failure patterns and cleaned data with spatial correlations, and diagnoses, processes offline, and repairs equipment identified as having potential faults.

[0013] Furthermore, the method of performing data cleansing on the multi-dimensional operation and maintenance perception data, performing adaptive multi-level encryption according to the sensitivity level and importance of the data to obtain a secure data packet, transmitting the secure data packet to the master station using a dynamic transmission protocol switching algorithm according to the stability and bandwidth conditions of the network transmission link, restoring and verifying the data quality of the secure data packet received by the master station, and obtaining cleaned data with spatial association includes:

[0014] According to the null values, duplicate values and outliers existing in the multi-dimensional operation and maintenance perception data, a statistical filtering algorithm and an intelligent value filling method are used to obtain second temperature data, second humidity data, second smoke concentration data, second video image data, second equipment operating parameters, second alarm information, and second historical operation and maintenance records with unified format and complete data; according to the sensitivity level and importance of the data, the second temperature data, second humidity data, and second smoke concentration data are divided into three-level sensitive data, the second video image data and the second historical operation and maintenance records are divided into two-level sensitive data, and the second equipment operating parameters and the second alarm information are divided into one-level sensitive data; an adaptive multi-level encryption method is used, RSA asymmetric encryption is used for the first-level sensitive data to obtain first-level encrypted data, AES symmetric encryption is used for the second-level sensitive data to obtain second-level encrypted data, and lightweight encryption is used for the third-level sensitive data to obtain third-level encrypted data; the first-level encrypted data, the second-level encrypted data, and the third-level encrypted data are combined to obtain a secure data packet.

[0015] Based on the stability and bandwidth conditions of the network transmission link, a dynamic transmission protocol switching algorithm is used to transmit the security data packet to the main station; based on the security data packet received by the main station, a decryption algorithm is used to calculate the restored original data information; based on the preset data quality verification algorithm, the integrity rate of the restored original data information is evaluated; data with an integrity rate less than a pre-set integrity rate threshold is intelligently supplemented to obtain valid restored data; based on the valid restored data and the spatial location information of the computer room, a geographic coordinate mapping algorithm is used to obtain spatially associated cleaned data containing valid restored data and spatial location.

[0016] Furthermore, the method of transmitting the security data packet to the master station by using a dynamic transmission protocol switching algorithm according to the stability and bandwidth conditions of the network transmission link includes:

[0017] The signal strength, packet loss rate and delay time of the network transmission link are detected in real time using a pre-set first period as a sliding time window, and a network environment evaluation algorithm is used to obtain the network environment quality level within the sliding time window; the network environment quality level is one of level one, level two and level three; when the network environment quality level is level one, a standard data transmission protocol is used to simultaneously transmit level one encrypted data, level two encrypted data and level three encrypted data; when the network environment quality level is level two, a high-reliability transmission protocol is first used to transmit level one encrypted data, and after the transmission is completed, the level two encrypted data and the level three encrypted data are transmitted in sequence; when the network environment quality level is level three, a lightweight transmission protocol is used to transmit level one encrypted data, and the level two encrypted data and the level three encrypted data are temporarily stored in a local cache, and are transmitted after the network environment quality level is upgraded to level two or level one.

[0018] Furthermore, the method of detecting the signal strength, packet loss rate, and delay time of the network transmission link in real time using a preset first period as a sliding time window, and using a network environment evaluation algorithm to obtain the network environment quality level within the sliding time window includes:

[0019] Within the sliding time window, the signal strength, packet loss rate and delay time of the network transmission link are sampled in real time at every preset first sampling interval to obtain a signal strength sample set, a packet loss rate sample set and a delay time sample set within the sliding time window; the average value of the signal strength sample set is calculated to obtain the average signal strength, the average value of the packet loss rate sample set is calculated to obtain the average packet loss rate, and the average value of the delay time sample set is calculated to obtain the average delay time.

[0020] According to the preset signal strength reference range, the average signal strength is normalized into a signal strength index using forward correlation mapping; according to the preset packet loss rate reference range, the average packet loss rate is normalized into a packet loss rate index using a preset first reverse correlation mapping; according to the preset delay time reference range, the average delay time is normalized into a delay time index using a preset second reverse correlation mapping; the signal strength index, packet loss rate index and delay time index are multiplied by preset weight coefficients respectively and then summed to obtain a comprehensive network environment index; the comprehensive network environment index is compared with the preset first scoring threshold and second scoring threshold to obtain the network environment quality level within the sliding time window.

[0021] The average resource utilization of the network transmission link is counted at intervals of a preset second period, and the first scoring threshold and the second scoring threshold are dynamically adjusted according to the average resource utilization; the second period is an integer multiple of the first period.

[0022] Furthermore, the method of comparing the network environment comprehensive index with a preset first scoring threshold and a second scoring threshold to obtain a network environment quality level within a sliding time window includes:

[0023] When the comprehensive network environment index is greater than or equal to the first scoring threshold, the network environment quality level is level one; when the comprehensive network environment index is less than the first scoring threshold and greater than or equal to the second scoring threshold, the network environment quality level is level two; when the comprehensive network environment index is less than the second scoring threshold, the network environment quality level is level three.

[0024] Furthermore, the method for obtaining a dynamic interactive equipment operation and maintenance digital twin environment using satellite positioning technology and three-dimensional visualization technology based on the cleaned data with spatial correlation includes:

[0025] Beidou satellite positioning technology and geographic surveying and mapping technology are used to construct a three-dimensional spatial basic model of the railway operation and maintenance area; personnel location data is obtained based on the positioning devices worn by the operation and maintenance personnel; the three-dimensional spatial basic model is spatially aligned with the cleaned data and personnel location data with spatial association to obtain a basic visualization environment with geographic reference.

[0026] Extract valid restored data from the cleaned data with spatial association; divide the data corresponding to temperature data, humidity data, smoke concentration data, and video image data in the valid restored data into valid environmental monitoring data; divide the data corresponding to equipment operating parameters, alarm information, and historical operation and maintenance records in the valid restored data into valid equipment status data; use WebGL three-dimensional visualization technology to establish an association mapping between the valid equipment status data and the geometric entities of the corresponding equipment in the three-dimensional space basic model to obtain a digital twin model of the equipment; map the valid environmental monitoring data to the three-dimensional space basic model through visualization technology to obtain an environmental data visualization layer; map the personnel location data to the three-dimensional space basic model to obtain dynamic personnel icon data.

[0027] The equipment digital twin model, environmental data visualization layer, and dynamic personnel icon data are combined to obtain a dynamic and interactive equipment operation and maintenance digital twin environment.

[0028] Furthermore, the method of using time series feature extraction and multi-factor association analysis algorithms to identify potential equipment faults based on pre-set historical fault patterns and cleaned data with spatial correlation, and diagnosing, offline processing, and repairing equipment with identified potential faults includes:

[0029] The cleaned data with spatial correlation are sorted according to time series, and the time series features of effective environmental monitoring data and effective equipment status data are extracted. The time series features are matched with the feature templates in the pre-set historical fault mode library, and the matching similarity is calculated.

[0030] The device corresponding to the data with a matching similarity greater than a preset first fault threshold is marked as a potential fault device; the potential fault device represents a device that has been identified to have a potential fault; based on the computer room space location information and personnel location data corresponding to the potential fault device, the operation and maintenance personnel closest to the potential fault device is matched and recorded as the first operation and maintenance personnel; the computer room space location information corresponding to the potential fault device is pushed to the first operation and maintenance personnel; and the first operation and maintenance personnel performs offline processing and repair on the potential fault device.

[0031] Furthermore, the method of sorting the spatially correlated cleaned data according to time series, extracting time series features of effective environmental monitoring data and effective equipment status data, matching the time series features with feature templates in a preset historical fault mode library, and calculating matching similarity includes:

[0032] The cleaned data with spatial correlation are sorted according to the time series, and the preset second sliding time window is used to extract the temperature change rate, humidity change rate, smoke concentration change rate, video image gray value change rate, equipment operation parameter fluctuation rate, and periodic spectrum as time series features.

[0033] The time series features are standardized to obtain standardized time series features; based on the standardized time series features and the feature templates in the historical fault mode library, a Euclidean distance algorithm and a preset third reverse correlation function are used to perform similarity calculation to obtain a first similarity; the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate are associated with pattern recognition to obtain a second similarity; the second similarity represents the degree of conformity between the relationship between the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate and the physical law.

[0034] A weighted average of the second similarity and the first similarity is taken as the matching similarity.

[0035] Furthermore, the method of performing correlation pattern recognition on the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate to obtain the second similarity includes:

[0036] According to the corresponding time segment in the seasonal feature matching library to which the current time belongs, the preset benchmark functional relationship between the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate is obtained; the degree of deviation of the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate from the benchmark functional relationship is calculated to obtain a quantitative indicator characterizing the degree to which the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate conform to physical laws, which is recorded as the second similarity; the value of the second similarity is between 0 and 1; the seasonal feature matching library is obtained by pre-setting, and represents the typical functional relationship between the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate within the pre-divided time segment.

[0037] Based on the same inventive concept, on the other hand, the present invention also provides an intelligent equipment operation and maintenance system based on railway operation and maintenance, which includes: a data acquisition module, a data cleaning module, a digital twin module and a fault identification module connected in sequence.

[0038] The data acquisition module is used to collect multi-dimensional operation and maintenance perception data, including equipment environment data and operation status data; the equipment environment data includes temperature data, humidity data, smoke concentration data, and video image data; the operation status data includes equipment operation parameters, alarm information, and historical operation and maintenance records; the equipment operation parameters include equipment CPU usage.

[0039] The data cleaning module is used to clean the multi-dimensional operation and maintenance perception data, perform adaptive multi-level encryption according to the sensitivity level and importance of the data to obtain a secure data packet, adopt a dynamic transmission protocol switching algorithm to transmit the secure data packet to the main station according to the stability and bandwidth conditions of the network transmission link, restore and verify the data quality of the secure data packet received by the main station, and obtain cleaned data with spatial correlation.

[0040] The digital twin module is used to obtain a dynamic and interactive equipment operation and maintenance digital twin environment based on the cleaned data with spatial correlation using satellite positioning technology and three-dimensional visualization technology.

[0041] The fault identification module is used to use time series feature extraction and multi-factor association analysis algorithms to identify potential equipment faults based on pre-set historical fault patterns and cleaned data with spatial correlation, and to diagnose, offline process and repair equipment identified as having potential faults.

[0042] (3) Beneficial effects

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] By using satellite positioning technology and three-dimensional visualization technology, a dynamic and interactive digital twin environment for equipment operation and maintenance is obtained, realizing interactive perception of equipment status.

[0045] By adopting time series feature extraction and multi-factor association analysis algorithms, automatic identification of potential equipment failures is achieved, reducing equipment operation and maintenance labor costs and improving operation and maintenance efficiency.

[0046] Through the dynamic transmission protocol switching algorithm based on the network environment quality level, a data transmission solution that adapts to different network environments is obtained, achieving efficient and reliable data transmission under complex and changeable network conditions, and ensuring the transmission reliability and efficiency of key monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flowchart of an intelligent equipment operation and maintenance method based on railway operation and maintenance according to Example 1 of the present invention;

[0048] Figure 2This is a schematic diagram of the module composition of an intelligent equipment operation and maintenance system based on railway operation and maintenance according to Example 2 of the present invention. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0050] Before giving examples, it is necessary to explain the application scenarios of the present invention. The present invention is applied to data processing and potential fault identification of railway monitoring equipment. Along the 468.212-kilometer-long Hanhuang Railway, there are 51 machine room facilities, and various monitoring equipment are installed in these machine rooms to ensure the safety and stability of railway operations. These monitoring devices mainly include temperature sensors, humidity sensors, smoke detectors, and high-definition cameras, which are distributed in different machine rooms and collect machine room environmental data in real time. Monitoring data also includes operating status data of monitoring equipment, such as parameters such as the CPU usage of the processors connected to these monitoring devices, as well as alarm information and historical maintenance records generated by the equipment. These data are collectively referred to as multi-dimensional operation and maintenance perception data. For example, in the machine room of a certain railway section, the temperature sensor records the temperature value in the machine room once a minute; the humidity sensor records the humidity value once a minute; the smoke detector continuously monitors the smoke concentration value in the air; and the high-definition camera continuously captures video images of the machine room. At the same time, the monitoring equipment itself generates operational status data, including changes in CPU usage, device alarms (such as high-temperature warnings, network interruptions, and other abnormalities), and historical maintenance records (such as the time of the last component replacement and the personnel involved in maintenance). This raw, multi-dimensional sensory data often contains various issues, such as missing data, duplications, and outliers. Furthermore, the network environments of equipment rooms along the railway vary, impacting data transmission. This embodiment aims to cleanse monitoring data and optimize data transmission strategies based on the confidentiality level and network environment. Finally, the resulting data is used to identify faults in railway monitoring equipment. It should be noted that the equipment failures described in this embodiment do not refer to abnormal or missing monitoring data, but rather to hidden faults such as damage to the device's sensor or processor. In the field of railway monitoring equipment operation and maintenance, when the data collected by the monitoring equipment is abnormal or deviates from the true value, it cannot be directly assumed that the monitoring equipment is faulty. This is because abnormal monitoring data can also be caused by limitations of the signal processing algorithm or environmental interference or network transmission interference, and does not necessarily indicate a fault in the device's sensor or processor itself. However, when the abnormal characteristics of the monitoring data meet certain rules, it may mean two situations: First, the sensor device or processor and other components of the monitoring equipment are suffering from cumulative damage. When the accumulated damage exceeds the critical point, the device may fail. Second, the sensor device or processor and other components of the monitoring equipment have failed, but because the abnormal monitoring data may not be caused by the monitoring equipment itself, the operation and maintenance personnel are not yet aware of whether the failure exists. In this embodiment, the above two situations are collectively referred to as potential failures. After the potential failure is identified, the operation and maintenance personnel need to go to the site to dismantle, diagnose and repair the monitoring equipment with the potential failure.

[0051] Example 1: Figure 1 As shown, this embodiment provides an intelligent equipment operation and maintenance method based on railway operation and maintenance, the method comprising the following steps:

[0052] S1, collects multi-dimensional operation and maintenance perception data, including equipment environment data and operation status data; the equipment environment data includes temperature data, humidity data, smoke concentration data, and video image data; the operation status data includes equipment operation parameters, alarm information, and historical operation and maintenance records; the equipment operation parameters include equipment CPU usage.

[0053] S2, cleans the multi-dimensional operation and maintenance perception data, performs adaptive multi-level encryption according to the sensitivity level and importance of the data to obtain a security data packet, adopts a dynamic transmission protocol switching algorithm to transmit the security data packet to the main station according to the stability and bandwidth conditions of the network transmission link, restores the security data packet received by the main station and verifies the data quality to obtain cleaned data with spatial correlation.

[0054] S3, based on the cleaned data with spatial correlation, uses satellite positioning technology and three-dimensional visualization technology to obtain a dynamic and interactive equipment operation and maintenance digital twin environment.

[0055] S4 uses time series feature extraction and multi-factor association analysis algorithms to identify potential equipment faults based on pre-set historical failure patterns and cleaned data with spatial correlations, and diagnoses, processes offline, and repairs equipment identified as having potential faults.

[0056] For example, multi-dimensional operation and maintenance perception data is collected. The collected multi-dimensional perception data usually has various problems, such as missing data, duplication, or outliers.

[0057] The multidimensional operation and maintenance perception data is cleansed and adaptively encrypted at multiple levels based on the data's sensitivity and importance to create a secure data packet. Based on the stability and bandwidth of the network transmission link, a dynamic transmission protocol switching algorithm is used to transmit the secure data packet to the master station. The received secure data packet is restored and data quality verified to generate cleansed data with spatial correlation. This cleansed data with spatial correlation is more accurate than the multidimensional operation and maintenance perception data and is also associated with the spatial location information of the railway machine room, facilitating subsequent visualization and analysis.

[0058] Based on the cleaned data, a dynamic and interactive digital twin environment for equipment operations and maintenance was constructed using Beidou satellite positioning technology and WebGL 3D visualization. Within this digital twin environment, every machine room and piece of equipment along the railway line has its own corresponding 3D model, with equipment status and environmental data presented in an intuitive manner. This digital twin allows operators to monitor equipment operation in real time and quickly identify potential issues.

[0059] To identify potential equipment failures, we use time series feature extraction and multi-factor association analysis algorithms to conduct data mining on equipment status. By matching these data with pre-set historical failure patterns, we identify potential equipment failures and immediately notify the nearest maintenance personnel to conduct on-site diagnosis, offline processing, and repair the equipment.

[0060] Furthermore, the method of performing data cleansing on the multi-dimensional operation and maintenance perception data, performing adaptive multi-level encryption according to the sensitivity level and importance of the data to obtain a secure data packet, transmitting the secure data packet to the master station using a dynamic transmission protocol switching algorithm according to the stability and bandwidth conditions of the network transmission link, restoring and verifying the data quality of the secure data packet received by the master station, and obtaining cleaned data with spatial association includes:

[0061] According to the null values, duplicate values and outliers existing in the multi-dimensional operation and maintenance perception data, a statistical filtering algorithm and an intelligent value filling method are used to obtain second temperature data, second humidity data, second smoke concentration data, second video image data, second equipment operating parameters, second alarm information, and second historical operation and maintenance records with unified format and complete data; according to the sensitivity level and importance of the data, the second temperature data, second humidity data, and second smoke concentration data are divided into three-level sensitive data, the second video image data and the second historical operation and maintenance records are divided into two-level sensitive data, and the second equipment operating parameters and the second alarm information are divided into one-level sensitive data; an adaptive multi-level encryption method is used, RSA asymmetric encryption is used for the first-level sensitive data to obtain first-level encrypted data, AES symmetric encryption is used for the second-level sensitive data to obtain second-level encrypted data, and lightweight encryption is used for the third-level sensitive data to obtain third-level encrypted data; the first-level encrypted data, the second-level encrypted data, and the third-level encrypted data are combined to obtain a secure data packet.

[0062] Based on the stability and bandwidth conditions of the network transmission link, a dynamic transmission protocol switching algorithm is used to transmit the security data packet to the main station; based on the security data packet received by the main station, a decryption algorithm is used to calculate the restored original data information; based on the preset data quality verification algorithm, the integrity rate of the restored original data information is evaluated; data with an integrity rate less than a pre-set integrity rate threshold is intelligently supplemented to obtain valid restored data; based on the valid restored data and the spatial location information of the computer room, a geographic coordinate mapping algorithm is used to obtain spatially associated cleaned data containing valid restored data and spatial location.

[0063] For example, the multi-dimensional operational and maintenance perception data from various machine rooms along the railway line suffers from various quality issues and requires systematic processing before it can be effectively utilized. The primary issues faced are missing data, duplication, and outliers. For example, during temperature data collection in one machine room, network transmission issues may result in null values for several consecutive hours. In another machine room, humidity data at the same moment is recorded multiple times due to the retransmission mechanism in network transmission. In a third machine room, smoke detectors occasionally output abnormal readings that deviate significantly from the normal range due to external electromagnetic interference.

[0064] First, data cleaning is performed using statistical filtering algorithms and intelligent value-adding methods. For example, for missing temperature data, by analyzing the temperature change patterns of the computer room during the same historical period and combining them with the meteorological conditions of the day, time series interpolation technology is used to fill in the gaps. For repeated humidity data, redundant records are identified and removed by comparing timestamps and numerical consistency. For abnormal readings of smoke detectors, data that clearly exceeds the normal range is marked and replaced with reasonable estimates based on the outlier detection method in statistics. Through the statistical filtering algorithm and intelligent value-adding method, second temperature data, second humidity data, second smoke concentration data, second video image data, second equipment operating parameters, second alarm information, and second historical operation and maintenance records with unified format and complete data are obtained.

[0065] Then, based on data security requirements, the cleaned data is protected in a hierarchical manner. According to the sensitivity level and importance of the data, the second temperature data, the second humidity data, and the second smoke concentration data are classified as three-level sensitive data. Although the second temperature data, the second humidity data, and the second smoke concentration data are important, the degree of harm caused by leakage is relatively low; the second video image data and the second historical operation and maintenance records are classified as two-level sensitive data. Because these data may contain information such as equipment layout and maintenance strategy, leakage will lead to more serious consequences; the second equipment operating parameters and the second alarm information are classified as first-level sensitive data. Because these data are directly related to the operating status and safety alarms of railway equipment, they are crucial to railway operation safety. The importance of the first-level sensitive data, the second-level sensitive data, and the third-level sensitive data decreases in turn. For sensitive data of different levels, an adaptive multi-level encryption method is used for protection. For the most sensitive Level 1 data (equipment operating parameters and alarm information), RSA asymmetric encryption technology is used, using public key encryption and private key decryption to ensure security during transmission. For Level 2 sensitive data (video images and historical maintenance records), AES symmetric encryption technology is used to ensure security while balancing processing efficiency. For Level 3 sensitive data (temperature, humidity, and smoke concentration data), lightweight encryption methods with low computational overhead, such as PRESENT encryption, are used to optimize processing performance while ensuring basic security. After encryption, these three types of data are converted into Level 1, Level 2, and Level 3 encrypted data, respectively, which are then combined into secure data packets.

[0066] Because the network environments of various computer rooms along the Hanhuang Railway vary significantly, transmission strategies need to be dynamically adjusted based on actual network conditions. By continuously monitoring the stability and bandwidth of the network links from each computer room to the central station, appropriate transmission protocols are adopted for different network quality levels. Computer rooms in plain areas with good network conditions can transmit all levels of encrypted data simultaneously. Computer rooms in mountainous areas with poor network conditions prioritize the transmission of level 1 sensitive data, while other data is temporarily stored locally until network conditions improve before transmission. This dynamically adjusted transmission strategy ensures the timely arrival of critical data while also ensuring the integrity of other data.

[0067] When data packets arrive at the central station, the original data is restored using a corresponding decryption algorithm and a data quality assessment is performed. If data that may have been damaged during transmission falls below a preset integrity threshold, it is repaired using intelligent value-adding technology. For example, if a video segment is partially lost, it can be reconstructed by interpolating the content of previous and subsequent frames. For partially missing device operating parameter records, interpolation estimates are performed by combining historical data with current environmental conditions, resulting in more complete and reliable restored data.

[0068] Finally, based on the effective restoration of the data and the spatial location information of the computer room, a geographic coordinate mapping algorithm is used to obtain cleaned data with spatial association. This ensures that the data not only contains the numerical values of various monitoring parameters, but also has geographic location attributes, laying the foundation for subsequent three-dimensional visualization and spatial analysis.

[0069] Furthermore, the method of transmitting the security data packet to the master station by using a dynamic transmission protocol switching algorithm based on the stability and bandwidth conditions of the network transmission link includes:

[0070] The signal strength, packet loss rate and delay time of the network transmission link are detected in real time using a pre-set first period as a sliding time window, and a network environment evaluation algorithm is used to obtain the network environment quality level within the sliding time window; the network environment quality level is one of level one, level two and level three; when the network environment quality level is level one, a standard data transmission protocol is used to simultaneously transmit level one encrypted data, level two encrypted data and level three encrypted data; when the network environment quality level is level two, a high-reliability transmission protocol is first used to transmit level one encrypted data, and after the transmission is completed, the level two encrypted data and the level three encrypted data are transmitted in sequence; when the network environment quality level is level three, a lightweight transmission protocol is used to transmit level one encrypted data, and the level two encrypted data and the level three encrypted data are temporarily stored in a local cache, and are transmitted after the network environment quality level is upgraded to level two or level one.

[0071] For example, in the actual operating environment of the Handan-Huanghuai Railway, the network environments of the 51 computer rooms distributed along the line vary significantly. For example, computer rooms located in urban plains generally have stable network connections with high signal strength, low packet loss rates, and short latency times. However, computer rooms located in mountainous areas or far away from communication base stations often face network problems such as weak signals, high packet loss rates, and long latency times, and may even experience temporary network interruptions in severe weather conditions. To cope with complex network environments, this embodiment uses a dynamic transmission protocol switching algorithm to optimize data transmission strategies.

[0072] First, using a pre-set first period (e.g., 5 minutes) as a sliding time window, the network transmission link from each computer room to the master station is monitored in real time. Within this sliding time window, network probing technology continuously collects three key parameters: signal strength, packet loss rate, and latency. For example, in a computer room located in a mountainous area, the network signal strength fluctuates at a low level, the packet loss rate fluctuates, and the latency frequently exceeds the normal range. A comprehensive analysis of signal strength, packet loss rate, and latency is performed, using a network environment assessment algorithm to determine the network quality level within this sliding time window.

[0073] Based on the assessment results, network environment quality is categorized into three levels: Level 1 indicates a good network environment suitable for high-speed transmission of large amounts of data; Level 2 indicates an average network environment, capable of reliable but not necessarily high-speed data transmission; and Level 3 indicates a poor network environment suitable only for transmitting small amounts of critical data. When a computer room's network environment is assessed as Level 1, standard data transmission protocols (such as TCP / IP) are used to transmit all types of encrypted data simultaneously. In this scenario, Level 1 encrypted data (including equipment operating parameters and alarm information), Level 2 encrypted data (including video images and historical maintenance records), and Level 3 encrypted data (including temperature, humidity, and smoke concentration data) can all be quickly and reliably transmitted to the master station, ensuring the monitoring center has a comprehensive understanding of the equipment status and environmental conditions in the computer room. When the network environment is assessed as Level 2, a more cautious transmission strategy is adopted. In this case, highly reliable transmission protocols (such as MQTT, which has stronger error correction capabilities and retransmission mechanisms) are prioritized for transmitting Level 1 encrypted data, ensuring that the most critical equipment operating parameters and alarm information reach the master station accurately and without error. Only after Level 1 encrypted data has been successfully transmitted are Level 2 and Level 3 encrypted data transmitted in sequence. While this phased transmission approach increases overall transmission time, it ensures that even under poor network conditions, critical information is not lost due to congestion or transmission errors. When the network quality is assessed as Level 3, representing extremely poor network conditions, only lightweight transmission protocols (such as UDP) are used to transmit Level 1 encrypted data. While these protocols do not guarantee complete data delivery, their low resource consumption makes them ideal for transmitting small amounts of critical data under extremely poor network conditions. Furthermore, Level 2 and Level 3 encrypted data are temporarily stored in a local cache until the network quality improves to Level 2 or Level 1 before transmission. This ensures that even under the worst network conditions, even the most basic equipment status information can be promptly transmitted to the master station, providing essential assurance for railway operational safety. By employing a transmission strategy that dynamically adjusts based on network quality, the timeliness and reliability of monitoring data transmission are maximized in complex and changing network environments.

[0074] Furthermore, the method of detecting the signal strength, packet loss rate, and delay time of the network transmission link in real time using a preset first period as a sliding time window, and using a network environment evaluation algorithm to obtain the network environment quality level within the sliding time window includes:

[0075] Within the sliding time window, the signal strength, packet loss rate and delay time of the network transmission link are sampled in real time at every preset first sampling interval to obtain a signal strength sample set, a packet loss rate sample set and a delay time sample set within the sliding time window; the average value of the signal strength sample set is calculated to obtain the average signal strength, the average value of the packet loss rate sample set is calculated to obtain the average packet loss rate, and the average value of the delay time sample set is calculated to obtain the average delay time.

[0076] According to the preset signal strength reference range, the average signal strength is normalized into a signal strength index using forward correlation mapping; according to the preset packet loss rate reference range, the average packet loss rate is normalized into a packet loss rate index using a preset first reverse correlation mapping; according to the preset delay time reference range, the average delay time is normalized into a delay time index using a preset second reverse correlation mapping; the signal strength index, packet loss rate index and delay time index are multiplied by preset weight coefficients respectively and then summed to obtain a comprehensive network environment index; the comprehensive network environment index is compared with the preset first scoring threshold and second scoring threshold to obtain the network environment quality level within the sliding time window.

[0077] The average resource utilization of the network transmission link is counted at intervals of a preset second period, and the first scoring threshold and the second scoring threshold are dynamically adjusted according to the average resource utilization; the second period is an integer multiple of the first period.

[0078] For example, if the first period is set to 5 minutes, the sliding time window is 5 minutes. Within the 5-minute sliding time window, the signal strength, packet loss rate, and delay time of the network transmission link are sampled in real time at every preset first sampling interval (set to 10 seconds). Taking a computer room located in a mountainous area as an example, within a 5-minute sliding time window, a total of 30 signal strength samples, 30 packet loss rate samples, and 30 delay time samples are collected, forming the signal strength sample set, packet loss rate sample set, and delay time sample set, respectively. From these sample sets, the average signal strength, average packet loss rate, and average delay time within the time window are obtained by averaging.

[0079] However, these three parameters cannot be directly compared or combined due to their different units and meanings. For example, signal strength is measured in decibel milliwatts, with larger values indicating stronger signals. Packet loss rate is expressed as a percentage, ranging from 0 to 100, with smaller values indicating better network quality. Latency is measured in milliseconds, typically ranging from tens to hundreds, with smaller values indicating better network quality. Therefore, three different mapping methods are used to convert these parameters into standardized index values. For average signal strength, a positive correlation mapping is used, mapping signal strength to a signal strength index between 0 and 1, with stronger signals corresponding to higher index values. For example, when signal strength is above -60 decibel milliwatts, the signal strength is mapped to a signal strength index close to 1; when signal strength is below -90 decibel milliwatts, the signal strength is mapped to an index close to 0. For average packet loss rate and average latency, since they are negatively correlated with network quality, with smaller values indicating better quality, a negative correlation mapping is used. Specifically, through the pre-set first reverse association mapping, the packet loss rate is converted into a packet loss rate index, and the lower the packet loss rate, the higher the corresponding index value; through the pre-set second reverse association mapping, the delay time is converted into a delay time index, and the shorter the delay time, the higher the corresponding index value. Through the above processing, the three parameters are all standardized into index values between 0 and 1, and all follow the unified meaning of "the larger the value, the better the network quality". According to the relative importance of these three indices in network quality assessment, they are assigned pre-set weight coefficients. For example, a higher weight is given to the packet loss rate index because the impact of packet loss on data transmission is particularly significant; while relatively lower weights are given to the signal strength index and the delay time index. By multiplying these three indices by their respective weight coefficients and summing them up, a comprehensive network environment index that comprehensively reflects the quality of the network environment is obtained.

[0080] To convert the continuous network environment comprehensive index into discrete quality levels, a first scoring threshold and a second scoring threshold are set. The network environment comprehensive index is compared with the preset first and second scoring thresholds to determine the network environment quality level within the sliding time window. For example, when the comprehensive index is higher than the first scoring threshold, the network environment is judged as level 1 quality; when the comprehensive index is lower than the first scoring threshold but higher than the second scoring threshold, the network environment is judged as level 2 quality; and when the comprehensive index is lower than the second scoring threshold, the network environment is judged as level 3 quality.

[0081] However, fixed scoring thresholds cannot cope with complex and changing network environments. For example, during periods of high overall network load, even a relatively good network environment may not meet transmission timeliness and reliability requirements. Therefore, the average resource utilization of network transmission links is calculated at intervals of a pre-set second period (set as an integer multiple of the first period, such as one hour), and the first and second scoring thresholds are dynamically adjusted based on this metric. For example, when high overall network resource utilization is detected, a pre-set threshold adjustment, whose value is positive and positively correlated with the average resource utilization, is added to the first and second scoring thresholds to increase the first and second scoring thresholds, thereby avoiding network congestion. Conversely, when network resource utilization is low, a pre-set threshold adjustment, whose value is negative and whose absolute value is positively correlated with the average resource utilization, is added to the first and second scoring thresholds to lower the first and second scoring thresholds, thereby improving network resource utilization.

[0082] Furthermore, the method of comparing the network environment comprehensive index with a preset first scoring threshold and a second scoring threshold to obtain a network environment quality level within a sliding time window includes:

[0083] When the comprehensive network environment index is greater than or equal to the first scoring threshold, the network environment quality level is level one; when the comprehensive network environment index is less than the first scoring threshold and greater than or equal to the second scoring threshold, the network environment quality level is level two; when the comprehensive network environment index is less than the second scoring threshold, the network environment quality level is level three.

[0084] Exemplarily, the first scoring threshold and the second scoring threshold are pre-set based on historical data analysis and actual transmission requirements. For example, the first scoring threshold is set to 0.8 and the second scoring threshold is set to 0.5, thereby dividing the network environment quality into three different levels.

[0085] When the comprehensive network environment index is greater than or equal to the first scoring threshold, it indicates that the current network environment is in good condition, with high signal strength, low packet loss rate, and short latency, making it suitable for high-speed transmission of large amounts of data. Therefore, it is classified as Level 1 quality. For example, a computer room in a plain area has a comprehensive network environment index of 0.9, exceeding the first scoring threshold of 0.8 and therefore classified as Level 1 quality. In this case, the computer room can use standard data transmission protocols to transmit all levels of encrypted data simultaneously without worrying about network congestion or transmission failures. When the comprehensive network environment index is less than the first scoring threshold but greater than or equal to the second scoring threshold, it indicates that the current network environment is fair. Signal fluctuations, occasional packet loss, or increased latency may exist, making it unsuitable for simultaneous transmission of large amounts of data, but basic data transmission reliability can still be guaranteed. Therefore, it is classified as Level 2 quality. For example, a computer room in a hilly area has a comprehensive network environment index of 0.6, classified as Level 2 quality. Therefore, this computer room uses a highly reliable transmission protocol to prioritize the transmission of Level 1 encrypted data (critical equipment operating parameters and alarm information), followed by the transmission of other data. When the comprehensive network environment index falls below the second scoring threshold, it indicates that the current network environment is poor, potentially experiencing weak signals, significant packet loss, or severe latency. This makes the network suitable only for transmitting small amounts of critical data, and therefore is classified as Level 3 quality. For example, a data center in a mountainous area experiencing severe weather conditions had its comprehensive network environment index drop to 0.3, below the second scoring threshold of 0.5, resulting in a Level 3 quality rating. In this extreme case, the data center will only transmit Level 1 encrypted data using a lightweight transmission protocol and temporarily store other data locally until network conditions improve before transmitting it again.

[0086] Through a hierarchical decision-making mechanism, appropriate data transmission strategies can be adopted based on the actual network environment, ensuring the timely transmission of critical data while avoiding network congestion or transmission failures caused by hastily transmitting large amounts of data under poor network conditions. This maximizes the efficiency and reliability of data transmission. This technology effectively improves the robustness of remote monitoring data transmission for equipment in the Hanhuang Railway's machine room, which is distributed across complex terrain.

[0087] Furthermore, the method for obtaining a dynamic interactive equipment operation and maintenance digital twin environment using satellite positioning technology and three-dimensional visualization technology based on the cleaned data with spatial correlation includes:

[0088] Beidou satellite positioning technology and geographic surveying and mapping technology are used to construct a three-dimensional spatial basic model of the railway operation and maintenance area; personnel location data is obtained based on the positioning devices worn by the operation and maintenance personnel; the three-dimensional spatial basic model is spatially aligned with the cleaned data and personnel location data with spatial association to obtain a basic visualization environment with geographic reference.

[0089] Extract valid restored data from the cleaned data with spatial association; divide the data corresponding to temperature data, humidity data, smoke concentration data, and video image data in the valid restored data into valid environmental monitoring data; divide the data corresponding to equipment operating parameters, alarm information, and historical operation and maintenance records in the valid restored data into valid equipment status data; use WebGL three-dimensional visualization technology to establish an association mapping between the valid equipment status data and the geometric entities of the corresponding equipment in the three-dimensional space basic model to obtain a digital twin model of the equipment; map the valid environmental monitoring data to the three-dimensional space basic model through visualization technology to obtain an environmental data visualization layer; map the personnel location data to the three-dimensional space basic model to obtain dynamic personnel icon data.

[0090] The equipment digital twin model, environmental data visualization layer, and dynamic personnel icon data are combined to obtain a dynamic and interactive equipment operation and maintenance digital twin environment.

[0091] For example, to intuitively display equipment operating status and environmental data, a highly realistic 3D visualization environment was constructed. First, Beidou satellite positioning technology was used to precisely locate each machine room along the railway line and obtain their geographic coordinates. Simultaneously, geo-mapping technology was used to collect terrain data surrounding the railway line. This led to the construction of a 3D spatial base model that closely matches the real-world geographic environment. This 3D base model encompasses not only the railway line itself but also each machine room building and the equipment layout within. To enable real-time monitoring of personnel locations, each operation and maintenance personnel was equipped with a smart terminal device equipped with a built-in Beidou positioning module. These devices periodically transmit their location information to the master station, generating accurate personnel location data. Using a location mapping algorithm, the real-time updated personnel location data was spatially aligned with the 3D spatial base model, ensuring that personnel locations in the model remained synchronized with reality. Furthermore, spatially correlated cleaned data was also linked to the 3D spatial base model through spatial coordinate mapping, resulting in a geographically referenced base visualization environment.

[0092] From the cleaned data with spatial associations, valid restored data is extracted and classified according to data type. Temperature data, humidity data, smoke concentration data, and video image data are classified as valid environmental monitoring data, which reflect the environmental conditions in the computer room; equipment operating parameters, alarm information, and historical operation and maintenance records are classified as valid equipment status data, which directly reflect the working status of the equipment. Using WebGL three-dimensional visualization technology, an association mapping is established between the valid equipment status data and the geometric entities of the corresponding equipment in the three-dimensional space basic model to obtain a digital twin model of the equipment. The valid environmental monitoring data is mapped to the three-dimensional space basic model through visualization technology to obtain an environmental data visualization layer. The personnel location data is mapped to the three-dimensional space basic model to obtain dynamic personnel icon data. Finally, a complete dynamic interactive equipment operation and maintenance digital twin environment is constructed.

[0093] Furthermore, the method of using time series feature extraction and multi-factor association analysis algorithms to identify potential equipment faults based on pre-set historical fault patterns and cleaned data with spatial correlation, and diagnosing, offline processing, and repairing equipment with identified potential faults includes:

[0094] The cleaned data with spatial correlation are sorted according to time series, and the time series features of effective environmental monitoring data and effective equipment status data are extracted. The time series features are matched with the feature templates in the pre-set historical fault mode library, and the matching similarity is calculated.

[0095] The device corresponding to the data with a matching similarity greater than a preset first fault threshold is marked as a potential fault device; the potential fault device represents a device that has been identified to have a potential fault; based on the computer room space location information and personnel location data corresponding to the potential fault device, the operation and maintenance personnel closest to the potential fault device is matched and recorded as the first operation and maintenance personnel; the computer room space location information corresponding to the potential fault device is pushed to the first operation and maintenance personnel; and the first operation and maintenance personnel performs offline processing and repair on the potential fault device.

[0096] For example, when the abnormal characteristics of the spatially correlated cleaned data meet certain rules, it may mean two situations: one is that the sensor device or processor and other components of the monitoring equipment are suffering from cumulative damage. When the accumulated damage exceeds the critical point, the device may fail. The second is that the sensor device or processor and other components of the monitoring equipment have failed, but because the abnormal monitoring data may not be caused by the monitoring equipment itself, the operation and maintenance personnel do not yet know whether the failure exists. In this embodiment, the above two situations are collectively referred to as potential failures. After the potential failure is identified, the operation and maintenance personnel need to go to the site to dismantle, diagnose and repair the monitoring equipment with the potential failure.

[0097] First, the spatially correlated cleaned data is sorted according to time series. For example, the spatially correlated cleaned data for each monitoring device in a computer room is arranged in chronological order to form a continuous data sequence. From this continuous data sequence, the time series features of the valid environmental monitoring data and valid device status data are extracted. These time series features include not only the data values at each moment but also the patterns of data change over time, such as upward trends, periodic fluctuations, or sudden changes, specifically manifested in rates of change, periodic spectra, and sudden changes. The extracted time series features are matched against feature templates in a pre-set historical fault pattern library, and the matching similarity is calculated. The historical fault pattern library is built based on long-term accumulated maintenance records and failure case analysis and contains data features of various types of equipment under potential fault conditions. For example, a potential fault in a certain temperature sensor model may exhibit the following characteristics: an abnormal decrease in the CPU usage of the processor connected to the temperature sensor and a constant temperature data value, or an abnormal increase in the CPU usage of the processor connected to the temperature sensor and erratic temperature fluctuations. The matching similarity is calculated by calculating the degree of similarity between the spatially correlated cleaned data and these historical fault patterns. When the matching similarity of a device exceeds a preset first fault threshold, it means that the device is likely to have a potential fault, and the device is marked as a potential fault device.

[0098] Based on the spatial location information of the computer room corresponding to the potential faulty equipment and the location data of the currently on-duty maintenance personnel, the maintenance personnel closest to the equipment and with the corresponding skills are automatically matched and recorded as the first operation and maintenance personnel. For example, when the temperature sensor in a certain computer room is determined to be a potential faulty equipment, the location matching algorithm finds that there is currently an operation and maintenance personnel inspecting the nearby lines, so he is designated as the first operation and maintenance personnel. The key information such as the spatial location information of the computer room corresponding to the potential faulty equipment, the equipment type, the predicted fault type and the handling suggestions are pushed to the mobile terminal device of the first operation and maintenance personnel. After receiving the task, the first operation and maintenance personnel goes to the designated location to diagnose, inspect offline and repair the potential faulty equipment. The diagnosis, offline inspection and repair include equipment status detection, parameter testing, parts replacement or software reset, etc. The specific operations depend on the type of fault.

[0099] Furthermore, the method of sorting the spatially correlated cleaned data according to time series, extracting time series features of effective environmental monitoring data and effective equipment status data, matching the time series features with feature templates in a preset historical fault mode library, and calculating matching similarity includes:

[0100] The cleaned data with spatial correlation are sorted according to the time series, and the preset second sliding time window is used to extract the temperature change rate, humidity change rate, smoke concentration change rate, video image gray value change rate, equipment operation parameter fluctuation rate, and periodic spectrum as time series features.

[0101] The time series features are standardized to obtain standardized time series features; based on the standardized time series features and the feature templates in the historical fault mode library, a Euclidean distance algorithm and a preset third reverse correlation function are used to perform similarity calculation to obtain a first similarity; the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate are associated with pattern recognition to obtain a second similarity; the second similarity represents the degree of conformity between the relationship between the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate and the physical law.

[0102] A weighted average of the second similarity and the first similarity is taken as the matching similarity.

[0103] Exemplarily, the cleaned data with spatial correlation are sorted according to the time series to form a continuous data sequence. The time series data is segmented using a preset second sliding time window. The second sliding time window is usually set to a range from a few hours to a day, depending on the device type and parameter characteristics. Time series features are extracted from the data in the second sliding time window, and the time series features include temperature change rate, humidity change rate, smoke concentration change rate, video image gray value change rate, equipment operation parameter fluctuation rate, and periodic spectrum. The periodic spectrum is calculated by Fourier decomposition. The temperature change rate reflects the speed at which the monitored temperature increases or decreases; the humidity change rate reflects the speed at which the monitored ambient humidity increases or decreases; the smoke concentration change rate reflects the speed at which the abnormal gas concentration increases or decreases; the video image gray value change rate reflects the degree of change in the ambient video image; the equipment operation parameter fluctuation rate reflects the speed of change in the CPU usage of the processor connected to the monitoring device; the numerical mutation rate reflects the mutation of the monitoring data; and the periodic spectrum reflects the periodic change law of the monitoring data at different time scales.

[0104] To make different types of time series features comparable, the extracted time series features are standardized. This standardization process comprehensively considers the normal range of each time series feature and converts each time series feature into a dimensionless standard value, known as a standardized time series feature. This standardization process includes algorithms such as normalization. The standardized time series features are compared with feature templates in a historical failure pattern library. This historical failure pattern library is built based on a long history of accumulated equipment failure cases and contains typical manifestations of various potential faults. For example, improperly setting the parameters of the moving average filter algorithm in the temperature sensor firmware can amplify periodic noise, resulting in characteristic subharmonics in the periodic spectrum of the monitored temperature values. A damaged ADC chip, drifting reference voltage, or unstable sampling clock in the temperature sensor can cause the monitored temperature change rate to be excessively large. A similarity calculation is performed using the Euclidean distance algorithm based on the standardized time series features and the feature templates in the historical failure pattern library. The Euclidean distance algorithm calculates the straight-line distance between two points in a multidimensional space; smaller distances indicate higher similarity. The Euclidean distance is input into a pre-set third inverse correlation function to obtain a first similarity. The greater the value of the first similarity, the greater the similarity between the standardized time series features and the feature templates in the historical fault pattern library, that is, the greater the possibility of a potential fault. The second similarity is obtained by performing correlation pattern recognition on the temperature change rate, humidity change rate, and smoke concentration change rate. The second similarity is a quantitative indicator that represents the degree to which the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate conform to physical laws. The greater the second similarity, the less consistent the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate are with physical laws, that is, the greater the possibility of a potential fault. The weighted average of the second similarity and the first similarity is taken as the matching similarity.

[0105] Furthermore, the method of performing correlation pattern recognition on the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate to obtain the second similarity includes:

[0106] According to the corresponding time segment in the seasonal feature matching library to which the current time belongs, the preset benchmark functional relationship between the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate is obtained; the degree of deviation of the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate from the benchmark functional relationship is calculated to obtain a quantitative indicator characterizing the degree to which the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate conform to physical laws, which is recorded as the second similarity; the value of the second similarity is between 0 and 1; the seasonal feature matching library is obtained by pre-setting, and represents the typical functional relationship between the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate within the pre-divided time segment.

[0107] For example, under normal circumstances, a specific relationship exists between the temperature change rate, humidity change rate, smoke concentration change rate, and device operating parameter fluctuation rate. This relationship is recorded as a baseline function relationship. For example, when the temperature change rate is high, to maintain data collection accuracy, the device operating parameter fluctuation rate, i.e., the device CPU usage change rate, will also be high. Therefore, the correlation between the temperature change rate and the device operating parameter fluctuation rate can be measured using the baseline function relationship between the temperature change rate and the device operating parameter fluctuation rate. This baseline function relationship is also seasonal. For example, in summer, the temperature change rate and the humidity change rate exhibit a strong positive correlation, while this relationship is less pronounced in winter. The humidity change rate and the smoke concentration change rate exhibit a negative correlation within a certain range. The degree of deviation of the temperature change rate, humidity change rate, and smoke concentration change rate from the baseline function relationship is calculated to obtain a quantitative indicator representing the degree to which the temperature change rate, humidity change rate, and smoke concentration change rate conform to physical laws, recorded as a second similarity. The greater the second similarity, the greater the degree of deviation of the temperature change rate, humidity change rate, and smoke concentration change rate from the baseline function relationship. The seasonal feature matching library is pre-set.

[0108] Example 2: Based on the same inventive concept, Figure 2 As shown, this embodiment also provides an equipment intelligent operation and maintenance system based on railway operation and maintenance, and the system includes: a data acquisition module, a data cleaning module, a digital twin module and a fault identification module connected in sequence.

[0109] The data acquisition module is used to collect multi-dimensional operation and maintenance perception data, including equipment environment data and operation status data; the equipment environment data includes temperature data, humidity data, smoke concentration data, and video image data; the operation status data includes equipment operation parameters, alarm information, and historical operation and maintenance records; the equipment operation parameters include equipment CPU usage.

[0110] The data cleaning module is used to clean the multi-dimensional operation and maintenance perception data, perform adaptive multi-level encryption according to the sensitivity level and importance of the data to obtain a secure data packet, adopt a dynamic transmission protocol switching algorithm to transmit the secure data packet to the main station according to the stability and bandwidth conditions of the network transmission link, restore and verify the data quality of the secure data packet received by the main station, and obtain cleaned data with spatial correlation.

[0111] The digital twin module is used to obtain a dynamic and interactive equipment operation and maintenance digital twin environment based on the cleaned data with spatial correlation using satellite positioning technology and three-dimensional visualization technology.

[0112] The fault identification module is used to use time series feature extraction and multi-factor association analysis algorithms to identify potential equipment faults based on pre-set historical fault patterns and cleaned data with spatial correlation, and to diagnose, offline process and repair equipment identified as having potential faults.

[0113] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0114] Finally, it should be noted that although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent equipment operation and maintenance method based on railway operation and maintenance, characterized in that: The method comprises the following steps: S1, collect multi-dimensional operation and maintenance perception data, including equipment environment data and operation status data; the equipment environment data includes temperature data, humidity data, smoke concentration data, and video image data; the operation status data includes equipment operation parameters, alarm information, and historical operation and maintenance records; the equipment operation parameters include equipment CPU usage; S2, performing data cleansing on the multi-dimensional operation and maintenance perception data, performing adaptive multi-level encryption based on the sensitivity level and importance of the data to obtain a secure data packet, transmitting the secure data packet to the master station using a dynamic transmission protocol switching algorithm based on the stability and bandwidth conditions of the network transmission link, restoring the secure data packet received by the master station and performing data quality verification to obtain cleaned data with spatial correlation; S3, based on the cleaned data with spatial correlation, uses satellite positioning technology and 3D visualization technology to obtain a dynamic and interactive equipment operation and maintenance digital twin environment; S4 uses time series feature extraction and multi-factor correlation analysis algorithms to identify potential equipment faults based on pre-set historical fault patterns and cleaned data with spatial correlations. It then diagnoses, processes offline, and repairs equipment with identified potential faults. The method of performing data cleansing on the multi-dimensional operation and maintenance perception data, performing adaptive multi-level encryption according to the sensitivity level and importance of the data to obtain a secure data packet, transmitting the secure data packet to the master station using a dynamic transmission protocol switching algorithm according to the stability and bandwidth conditions of the network transmission link, restoring and verifying the data quality of the secure data packet received by the master station, and obtaining cleaned data with spatial correlation includes: According to the null values, duplicate values and outliers existing in the multi-dimensional operation and maintenance perception data, a statistical filtering algorithm and an intelligent value filling method are used to obtain second temperature data, second humidity data, second smoke concentration data, second video image data, second equipment operating parameters, second alarm information, and second historical operation and maintenance records with unified format and complete data; according to the sensitivity level and importance of the data, the second temperature data, second humidity data, and second smoke concentration data are divided into three-level sensitive data, the second video image data and the second historical operation and maintenance records are divided into two-level sensitive data, and the second equipment operating parameters and the second alarm information are divided into one-level sensitive data; an adaptive multi-level encryption method is used, RSA asymmetric encryption is used for the first-level sensitive data to obtain first-level encrypted data, AES symmetric encryption is used for the second-level sensitive data to obtain second-level encrypted data, and lightweight encryption is used for the third-level sensitive data to obtain third-level encrypted data; the first-level encrypted data, the second-level encrypted data, and the third-level encrypted data are combined to obtain a secure data packet; Based on the stability and bandwidth conditions of the network transmission link, a dynamic transmission protocol switching algorithm is used to transmit the secure data packet to the main station. Based on the secure data packet received by the main station, a decryption algorithm is used to calculate the restored original data information. Based on the preset data quality verification algorithm, the integrity rate of the restored original data information is evaluated. Data with an integrity rate lower than the pre-set integrity rate threshold is intelligently supplemented to obtain valid restored data. Based on the valid restored data and the spatial location information of the computer room, a geographic coordinate mapping algorithm is used to obtain spatially associated cleaned data containing the valid restored data and the spatial location. The method of transmitting the security data packet to the master station by using a dynamic transmission protocol switching algorithm based on the stability and bandwidth conditions of the network transmission link includes: The signal strength, packet loss rate and delay time of the network transmission link are detected in real time using a preset first period as a sliding time window, and a network environment evaluation algorithm is used to obtain the network environment quality level within the sliding time window; the network environment quality level is one of level one, level two and level three; when the network environment quality level is level one, a standard data transmission protocol is used to simultaneously transmit level one encrypted data, level two encrypted data and level three encrypted data; when the network environment quality level is level two, a high-reliability transmission protocol is first used to transmit level one encrypted data, and after the transmission is completed, the level two encrypted data and the level three encrypted data are transmitted in sequence; when the network environment quality level is level three, a lightweight transmission protocol is used to transmit level one encrypted data, and the level two encrypted data and the level three encrypted data are temporarily stored in a local cache, and are transmitted after the network environment quality level is upgraded to level two or level one; The method of detecting the signal strength, packet loss rate, and delay time of the network transmission link in real time using a preset first period as a sliding time window, and obtaining the network environment quality level within the sliding time window using a network environment evaluation algorithm includes: Within the sliding time window, the signal strength, packet loss rate, and delay time of the network transmission link are sampled in real time at every preset first sampling interval to obtain a signal strength sample set, a packet loss rate sample set, and a delay time sample set within the sliding time window; the average value of the signal strength sample set is calculated to obtain the average signal strength, the average value of the packet loss rate sample set is calculated to obtain the average packet loss rate, and the average value of the delay time sample set is calculated to obtain the average delay time; Based on a preset signal strength reference range, a forward correlation mapping is used to normalize the average signal strength into a signal strength index; based on a preset packet loss rate reference range, a preset first reverse correlation mapping is used to normalize the average packet loss rate into a packet loss rate index; based on a preset delay time reference range, a preset second reverse correlation mapping is used to normalize the average delay time into a delay time index; the signal strength index, packet loss rate index, and delay time index are multiplied by preset weight coefficients and summed to obtain a comprehensive network environment index; the comprehensive network environment index is compared with a preset first scoring threshold and a preset second scoring threshold to obtain a network environment quality level within a sliding time window; Counting the average resource utilization of the network transmission link at intervals of a preset second period, and dynamically adjusting the first scoring threshold and the second scoring threshold according to the average resource utilization; the second period is an integer multiple of the first period; The method of comparing the network environment comprehensive index with a preset first scoring threshold and a preset second scoring threshold to obtain the network environment quality level within the sliding time window includes: When the network environment comprehensive index is greater than or equal to the first scoring threshold, the network environment quality level is level one; when the network environment comprehensive index is less than the first scoring threshold and greater than or equal to the second scoring threshold, the network environment quality level is level two; when the network environment comprehensive index is less than the second scoring threshold, the network environment quality level is level three. The method for obtaining a dynamic interactive equipment operation and maintenance digital twin environment using satellite positioning technology and three-dimensional visualization technology based on cleaned data with spatial correlation includes: Using Beidou satellite positioning technology and geographic mapping technology, a three-dimensional spatial basic model of the railway operation and maintenance area is constructed; personnel location data is obtained based on the positioning devices worn by the operation and maintenance personnel; the three-dimensional spatial basic model is spatially aligned with the spatially associated cleaned data and personnel location data to obtain a basic visualization environment with geographic reference; Extract valid restored data from the cleaned data with spatial associations; classify the data corresponding to temperature data, humidity data, smoke concentration data, and video image data in the valid restored data as valid environmental monitoring data; classify the data corresponding to equipment operating parameters, alarm information, and historical operation and maintenance records in the valid restored data as valid equipment status data; use WebGL three-dimensional visualization technology to establish an association mapping between the valid equipment status data and the geometric entities of the corresponding equipment in the three-dimensional space basic model to obtain a digital twin model of the equipment; map the valid environmental monitoring data to the three-dimensional space basic model through visualization technology to obtain an environmental data visualization layer; map the personnel location data to the three-dimensional space basic model to obtain dynamic personnel icon data; Combine the equipment digital twin model, the environmental data visualization layer, and the dynamic personnel icon data to obtain a dynamic and interactive equipment operation and maintenance digital twin environment; The method of using time series feature extraction and multi-factor correlation analysis algorithms to identify potential equipment faults based on pre-set historical fault patterns and cleaned data with spatial correlation, and diagnosing, offline processing, and repairing equipment with identified potential faults includes: Sort the cleaned data with spatial correlation according to time series, extract the time series features of effective environmental monitoring data and effective equipment status data, match the time series features with the feature templates in the pre-set historical fault mode library, and calculate the matching similarity; The device corresponding to the data with a matching similarity greater than a preset first fault threshold is marked as a potential fault device; the potential fault device represents a device that has been identified to have a potential fault; based on the computer room space location information and personnel location data corresponding to the potential fault device, the operation and maintenance personnel closest to the potential fault device is matched and recorded as the first operation and maintenance personnel; the computer room space location information corresponding to the potential fault device is pushed to the first operation and maintenance personnel; and the first operation and maintenance personnel performs offline processing and repair on the potential fault device.

2. The intelligent equipment operation and maintenance method based on railway operation and maintenance according to claim 1, characterized in that: The method of sorting the cleaned data with spatial correlation according to time series, extracting time series features of effective environmental monitoring data and effective equipment status data, matching the time series features with feature templates in a preset historical fault mode library, and calculating matching similarity includes: The cleaned data with spatial correlation are sorted according to time series. Using the preset second sliding time window, the temperature change rate, humidity change rate, smoke concentration change rate, video image grayscale value change rate, equipment operating parameter fluctuation rate, and periodic spectrum are extracted as time series features. The time series features are standardized to obtain standardized time series features; a similarity calculation is performed based on the standardized time series features and feature templates in the historical fault pattern library using a Euclidean distance algorithm and a preset third reverse correlation function to obtain a first similarity; correlation pattern recognition is performed on the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate to obtain a second similarity; the second similarity indicates the degree to which the relationship between the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate conforms to physical laws; A weighted average of the second similarity and the first similarity is taken as the matching similarity.

3. The intelligent equipment operation and maintenance method based on railway operation and maintenance according to claim 2, characterized in that: The method of performing correlation pattern recognition on the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate to obtain the second similarity includes: According to the corresponding time segment in the seasonal feature matching library to which the current time belongs, the preset benchmark functional relationship between the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate is obtained; the degree of deviation of the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate from the benchmark functional relationship is calculated to obtain a quantitative indicator characterizing the degree to which the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate conform to physical laws, which is recorded as the second similarity; the value of the second similarity is between 0 and 1; the seasonal feature matching library is obtained by pre-setting, and represents the typical functional relationship between the temperature change rate, humidity change rate, smoke concentration change rate, and equipment operating parameter fluctuation rate within the pre-divided time segment.

4. An intelligent equipment operation and maintenance system based on railway operation and maintenance, used to execute the method according to any one of claims 1 to 3, characterized in that: The system includes: a data acquisition module, a data cleaning module, a digital twin module and a fault identification module connected in sequence; The data acquisition module is used to collect multi-dimensional operation and maintenance perception data, including equipment environment data and operation status data; the equipment environment data includes temperature data, humidity data, smoke concentration data, and video image data; the operation status data includes equipment operation parameters, alarm information, and historical operation and maintenance records; the equipment operation parameters include equipment CPU usage; The data cleaning module is used to clean the multi-dimensional operation and maintenance perception data, perform adaptive multi-level encryption based on the sensitivity level and importance of the data to obtain a secure data packet, adopt a dynamic transmission protocol switching algorithm based on the stability and bandwidth conditions of the network transmission link to transmit the secure data packet to the master station, restore and verify the data quality of the secure data packet received by the master station, and obtain cleaned data with spatial correlation; The digital twin module is used to obtain a dynamic and interactive equipment operation and maintenance digital twin environment based on the cleaned data with spatial correlation using satellite positioning technology and three-dimensional visualization technology; The fault identification module is used to use time series feature extraction and multi-factor association analysis algorithms to identify potential equipment faults based on pre-set historical fault patterns and cleaned data with spatial correlation, and to diagnose, offline process and repair equipment identified as having potential faults.

Images