Method and device for generating monitoring sequence data

Abstract

The invention provides a method and a device for generating monitoring sequence data. The method comprises the following steps: acquiring at least one acquisition signal, determining a signal type corresponding to the acquisition signal for any acquisition signal, processing the acquisition signal according to the signal type corresponding to the acquisition signal to obtain state data corresponding to the acquisition signal, fusing the state data corresponding to the at least one acquisition signal, and obtaining the state data corresponding to the at least one acquisition signal. And generating monitoring sequence data. Therefore, the acquired signals are processed according to the signal type corresponding to each acquired signal to obtain the corresponding state data, and the state data corresponding to each acquired signal are fused to generate the monitoring sequence data, so that the problems of tedious implementation process, low efficiency, high reliability and the like in the prior art can be solved. The technical problems that in the prior art, real-time synchronous processing requirements of multi-source signals are difficult to meet, the system highly depends on experience of operators, data mismatching and analysis errors are prone to being caused by human errors, and accuracy, consistency and generation timeliness of monitoring sequence data are seriously affected are solved.

Description

Technical Field

[0001] This application relates to the field of sensor data processing technology, and in particular to a method and apparatus for generating monitoring sequence data. Background Technology

[0002] As the integration of monitoring systems increases and monitoring needs become more refined, the types of data that need to be collected are becoming increasingly diverse, and the corresponding types of sensor signals are also increasing significantly.

[0003] However, due to significant differences in protocol formats, baud rates, and data frame structures between the output signals of sensors from different manufacturers and of different types, traditional methods typically require manual identification and configuration of each signal, and the use of various specialized analysis tools to analyze and convert signals from different sources to generate monitoring sequence data. This method is not only cumbersome and inefficient, making it difficult to meet the real-time synchronous processing requirements of multi-source signals, but it also heavily relies on the operator's experience, making it prone to data mismatch and parsing errors due to human error, severely impacting the accuracy, consistency, and timeliness of monitoring sequence data generation. Summary of the Invention

[0004] The purpose of this application is to provide a method and apparatus for generating monitoring sequence data, thereby solving the technical problems of existing technologies, which are not only cumbersome and inefficient in implementation, making them difficult to adapt to the real-time synchronization processing requirements of multi-source signals, but also highly dependent on the experience of operators, making them prone to data mismatch and parsing errors due to human error, seriously affecting the accuracy, consistency, and timeliness of monitoring sequence data generation. The specific technical solution is as follows: In a first aspect of this application, a method for generating monitoring sequence data is provided, the method comprising: Acquire at least one acquisition signal; For any of the acquired signals, determine the signal type corresponding to the acquired signal; Based on the signal type corresponding to the acquired signal, the acquired signal is processed to obtain the status data corresponding to the acquired signal; The status data corresponding to at least one of the acquired signals are fused to generate monitoring sequence data.

[0005] In an optional implementation, determining the signal type corresponding to the acquired signal includes: Signal features are obtained from the acquired signal, the signal features including at least one of baud rate, data frame structure and data format; Search for target features that match the signal features from a preset feature library; The signal type corresponding to the target feature is determined as the signal type corresponding to the acquired signal.

[0006] In an optional implementation, processing the acquired signal according to the signal type corresponding to the acquired signal to obtain the status data corresponding to the acquired signal includes: Determine the parsing rules corresponding to the signal type; Based on the parsing rules, the acquired signal is processed to obtain the state data corresponding to the acquired signal.

[0007] In an optional implementation, processing the acquired signal based on the parsing rules to obtain the state data corresponding to the acquired signal includes: According to the parsing rules, valid data is extracted from the acquired signals; Feature value calculation is performed on the valid data to obtain the state data corresponding to the acquired signal.

[0008] In an optional implementation, fusing the state data corresponding to at least one of the acquired signals to generate monitoring sequence data includes: Obtain preset fusion rules; Based on the preset fusion rules, a target dataset is determined from the state data corresponding to at least one of the acquired signals; The data in the target dataset are time-aligned to generate the monitoring sequence data.

[0009] In an optional implementation, after generating the monitoring sequence data, the following steps are included: A correlation analysis is performed on the state data of different signal types in the monitoring sequence data to generate correlation analysis results; Based on the correlation analysis results, a detection report is generated and / or a fault diagnosis is performed.

[0010] In an optional implementation, before determining the signal type corresponding to the acquired signal, the following steps are included: The acquired signals are preprocessed to generate initial acquired signals; The initial acquired signal is subjected to quality verification. If the quality verification of the initial acquired signal is successful, the step of determining the signal type corresponding to the acquired signal is executed.

[0011] In an optional implementation, the method further includes: The frequency of acquiring the acquired signal is adjusted according to the signal type and / or the attributes of the acquired signal.

[0012] In an optional implementation, after generating the monitoring sequence data, the following steps are included: Obtain historical operating baseline; The monitoring sequence data is compared with the historical operating baseline to determine the degree to which the monitoring sequence data deviates from the historical operating baseline; If the monitored sequence data deviates from the historical operating baseline by more than a preset threshold, an abnormal warning message is generated.

[0013] In a second aspect of this application, a monitoring sequence data generation apparatus is also provided, the apparatus comprising: The device includes: The signal acquisition module is used to acquire at least one acquisition signal; The signal type determination module is used to determine the signal type corresponding to any of the acquired signals; The status data determination module is used to process the acquired signal according to the signal type corresponding to the acquired signal to obtain the status data corresponding to the acquired signal; The monitoring sequence data generation module is used to fuse state data corresponding to at least one of the acquired signals to generate monitoring sequence data.

[0014] In a third aspect of the embodiments of this application, an electronic device is also provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method for generating monitoring sequence data as described in any of the first aspects above.

[0015] In a fourth aspect of the embodiments of this application, a storage medium is also provided, the storage medium storing instructions that, when run on a computer, cause the computer to execute the method for generating monitoring sequence data as described in any of the first aspects above.

[0016] In a fifth aspect of the embodiments of this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform the method for generating monitoring sequence data as described in any of the first aspects above.

[0017] The technical solution provided in this application acquires at least one acquisition signal, determines the signal type corresponding to any acquisition signal, processes the acquisition signal according to the signal type to obtain the corresponding state data, and fuses the state data corresponding to at least one acquisition signal to generate monitoring sequence data. By processing the acquisition signal according to the signal type corresponding to each acquisition signal to obtain the corresponding state data, and fusing the state data corresponding to each acquisition signal to generate monitoring sequence data, this method can achieve the fusion processing of multiple acquisition signals. This solves the technical problems of existing technologies, which are not only cumbersome and inefficient, making them unsuitable for real-time synchronous processing of multi-source signals, but also highly dependent on operator experience, easily leading to data mismatch and parsing errors due to human error, seriously affecting the accuracy, consistency, and timeliness of monitoring sequence data generation. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0021] Figure 1 A schematic diagram illustrating the implementation process of a method for generating monitoring sequence data provided in this application embodiment; Figure 2 A schematic diagram illustrating the implementation process of another method for generating monitoring sequence data provided in this application embodiment; Figure 3 A schematic diagram illustrating the implementation process of a signal type determination method provided in this application embodiment; Figure 4 A schematic diagram illustrating the implementation process of another method for generating monitoring sequence data provided in this application embodiment; Figure 5 This is a schematic diagram of a multi-sensor system architecture provided in an embodiment of this application; Figure 6This is a schematic diagram of the structure of a monitoring sequence data generation device provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0024] To address the technical problems of existing technologies, which are not only cumbersome and inefficient in implementation, making them unsuitable for real-time synchronous processing of multi-source signals, but also highly dependent on operator experience and prone to data mismatch and parsing errors due to human error, severely affecting the accuracy, consistency, and timeliness of monitoring sequence data generation, this application provides a method and apparatus for generating monitoring sequence data. The method involves acquiring at least one acquisition signal, determining the signal type corresponding to each acquisition signal, processing the acquisition signal according to its signal type to obtain corresponding state data, and fusing the state data corresponding to at least one acquisition signal to generate monitoring sequence data. This process of processing acquisition signals according to their signal types to obtain corresponding state data and fusing the state data of various acquisition signals to generate monitoring sequence data enables the fusion processing of multiple acquisition signals.

[0025] like Figure 1 The diagram shown is a schematic representation of the implementation flow of a method for generating monitoring sequence data according to an embodiment of this application, which may specifically include the following steps: S101, acquire at least one acquisition signal.

[0026] In this embodiment, at least one acquisition signal is obtained. The acquisition signal refers to the raw electrical signal output from various sensors (such as gap sensors, acceleration sensors, speed sensors, etc.). The acquisition signal can take forms including, but is not limited to, voltage signals (0-5V / 4-20mA standard signals), pulse signals, digital bus signals, etc., and is used to directly carry the raw sensing information of the sensors regarding the train's operating status. The acquisition signal may include gap sensor signals (to reflect the suspension gap between the vehicle body and the track), acceleration sensor signals (to reflect the vehicle body vibration state), speed sensor signals (to reflect the train's operating speed), and diagnostic sensor signals (to reflect the equipment's operating condition). This embodiment does not limit the specific examples.

[0027] Specifically, signals from at least one physical sensor can be received synchronously via a multi-channel (e.g., 32 independent channels) parallel input interface. Each channel supports signal isolation and conditioning to ensure signal integrity during transmission and provides anti-interference capabilities, enabling reliable data acquisition by maglev trains in complex electromagnetic environments.

[0028] S102, for any acquired signal, determine the signal type corresponding to the acquired signal.

[0029] In this embodiment of the application, for any acquired signal, the signal type corresponding to the acquired signal is determined. The signal type refers to the signal category classified according to the signal characteristics (such as baud rate, data frame structure, data format, etc.) corresponding to the acquired signal.

[0030] S103, based on the signal type corresponding to the acquired signal, process the acquired signal to obtain the status data corresponding to the acquired signal.

[0031] In this embodiment, the acquired signal is processed according to its signal type to obtain the corresponding status data. The status data refers to structured data processed through protocol parsing, noise reduction, and feature extraction, reflecting the actual measured value of the sensor or the device status.

[0032] S104, fuse the state data corresponding to at least one acquired signal to generate monitoring sequence data.

[0033] In this embodiment, the status data corresponding to at least one acquired signal are fused to generate monitoring sequence data. The monitoring sequence data refers to a structured dataset formed by aligning and integrating the status data from multiple sensors according to a time series. Monitoring sequence data possesses characteristics of temporal consistency, dimensional integrity, and standardized format, and can be directly used in scenarios such as fault diagnosis, trend analysis, and report generation.

[0034] Based on the above description of the technical solution provided in the embodiments of this application, at least one acquisition signal is acquired. For any acquisition signal, the signal type corresponding to the acquisition signal is determined. According to the signal type corresponding to the acquisition signal, the acquisition signal is processed to obtain the state data corresponding to the acquisition signal. The state data corresponding to at least one acquisition signal is fused to generate monitoring sequence data. In this way, the acquisition signal is processed according to the signal type corresponding to each acquisition signal to obtain the corresponding state data. The state data corresponding to each acquisition signal is fused to generate monitoring sequence data. This can realize the fusion processing of multiple acquisition signals, solving the technical problems of existing technologies, which are not only cumbersome and inefficient, but also difficult to adapt to the real-time synchronous processing requirements of multi-source signals. Moreover, they are highly dependent on the experience of operators and prone to data mismatch and parsing errors due to human error, which seriously affects the accuracy, consistency and timeliness of monitoring sequence data generation.

[0035] like Figure 2 The diagram shown illustrates the implementation flow of another method for generating monitoring sequence data provided in this application, which may specifically include the following: S201, acquire at least one acquisition signal.

[0036] In this embodiment of the application, this step is similar to step S101 above, and will not be described in detail here.

[0037] S202, for any acquired signal, determine the signal type corresponding to the acquired signal.

[0038] In this embodiment of the application, for any acquired signal, the signal type corresponding to the acquired signal is determined.

[0039] For details on how to determine the signal type corresponding to the acquired signal, please refer to the following: Figure 3 The method shown. (As illustrated) Figure 3 The diagram shown is a schematic representation of an implementation flow of a signal type determination method provided in this application, which may specifically include the following steps: S301, acquire signal characteristics from the acquired signal, the signal characteristics including at least one of baud rate, data frame structure and data format.

[0040] In this embodiment, signal features are obtained from the acquired signal. These signal features include at least one of baud rate, data frame structure, and data format. Signal features refer to the set of key parameters analyzed and extracted from the acquired signal that uniquely characterizes its communication protocol or source type. Baud rate refers to the number of symbols transmitted per second, a fundamental characteristic of communication speed. Different sensors or manufacturers use different baud rates (e.g., 9600, 115200, etc.) to quickly narrow down the range of protocol matching. Data frame structure refers to the rules governing the composition of a complete data frame, which may include start bits, data bit length, parity bit type (e.g., parity check, CRC), stop bits, etc. Data format refers to the organization and meaning of valid data bytes, which may include byte order (big-endian / little-endian), data type (integer, floating-point), engineering unit conversion factors, and custom fields, etc. This embodiment does not limit these aspects.

[0041] S302, Search for target features that match the signal features from the preset feature library.

[0042] In this embodiment, a target feature matching the signal feature is searched from a preset feature library. The preset feature library refers to a database pre-built and stored in the device's non-volatile memory. The target feature refers to the feature entry in the preset feature library that has the highest similarity or a perfect match with the feature extracted from the currently acquired signal.

[0043] S303, determine the signal type corresponding to the target feature as the signal type corresponding to the acquired signal.

[0044] In this embodiment of the application, the signal type corresponding to the target feature is determined as the signal type corresponding to the acquired signal.

[0045] In addition, the following steps may be included before determining the signal type corresponding to the acquired signal: Step 31: Preprocess the acquired signal to generate the initial acquired signal.

[0046] In this embodiment of the application, the acquired signal can be preprocessed to generate an initial acquired signal.

[0047] Specifically, preprocessing of the acquired signal can include filtering and noise reduction (using hardware filters such as RC filters or digital filters such as FIR and IIR to remove high-frequency noise and power frequency interference), signal amplification / attenuation (using programmable gain amplifiers (PGA) to adjust the signal amplitude to match the optimal input range of the analog-to-digital converter (ADC) and improve the signal-to-noise ratio and resolution), baseline calibration (eliminating DC bias of the signal (such as sensor zero drift) to make the signal fluctuate near a zero reference), isolation protection (using opto-isolation or magnetic isolation technology to cut off ground loop interference and protect the back-end circuit from high voltage impact), and analog-to-digital conversion (converting analog signals into high-precision digital signal sequences for subsequent processing by digital signal processors (such as processing chips).

[0048] Step 32: Perform quality verification on the initial acquired signal. If the quality verification of the initial acquired signal is successful, proceed to the step of determining the signal type corresponding to the acquired signal.

[0049] In this embodiment, the initial acquired signal undergoes quality verification. If the quality verification of the initial acquired signal is successful, the step of determining the signal type corresponding to the acquired signal is executed. That is, step S202. The quality verification refers to verifying the availability and integrity of the initial acquired signal, which may include signal presence detection, amplitude range verification, signal-to-noise ratio evaluation, signal stability check, and basic protocol activity detection.

[0050] It should be noted that signal presence detection is used to determine whether the acquired signal is valid; amplitude range verification is used to verify whether the peak-to-peak value or effective value of the signal is within the normal operating range of the sensor and the measurement range of the device; signal-to-noise ratio evaluation is used to calculate the power ratio of the acquired signal to the noise, and to determine whether the acquired signal is overwhelmed by noise. Signal stability check is used to check whether the signal fluctuation is abnormally drastic (such as continuous glitches) in a short period of time, which may indicate unstable connection or sensor failure; basic protocol activity detection is used to preliminarily detect whether valid data packets conforming to common frame structures appear for digital communication signals.

[0051] S203, determine the parsing rules corresponding to the signal type.

[0052] In this embodiment, a parsing rule corresponding to the signal type is determined. The parsing rule refers to a predefined set of data processing instructions and algorithms for the corresponding signal type, used to decode the acquired signal to obtain physical quantity data. This may include data extraction logic (e.g., reading from a specific byte offset in a data frame), decoding algorithms (e.g., Manchester decoding, differential decoding), physical quantity conversion formulas (e.g., converting ADC count values ​​to voltage, and then converting them to displacement or acceleration based on sensor sensitivity coefficients), and verification and fault-tolerance mechanisms (e.g., CRC check, timeout retry), etc. This embodiment does not limit these specific rules.

[0053] It should be noted that the parsing rules can be stored in the device memory, including data mapping relationships, dimension conversion coefficients, and data validity verification algorithms, such as identifier-data mapping tables for CAN protocol signals, or voltage-displacement linear conversion formulas for analog signals.

[0054] S204, based on the parsing rules, processes the acquired signal to obtain the state data corresponding to the acquired signal.

[0055] In this embodiment of the application, the acquired signal is processed based on the parsing rules to obtain the state data corresponding to the acquired signal.

[0056] Based on the parsing rules, the acquired signals are processed to obtain the corresponding state data. Specifically, this may include the following steps: Step 41: Extract valid data from the acquired signal according to the parsing rules.

[0057] In this embodiment of the application, valid data is extracted from the acquired signal according to the parsing rules. Valid data refers to physically meaningful numerical information obtained from the acquired signal after parsing, such as gap value (unit: mm), acceleration value (unit: m / s²), velocity value (unit: km / h), or device status code.

[0058] Step 42: Calculate the feature values ​​of the valid data to obtain the state data corresponding to the acquired signal.

[0059] In this embodiment, feature value calculation is performed on the valid data to obtain the state data corresponding to the acquired signal. The feature value calculation may include real-time statistics and signal analysis, such as calculating the moving average, effective value (RMS), peak-to-peak value, spectral frequency, waveform distortion rate, etc., thereby forming structured state data reflecting the sensor's operating state, and adding timestamps and quality identifiers.

[0060] S205, fuse the status data corresponding to at least one acquired signal to generate monitoring sequence data.

[0061] In this embodiment of the application, this step is similar to step S104 above, and will not be described in detail here.

[0062] In addition, after generating the monitoring sequence data, the following anomaly monitoring and early warning steps can also be included: Step 51: Obtain the historical operating baseline.

[0063] In this embodiment, a historical operating baseline is obtained. The historical operating baseline is a reference model or set of statistical features constructed based on long-term monitoring data of the equipment under normal operating conditions. It may include the typical numerical range, normal variation trend, characteristic value distribution (such as mean and variance) of each signal type under different operating conditions (such as start-up, constant speed, and braking), and the correlation between multiple signals (such as the correlation coefficient between gap and acceleration). This embodiment does not limit this aspect.

[0064] Step 52: Compare the monitoring sequence data with the historical operating baseline to determine the degree to which the monitoring sequence data deviates from the historical operating baseline.

[0065] In this embodiment, the monitored sequence data is compared with the historical operating baseline to determine the degree to which the monitored sequence data deviates from the historical operating baseline. The comparison method may include threshold comparison (checking whether the current data exceeds the normal upper and lower limits defined by the baseline), trend similarity analysis (comparing the difference between the current data change curve and the baseline trend), cluster analysis (determining whether the current data point still belongs to the normal operating condition cluster), or using machine learning models (such as single-class support vector machines or autoencoders) to infer anomaly scores. The degree to which the monitored sequence data deviates from the historical operating baseline refers to the difference between the current data and the normal state, which can be quantified by specific metrics, such as the magnitude of exceeding a threshold, trend correlation coefficient, or the model's anomaly score.

[0066] Step 53: If the degree to which the monitored sequence data deviates from the historical operating baseline exceeds a preset threshold, an abnormal warning message is generated.

[0067] In this embodiment, if the deviation of the monitored sequence data from the historical operating baseline exceeds a preset threshold, an anomaly warning message is generated. This warning message may include an anomaly channel identifier, anomaly type (e.g., data exceeding limits, abnormal trend, broken correlation), degree of deviation or anomaly score, precise timestamp of the anomaly occurrence, and preliminary processing suggestions based on a rule base or case base. The warning message can be output through various means, such as the device's human-machine interface (e.g., screen display, sound prompts), logs, or network communication interfaces (e.g., sent to a remote monitoring center), to support rapid response from maintenance personnel.

[0068] like Figure 4 The diagram shown illustrates the implementation flow of another method for generating monitoring sequence data provided in this application, which may specifically include the following: S401, acquire at least one acquisition signal.

[0069] In this embodiment of the application, this step is similar to step S101 above, and will not be described in detail here.

[0070] S402, for any acquired signal, determine the signal type corresponding to the acquired signal.

[0071] In this embodiment of the application, this step is similar to step S102 above, and will not be described in detail here.

[0072] S403 processes the acquired signal according to the signal type corresponding to the acquired signal to obtain the status data corresponding to the acquired signal.

[0073] In this embodiment of the application, this step is similar to step S103 above, and will not be described in detail here.

[0074] S404, Obtain preset fusion rules.

[0075] In this embodiment, preset fusion rules are obtained. These preset fusion rules refer to data integration logic predefined based on monitoring targets, sensor layout, and physical relationships, used to guide the selection, organization, and construction of a unified monitoring view from multi-source state data. Fusion rules may include spatial fusion rules for aggregating data from multiple sensors on the same physical component (e.g., a single-sided suspension frame); logical fusion rules for combining data based on causal relationships or functional coupling between signals (e.g., the correlation between train speed and vehicle vibration acceleration); and task-oriented rules for selecting the most relevant subset of key sensor data for a specific analysis task (e.g., suspension stability fault diagnosis, guidance performance evaluation). This embodiment does not limit these specific rules.

[0076] S405, based on preset fusion rules, determines the target dataset from the state data corresponding to at least one acquired signal.

[0077] In this embodiment, a target dataset is determined from the state data corresponding to at least one acquired signal based on preset fusion rules. The target dataset is a subset of data that is directly relevant or of high value, selected from all state data according to the current analysis requirements. For example, when performing "suspension stability analysis," the target dataset may include state data from all gap sensors and vertical acceleration sensors; when performing "guide system inspection," the target dataset may include data from guide gap and lateral acceleration sensors.

[0078] S406 performs time alignment on the data in the target dataset to generate monitoring sequence data.

[0079] In this embodiment, the data in the target dataset is time-aligned to generate monitoring sequence data. Specifically, high-precision synchronous clocks (such as the PTP protocol) or timestamp interpolation algorithms can be used to uniformly correct data from different acquisition channels, which may have slight acquisition time differences, to the same time base, forming a strictly time-corresponding data sequence, i.e., monitoring sequence data. This embodiment does not limit this approach.

[0080] In addition, after generating the monitoring sequence data, the following steps may also be included: Step 61: Perform correlation analysis on the state data of different signal types in the monitoring sequence data to generate correlation analysis results.

[0081] In this embodiment of the application, correlation analysis is performed on the state data of different signal types in the monitoring sequence data to generate correlation analysis results.

[0082] Correlation analysis aims to uncover the inherent connections, interaction patterns, or synergistic changes in state data of different signal types. For example, it can analyze the time-domain or frequency-domain correlation between abnormal gap fluctuations and vibration acceleration at specific frequencies (such as frequencies related to mechanical resonance); the statistical dependence between changes in train speed and statistical characteristics of acceleration in each direction (vertical, lateral, and longitudinal) (such as RMS and peak values); and identify the co-occurrence patterns or temporal causal relationships between specific alarm codes issued by equipment diagnostic sensors and abnormalities in key operating parameters (such as current and temperature). The analysis results can be quantified into correlation coefficient matrices, correlation rules, or probability graphs characterizing causal strength, used to reveal the root causes of complex faults, predict performance degradation trends, or depict deep-seated characteristics of system operation.

[0083] Step 62: Based on the correlation analysis results, generate a detection report and / or perform fault diagnosis.

[0084] In this embodiment of the application, a detection report is generated and / or a fault diagnosis is performed based on the correlation analysis results.

[0085] For example, by summarizing monitoring sequence data, key feature value statistics, correlation analysis results, identified abnormal events and their timestamps, a structured detection report (supporting PDF, Word, and other formats) can be generated according to a preset template. The report may include data change graphs, anomaly markers, correlation analysis charts, a summary of diagnostic conclusions, and complete data traceability information (such as sensor ID, acquisition time, processing parameters, etc.).

[0086] For example, based on the results of correlation analysis and a pre-set fault knowledge base (including fault modes, feature vectors and handling suggestions), the current equipment status can be diagnosed through rule reasoning or model matching, and output the suspected fault type, the physical location where the fault may occur (such as a specific bogie or an electromagnet on a certain side), the severity level of the fault (such as warning or serious), and targeted maintenance inspection or operation guidance suggestions.

[0087] In another embodiment of this application, the frequency of acquiring the acquired signal can be adjusted according to the signal type and / or the attributes of the acquired signal.

[0088] For example, for slowly changing signals (such as static gaps), the sampling rate can be reduced to save storage and processing resources; for high-frequency or transient signals (such as shock vibrations), the sampling rate can be increased to ensure signal integrity.

[0089] Furthermore, in this application embodiment, the method for generating monitoring sequence data provided in this application embodiment is described with reference to specific examples: like Figure 5 The diagram shown is a structural schematic of a multi-sensor system architecture provided in an embodiment of this application.

[0090] The multi-sensor system is based on an x86 architecture main control platform, equipped with a touch screen and various peripheral interfaces, supporting both external power supply and battery power to meet the needs of various operating scenarios. Simultaneously, it carries and runs a self-developed data processing module and software, which work together to achieve a closed-loop process from signal acquisition and analysis to data application. Specific technical details are as follows: 1. Data processing module: As the core functional unit of the entire multi-sensor system, this module uses a high-performance FPGA (Field Programmable Gate Array) as the core processing chip to receive input signals from 32 sensors.

[0091] This data processing module specifically achieves the following functions: Multi-channel synchronous acquisition capability: Supports simultaneous acquisition of physical signals (such as voltage signals, current signals, pulse signals, etc.) from 32 sensors, with acquisition timing deviation controlled at the sub-nanosecond level, ensuring the time consistency of multi-sensor data and laying the foundation for subsequent multi-dimensional data fusion analysis. Intelligent protocol recognition and parsing: After signal acquisition, preprocessing is performed (including filtering and noise reduction, signal amplification, baseline calibration, etc.). Then, key features such as baud rate, frame structure (such as start bit, data bit, parity bit, stop bit), and data format are automatically detected and stored. Based on the feature library, the specific sensor type (such as displacement sensor, acceleration sensor, velocity sensor, etc.) is identified. After identification, the corresponding sensor's protocol parsing algorithm is called (supporting adaptation to custom protocols from different manufacturers) to perform secondary deep processing on the acquired signal, accurately extracting original valid sensor data such as gap, acceleration, velocity, and device diagnostic codes. Independent channel configuration and scenario-based adaptation: Each of the 32 sensor channels supports independent configuration of sensor types, allowing for flexible matching of different sensor types according to actual detection needs.

[0092] In addition, three scenario-based data processing modes can be provided to meet the performance and efficiency balance requirements in different detection scenarios: Dynamic sampling rate adjustment: The sampling rate is adjusted in real time according to the sensor type and signal characteristics. For slowly changing signals (such as static gaps in equipment), a low sampling rate (as low as 1Hz) is used to reduce data throughput and equipment power consumption. For critical signals or drastically changing signals (such as equipment vibration acceleration), the sampling rate is automatically increased (up to 200kHz) to ensure detection accuracy and data integrity. Multi-channel synchronous status recording: Simultaneously records the operating status data of 32 sensors at the same time. Through multi-dimensional data fusion (such as correlation analysis of displacement data and acceleration data), the cause of equipment abnormality in actual test scenarios can be quickly located (such as judging the degree of wear of mechanical parts by correlation analysis of gap changes and vibration data). Full data storage and feature value calculation: On the one hand, it fully records every frame of raw data from the sensor (including raw signal waveform, acquisition timestamp, channel number, etc.) to ensure data traceability; on the other hand, it calculates key feature values ​​of each sensor data in real time, including peak-to-peak value (signal fluctuation range), frequency center (signal main frequency components), average value (signal steady-state level), standard deviation (signal dispersion), etc. This not only provides data support for subsequent equipment fault analysis, but also forms an equipment operating baseline through long-term feature value statistics, providing a quantitative reference for product iteration and optimization.

[0093] 2. Data processing software: This software runs on a main control module with an x86 hardware architecture and a Windows 10 / 11 operating system. It interacts with the data processing module via a high-speed PCIe bus for low-level command interaction (such as configuration of acquisition parameters and parsing algorithm calls) and high-speed data transmission, providing core control and data application support for the entire multi-sensor system. Specific functions may include: 1) Full-process data management and control: Supports independent control of 32 sensor acquisition channels, including sensor type analysis and recording, configuration of acquisition parameters (such as sampling rate and acquisition duration), start and stop of data acquisition, and real-time storage of raw data (supporting both local hard drive and network storage modes), realizing full-process visual management from acquisition to storage. 2) Real-time Data Visualization and Diagnostic Analysis: Provides intuitive real-time waveform display, dynamically showing the raw signal waveforms and key parameter change trends of each sensor. For specific scenarios such as rail transit, it supports drawing specialized analysis charts such as gap change curves, acceleration change curves, and velocity change curves. Users can intuitively observe the operating status of the equipment in actual working or testing scenarios, and detect abnormal data (such as sudden acceleration increases, gap exceeding limits, etc.) in real time for preliminary diagnosis. 3) Test Report Generation and Data Export: Automatically summarizes information such as sensor type, acquisition parameters, raw data, feature values, and analysis charts to generate standardized test reports (supporting PDF / Excel format export). The reports include data traceability information and diagnostic conclusion suggestions, facilitating subsequent querying, archiving, and test result review. It also supports exporting raw sensor data (supporting CSV / TXT format), which users can import into third-party data processing software such as MATLAB and Python for secondary in-depth analysis to meet personalized data application needs.

[0094] 3. The touchscreen display is connected to the main control platform, serving as the primary human-machine interface. It receives real-time waveforms, analysis charts, status parameters, and diagnostic results from the data processing software. Simultaneously, it allows users to directly perform interactive control such as parameter configuration, function selection, and report retrieval via touch operation, achieving visualization of the testing process and ease of operation.

[0095] 4. Peripheral Interfaces (USB, Ethernet): The device integrates multiple standard peripheral interfaces, including but not limited to USB and Ethernet ports. The USB port is used to connect external storage devices (such as USB flash drives or external hard drives) for quickly exporting test reports and raw data, or to connect auxiliary input devices such as mice and keyboards. The Ethernet port is used to connect the device to a local area network (LAN) or the internet, enabling remote uploading, sharing, and storage of test data, supporting remote monitoring, online software upgrades, and data interaction with upper-level information management systems (such as MES).

[0096] 5. The power adapter is the external power input module for the equipment, used to convert mains power (e.g., AC 100-240V) into a stable DC operating voltage (e.g., DC 12V / 19V) required by the various modules inside the equipment (main control platform, data processing module, display screen, etc.). It has wide voltage input adaptability and overvoltage / overcurrent / short circuit protection functions to ensure the safe, stable, and long-term operation of the equipment in laboratories, workshops, and other environments with fixed power supplies.

[0097] 6. Battery management is the intelligent control core of the built-in power system, connected to the battery pack and main system circuitry. It is responsible for monitoring the real-time status of the battery pack (such as voltage, current, temperature, and remaining charge), enabling intelligent management of the charging and discharging process, including but not limited to: constant current / constant voltage control, battery balancing, and temperature protection during charging; over-discharge protection and load management during discharging; and reporting power status to the system software to ensure safe, efficient, and long-term operation of the equipment in battery-powered mode.

[0098] 7. The battery pack is the device's built-in rechargeable energy storage unit, which can be composed of multiple high-energy-density lithium-ion batteries connected in series and parallel. It is connected to the system through the battery management module and can be used to provide continuous DC power to the entire multi-sensor system in scenarios where there is no external mains power or mobile operation is required (such as track inspection and garage mobile maintenance). This ensures that the device can still complete several hours of continuous detection tasks after being disconnected from a fixed power source. It is a key component in realizing the portability and field applicability of the device.

[0099] In practical applications, this multi-sensor system can quickly achieve adaptive protocol matching and high-precision data parsing and detection for key multi-channel gap sensors (such as suspension gap sensors and guide gap sensors) on maglev trains, enabling compatible access to gap sensors from different manufacturers without manual intervention. At the data processing level, the system offers flexible processing methods such as dynamic sampling adjustment, multi-channel synchronous analysis, and real-time feature value calculation. This meets the accuracy and efficiency requirements of different detection scenarios (such as low-power processing during static debugging and high-frequency sampling during dynamic monitoring) and assists engineers in quickly locating anomalies through multi-dimensional data fusion. In data storage, it can completely record all dimensions of information for each sensor, including the original signal, acquisition timestamp, protocol type, and processing parameters, ensuring data traceability and reproducibility. This provides reliable data support for subsequent fault backtracking analysis and detection result verification. Overall, with its high adaptability, flexible processing capabilities, and complete data recording characteristics, this multi-sensor system fully meets the requirements for on-site mobile detection of various sensors (including gap, acceleration, and speed) on maglev trains, and is suitable for diverse operating environments such as trackside and depot maintenance.

[0100] Corresponding to the above method embodiments, this application also provides a monitoring sequence data generation apparatus, such as... Figure 6 As shown, the device may include a signal acquisition module 601, a signal type determination module 602, a status data determination module 603, and a monitoring sequence data generation module 604.

[0101] Signal acquisition module 601 is used to acquire at least one acquisition signal; The signal type determination module 602 is used to determine the signal type corresponding to any acquired signal. The status data determination module 603 is used to process the acquired signal according to the signal type corresponding to the acquired signal to obtain the status data corresponding to the acquired signal. The monitoring sequence data generation module 604 is used to fuse the state data corresponding to at least one acquired signal to generate monitoring sequence data.

[0102] This application also provides an electronic device, such as... Figure 7 As shown, it includes a processor 701, a communication interface 702, a memory 703, and a communication bus 704, wherein the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704. Memory 703 is used to store computer programs; In one embodiment of this application, when the processor 701 executes a program stored in the memory 703, it performs the following steps: Acquire at least one acquisition signal; for any acquisition signal, determine the signal type corresponding to the acquisition signal, process the acquisition signal according to the signal type corresponding to the acquisition signal to obtain the status data corresponding to the acquisition signal; fuse the status data corresponding to at least one acquisition signal to generate monitoring sequence data.

[0103] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0104] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0105] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0106] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0107] In another embodiment provided in this application, a storage medium is also provided, which stores instructions that, when run on a computer, cause the computer to execute the monitoring sequence data generation method described in any of the above embodiments.

[0108] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the monitoring sequence data generation method described in any of the above embodiments.

[0109] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a storage medium or transmitted from one storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0110] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0111] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0112] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the protection scope of this application.

Claims

1. A method for generating monitoring sequence data, characterized in that, The method includes: Acquire at least one acquisition signal; For any of the acquired signals, determine the signal type corresponding to the acquired signal; Based on the signal type corresponding to the acquired signal, the acquired signal is processed to obtain the status data corresponding to the acquired signal; The status data corresponding to at least one of the acquired signals are fused to generate monitoring sequence data.

2. The method according to claim 1, characterized in that, Determining the signal type corresponding to the acquired signal includes: Signal features are obtained from the acquired signal, the signal features including at least one of baud rate, data frame structure and data format; Search for target features that match the signal features from a preset feature library; The signal type corresponding to the target feature is determined as the signal type corresponding to the acquired signal.

3. The method according to claim 1, characterized in that, The step of processing the acquired signal according to the signal type corresponding to the acquired signal to obtain the status data corresponding to the acquired signal includes: Determine the parsing rules corresponding to the signal type; Based on the parsing rules, the acquired signal is processed to obtain the state data corresponding to the acquired signal.

4. The method according to claim 3, characterized in that, The process of processing the acquired signal based on the parsing rules to obtain the state data corresponding to the acquired signal includes: According to the parsing rules, valid data is extracted from the acquired signals; Feature value calculation is performed on the valid data to obtain the state data corresponding to the acquired signal.

5. The method according to claim 1, characterized in that, The step of fusing state data corresponding to at least one of the acquired signals to generate monitoring sequence data includes: Obtain preset fusion rules; Based on the preset fusion rules, a target dataset is determined from the state data corresponding to at least one of the acquired signals; The data in the target dataset are time-aligned to generate the monitoring sequence data.

6. The method according to claim 5, characterized in that, After generating the monitoring sequence data, the following steps are included: A correlation analysis is performed on the state data of different signal types in the monitoring sequence data to generate correlation analysis results; Based on the correlation analysis results, a detection report is generated and / or a fault diagnosis is performed.

7. The method according to claim 1, characterized in that, Before determining the signal type corresponding to the acquired signal, the process includes: The acquired signals are preprocessed to generate initial acquired signals; The initial acquired signal is subjected to quality verification. If the quality verification of the initial acquired signal is successful, the step of determining the signal type corresponding to the acquired signal is executed.

8. The method according to claim 1, characterized in that, The method further includes: The frequency of acquiring the acquired signal is adjusted according to the signal type and / or the attributes of the acquired signal.

9. The method according to claim 1, characterized in that, After generating the monitoring sequence data, the following is included: Obtain historical operating baseline; The monitoring sequence data is compared with the historical operating baseline to determine the degree to which the monitoring sequence data deviates from the historical operating baseline; If the monitored sequence data deviates from the historical operating baseline by more than a preset threshold, an abnormal warning message is generated.

10. A device for generating monitoring sequence data, characterized in that, The device includes: The signal acquisition module is used to acquire at least one acquisition signal; The signal type determination module is used to determine the signal type corresponding to any of the acquired signals; The status data determination module is used to process the acquired signal according to the signal type corresponding to the acquired signal to obtain the status data corresponding to the acquired signal; The monitoring sequence data generation module is used to fuse state data corresponding to at least one of the acquired signals to generate monitoring sequence data.

Images