Multi-source data fusion underground pipe gallery real-time state dynamic monitoring method and system

Abstract

The invention discloses an underground pipe gallery real-time state dynamic monitoring method and system based on multi-source data fusion, and relates to the technical field of state monitoring, and the method comprises the steps: obtaining a monitoring point set of an underground pipe gallery, and monitoring the monitoring point set; performing real-time risk identification, determining a risk real-time receiving data set and a risk monitoring point set, then performing causal traceability, and determining a traceability clue cluster; by taking the traceability clue cluster as an index, clue extraction is carried out, a traceability receiving data sequence cluster is determined, time sequence iteration trend risk authentication is carried out, and a risk trend feature cluster is determined; and determining a first dynamic monitoring frequency and a second dynamic monitoring frequency, and distributing the first dynamic monitoring frequency and the second dynamic monitoring frequency to the state monitoring terminal to monitor the monitoring point set. The technical problem that the real-time state monitoring frequency of the underground pipe gallery is fixed and cannot be dynamically adjusted according to the risk change in the prior art is solved, and the technical effects that the monitoring frequency is adaptively adjusted along with the risk state, and the monitoring accuracy and the response timeliness are improved are achieved.

Description

Technical Field

[0001] The present application relates to the field of condition monitoring technology, and specifically to a method and system for real-time dynamic monitoring of the condition of underground pipeline corridors by fusion of multi-source data. Background Art

[0002] Real-time status monitoring of underground utility corridors typically relies on a fixed, pre-set monitoring frequency. This fixed-frequency monitoring approach lacks the flexibility to respond to changes in the corridor's status. In particular, when risks arise, the monitoring frequency cannot be increased promptly to obtain more real-time data for analysis. Due to the lack of a dynamic adjustment mechanism, the monitoring system is unable to capture critical data in a timely manner when risks emerge, resulting in delayed risk identification and early warning responses, which in turn impacts the corridor's safety and operational efficiency. Summary of the Invention

[0003] The present application provides a method and system for real-time dynamic monitoring of the status of underground pipeline corridors by fusion of multi-source data, which is used to solve the technical problem in the prior art that the frequency of real-time status monitoring of underground pipeline corridors is fixed and cannot be dynamically adjusted according to changes in risks.

[0004] In view of the above problems, the present application provides a method and system for real-time dynamic monitoring of the status of underground pipeline corridors by fusing multi-source data.

[0005] The first aspect of the present application provides a method for real-time dynamic monitoring of the underground pipeline corridor using multi-source data fusion, the method comprising: Acquire a set of monitoring points of the underground pipeline corridor, monitor the set of monitoring points according to a preset monitoring frequency using a multi-source status monitoring terminal set, and transmit the monitoring data to a data transmission center, wherein the data transmission center has a data transfer memory with window constraints; perform real-time risk identification based on the data transmission center, and determine a risk real-time receiving data set and a risk monitoring point set; perform causal tracing based on the risk monitoring point set and the risk real-time receiving data set, and determine a tracing clue cluster; use the tracing clue cluster as an index to extract clues from the data transfer memory, and determine a tracing receiving data sequence cluster; perform time-series iterative trend risk authentication on the tracing receiving data sequence cluster, and determine a risk trend feature cluster; determine a first dynamic monitoring frequency and a second dynamic monitoring frequency based on the risk trend feature cluster, and distribute the first dynamic monitoring frequency and the second dynamic monitoring frequency to the status monitoring terminal, and perform dual-frequency synchronous status monitoring on the monitoring point set.

[0006] The second aspect of the present application provides a real-time dynamic monitoring system for underground pipeline corridors using multi-source data fusion, the system comprising: A monitoring module is used to obtain a set of monitoring points of an underground pipeline corridor, monitor the set of monitoring points according to a preset monitoring frequency using a set of multi-source status monitoring terminals, and transmit the monitoring data to a data transmission center, wherein the data transmission center has a data transfer memory with window constraints; a risk identification module is used to perform real-time risk identification based on the data transmission center, and determine a risk real-time receiving data set and a risk monitoring point set; a causal tracing module is used to perform causal tracing based on the risk monitoring point set and the risk real-time receiving data set, and determine a tracing clue cluster; a clue extraction module is used to extract clues from the data transfer memory with the tracing clue cluster as an index, and determine a tracing receiving data sequence cluster; a risk authentication module is used to perform time series iterative trend risk authentication on the tracing receiving data sequence cluster respectively, and determine a risk trend feature cluster; a dual-frequency synchronous monitoring module is used to determine a first dynamic monitoring frequency and a second dynamic monitoring frequency based on the risk trend feature cluster, and distribute the first dynamic monitoring frequency and the second dynamic monitoring frequency to the status monitoring terminal, and perform dual-frequency synchronous status monitoring on the monitoring point set.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application obtains a set of monitoring points of an underground pipeline corridor, uses a set of multi-source status monitoring terminals to monitor the set of monitoring points according to a preset monitoring frequency, and transmits the monitoring data to a data transmission center, wherein the data transmission center has a data transfer memory with window constraints; performs real-time risk identification based on the data transmission center, and determines a risk real-time receiving data set and a risk monitoring point set; performs causal tracing based on the risk monitoring point set and the risk real-time receiving data set, and determines a tracing clue cluster; uses the tracing clue cluster as an index, performs clue extraction on the data transfer memory, and determines a tracing receiving data sequence cluster; performs time-series iterative trend risk authentication on the tracing receiving data sequence cluster, and determines a risk trend feature cluster; determines a first dynamic monitoring frequency and a second dynamic monitoring frequency based on the risk trend feature cluster, and distributes the first dynamic monitoring frequency and the second dynamic monitoring frequency to the status monitoring terminal, and performs dual-frequency synchronous status monitoring on the monitoring point set. This application solves the technical problem in the existing technology that the frequency of real-time status monitoring of underground pipelines is fixed and cannot be dynamically adjusted according to risk changes. By integrating multi-source monitoring data to perform causal tracing and trend risk authentication, and generating a dynamic monitoring frequency based on this, the monitoring frequency can be adaptively adjusted according to the risk status, thereby improving the monitoring accuracy and response timeliness. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0009] Figure 1 A flowchart of a method for real-time dynamic monitoring of underground pipeline corridor status using multi-source data fusion provided in an embodiment of the present application; Figure 2 Schematic diagram of the structure of the real-time dynamic status monitoring system of the underground pipeline corridor with multi-source data fusion provided in the embodiment of the present application.

[0010] Explanation of the accompanying symbols: monitoring module 11, risk identification module 12, cause-and-effect tracing module 13, clue extraction module 14, risk authentication module 15, dual-frequency synchronization monitoring module 16. DETAILED DESCRIPTION

[0011] This application provides a method and system for real-time dynamic monitoring of the status of underground pipelines by fusing multi-source data. It aims to solve the technical problem in the existing technology that the frequency of real-time status monitoring of underground pipelines is fixed and cannot be dynamically adjusted according to risk changes. By fusing multi-source monitoring data, causal tracing and trend risk authentication are performed, and a dynamic monitoring frequency is generated accordingly, so as to achieve the technical effect of adaptively adjusting the monitoring frequency according to the risk status, thereby improving the monitoring accuracy and response timeliness.

[0012] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0013] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0014] Example 1, as Figure 1 As shown, the present application provides a method for real-time dynamic monitoring of underground pipeline corridor status by multi-source data fusion, the method comprising: Step S100: Obtain a set of monitoring points of the underground pipeline corridor, monitor the set of monitoring points according to a preset monitoring frequency using a multi-source status monitoring terminal set, and transmit the monitoring data to a data transmission center, wherein the data transmission center has a data transfer memory with window constraints.

[0015] In the embodiments of the present application, a predetermined set of monitoring points for the underground utility corridor is first obtained. These monitoring points are sensors or devices installed at key locations in the utility corridor, used to collect various status data of the utility corridor in real time, such as temperature, humidity, and gas concentration. A multi-source status monitoring terminal set, consisting of multiple different types of monitoring devices (such as gas sensors, temperature sensors, and video surveillance), is then used to regularly or continuously monitor these monitoring points according to a preset monitoring frequency. The monitoring frequency refers to the time interval between data collection by the device.

[0016] Data collected by multi-source monitoring terminals is transmitted to the data transmission center. The data transmission center is responsible for centrally receiving, processing, and storing monitoring data. To ensure efficient and real-time data processing, the data transmission center uses a data transfer memory with window constraints. This window constraint imposes a time limit or data volume limit on data storage, ensuring efficient and timely data transmission and processing.

[0017] Step S200: performing real-time risk identification based on the data transmission center to determine a risk real-time receiving data set and a risk monitoring point set.

[0018] In an embodiment of the present application, when performing real-time risk identification based on a data transmission center, a set of real-time received data from multiple sources is first extracted from the data transmission center. Deviations are then identified on the extracted real-time data using a multi-source standard state data set to identify anomalies or deviations in the data. Risk identification is then performed on the identified deviation data based on a preset risk deviation threshold, screening out real-time received data that may pose a risk. Ultimately, a set of risky real-time received data and a set of risk monitoring points are determined.

[0019] Furthermore, in the method provided in the embodiment of the application, real-time risk identification is performed based on the data transmission center to determine the risk real-time receiving data set and the risk monitoring point set, and further includes: A multi-source real-time received data set is extracted from the data transmission center, and deviations of the multi-source real-time received data set are identified using a multi-source standard status data set to determine a multi-source real-time received data deviation set; risk identification is performed on the multi-source real-time received data deviation set according to a preset risk deviation threshold to determine a risk real-time received data set and a risk monitoring point set, wherein each multi-source real-time received data corresponds to a monitoring point.

[0020] In an embodiment of the present application, a multi-source real-time received data set is first extracted from a data transmission center. These data come from multiple monitoring terminals in an underground tunnel, such as gas sensors, temperature sensors, etc. These monitoring terminals are used to collect environmental status information of each monitoring point in the tunnel in real time. Next, these real-time received data are compared with a multi-source standard state data set. The standard data set is based on historical data or preset standard reference data under normal operating conditions of the tunnel. By comparison, deviation identification is performed using a method of subtracting the corresponding multi-source real-time received data from the multi-source standard state data, and the difference between the real-time data and the standard data of each monitoring point is calculated, thereby obtaining a multi-source real-time received data deviation set.

[0021] Next, risk identification is performed on the multi-source real-time received data deviation set, based on a pre-set risk deviation threshold set by technical experts. When deviation data exceeds the set threshold, the monitoring point is deemed risky, and a risky real-time received data set is generated. This set contains all real-time received data with deviations exceeding the threshold. Simultaneously, a risky monitoring point set is identified—the set of monitoring points associated with this deviation data.

[0022] Step S300: performing causal tracing based on the risk monitoring point set and the risk real-time received data set to determine a tracing clue cluster.

[0023] In an embodiment of the present application, when causal tracing is performed based on the risk monitoring point set and the risk real-time receiving data set, the underground pipeline corridor historical risk log set is first obtained. These logs contain records of various risk events that occurred in the pipeline corridor in the past. Then, a causal tracing vector set is constructed based on the risk monitoring point set and the risk real-time receiving data set. This set forms a causal relationship network of potential risks by associating real-time data and historical data. The causal tracing vector set is then approximately matched in the underground pipeline corridor historical risk log set, thereby obtaining a set of matching underground pipeline corridor historical risk log clusters related to real-time data. Finally, traceability clues are extracted for each log set in these matching historical risk log clusters to obtain a traceability clue cluster.

[0024] Furthermore, in the method provided in the embodiment of the application, causal tracing is performed based on the risk monitoring point set and the risk real-time received data set to determine a tracing clue cluster, and further includes: Obtain a set of historical risk logs for underground pipeline corridors; construct a set of causal tracing vectors based on the risk monitoring point set and the risk real-time receiving data set; perform approximate matching on the set of causal tracing vectors in the set of historical risk logs for underground pipeline corridors to obtain a matching cluster of historical risk logs for underground pipeline corridors; extract tracing clues from each matching set of historical risk logs for underground pipeline corridors in the matching cluster of historical risk logs for underground pipeline corridors to obtain the tracing clue cluster.

[0025] In an embodiment of the present application, a set of historical risk logs of underground tunnels is first obtained from a historical database. These logs record risk events and fault information that occurred in the tunnel history, including equipment failures, environmental anomalies, system failures, etc.

[0026] Next, a set of causal traceability vectors is constructed based on the set of risk monitoring points and the set of real-time risk data received. Each causal traceability vector consists of a risk monitoring point and a set of real-time risk data received. For example, a monitoring point might be a gas sensor in an underground pipeline corridor, and the real-time data received is the gas concentration value detected by the sensor. By subtracting the real-time data from the standard data, the deviation is calculated and these deviation values are compared with the data at the monitoring point to construct a set of causal traceability vectors. For example, if the deviation of the real-time gas concentration data exceeds the set threshold, a corresponding causal traceability vector will be generated.

[0027] Then, through an approximate matching method, the constructed causal traceability vector set is matched with the underground pipeline corridor historical risk log set. To perform this operation, a similarity measurement algorithm, such as cosine similarity, is used to calculate the similarity between the current causal traceability vector and each event in the historical log. Only when the causal traceability vector and the event in the historical log reach the preset matching threshold in terms of time, space, and characteristics, will the event be considered to have significant similarity with the current risk status. Through similarity calculation, matching underground pipeline corridor historical risk log clusters are obtained. These clusters contain all historical risk logs similar to the current monitoring data.

[0028] Then, the first matching underground pipeline corridor historical risk log set is extracted from the matching underground pipeline corridor historical risk log cluster, that is, the historical log that matches the current monitoring data is found. Then, the associated monitoring point set is extracted from the log, that is, all monitoring points associated with the historical event. These associated monitoring point sets are processed by union, and the monitoring points in different logs are merged to obtain the first tracing clue set. These clue sets reveal potential risk sources and their associated monitoring points. Finally, by traversing the entire matching underground pipeline corridor historical risk log cluster, tracing clues are extracted for all matching logs, and finally a complete tracing clue cluster is obtained.

[0029] Furthermore, in the method provided in the embodiment of the application, extracting traceability clues from each matching underground utility gallery historical risk log set in the matching underground utility gallery historical risk log cluster to obtain the traceability clue cluster further includes: Extract a first matching underground pipeline corridor historical risk log set from the matching underground pipeline corridor historical risk log cluster; extract a set of associated monitoring points in the first matching underground pipeline corridor historical risk log set; perform union processing on the associated monitoring point set, and obtain a first tracing clue set based on the processing result; traverse the matching underground pipeline corridor historical risk log cluster to extract tracing clues and obtain the tracing clue cluster.

[0030] In the embodiment of the present application, a first matching underground pipeline gallery historical risk log set is first extracted from the matching underground pipeline gallery historical risk log cluster. The set is randomly selected from the obtained historical risk log cluster.

[0031] Next, we extract the associated monitoring point set from the first matching underground tunnel historical risk log set. This step analyzes the risk events in the historical logs to identify the monitoring points associated with each log entry. For example, if the historical log records a gas leak, we extract the gas sensor monitoring points associated with the event and group them into an associated monitoring point set.

[0032] The associated monitoring point sets are then unioned. The purpose of this step is to merge the monitoring points mentioned in different log entries and eliminate duplicates. By unioning, it is ensured that a set containing all relevant monitoring points is finally obtained. For example, if gas sensor A is involved in multiple log entries, the sensor will only appear once in the final set and will not appear repeatedly. Next, based on the associated monitoring point set after union, the first traceability clue set is obtained according to the processing results. This step uses data analysis and feature extraction methods to identify monitoring points and their behaviors that may be closely related to the occurrence of risk events by analyzing the historical data, deviation values and change trends of each monitoring point. The characteristics of these monitoring points (such as abnormal fluctuations, changes exceeding the threshold, etc.) are used to construct a traceability clue set, which contains all monitoring points related to the current risk and provides a basis for subsequent risk tracing analysis.

[0033] Finally, traceability clues are extracted from each historical log entry in the matching underground tunnel historical risk log cluster, identifying possible risk sources and causal chains within each log. Causal reasoning methods are used to analyze the time series and monitoring point data in the logs to determine the causal relationships between different events. For example, if abnormal data from a gas sensor coincides with the time of an equipment failure, a causal relationship between the two events is inferred and extracted as a traceability clue, ultimately resulting in a traceability clue cluster.

[0034] Step S400: using the tracing clue cluster as an index, extracting clues from the data transfer memory to determine a tracing received data sequence cluster.

[0035] In an embodiment of the present application, the traceability clue cluster is used as an index to extract clues from the data transfer memory, quickly locating the data set related to the traceability clue. By using the monitoring points and event information specified in the traceability clue cluster, the corresponding historical and real-time data is searched in the data transfer memory. This data is closely related to the key monitoring points or events extracted from the traceability clue cluster, including sensor data, device status, environmental parameters, etc.

[0036] After retrieving relevant data, the traceability receiving data sequence cluster is determined. This step organizes the data extracted from the transit storage into a data sequence cluster in chronological order, forming a data time series related to the traceability clue. This sequence cluster shows the data's changing trends over time, helping to analyze behavioral patterns and abnormal fluctuations at monitoring points, further revealing potential risk factors. For example, gas sensor readings over different time periods can be aggregated to construct a complete time series.

[0037] Step S500: performing time series iterative trend risk authentication on the source-received data sequence clusters respectively to determine risk trend feature clusters.

[0038] In an embodiment of the present application, the first traceability reception data sequence is first extracted from the traceability reception data sequence cluster. Then, a time series iterative correlation trend analysis is performed on the sequence in chronological order to identify the changing trends and potential risks in the data sequence. By analyzing the pattern of data changes over time, data trend features are extracted, such as abnormal fluctuations or continuous growth trends. Subsequently, a pre-trained risk trend identifier is called to perform risk authentication on the extracted trend features. If the data trend meets the preset risk standard, the trend feature is added to the risk trend feature cluster. Finally, all traceability reception data sequence clusters are traversed, a time series iterative trend analysis is performed on each sequence, and it is authenticated by the risk trend identifier to finally obtain a complete risk trend feature cluster.

[0039] Furthermore, in the method provided in the embodiment of the application, the time series iterative trend risk authentication is performed on the traceability received data sequence clusters respectively to determine the risk trend feature clusters, and further includes: Extract the first traceability received data sequence from the traceability received data sequence cluster; perform time series iterative correlation trend analysis on the first traceability received data sequence in chronological order from front to back to determine the trend feature of the first traceability received data; call the risk trend identifier to perform risk authentication on the first traceability received data trend feature; if the authentication is passed, add the first traceability received data trend feature to the risk trend feature cluster; traverse the traceability received data sequence cluster to perform time series iterative trend analysis, and use the risk trend identifier to perform risk authentication on the analysis results to obtain the risk trend feature cluster.

[0040] In this embodiment of the present application, a first traceability received data sequence is randomly selected from the traceability received data sequence cluster. This sequence contains real-time monitoring data related to the traceability clue. This data reflects the status and changes of the risk monitoring point, such as temperature and gas concentration.

[0041] Next, we perform a time-series iterative correlation trend analysis on the first provenance received data sequence, chronologically from front to back. This process begins by extracting features from the first provenance received data sequence, including extracting corresponding temporal trend features and spatial trend features from both the temporal and spatial scales. These features are then similarity-identified, and by comparing the similarities between the temporal and spatial trend features, a first trend feature similarity set is determined. Next, based on the similarity set, a first iterative correlation matrix is constructed, and this matrix is used to perform feature convolution on the spatial trend features, thereby generating the final trend features of the first provenance received data.

[0042] The risk trend identifier is then called to perform risk authentication on the extracted trend features of the first traceability reception data. The risk trend identifier is a pre-trained machine learning model whose training data includes historical traceability reception data trend features and labels annotated by technical experts. These labels are divided into pass (indicating that the data trend conforms to the normal risk pattern) and fail (indicating that the data trend does not conform to the known risk pattern). By using these data for training, the identifier can learn the relationship between different trend features and risk events. During the authentication process, the trend features of the first traceability reception data are input into the risk trend identifier for risk authentication, and the output is pass or fail. If the authentication passes, it means that the current trend conforms to the characteristics of potential risks, and the trend feature is added to the risk trend feature cluster.

[0043] Finally, all data sequences in the source-received data sequence cluster are traversed, and time series iterative trend analysis is performed on each sequence. The risk trend identifier then verifies the risk of each data sequence. Each data sequence undergoes time series analysis to extract its trend characteristics. The identifier then determines whether it meets the risk criteria. If it does, the trend characteristic is added to the risk trend feature cluster. This method ultimately yields a risk trend feature cluster.

[0044] Furthermore, in the method provided in the embodiment of the application, performing a time series iterative correlation trend analysis on the first source tracing received data sequence in chronological order to determine the trend characteristics of the first source tracing received data further includes: Perform feature extraction on the first provenance tracing received data sequence according to the time scale and the spatial scale to obtain the time trend feature of the first provenance tracing received data and the spatial trend feature of the first provenance tracing received data; perform similarity identification on the time trend feature of the first provenance tracing received data and the spatial trend feature of the first provenance tracing received data to determine a first trend feature similarity set; construct a first iterative correlation matrix based on the first trend feature similarity set, and use the first iterative correlation matrix to perform feature convolution on the spatial trend feature of the first provenance tracing received data to generate the first provenance tracing received data trend feature.

[0045] Furthermore, the method provided in the application embodiment also includes: The first trend feature similarity set is normalized, and the processing result is filled into an initially empty diagonal matrix to generate the first iterative correlation matrix.

[0046] In an embodiment of the present application, feature extraction is first performed on the first traceability received data sequence according to the time scale and the spatial scale. In this process, the time trend features of the first traceability received data sequence are extracted in the time dimension through a one-dimensional convolution operation, and the pattern of data change over time is captured, such as gradual increase, decrease or periodic fluctuation. At the same time, the spatial trend features of the first traceability received data sequence are extracted in both time and space dimensions through a two-dimensional convolution operation, thereby identifying the spatial relationship and change trend between the monitoring points. Through this step, features reflecting the laws of time and space changes are obtained, and the time trend features of the first traceability received data and the spatial trend features of the first traceability received data are obtained respectively.

[0047] Next, similarity analysis is performed on the extracted temporal and spatial trend features of the first traceability received data. This process uses methods such as cosine similarity or Euclidean distance to calculate the similarity between each temporal and spatial trend feature, identifying which data sequences exhibit similar patterns of change in time and space. This process yields a first trend feature similarity set, which contains the similarity values between all temporal and spatial features.

[0048] Based on the first trend feature similarity set, a first iterative correlation matrix is then constructed. During this process, the similarity values in the similarity set are normalized to ensure that all similarity values are within the same scale (e.g., 0 to 1). The normalized similarity values are then populated into an initially empty diagonal matrix to generate the first iterative correlation matrix.

[0049] Finally, the first iterative association matrix is used to perform feature convolution on the spatial trend features of the first traceability received data. Feature convolution combines the similarity information in the association matrix with the spatial trend features, processing the spatial trend features in a weighted manner. Specifically, the convolution operation uses the similarity values of the association matrix as weights to perform a weighted average on the spatial trend features, thereby strengthening the features of monitoring points with similar patterns in the space. This weighted convolution operation can better capture the potential relationships between data, enhance the correlation of features, and ultimately generate more accurate trend features of the first traceability received data.

[0050] Step S600: determining a first dynamic monitoring frequency and a second dynamic monitoring frequency based on the risk trend feature cluster, and distributing both the first dynamic monitoring frequency and the second dynamic monitoring frequency to a status monitoring terminal, and performing dual-frequency synchronous status monitoring on a set of monitoring points.

[0051] In an embodiment of the present application, risk scoring is first performed based on the risk trend feature cluster to obtain a risk score set. These scores reflect the severity and priority of each risk trend feature, and the potential risk level is determined by evaluating the changing trend of each feature. Then, according to the maximum and minimum values of the risk score set, dynamic monitoring frequency matching is performed to generate a first dynamic monitoring frequency and a second dynamic monitoring frequency. The first dynamic monitoring frequency corresponds to high-risk points, usually high-frequency sampling, for rapid response to changes, while the second dynamic monitoring frequency corresponds to low-risk points, using lower-frequency monitoring to reduce data redundancy and reduce the sampling burden.

[0052] Both frequencies are then distributed to the condition monitoring terminals, ensuring that data is appropriately sampled for each monitoring point based on its risk level. This enables dual-frequency synchronous condition monitoring, meaning that different monitoring points are monitored in real time at a set dynamic frequency, ensuring efficient and accurate data collection.

[0053] Furthermore, in the method provided in the embodiment of the application, determining the first dynamic monitoring frequency and the second dynamic monitoring frequency based on the risk trend feature cluster further includes: Perform risk scoring based on the risk trend feature cluster to obtain a risk score set; perform dynamic monitoring frequency matching based on the maximum value and minimum value of the risk score set to generate a first dynamic monitoring frequency and a second dynamic monitoring frequency.

[0054] In this embodiment, a risk score is first performed based on a cluster of risk trend features, thereby obtaining a risk score set. Specifically, a score is assigned to each trend feature in the cluster. The scoring process depends on the magnitude of change, speed of change, duration, and degree of abnormality. For example, if the gas concentration at a monitoring point changes significantly over a period of time, a higher score is assigned to that feature based on pre-set rules. For example, if the gas concentration changes by more than 10% within one minute, the feature is assigned a score of 10; if the change is between 1% and 5%, it is assigned a score of 5; and if the change is less than 1%, it is assigned a score of 1. Similarly, the speed of change and duration are also scored based on pre-set thresholds. A faster rate of change, such as a fluctuation of more than 5% per second, results in a higher score (e.g., 10); a slower rate results in a lower score (e.g., 3). Scoring is performed based on the degree of abnormality; if the data deviates significantly from the normal range and persists for a longer period, the abnormality score is higher. Finally, these scores are weighted and summed, with the weights of each scoring factor set by technical experts based on actual needs, to obtain a total score for each risk feature. Through these steps, a risk score set is obtained.

[0055] Next, dynamic monitoring frequency matching is performed based on the maximum and minimum values of the risk score set. First, all risk scores are normalized, that is, the score values are converted to the range of [0, 1]. After normalization, the maximum risk score and minimum risk score obtained represent the highest and lowest risk scores in the monitoring point, respectively. The normalized maximum and minimum score values are matched with the preset rule table. In the preset rule table, corresponding monitoring frequencies are set according to different risk score values. For example, the rule table may specify that when the risk score is close to 1 (i.e., high risk), the monitoring frequency is sampled once per second; when the risk score is close to 0 (i.e., low risk), the monitoring frequency is sampled once per minute. According to the settings of the rule table, these normalized score values are matched with the corresponding frequencies to obtain the first dynamic monitoring frequency and the second dynamic monitoring frequency.

[0056] Furthermore, the method provided in the application embodiment also includes: Based on the maximum value in the risk score set, the size of the window constraint of the data transfer memory is optimized and adjusted.

[0057] In an embodiment of the present application, when optimizing the size of the data transfer memory's window constraint based on the maximum value in a risk score set, the maximum risk score is first extracted and normalized to ensure that the score value is within a uniform range (between 0 and 1). After normalization, the normalized maximum risk score value is converted to the window size through a linear mapping. Specifically, window size = minimum window size + normalized maximum risk score × (maximum window size − minimum window size). Through this method, the optimized adjustment of the data transfer memory's window constraint size is completed.

[0058] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects: The present application obtains a set of monitoring points of an underground pipeline corridor, uses a set of multi-source status monitoring terminals to monitor the set of monitoring points according to a preset monitoring frequency, and transmits the monitoring data to a data transmission center, wherein the data transmission center has a data transfer memory with window constraints; performs real-time risk identification based on the data transmission center, and determines a risk real-time receiving data set and a risk monitoring point set; performs causal tracing based on the risk monitoring point set and the risk real-time receiving data set, and determines a tracing clue cluster; uses the tracing clue cluster as an index, performs clue extraction on the data transfer memory, and determines a tracing receiving data sequence cluster; performs time-series iterative trend risk authentication on the tracing receiving data sequence cluster, and determines a risk trend feature cluster; determines a first dynamic monitoring frequency and a second dynamic monitoring frequency based on the risk trend feature cluster, and distributes the first dynamic monitoring frequency and the second dynamic monitoring frequency to the status monitoring terminal, and performs dual-frequency synchronous status monitoring on the monitoring point set. This application solves the technical problem in the existing technology that the frequency of real-time status monitoring of underground pipelines is fixed and cannot be dynamically adjusted according to risk changes. By integrating multi-source monitoring data to perform causal tracing and trend risk authentication, and generating a dynamic monitoring frequency based on this, the monitoring frequency can be adaptively adjusted according to the risk status, thereby improving the monitoring accuracy and response timeliness.

[0059] Example 2, based on the same inventive concept as the method for real-time dynamic monitoring of underground pipeline corridor status by multi-source data fusion in the above embodiment, Figure 2 As shown, the present application provides a real-time dynamic monitoring system for underground pipe corridors with multi-source data fusion. The system and method embodiments in the present application are based on the same inventive concept. The system includes: The monitoring module 11 is used to obtain a set of monitoring points of the underground pipeline corridor, monitor the set of monitoring points according to a preset monitoring frequency using a multi-source status monitoring terminal set, and transmit the monitoring data to a data transmission center, wherein the data transmission center has a data transfer memory with window constraints; the risk identification module 12 is used to perform real-time risk identification based on the data transmission center, and determine a risk real-time receiving data set and a risk monitoring point set; the causal tracing module 13 is used to perform causal tracing based on the risk monitoring point set and the risk real-time receiving data set, and determine a tracing clue cluster; the clue extraction module 14 is used to extract clues from the data transfer memory with the tracing clue cluster as an index, and determine a tracing receiving data sequence cluster; the risk authentication module 15 is used to perform time series iterative trend risk authentication on the tracing receiving data sequence cluster respectively, and determine a risk trend feature cluster; the dual-frequency synchronous monitoring module 16 is used to determine a first dynamic monitoring frequency and a second dynamic monitoring frequency based on the risk trend feature cluster, and distribute the first dynamic monitoring frequency and the second dynamic monitoring frequency to the status monitoring terminal, and perform dual-frequency synchronous status monitoring on the monitoring point set.

[0060] Furthermore, the system is also used to implement the following functions: A multi-source real-time received data set is extracted from the data transmission center, and deviations of the multi-source real-time received data set are identified using a multi-source standard status data set to determine a multi-source real-time received data deviation set; risk identification is performed on the multi-source real-time received data deviation set according to a preset risk deviation threshold to determine a risk real-time received data set and a risk monitoring point set, wherein each multi-source real-time received data corresponds to a monitoring point.

[0061] Furthermore, the system is also used to implement the following functions: Obtain a set of historical risk logs for underground pipeline corridors; construct a set of causal tracing vectors based on the risk monitoring point set and the risk real-time receiving data set; perform approximate matching on the set of causal tracing vectors in the set of historical risk logs for underground pipeline corridors to obtain a matching cluster of historical risk logs for underground pipeline corridors; extract tracing clues from each matching set of historical risk logs for underground pipeline corridors in the matching cluster of historical risk logs for underground pipeline corridors to obtain the tracing clue cluster.

[0062] Furthermore, the system is also used to implement the following functions: Extract a first matching underground pipeline corridor historical risk log set from the matching underground pipeline corridor historical risk log cluster; extract a set of associated monitoring points in the first matching underground pipeline corridor historical risk log set; perform union processing on the associated monitoring point set, and obtain a first tracing clue set based on the processing result; traverse the matching underground pipeline corridor historical risk log cluster to extract tracing clues and obtain the tracing clue cluster.

[0063] Furthermore, the system is also used to implement the following functions: Extract the first traceability received data sequence from the traceability received data sequence cluster; perform time series iterative correlation trend analysis on the first traceability received data sequence in chronological order from front to back to determine the trend feature of the first traceability received data; call the risk trend identifier to perform risk authentication on the first traceability received data trend feature; if the authentication is passed, add the first traceability received data trend feature to the risk trend feature cluster; traverse the traceability received data sequence cluster to perform time series iterative trend analysis, and use the risk trend identifier to perform risk authentication on the analysis results to obtain the risk trend feature cluster.

[0064] Furthermore, the system is also used to implement the following functions: Perform feature extraction on the first provenance tracing received data sequence according to the time scale and the spatial scale to obtain the time trend feature of the first provenance tracing received data and the spatial trend feature of the first provenance tracing received data; perform similarity identification on the time trend feature of the first provenance tracing received data and the spatial trend feature of the first provenance tracing received data to determine a first trend feature similarity set; construct a first iterative correlation matrix based on the first trend feature similarity set, and use the first iterative correlation matrix to perform feature convolution on the spatial trend feature of the first provenance tracing received data to generate the first provenance tracing received data trend feature.

[0065] Furthermore, the system is also used to implement the following functions: The first trend feature similarity set is normalized, and the processing result is filled into an initially empty diagonal matrix to generate the first iterative correlation matrix.

[0066] Furthermore, the system is also used to implement the following functions: Perform risk scoring based on the risk trend feature cluster to obtain a risk score set; perform dynamic monitoring frequency matching based on the maximum value and minimum value of the risk score set to generate a first dynamic monitoring frequency and a second dynamic monitoring frequency.

[0067] Furthermore, the system is also used to implement the following functions: Based on the maximum value in the risk score set, the size of the window constraint of the data transfer memory is optimized and adjusted.

[0068] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0070] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for real-time dynamic monitoring of underground pipeline corridors based on multi-source data fusion, characterized in that: The method comprises: Obtain a set of monitoring points in the underground pipeline corridor, monitor the set of monitoring points using a set of multi-source status monitoring terminals according to a preset monitoring frequency, and transmit the monitoring data to a data transmission center, wherein the data transmission center has a data transfer memory with window constraints; Performing real-time risk identification based on the data transmission center to determine a risk real-time receiving data set and a risk monitoring point set; Perform causal tracing based on the risk monitoring point set and the risk real-time received data set to determine a tracing clue cluster; Using the tracing clue cluster as an index, extracting clues from the data transfer memory to determine the tracing received data sequence cluster; Performing time series iterative trend risk authentication on the traceability received data sequence clusters respectively to determine the risk trend feature clusters; A first dynamic monitoring frequency and a second dynamic monitoring frequency are determined based on the risk trend feature cluster, and the first dynamic monitoring frequency and the second dynamic monitoring frequency are distributed to the status monitoring terminal to perform dual-frequency synchronous status monitoring on the monitoring point set.

2. The method for real-time dynamic monitoring of underground pipeline corridors based on multi-source data fusion according to claim 1, characterized in that: Performing real-time risk identification based on the data transmission center and determining a risk real-time receiving data set and a risk monitoring point set includes: Extracting a multi-source real-time received data set from the data transmission center, performing deviation identification on the multi-source real-time received data set using a multi-source standard state data set, and determining a multi-source real-time received data deviation set; Risk identification is performed on the multi-source real-time received data deviation set according to a preset risk deviation threshold, and a risk real-time received data set and a risk monitoring point set are determined, wherein each multi-source real-time received data corresponds to a monitoring point.

3. The method for real-time dynamic monitoring of underground pipeline corridors based on multi-source data fusion according to claim 1 is characterized in that: Performing causal tracing based on the risk monitoring point set and the risk real-time received data set to determine a tracing clue cluster includes: Obtain a collection of historical risk logs for underground pipeline corridors; Constructing a causal traceability vector set based on the risk monitoring point set and the risk real-time received data set; Approximately matching the causal traceability vector set in the underground pipeline gallery historical risk log set to obtain a matching underground pipeline gallery historical risk log cluster; Extracting traceability clues from each matching underground pipeline gallery historical risk log set in the matching underground pipeline gallery historical risk log cluster to obtain the traceability clue cluster.

4. The method for real-time dynamic monitoring of underground pipeline corridors based on multi-source data fusion according to claim 3 is characterized in that: Extracting traceability clues from each matching underground utility gallery historical risk log set in the matching underground utility gallery historical risk log cluster to obtain the traceability clue cluster includes: Extracting a first matching underground pipeline gallery historical risk log set from the matching underground pipeline gallery historical risk log cluster; Extracting a set of associated monitoring points from the first matching underground pipeline gallery historical risk log set; Performing a union process on the associated monitoring point set, and obtaining a first tracing clue set according to the process result; The matching underground pipeline corridor historical risk log cluster is traversed to extract traceability clues to obtain the traceability clue cluster.

5. The method for real-time dynamic monitoring of underground pipeline corridors based on multi-source data fusion according to claim 1, characterized in that: Performing time series iterative trend risk authentication on the traceability received data sequence clusters to determine the risk trend feature clusters, including: Extracting a first traceability received data sequence from the traceability received data sequence cluster; Performing a time series iterative correlation trend analysis on the first source tracing received data sequence in chronological order to determine trend characteristics of the first source tracing received data; Calling a risk trend identifier to perform risk authentication on the first traceability received data trend feature, and if the authentication passes, adding the first traceability received data trend feature to a risk trend feature cluster; The traceability received data sequence cluster is traversed to perform time series iterative trend analysis, and a risk trend identifier is used to perform risk authentication on the analysis result to obtain the risk trend feature cluster.

6. The method for real-time dynamic monitoring of underground pipeline corridors based on multi-source data fusion according to claim 5 is characterized in that: Performing a time series iterative correlation trend analysis on the first source tracing received data sequence in chronological order to determine trend characteristics of the first source tracing received data includes: Perform feature extraction on the first source tracing received data sequence according to a time scale and a spatial scale to obtain a time trend feature of the first source tracing received data and a spatial trend feature of the first source tracing received data; Performing similarity identification on the time trend feature of the first source tracing received data and the spatial trend feature of the first source tracing received data to determine a first trend feature similarity set; A first iterative correlation matrix is constructed based on the first trend feature similarity set, and the first iterative correlation matrix is used to perform feature convolution on the first source tracing received data spatial trend feature to generate the first source tracing received data trend feature.

7. The method for real-time dynamic monitoring of underground pipeline corridors based on multi-source data fusion according to claim 6, characterized in that: Constructing a first iterative correlation matrix based on the first trend feature similarity set includes: The first trend feature similarity set is normalized, and the processing result is filled into an initially empty diagonal matrix to generate the first iterative correlation matrix.

8. The method for real-time dynamic monitoring of underground pipeline corridor status by multi-source data fusion according to any one of claims 1 to 7, characterized in that: Determining a first dynamic monitoring frequency and a second dynamic monitoring frequency based on the risk trend feature cluster includes: Performing risk scoring based on the risk trend feature cluster to obtain a risk score set; Dynamic monitoring frequency matching is performed according to the maximum value and the minimum value of the risk score set to generate a first dynamic monitoring frequency and a second dynamic monitoring frequency.

9. The method for real-time dynamic monitoring of underground pipeline corridors based on multi-source data fusion according to claim 8, characterized in that: Based on the maximum value in the risk score set, the size of the window constraint of the data transfer memory is optimized and adjusted.

10. A multi-source data fusion underground pipeline corridor real-time dynamic monitoring system, characterized in that: The system is used to execute the method for real-time dynamic monitoring of the underground pipeline corridor status by multi-source data fusion according to any one of claims 1 to 9, and the system includes: A monitoring module is used to obtain a set of monitoring points in the underground pipeline corridor, monitor the set of monitoring points according to a preset monitoring frequency using a set of multi-source status monitoring terminals, and transmit the monitoring data to a data transmission center, wherein the data transmission center has a data transfer memory with window constraints; A risk identification module, configured to perform real-time risk identification based on the data transmission center, and determine a risk real-time receiving data set and a risk monitoring point set; A causal tracing module is used to perform causal tracing based on the risk monitoring point set and the risk real-time received data set to determine a tracing clue cluster; A clue extraction module is used to extract clues from the data transfer memory using the traceability clue cluster as an index to determine a traceability received data sequence cluster; A risk authentication module is used to perform time series iterative trend risk authentication on each of the traceability received data sequence clusters to determine a risk trend feature cluster; The dual-frequency synchronous monitoring module is used to determine the first dynamic monitoring frequency and the second dynamic monitoring frequency based on the risk trend feature cluster, and distribute the first dynamic monitoring frequency and the second dynamic monitoring frequency to the status monitoring terminal to perform dual-frequency synchronous status monitoring on the monitoring point set.

Images