Comprehensive pipe gallery dynamic risk prediction method and system based on Internet of Things

Abstract

The invention provides a comprehensive pipe gallery dynamic risk prediction method and system based on the Internet of Things, and relates to the technical field of data processing. The method comprises the following steps: acquiring historical comprehensive pipe gallery monitoring data; performing principal component analysis on the historical comprehensive pipe gallery monitoring data, and determining a characteristic value and a characteristic vector of the historical comprehensive pipe gallery monitoring data; determining the main axis direction and the main axis direction half axis length according to the feature vectors and the feature values, and establishing a minimum ellipsoid for describing the normal operation state of the comprehensive pipe gallery in combination with chi-square test and the law of great numbers; the minimum ellipsoid is issued to the edge end; acquiring current comprehensive pipe gallery monitoring data through a data acquisition terminal; the current comprehensive pipe gallery monitoring data are uploaded to an edge end, and under the condition that the current comprehensive pipe gallery monitoring data are abnormal, abnormal pipe gallery features are determined through a Shapley value; and outputting abnormal current comprehensive pipe gallery monitoring data and abnormal pipe gallery characteristics, and sending risk early warning. And the accuracy and timeliness of comprehensive pipe gallery risk prediction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for dynamic risk prediction of an integrated pipe gallery based on the Internet of Things. Background Art

[0002] The Internet of Things refers to a technical system that connects devices, systems and environments in the physical world through sensors, devices and networks to achieve information collection, transmission, processing and sharing. It enables devices to operate automatically and interact in real time through intelligent perception and interconnection. An integrated pipeline corridor refers to a centralized tunnel space built underground in a city to house a variety of municipal pipelines (such as electricity, communications, tap water, gas, heating, etc.) to achieve unified management and maintenance and avoid repeated ground excavation.

[0003] As a key infrastructure of the city, the integrated pipeline corridor will have a serious impact on the city's operations such as water supply, power supply, and communications once pipeline leakage, collapse, overload, etc. Through risk prediction methods, potential problems in the operation of the pipeline corridor can be discovered in advance, the probability of failure can be reduced, the safety and reliability of the pipeline corridor can be improved, and the maintenance cost and interference with urban life can be reduced, ensuring the normal operation of the city and the safety of residents.

[0004] However, the existing risk prediction of integrated pipe corridors often uses fixed values ​​to predict the operation factors of integrated pipe corridors independently. If the fixed value is exceeded, there is a risk, and if it is not exceeded, there is no risk. This risk prediction method does not consider the potential coupling relationship between various operation factors. The risk prediction method that only analyzes single factors and fixed thresholds cannot consider the correlation and change trend between multiple factors. The risk prediction accuracy is low, and it is easy to have false positives and false negatives. It cannot discover potential risks, which affects the safe operation of the integrated pipe corridor. Summary of the invention

[0005] In order to solve the problem that the risk prediction of integrated pipe corridors in the prior art often uses fixed values ​​to independently predict the operating factors of the integrated pipe corridors, and there is a risk if the fixed value is exceeded, and there is no risk if the fixed value is not exceeded. This risk prediction method does not take into account the potential coupling relationship between various operating factors. The risk prediction method that only analyzes by a single factor and a fixed threshold cannot consider the correlation and change trend between multiple factors. The risk prediction accuracy is low, and it is easy to have false positives and false negatives, and it cannot discover potential risks, which affects the technical problems of the safe operation of the integrated pipe corridor. The present invention provides a dynamic risk prediction method and system for integrated pipe corridors based on the Internet of Things.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect

[0008] An embodiment of the present invention provides a dynamic risk prediction method for an integrated pipe gallery based on the Internet of Things, which is applied to a risk prediction platform for an integrated pipe gallery. The risk prediction platform includes a data acquisition terminal, an edge terminal, and a cloud end connected in sequence, and the data acquisition terminal is connected to the cloud end. The method includes:

[0009] S1: Obtain historical comprehensive pipeline corridor monitoring data including different pipeline corridor characteristics through the cloud;

[0010] S2: Perform principal component analysis on the historical monitoring data of the utility corridor to determine the eigenvalues ​​and eigenvectors of the historical monitoring data of the utility corridor;

[0011] S3: Determine the main axis direction and the semi-axis length of the main axis direction according to the eigenvector and eigenvalue, and establish the minimum ellipsoid describing the normal operation status of the integrated pipeline corridor by combining the chi-square test and the law of large numbers;

[0012] S4: Send the minimum ellipsoid to the edge;

[0013] S5: Collect the current integrated pipe gallery monitoring data through the data collection terminal;

[0014] S6: Upload the current monitoring data of the integrated pipe gallery to the edge end, and determine whether the current monitoring data of the integrated pipe gallery is abnormal by combining the minimum ellipsoid and the semi-axis length in the main axis direction. If so, proceed to step S7, otherwise, return to step S5;

[0015] S7: Determine the abnormal pipeline corridor characteristics in the abnormal current integrated pipeline corridor monitoring data through the Shapley value;

[0016] S8: Output abnormal current integrated pipeline corridor monitoring data and abnormal pipeline corridor characteristics, and issue risk warnings.

[0017] Second aspect

[0018] An embodiment of the present invention provides a dynamic risk prediction system for an integrated pipe gallery based on the Internet of Things, comprising:

[0019] processor;

[0020] A memory having computer-readable instructions stored thereon, which, when executed by a processor, implements the method for dynamic risk prediction of an integrated pipeline corridor based on the Internet of Things as in the first aspect.

[0021] The third aspect

[0022] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for dynamic risk prediction of an integrated pipeline corridor based on the Internet of Things as described in the first aspect is implemented.

[0023] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0024] (1) In the present invention, the historical integrated pipe corridor monitoring data is subjected to principal component analysis to determine the eigenvalues ​​and eigenvectors of the historical integrated pipe corridor monitoring data, the main axis direction and the length of the semi-axis in the main axis direction are determined according to the eigenvectors and eigenvalues, and the minimum ellipsoid describing the normal operation status of the integrated pipe corridor is established in combination with the chi-square test and the law of large numbers. The key features are extracted by principal component analysis, and the model is dynamically adjusted in combination with the chi-square test and the law of large numbers to fully capture the data distribution characteristics of normal pipe corridor data, thereby reversely improving the accuracy and adaptability of risk prediction, effectively reducing false positives and false negatives, adapting to changes in complex pipe corridor environments, and ensuring operational safety. Afterwards, the minimum ellipsoid and the length of the semi-axis in the main axis direction are used to judge whether the current integrated pipe corridor monitoring data is abnormal as a whole, i.e., associated data, rather than judging them separately. If the current integrated pipe corridor monitoring data is not located in the minimum ellipsoid, it is directly judged that it is abnormal. If it is located in the minimum ellipsoid, the semi-axis length in the main axis direction is used to further judge and verify whether it is abnormal. It can quickly process massive data with low latency and high accuracy in risk prediction. Finally, the Shapley value is used to accurately quantify the contribution of each feature to the anomaly, which can accurately locate the abnormal pipeline corridor characteristics, improve the pertinence and interpretability of risk prediction, and effectively reduce the scope of false alarms, providing a clear direction for subsequent risk intervention, and further enhancing the efficiency and accuracy of dynamic risk prediction of comprehensive pipeline corridors.

[0025] (2) In the present invention, an Internet of Things risk prediction platform including a data acquisition terminal, an edge terminal and a cloud terminal is also combined, which makes full use of the data local processing capability of the edge terminal to improve the real-time prediction, and uses the powerful data computing capability of the cloud terminal to accurately and quickly establish the minimum ellipsoid that describes the normal operating status of the integrated pipeline corridor, thereby further improving the risk prediction accuracy and real-time performance of the integrated pipeline corridor. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 A schematic diagram of a flow chart of a method for dynamic risk prediction of an integrated pipe gallery based on the Internet of Things provided in an embodiment of the present invention;

[0028] Figure 2 A schematic diagram of the structure of a risk prediction platform provided by an embodiment of the present invention;

[0029] Figure 3A structural schematic diagram of a dynamic risk prediction system for an integrated pipeline corridor based on the Internet of Things provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0031] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0032] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0033] Reference Manual Attached Figure 1 , showing a flow chart of a method for dynamic risk prediction of an integrated pipeline corridor based on the Internet of Things provided in an embodiment of the present invention.

[0034] Reference Manual Attached Figure 2 , showing a schematic diagram of the structure of a risk prediction platform provided by an embodiment of the present invention.

[0035] An embodiment of the present invention provides a dynamic risk prediction method for an integrated pipeline corridor based on the Internet of Things, which is applied to a risk prediction platform for the integrated pipeline corridor. The risk prediction platform includes a data acquisition terminal, an edge terminal and a cloud end connected in sequence, and the data acquisition terminal is connected to the cloud end.

[0036] Among them, the data acquisition terminal is composed of multimodal sensors deployed in the tunnel, which is responsible for real-time collection of monitoring data such as temperature, humidity, and vibration of the tunnel. These terminal devices upload data to the edge or cloud through the network. The edge is deployed on a local computing device close to the data acquisition terminal. It is responsible for rapid processing and preliminary analysis of data, reducing data transmission delays, and is suitable for scenarios that require real-time feedback. As a core computing and storage platform, the cloud is responsible for highly complex model training, risk prediction, and storage and analysis of global data. It connects the edge to achieve overall data management and centralized analysis. The IoT-based integrated tunnel dynamic risk prediction platform collects real-time tunnel data through data acquisition terminals, the edge quickly analyzes and reduces transmission delays, and the cloud is responsible for comprehensive storage and complex model calculations to achieve an efficient, multi-level dynamic risk prediction system.

[0037] The processing flow of the dynamic risk prediction method of the integrated pipeline corridor based on the Internet of Things can include the following steps:

[0038] S1: Obtain historical comprehensive pipeline corridor monitoring data including different pipeline corridor characteristics through the cloud.

[0039] It is understandable that the acquisition of historical comprehensive corridor monitoring data including different corridor characteristics through the cloud is aimed at comprehensively collecting multi-dimensional information on the corridor's operating status and providing a data basis for subsequent analysis. These characteristics include key indicators such as temperature, humidity, and gas concentration, which can reflect the corridor's environment and equipment operating conditions. Through comprehensive data collection, the accuracy and reliability of the risk prediction model are ensured.

[0040] In a possible implementation, the pipe gallery characteristics include temperature, humidity, gas concentration, light intensity, pressure value, vibration, displacement, cable voltage, and cable current.

[0041] It should be noted that through real-time monitoring and analysis of these data, the operation status and potential abnormal changes of the pipeline corridor can be accurately reflected, providing key multi-dimensional data support for dynamic risk prediction, thereby improving the safety of the system and prediction accuracy.

[0042] In a possible implementation manner, after S1, the method further includes:

[0043] The historical integrated pipeline corridor monitoring data is preprocessed including data cleaning and data normalization.

[0044] It should be noted that by performing data cleaning and normalization preprocessing on the historical integrated pipeline corridor monitoring data, outliers can be removed, missing data can be filled, and dimensions can be unified to ensure data quality and comparability between features, thereby providing more accurate and standardized input for subsequent analysis and modeling, and improving the reliability and effectiveness of risk prediction.

[0045] S2: Perform principal component analysis on the historical monitoring data of the integrated pipeline corridor to determine the eigenvalues ​​and eigenvectors of the historical monitoring data of the integrated pipeline corridor.

[0046] Among them, principal component analysis (PCA) is a dimensionality reduction technique that is used to extract the direction with the largest variance in the data through linear transformation, map high-dimensional data to low-dimensional space, and retain the main information of the original data as much as possible. It determines the main direction (eigenvector) and its importance (eigenvalue) of the data through eigenvalue decomposition or singular value decomposition, thereby reducing redundant information and revealing the potential structure between variables. Through principal component analysis, the main features are extracted from historical monitoring data, eigenvalues ​​and eigenvectors are determined, the coupling relationship between key features is captured, the data complexity is reduced, and a more accurate and concise input basis is provided for subsequent risk prediction models.

[0047] In a possible implementation, S2 specifically includes:

[0048] S201: Establish a data matrix of historical integrated pipeline corridor monitoring data:

[0049]

[0050] Where X represents the data matrix, represents the j-th corridor characteristic value of the i-th sample data, , , n represents the total number of sample data, and d represents the total number of corridor features.

[0051] S202: Solve the covariance matrix of the data matrix:

[0052]

[0053] in, represents the covariance matrix, x represents the element in the data matrix, It represents the mean value of the corridor characteristics, that is, the mean value of the column elements of the data matrix. The subscript T represents transposition. express The probability distribution of , W represents the diagonal weight matrix, represents the weight of the j-th pipeline corridor feature, diag represents the diagonal element, and log represents the logarithmic function.

[0054] It should be noted that the information entropy calculation weights are introduced to dynamically adjust the feature weights of the covariance matrix, so that features with large amounts of information are more influential in eigenvalue decomposition. Ultimately, the optimized covariance matrix can more accurately reflect the data distribution, which helps to improve the effect of principal component analysis. If the value range of a feature is large (such as uniform distribution), its information entropy is high, indicating that the feature contains more information. If the value range of a feature is small or concentrated (such as a constant value), its information entropy is low, indicating that the feature has less information or is a redundant feature. Features with higher weights (features with large amounts of information) occupy a more important position in the covariance matrix. Features with lower weights (features with less information or noise) are weakened, thereby improving the accuracy of principal component decomposition.

[0055] S203: Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors:

[0056]

[0057] in, represents the eigenvector matrix, represents the eigenvalue matrix, and Represents the eigenvector and eigenvalue of the j-th pipeline corridor feature in a one-to-one correspondence.

[0058] Specifically, firstly, by establishing a data matrix of historical integrated pipe corridor monitoring data, the system performs a structured representation of the multidimensional feature data in the sample. Then, by calculating the covariance matrix of the data matrix, the correlation and distribution characteristics between the features are analyzed. In order to improve the accuracy of the covariance matrix, a weight based on information entropy is introduced. By calculating the information entropy of each feature, the weight of the feature is dynamically adjusted. Features with high information entropy represent rich information and contribute more significantly to the covariance matrix, while the influence of features with low information entropy or noise features is weakened, thereby optimizing the reflection of the covariance matrix on the data distribution. Finally, by performing eigenvalue decomposition on the covariance matrix, the eigenvalue matrix and eigenvector matrix are obtained. The eigenvalue reflects the importance of the data in the direction of the corresponding eigenvector. These decomposition results are used to extract the key features of the data, reduce the dimension, and provide a mathematical basis for subsequent modeling. This process not only improves the accuracy and efficiency of data analysis. Accurately extract key features and eliminate redundant information, thereby improving the accuracy and efficiency of risk prediction, while dynamically adapting to the changes in the importance of different features.

[0059] S3: Determine the main axis direction and the semi-axis length of the main axis direction based on the eigenvector and eigenvalue, and combine the chi-square test and the law of large numbers to establish the minimum ellipsoid that describes the normal operating status of the integrated pipeline corridor.

[0060] Among them, the principal axis direction is defined by the eigenvector of the principal component analysis, which indicates the direction in which the data changes the most in a certain feature dimension. Each eigenvector corresponds to a principal axis direction, pointing to the main trend of the data distribution. The length of the semi-axis is determined by the square root of the eigenvalue, which indicates the distribution range of the data in the corresponding principal axis direction. The larger the eigenvalue, the longer the corresponding semi-axis, and the more significant the change in the data. The chi-square test is used to assess whether the data deviates from the expected distribution. In this application, it is used to determine whether the data points are within the range of the normal distribution, and the boundaries are set by the chi-square distribution to define normal and abnormal. The law of large numbers states that when the number of samples tends to infinity, the sample mean approaches the population mean. In this method, the law of large numbers is used to dynamically adjust the boundary range of the model to adapt it to the change in data scale. The minimum ellipsoid is a geometric model used to enclose the vast majority of points in the data set, with the mean of the data at its center, the semi-axis direction defined by the eigenvector, and the semi-axis length determined by the eigenvalue, which is used to describe the normal distribution range of the data.

[0061] It should be noted that the main axis direction is determined by the eigenvector, the semi-axis length is determined by the eigenvalue, the minimum ellipsoid is established by combining the chi-square test and the law of large numbers, and the boundary is dynamically adjusted to adapt to the data distribution. This is used to accurately describe the normal operating status of the corridor and provide a reliable reference standard for anomaly detection, thereby significantly improving the accuracy and dynamics of risk prediction.

[0062] In a possible implementation, the minimum ellipsoid is specifically:

[0063]

[0064] in, The mean value of the corridor characteristics is the mean value of the column elements of the data matrix, which is the center of the minimum ellipsoid. Represents the smallest ellipsoid The length of the semi-axis in the direction of the corresponding principal axis, R represents the maximum radius describing the boundary range of the minimum ellipsoid, represents the significance level, It means that the confidence level is 1- The chi-square distribution of Represents the sample data variance.

[0065] Specifically, by establishing a minimum ellipsoid based on the chi-square distribution and dynamic adjustment of sample variance, the normal operating status range of the integrated pipeline corridor can be accurately described, while dynamically adapting to changes in data distribution to avoid false alarms and omissions, thereby significantly improving the accuracy and reliability of dynamic risk prediction.

[0066] Alternatively, the significance level may be 0.05 or 0.01.

[0067] The determination of R is combined with the law of large numbers, with the goal of dynamically relaxing or tightening the bounds. Specifically, when n is large, Will be close to 0, adjustment factor approaches 1, in which case the boundary Close to the classic chi-square distribution value When 𝑛 is very small, is large, the adjustment factor is significantly greater than 1. This will result in is enlarged, thereby increasing the boundary range and better accommodating normal points. This is to prevent too many misjudgments (i.e., normal points are judged as abnormal points) when the sample size is too small and the boundary range is too small. In addition, when the variance of the data is large (i.e., the data distribution is more dispersed), When the variance of the data is small, the adjustment factor will also increase. This can appropriately relax the boundary and avoid excluding too many normal points. When the adjustment factor is close to 1, the boundary range will shrink accordingly, and the anomaly will be defined more strictly. In addition, when the variance of the data is large (that is, the data distribution is more dispersed), When the variance of the data is small, the adjustment factor will also increase. This can appropriately relax the boundary and avoid excluding too many normal points. The smaller the value is, the closer the adjustment factor is to 1, and the boundary range will shrink accordingly, defining the anomaly more strictly.

[0068] S4: Send the minimum ellipsoid to the edge.

[0069] It should be noted that the minimum ellipsoid model constructed in the cloud is sent to the edge, so that the edge can quickly make abnormal judgments on the real-time monitoring data locally, reduce data transmission delays and computing pressure, and achieve efficient real-time risk prediction.

[0070] S5: Collect current integrated pipeline corridor monitoring data through the data collection terminal.

[0071] Among them, the current integrated pipe gallery monitoring data is the environment and equipment operation status information collected in real time by sensors, reflecting the operation status of the pipe gallery at the current moment. The current integrated pipe gallery monitoring data refers to the real-time collected and tested pipe gallery operation data, which needs to be compared with the normal state (described by the minimum ellipsoid) to determine whether it is abnormal. This is the basic input data for dynamic detection and risk prediction.

[0072] S6: Upload the current integrated pipe gallery monitoring data to the edge end, and determine whether the current integrated pipe gallery monitoring data is abnormal based on the minimum ellipsoid and the semi-axis length in the main axis direction. If so, proceed to step S7, otherwise, return to step S5.

[0073] It should be noted that by uploading the current integrated pipe corridor monitoring data to be detected to the edge end, the minimum ellipsoid model and the semi-axis length in the main axis direction are used to determine the data abnormalities. Combined with the minimum ellipsoid, it is possible to judge whether the data conforms to the multidimensional distribution characteristics of normal operation as a whole. Combined with the semi-axis length in the main axis direction, it can be further verified whether the data in each direction exceeds the normal range. This method combines global judgment and local verification, which can not only quickly identify significant anomalies, but also reduce the misjudgment rate, and comprehensively improve the accuracy and robustness of risk prediction.

[0074] In a possible implementation manner, judging whether the current integrated pipe gallery monitoring data is abnormal by using the minimum ellipsoid in S6 specifically includes:

[0075] S601: Determine whether the current monitoring data of the integrated pipe gallery is located in the minimum ellipsoid, that is, whether it satisfies the following formula. If so, proceed to step S602; otherwise, proceed to step S605:

[0076]

[0077] in, Indicates the current monitoring data of the integrated pipeline corridor.

[0078] S602: Calculate the projection values ​​of the current integrated pipe gallery monitoring data in the directions of each principal axis of the minimum ellipsoid:

[0079]

[0080] in, Indicates the current monitoring data of the integrated pipeline corridor In the main axis direction The projection value of .

[0081] S603: Determine whether each projection value is less than the semi-axis length of the maximum principal axis direction of the minimum ellipsoid, that is, whether the following formula is satisfied. If so, proceed to step S604; otherwise, proceed to step S605:

[0082]

[0083] in, Indicates the maximum semi-axis length in the principal axis direction of the minimum drag sphere.

[0084] S604: Output the current integrated pipeline corridor monitoring data as normal data.

[0085] S605: Output the current integrated pipeline corridor monitoring data as abnormal data.

[0086] It should be noted that, through the hierarchical judgment method based on the minimum ellipsoid, the dynamic risk prediction of the integrated pipe gallery can gradually screen the abnormality of the monitoring data. First, it is judged whether the data as a whole falls into the minimum ellipsoid, and then the projection value in the main axis direction is used to further accurately verify the abnormality. This method combines global and local judgments to avoid misjudgment of a single standard and improve the accuracy of the prediction. At the same time, the computational requirements for abnormal analysis are reduced through hierarchical screening, which significantly reduces the diagnostic delay and computing resource consumption while ensuring the detection accuracy, enabling it to efficiently cope with the complex integrated pipe gallery monitoring data environment.

[0087] S7: Determine the abnormal corridor characteristics in the abnormal current integrated corridor monitoring data through the Shapley value.

[0088] Among them, Shapley Value is an indicator based on cooperative game theory, which is used to measure the contribution of each feature to the overall result. In the risk prediction of the pipeline corridor, Shapley Value quantifies the abnormal contribution of each feature by calculating the impact of each feature on the abnormal detection results, helping to accurately locate the source of the problem. The Shapley Value is used to calculate the contribution of each pipeline corridor feature to the abnormal detection results, accurately locate the most abnormal features, provide a clear basis for risk tracing, and further improve the pertinence and efficiency of risk prediction.

[0089] In a possible implementation, S7 specifically includes:

[0090] S701: Calculate the Shapley value of each pipe gallery feature:

[0091]

[0092] in, represents the Shapley value of the jth pipeline corridor feature, N represents the feature set including all pipeline corridor features, represents the mean value of the corridor characteristics of the jth corridor, represents the feature set that does not include the corridor feature j, Indicates belonging to A subset of features, represents the number of features of S, ! represents the factorial, represents the feature subset including the corridor feature j, and They respectively represent the score index values ​​for different pipeline corridor characteristics.

[0093] S702: Outputting the pipeline corridor feature corresponding to the maximum Shapley value as the abnormal pipeline corridor feature:

[0094]

[0095] in, represents the corridor characteristic j when the Shapley value is the largest, Indicates the abnormal pipe gallery feature index.

[0096] It should be noted that by calculating the Shapley value of each pipeline corridor feature and outputting the most contributing abnormal feature, the comprehensive pipeline corridor dynamic risk prediction method can accurately quantify the contribution of each feature to the abnormality and accurately locate the key features that cause the abnormality. This method improves the interpretability and pertinence of anomaly detection, helps reduce the scope of false alarms and provides clear intervention directions, thereby greatly improving the accuracy and practicality of risk prediction, and providing data support for subsequent optimization and management.

[0097] S8: Output abnormal current integrated pipeline corridor monitoring data and abnormal pipeline corridor characteristics, and issue risk warnings.

[0098] In a possible implementation manner, after S8, the method further includes:

[0099] Update the minimum ellipsoid at a preset interval.

[0100] It can be understood that updating the minimum ellipsoid at preset intervals can enable the model to dynamically adapt to the long-term changes in the corridor monitoring data, ensure the accuracy and applicability of the prediction results, thereby improving the system's sensitivity and robustness to environmental changes, and effectively reducing misjudgments or missed judgments caused by data distribution offsets.

[0101] It should be noted that those skilled in the art can set the preset duration according to actual needs, and the present invention is not limited thereto.

[0102] In the actual application process, first, historical comprehensive pipe gallery monitoring data is collected, and multi-dimensional features such as temperature, humidity, and vibration are extracted to provide a data basis for analysis. Principal component analysis is used to reduce the dimension of historical data, extract eigenvalues ​​and eigenvectors, and capture the correlation between key features. The minimum ellipsoid model is constructed based on the eigenvalues ​​and eigenvectors, and the boundaries are dynamically adjusted in combination with the chi-square test and the law of large numbers to accurately describe the normal operation status of the pipe gallery. The model is sent to the edge to support local real-time anomaly detection. The pipe gallery data to be detected is collected in real time as the input of dynamic risk detection. The current monitoring data is uploaded to the edge, and the minimum ellipsoid model and the semi-axis length are combined to determine whether the data is abnormal, and potential risks are quickly identified. If an anomaly is detected, the Shapley value is used to calculate the contribution of the abnormal feature to accurately locate the problem feature. Finally, the abnormal data and features are output and an early warning is issued. Through this process, real-time, efficient, and accurate dynamic risk prediction is achieved.

[0103] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0104] (1) In the present invention, the historical integrated pipe corridor monitoring data is subjected to principal component analysis to determine the eigenvalues ​​and eigenvectors of the historical integrated pipe corridor monitoring data, the main axis direction and the length of the semi-axis in the main axis direction are determined according to the eigenvectors and eigenvalues, and the minimum ellipsoid describing the normal operation status of the integrated pipe corridor is established in combination with the chi-square test and the law of large numbers. The key features are extracted by principal component analysis, and the model is dynamically adjusted in combination with the chi-square test and the law of large numbers to fully capture the data distribution characteristics of normal pipe corridor data, thereby reversely improving the accuracy and adaptability of risk prediction, effectively reducing false positives and false negatives, adapting to changes in complex pipe corridor environments, and ensuring operational safety. Afterwards, the minimum ellipsoid and the length of the semi-axis in the main axis direction are used to judge whether the current integrated pipe corridor monitoring data is abnormal as a whole, i.e., associated data, rather than judging them separately. If the current integrated pipe corridor monitoring data is not located in the minimum ellipsoid, it is directly judged that it is abnormal. If it is located in the minimum ellipsoid, the semi-axis length in the main axis direction is used to further judge and verify whether it is abnormal. It can quickly process massive data with low latency and high accuracy in risk prediction. Finally, the Shapley value is used to accurately quantify the contribution of each feature to the anomaly, which can accurately locate the abnormal pipeline corridor characteristics, improve the pertinence and interpretability of risk prediction, and effectively reduce the scope of false alarms, providing a clear direction for subsequent risk intervention, and further enhancing the efficiency and accuracy of dynamic risk prediction of comprehensive pipeline corridors.

[0105] (2) In the present invention, an Internet of Things risk prediction platform including a data acquisition terminal, an edge terminal and a cloud terminal is also combined, which makes full use of the data local processing capability of the edge terminal to improve the real-time prediction, and uses the powerful data computing capability of the cloud terminal to accurately and quickly establish the minimum ellipsoid that describes the normal operating status of the integrated pipeline corridor, thereby further improving the risk prediction accuracy and real-time performance of the integrated pipeline corridor.

[0106] Reference Manual Attached Figure 3 , showing a structural schematic diagram of a dynamic risk prediction system for an integrated pipeline corridor based on the Internet of Things provided by the present invention.

[0107] The present invention also provides an Internet of Things-based integrated pipe gallery dynamic risk prediction system 20, which is applied to the above-mentioned Internet of Things-based integrated pipe gallery dynamic risk prediction method, comprising:

[0108] Processor 201.

[0109] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, a dynamic risk prediction method for an integrated pipe gallery based on the Internet of Things as in the method embodiment is implemented.

[0110] The Internet of Things-based integrated pipeline corridor dynamic risk prediction system 20 provided by the present invention can execute the above-mentioned Internet of Things-based integrated pipeline corridor dynamic risk prediction method and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0111] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0112] (1) In the present invention, the historical integrated pipe corridor monitoring data is subjected to principal component analysis to determine the eigenvalues ​​and eigenvectors of the historical integrated pipe corridor monitoring data, the main axis direction and the length of the semi-axis in the main axis direction are determined according to the eigenvectors and eigenvalues, and the minimum ellipsoid describing the normal operation status of the integrated pipe corridor is established in combination with the chi-square test and the law of large numbers. The key features are extracted by principal component analysis, and the model is dynamically adjusted in combination with the chi-square test and the law of large numbers to fully capture the data distribution characteristics of normal pipe corridor data, thereby reversely improving the accuracy and adaptability of risk prediction, effectively reducing false positives and false negatives, adapting to changes in complex pipe corridor environments, and ensuring operational safety. Afterwards, the minimum ellipsoid and the length of the semi-axis in the main axis direction are used to judge whether the current integrated pipe corridor monitoring data is abnormal as a whole, i.e., associated data, rather than judging them separately. If the current integrated pipe corridor monitoring data is not located in the minimum ellipsoid, it is directly judged that it is abnormal. If it is located in the minimum ellipsoid, the semi-axis length in the main axis direction is used to further judge and verify whether it is abnormal. It can quickly process massive data with low latency and high accuracy in risk prediction. Finally, the Shapley value is used to accurately quantify the contribution of each feature to the anomaly, which can accurately locate the abnormal pipeline corridor characteristics, improve the pertinence and interpretability of risk prediction, and effectively reduce the scope of false alarms, providing a clear direction for subsequent risk intervention, and further enhancing the efficiency and accuracy of dynamic risk prediction of comprehensive pipeline corridors.

[0113] (2) In the present invention, an Internet of Things risk prediction platform including a data acquisition terminal, an edge terminal and a cloud terminal is also combined, which makes full use of the data local processing capability of the edge terminal to improve the real-time prediction, and uses the powerful data computing capability of the cloud terminal to accurately and quickly establish the minimum ellipsoid that describes the normal operating status of the integrated pipeline corridor, thereby further improving the risk prediction accuracy and real-time performance of the integrated pipeline corridor.

[0114] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0115] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0116] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. 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 computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0117] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0118] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0119] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0122] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0125] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0126] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for dynamic risk prediction of an integrated pipeline corridor based on the Internet of Things as described in the method embodiment is implemented.

[0127] A computer-readable storage medium provided by the present invention can implement the steps and effects of the dynamic risk prediction method for an integrated pipeline corridor based on the Internet of Things in the above-mentioned method embodiment. To avoid repetition, the present invention will not go into details.

[0128] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0129] (1) In the present invention, the historical integrated pipe gallery monitoring data is subjected to principal component analysis to determine the eigenvalues ​​and eigenvectors of the historical integrated pipe gallery monitoring data, the main axis direction and the length of the semi-axis in the main axis direction are determined according to the eigenvectors and the eigenvalues, and the minimum ellipsoid describing the normal operation state of the integrated pipe gallery is established in combination with the chi-square test and the law of large numbers. The key features are extracted by principal component analysis, and the model is dynamically adjusted in combination with the chi-square test and the law of large numbers to fully capture the data distribution characteristics of normal pipe gallery data, thereby reversely improving the accuracy and adaptability of risk prediction, effectively reducing false positives and false negatives, adapting to changes in complex pipe gallery environments, and ensuring operational safety. Afterwards, the minimum ellipsoid and the length of the semi-axis in the main axis direction are used to judge whether the current integrated pipe gallery monitoring data is abnormal as a whole, i.e., associated data, rather than judging them separately. If the current integrated pipe gallery monitoring data is not located in the minimum ellipsoid, it is directly judged that it is abnormal. If it is located in the minimum ellipsoid, the semi-axis length in the main axis direction is used to further judge and verify whether it is abnormal. This can quickly process massive data, with low latency and high accuracy in risk prediction. Finally, the Shapley value is used to accurately quantify the contribution of each feature to the anomaly, which can accurately locate the abnormal pipeline corridor characteristics, improve the pertinence and interpretability of risk prediction, and effectively reduce the scope of false alarms, providing a clear direction for subsequent risk intervention, and further enhancing the efficiency and accuracy of dynamic risk prediction of comprehensive pipeline corridors.

[0130] (2) In the present invention, an Internet of Things risk prediction platform including a data acquisition terminal, an edge terminal and a cloud terminal is also combined, which makes full use of the data local processing capability of the edge terminal to improve the real-time prediction, and uses the powerful data computing capability of the cloud terminal to accurately and quickly establish the minimum ellipsoid that describes the normal operating status of the integrated pipeline corridor, thereby further improving the risk prediction accuracy and real-time performance of the integrated pipeline corridor.

[0131] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0132] There are a few points to note:

[0133] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention. Other structures may refer to the general design.

[0134] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0135] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0136] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A dynamic risk prediction method for an integrated pipe gallery based on the Internet of Things, characterized in that: A risk prediction platform applied to the integrated pipe gallery, the risk prediction platform comprising a data acquisition terminal, an edge terminal and a cloud end connected in sequence, the data acquisition terminal being connected to the cloud end; the method comprising: S1: Obtaining historical comprehensive pipeline corridor monitoring data including different pipeline corridor characteristics through the cloud; S2: performing principal component analysis on the historical integrated pipe gallery monitoring data to determine the eigenvalues ​​and eigenvectors of the historical integrated pipe gallery monitoring data; S3: determining the main axis direction and the semi-axis length of the main axis direction according to the eigenvector and the eigenvalue, and establishing a minimum ellipsoid describing the normal operation state of the integrated pipe gallery in combination with the chi-square test and the law of large numbers; S4: Sending the minimum ellipsoid to the edge end; S5: Collecting current integrated pipe gallery monitoring data through the data acquisition terminal; S6: Upload the current monitoring data of the integrated pipe gallery to the edge end, and determine whether the current monitoring data of the integrated pipe gallery is abnormal by combining the minimum ellipsoid and the semi-axis length in the main axis direction. If so, proceed to step S7, otherwise, return to step S5; S7: Determine the abnormal pipeline corridor characteristics in the abnormal current integrated pipeline corridor monitoring data through the Shapley value; S8: Output the abnormal current integrated pipeline corridor monitoring data and the abnormal pipeline corridor characteristics, and issue a risk warning.

2. According to the method for dynamic risk prediction of integrated pipe gallery based on Internet of Things in claim 1, it is characterized in that: The pipeline corridor characteristics include temperature, humidity, gas concentration, light intensity, pressure value, vibration, displacement, cable voltage and cable current.

3. According to the method for dynamic risk prediction of integrated pipe gallery based on Internet of Things in claim 1, it is characterized in that: After S1, it also includes: The historical integrated pipeline corridor monitoring data is preprocessed including data cleaning and data normalization.

4. The method for predicting dynamic risks of integrated pipe gallery based on the Internet of Things according to claim 1 is characterized in that: The S2 specifically includes: S201: Establishing a data matrix of the historical integrated pipe gallery monitoring data: ； Where X represents the data matrix, represents the j-th corridor characteristic value of the i-th sample data, , , n represents the total number of sample data, and d represents the total number of pipeline corridor features; S202: Solve the covariance matrix of the data matrix: ； in, represents the covariance matrix, x represents the element in the data matrix, It represents the mean value of the corridor characteristics, that is, the mean value of the column elements of the data matrix. The subscript T represents transposition. express The probability distribution of , W represents the diagonal weight matrix, represents the weight of the j-th corridor feature, diag represents the diagonal element, and log represents the logarithmic function; S203: Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalues ​​and the eigenvectors: ； in, represents the eigenvector matrix, represents the eigenvalue matrix, and Represents the eigenvector and eigenvalue of the j-th pipeline corridor feature in a one-to-one correspondence.

5. According to the method for dynamic risk prediction of integrated pipe gallery based on Internet of Things according to claim 4, it is characterized in that: The minimum ellipsoid is specifically: ； in, The mean value of the corridor characteristics is the mean value of the column elements of the data matrix, which is the center of the minimum ellipsoid. Represents the smallest ellipsoid The length of the semi-axis in the direction of the corresponding principal axis, R represents the maximum radius describing the boundary range of the minimum ellipsoid, represents the significance level, It means that the confidence level is 1- The chi-square distribution of Represents the sample data variance.

6. The method for predicting dynamic risks of integrated pipe gallery based on the Internet of Things according to claim 5 is characterized in that: The step S6 of judging whether the current integrated pipe gallery monitoring data is abnormal by using the minimum ellipsoid specifically includes: S601: Determine whether the current monitoring data of the integrated pipe gallery is located in the minimum ellipsoid, that is, whether it satisfies the following formula. If so, proceed to step S602; otherwise, proceed to step S605: ； in, Indicates the current monitoring data of the integrated pipeline corridor; S602: Calculate the projection values ​​of the current integrated pipe gallery monitoring data in each main axis direction of the minimum ellipsoid: ； in, Indicates the current monitoring data of the integrated pipeline corridor In the main axis direction The projection value of S603: Determine whether each projection value is less than the semi-axis length of the maximum principal axis direction of the minimum ellipsoid, that is, whether the following formula is satisfied. If so, proceed to step S604; otherwise, proceed to step S605: ； in, Indicates the semi-axis length of the maximum principal axis direction of the minimum drag sphere; S604: Output the current integrated pipe gallery monitoring data as normal data; S605: Output the current integrated pipeline corridor monitoring data as abnormal data.

7. The method for predicting dynamic risks of integrated pipe gallery based on the Internet of Things according to claim 5 is characterized in that: The S7 specifically includes: S701: Calculate the Shapley value of each pipe gallery feature: ； in, represents the Shapley value of the jth pipeline corridor feature, N represents the feature set including all pipeline corridor features, represents the mean value of the corridor characteristics of the jth corridor, represents the feature set that does not include the corridor feature j, Indicates belonging to A subset of features, represents the number of features of S, ! represents the factorial, represents the feature subset including the corridor feature j, and Respectively represent the score index values ​​for different pipe gallery characteristics; S702: Outputting the pipeline corridor feature corresponding to the maximum Shapley value as the abnormal pipeline corridor feature: ； in, represents the corridor characteristic j when the Shapley value is the largest, Indicates the abnormal pipe gallery feature index.

8. The method for predicting dynamic risks of integrated pipe gallery based on the Internet of Things according to claim 1 is characterized in that: After S8, the method further includes: The minimum ellipsoid is updated at preset time intervals.

9. A dynamic risk prediction system for integrated pipe gallery based on the Internet of Things, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for dynamic risk prediction of an integrated pipeline corridor based on the Internet of Things as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a dynamic risk prediction method for an integrated pipeline corridor based on the Internet of Things as described in any one of claims 1 to 8 is implemented.

Images