Pipeline support monitoring system, method, equipment, medium and product

Abstract

The invention relates to the technical field of intelligent monitoring, and discloses a pipeline support monitoring system, method and device, a medium and a product. The acquisition unit acquires real-time stress data of the stress sensor and temperature data of the temperature sensor, and constructs a support stress data chain; the processing unit splits the support stress data chain into an important influence data chain and an associated influence data chain; the classification unit constructs a same-type stress sequence to obtain a sub-support influence factor; obtaining a support influence factor set according to all the sub-support influence factors; and the judgment unit integrates the support influence factor set to obtain a final influence factor of the monitoring area, and judges whether to generate a support stress early warning for the monitoring area. According to the method, the stress sensor and the temperature sensor are combined, so that the limitation of a traditional pipeline monitoring method is solved, the real-time performance, the accuracy and the automation degree of pipeline monitoring are improved, and the workload of manual inspection is effectively reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent monitoring technology. Specifically, it relates to a pipeline support monitoring system, method, device, medium and product. Background Art

[0002] With the continuous advancement of the industrialization process, especially in fields such as oil, natural gas, and electricity, large pipeline systems bear huge pressure and temperature changes during transportation. As an important part of the pipeline system, the pipeline support structure plays a role in fixing and supporting the pipeline, ensuring the stability and safety of the pipeline. Pipeline support columns are deployed at key positions of the pipeline to bear factors such as the weight of the pipeline itself, the pressure caused by fluid flow, and the thermal expansion caused by temperature changes. The state of these support columns is directly related to the safe operation of the entire pipeline system.

[0003] Currently, in traditional pipeline support monitoring, it usually relies on manual inspections and regular physical checks, which require a large amount of manpower and time. Moreover, due to the influence of environmental factors, the difficulty of inspections increases, and continuous monitoring cannot be achieved. Summary of the Invention

[0004] In view of this, this application proposes a pipeline support monitoring system, method, device, medium and product, aiming to solve the problems of time-consuming and laborious manual detection and low reliability in current pipeline support monitoring.

[0005] In a first aspect, this application proposes a pipeline support monitoring system, including: a sensor module, including a stress sensor and a temperature sensor, the sensor module is deployed on the surface of the support column of the pipeline, each stress sensor is arranged in cooperation with a temperature sensor, and a number of stress sensors and temperature sensors are provided; an acquisition unit, configured to acquire the real-time stress data of the stress sensor and the temperature data of the temperature sensor, and construct the real-time stress data into a support stress data chain; a processing unit, configured to output the importance data of each real-time stress data in the support stress data chain based on an information importance model, and split the support stress data chain into an important influence data chain and an associated influence data chain according to the importance data; a classification unit, configured to classify the real-time stress data in the important influence data chain based on a clustering algorithm, construct a same-type stress sequence, and obtain a sub-support influence factor of the same-type stress sequence according to the same-type stress sequence and the corresponding temperature data; the classification unit is also configured to determine the sub-support influence factors corresponding to the remaining same-type stress sequences in the important influence data chain, and obtain a support influence factor set according to all sub-support influence factors; a judgment unit, configured to integrate the support influence factor set to obtain a final influence factor of the monitored area of the pipeline, and judge whether to generate a support stress warning for the monitored area according to the final influence factor.

[0006] Optionally, when the processing unit splits the support stress data chain into an important influence data chain and an associated influence data chain according to the importance data, it includes: obtaining a first initial data chain and a second initial data chain, where multiple data chain nodes and connection nodes are set on each initial data chain; generating a chain change mark for the real-time stress data greater than or equal to the importance data threshold on the support stress data chain; transferring all the real-time stress data carrying the chain change mark to the first initial data chain to obtain the important influence data chain; and transferring the remaining real-time stress data on the support stress data chain to the second initial data chain to obtain the associated influence data chain.

[0007] Optionally, the processing unit is further configured to: obtain historical stress data and construct a historical data set according to the historical stress data; sample the historical data set according to a preset ratio to obtain a training subset and a test subset; obtain a preselected neural network model, iteratively train the neural network model according to the training subset, evaluate the iteratively trained neural network model according to the test subset, and obtain an information importance model.

[0008] Optionally, the processing unit is further configured to: when the evaluation value of the current iteratively trained neural network model is less than the evaluation value of the previous iteratively trained neural network model, reduce the amplitude of the change of the neural network model in the gradient direction and continue the iterative training until a preset number of iterations is reached; the evaluation value is obtained by evaluating the iteratively trained neural network model according to the test subset; when the evaluation value of the current iteratively trained neural network model is greater than or equal to the evaluation value of the previous iteratively trained neural network model, stop the iterative training.

[0009] Optionally, when the classification unit classifies the real-time stress data in the important influence data chain based on a clustering algorithm and constructs a same-type stress sequence, it includes: obtaining the temperature data corresponding to the real-time stress data in the important influence data chain, constructing each real-time stress data and the corresponding temperature data into a set of feature data, and performing normalization processing on the feature data; integrating all the feature data into a feature data matrix, where the rows represent the sensor positions and the columns represent the corresponding feature data; calculating the Euclidean distance between every two data in the feature data matrix to generate a distance matrix; performing hierarchical clustering on the distance matrix using average linkage to obtain a classification result, and constructing a same-type stress sequence according to the classification result.

[0010] Optionally, when the classification unit obtains the sub-support influence factor of the same-type stress sequence according to the same-type stress sequence and the corresponding temperature data, it includes:

[0011]

[0012] Among them, Yz represents the sub - support influence factor, N represents the number of real - time stress data in the stress sequence of the same type, Ei represents the i - th real - time stress data in the stress sequence of the same type, Wi represents the i - th temperature data in the stress sequence of the same type, E0 represents the basic real - time stress data, and W0 represents the basic temperature data.

[0013] Optionally, when the classification unit obtains the support influence factor set according to all sub - support influence factors, it includes: determining the median and variance of all sub - support influence factors; extracting the sub - support influence factors greater than the median among all sub - support influence factors to construct a first data set; extracting the sub - support influence factors greater than the variance among all sub - support influence factors to construct a second data set; if there is an intersection between the first data set and the second data set, constructing the support influence factor set according to the intersection value; if there is no intersection between the first data set and the second data set, performing non - duplicate fusion on the first data set and the second data set to construct the support influence factor set, where non - duplicate fusion means retaining the non - duplicate sub - support influence factors in the first data set and the second data set, retaining one of the duplicate sub - support influence factors in the first data set and the second data set, and deleting the remaining duplicate sub - support influence factors.

[0014] Optionally, when the judgment unit integrates the support influence factor set to obtain the final influence factor of the monitored area of the pipeline, it includes: comparing the support influence factor set with historical judgment data, where the historical judgment data includes a historical support influence factor set and a historical final influence factor; when there is data in the historical judgment data with a similarity greater than the similarity threshold to the support influence factor set, taking the historical final influence factor corresponding to the historical support influence factor as the final influence factor; when the similarity between the historical support influence factor set in the historical judgment data and the support influence factor set is less than or equal to the similarity threshold, determining the final influence factor according to the support influence factor set.

[0015] Optionally, when the judgment unit determines the final influence factor according to the support influence factor set, it includes:

[0016]

[0017] Among them, Z represents the final influence factor, m represents the number of sub - support influence factors in the support influence factor set, Q j represents the weight corresponding to the j - th sub - support influence factor, Yz j represents the j - th sub - support influence factor, Yz min represents the minimum sub - support influence factor, Yz max is the maximum sub - support influence factor, is all the maximum value in.

[0018] Optionally, when the judgment unit determines whether to generate a support stress warning for the monitoring area based on the final influence factor, it includes: when the final influence factor is greater than the influence factor threshold, obtaining the influence factor overflow value, determining the warning level according to the influence factor overflow value, where the influence factor overflow value is the difference between the final influence factor and the influence factor threshold, and the warning level is directly proportional to the influence factor overflow value; when the final influence factor is less than or equal to the influence factor threshold, no support stress warning is generated for the monitoring area.

[0019] Optionally, the sensor module is a wireless passive sensor.

[0020] In a second aspect, a pipeline support monitoring method is provided, which is applied to the pipeline support monitoring system according to any one of the first aspect, and includes: collecting the real-time stress data of the stress sensor and the temperature data of the temperature sensor, and constructing the real-time stress data into a support stress data chain; the stress sensor and the temperature sensor are deployed on the surface of the support column of the pipeline, each stress sensor is arranged in cooperation with the temperature sensor, and several stress sensors and temperature sensors are provided; outputting the importance data of each real-time stress data in the support stress data chain based on the information importance model, and splitting the support stress data chain into an important influence data chain and an associated influence data chain according to the importance data; classifying the real-time stress data in the important influence data chain based on the clustering algorithm, constructing the same-type stress sequence, and obtaining the sub-support influence factor of the same-type stress sequence according to the same-type stress sequence and the corresponding temperature data; determining the sub-support influence factors corresponding to the remaining same-type stress sequences in the important influence data chain, and obtaining a support influence factor set according to all the sub-support influence factors; integrating the support influence factor set to obtain the final influence factor of the monitoring area of the pipeline, and determining whether to generate a support stress warning for the monitoring area according to the final influence factor.

[0021] In a third aspect, a pipeline support monitoring device is provided, including a memory and a processor; the memory is used to store computer execution instructions, and the processor is connected to the memory through a bus; when the pipeline support monitoring device runs, the processor executes the computer execution instructions stored in the memory, so that the pipeline support monitoring device executes the pipeline support monitoring method described in the second aspect.

[0022] The pipeline support monitoring device can be a network device or a part of the device in the network device, such as a chip system in the network device. The chip system is used to support the network device to implement the functions involved in the first aspect and any one of its possible implementation manners. For example, obtaining, determining, and sending the data and / or information involved in the pipeline support monitoring method described above. The chip system includes a chip and may also include other discrete devices or circuit structures.

[0023] Fourthly, a computer-readable storage medium is provided. The computer-readable storage medium includes computer-executable instructions, which, when running on a computer, cause the computer to execute the pipeline support monitoring method described in the second aspect.

[0024] Fifthly, a computer program product is further provided. The computer program product includes computer instructions, which, when running on a pipeline support monitoring device, cause the pipeline support monitoring device to execute the pipeline support monitoring method described in the second aspect above.

[0025] It should be noted that the above computer instructions can be stored in whole or in part on a computer-readable storage medium. Among them, the computer-readable storage medium can be packaged together with the processor of the pipeline support monitoring device, or can be separately packaged from the processor of the pipeline support monitoring device. The embodiments of the present application do not make any limitations in this regard.

[0026] The descriptions of the second aspect, the third aspect, the fourth aspect and the fifth aspect in the present application can refer to the detailed description of the first aspect.

[0027] In the embodiments of the present application, the name of the above pipeline support monitoring device does not limit the device or function module itself. In actual implementation, these devices or function modules can appear under other names. For example, the receiving unit can also be called a receiving module, a receiver, etc. As long as the functions of each device or function module are similar to those of the present application and fall within the scope of the claims of the present application and their equivalent technologies.

[0028] The embodiments of the present application solve the limitations of traditional pipeline monitoring methods by combining stress sensors and temperature sensors. By collecting real-time stress data and constructing a support stress data chain, and intelligently screening the data in combination with the information importance model, the data is automatically divided into important impact data chains and associated impact data chains, improving the efficiency and accuracy of data processing. Classify important data through a clustering algorithm and combine temperature data to calculate the sub-support impact factor, and obtain a set of support impact factors by integrating all impact factors, realizing a comprehensive analysis of the monitoring area. Determine whether to issue a support stress warning according to the final impact factor, realizing a dynamic and intelligent warning mechanism, identifying potential pipeline support problems in advance, improving the real-time performance, accuracy and automation of pipeline monitoring, and effectively reducing the workload of manual inspection. Description of the Drawings

[0029] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0030] Figure 1 This is a schematic structural diagram of a pipeline support monitoring system provided by an embodiment of the present application;

[0031] Figure 2 This is a schematic flowchart of a pipeline support monitoring method provided by an embodiment of the present application;

[0032] Figure 3 This is a schematic structural diagram of a pipeline support monitoring device provided by an embodiment of the present application. Detailed implementation manners

[0033] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. Hereinafter, the present application will be described in detail with reference to the drawings and in conjunction with the embodiments.

[0034] In some embodiments of the present application, referring to Figure 1 as shown, a pipeline support monitoring system includes: a sensor module, an acquisition unit, a processing unit, a classification unit, and a judgment unit, wherein,

[0035] The sensor module includes a stress sensor and a temperature sensor. The sensor module is deployed on the surface of the support column of the pipeline. Each stress sensor is arranged in cooperation with a temperature sensor, and a plurality of stress sensors and temperature sensors are provided.

[0036] Optionally, the sensor module is a wireless passive sensor, that is, both the stress sensor and the temperature sensor are wireless passive sensors. In this way, by using the wireless passive sensor, the high maintenance cost of the active sensor that requires regular battery replacement is avoided, and the state of the support column can be continuously monitored at the key positions of the pipeline.

[0037] The acquisition unit is configured to acquire the real-time stress data of the stress sensor and the temperature data of the temperature sensor, and construct the real-time stress data into a support stress data chain.

[0038] The processing unit is configured to output the importance data of each real-time stress data in the support stress data chain based on the information importance model, and split the support stress data chain into an important influence data chain and an associated influence data chain according to the importance data.

[0039] The classification unit is configured to classify the real-time stress data in the important impact data chain based on a clustering algorithm, construct stress number sequences of the same type, and obtain the sub-support impact factors of the stress number sequences of the same type according to the stress number sequences of the same type and the corresponding temperature data. The classification unit is also configured to determine the sub-support impact factors corresponding to the remaining stress number sequences of the same type in the important impact data chain, and obtain a set of support impact factors according to all the sub-support impact factors.

[0040] The judgment unit is configured to integrate the set of support impact factors to obtain the final impact factor of the monitored area of the pipeline, and determine whether to generate a support stress warning for the monitored area according to the final impact factor.

[0041] Specifically, the sensor module is deployed on the surface of the pipeline support column and includes a stress sensor and a temperature sensor. Each stress sensor and temperature sensor are arranged in cooperation to simultaneously monitor the stress and temperature changes of the support column. The sensor uses wireless passive technology and does not require a battery or an external power source. When the pressure or temperature changes, the sensor material deforms, thereby changing the electromagnetic characteristics (such as impedance, reflectivity, etc.) of the sensor, which is convenient for long-term use and has low maintenance costs. The acquisition unit is responsible for real-time acquisition of the data of the stress sensor and the temperature sensor, and forms a support stress data chain with all the real-time stress data. This data chain contains the stress data of each monitoring point within a certain period of time, reflecting the dynamic load changes of the pipeline support column during actual operation. The processing unit, based on the information importance model, evaluates the importance of each real-time data in the support stress data chain and outputs the "importance data" of each data point. According to the importance data, the support stress data chain is split into two categories: important impact data chain: representing data that has a greater impact on the health of the pipeline support structure. Associated impact data chain: representing data that has a relatively small relationship with the health status of the support column but may have an indirect impact. The classification unit uses a clustering algorithm to classify the real-time stress data in the important impact data chain. By using the clustering method, the stress data of the same type are grouped into one category, and combined with the corresponding temperature information of these data, the sub-support impact factors of each category of stress data are calculated, that is, the degree of influence of this category of data on the health of the support column. For the remaining stress number sequences of the same type in the important impact data chain, the classification unit will further analyze and determine their corresponding sub-support impact factors. Then, all the sub-support impact factors are integrated to form a set of support impact factors. The judgment unit integrates the set of support impact factors to obtain the final impact factor of the entire monitored area. The final impact factor reflects the current health status of the pipeline support column. According to the evaluation result of the final impact factor, the judgment unit decides whether to generate a support stress warning for the monitored area. If the final impact factor exceeds a certain preset threshold, a support stress warning is issued to prompt relevant personnel to conduct inspections and maintenance.

[0042] It can be understood that through the application of wireless passive sensors, the dependence on batteries of traditional active sensors is avoided, the operating cost of the system is reduced, and the need for regular maintenance and battery replacement is decreased. Through the information importance model and clustering algorithm, massive real-time data is intelligently screened and classified to automatically distinguish the data that is most important for pipeline support safety, avoiding the errors and cumbersome processes of manual operations and improving the accuracy and efficiency of data processing. Monitor data is obtained and processed in real time, and dynamic support stress warnings are generated based on the final support impact factors to timely remind relevant personnel to conduct inspections and maintenance. Compared with traditional static threshold-based monitoring systems, it has flexibility and adaptability and can adjust the warning strategy in real time according to changes in the environment and data. By comprehensively analyzing the stress and temperature data of the support columns, potential risk points can be identified in a timely manner, problems that may lead to pipeline support failure can be discovered in advance, and pipeline accidents can be prevented, thereby improving the safety and stability of the entire pipeline system.

[0043] In some embodiments of the present application, when the processing unit splits the support stress data chain into an important impact data chain and an associated impact data chain according to the importance data, it includes: obtaining a first initial data chain and a second initial data chain, where multiple data chain nodes and connection nodes are set on each initial data chain. Generating a chain-changing mark for the real-time stress data on the support stress data chain that is greater than or equal to the importance data threshold. Transferring all the real-time stress data carrying the chain-changing mark to the first initial data chain to obtain the important impact data chain. Transferring the remaining real-time stress data on the support stress data chain to the second initial data chain to obtain the associated impact data chain.

[0044] It can be understood that the first initial data chain and the second initial data chain are initially blank data chains. Each initial data chain contains multiple data nodes and connection nodes. The data nodes are blank data, and the connection nodes are used to organize and connect these data nodes. The importance data threshold is a preset value used to evaluate the importance of each data node. The importance data threshold can be set according to the actual required sensitivity. If the importance data of a certain data point is greater than or equal to this threshold, then this data point is considered a key data that has a significant impact on the health of the pipeline support. When the importance data of the real-time stress data exceeds the set threshold, a chain-changing mark is generated for this data point, indicating that this data has a higher priority during the monitoring process. The generation of the chain-changing mark is to distinguish the data that has a greater impact on the health of the pipeline support from other data. All the stress data carrying the chain-changing mark will be transferred to the first initial data chain to form the important impact data chain. These data are considered important indicators of the pipeline support state and directly affect the health and safety of the support columns. The remaining stress data is transferred to the second initial data chain to form the associated impact data chain. These data may have an indirect or minor impact on the state of the support columns but still play a certain role in the overall monitoring results.

[0045] It is understandable that a large amount of data is classified through the importance data threshold and the link replacement mark, enabling the processing unit to focus on the most critical stress data and reducing unnecessary data redundancy. The important impact data chain centrally reflects the key health status of the pipeline support columns, thereby improving the system processing efficiency and the accuracy of data analysis. By setting the importance data threshold, intelligent screening is performed according to the actual impact of the real-time stress data. This ensures that the data with the most significant impact on the pipeline support columns is processed first, avoiding the errors caused by static thresholds or manual screening. By classifying the data into two categories, the most important stress data is processed preferentially, while the processing frequency of relatively less important data can be delayed or reduced. This effectively reduces data redundancy and also improves the system response speed.

[0046] In some embodiments of the present application, the processing unit is further configured to:

[0047] Obtain historical stress data and construct a historical data set based on the historical stress data. Sample the historical data set according to a preset ratio to obtain a training subset and a test subset. Obtain a pre-selected neural network model, and perform iterative training on the neural network model according to the training subset, evaluate the iteratively trained neural network model according to the test subset, and obtain an information importance model.

[0048] In some embodiments of the present application, the processing unit is further configured to:

[0049] Judge whether to stop iterative training according to the evaluation value. The evaluation value is obtained by evaluating the iteratively trained neural network model according to the test subset.

[0050] When the evaluation value of the current iteratively trained neural network model is less than the evaluation value of the previous iteratively trained neural network model, reduce the amplitude of the change of the neural network model in the gradient direction and continue iterative training until the preset number of iterations is reached.

[0051] When the evaluation value of the current iteratively trained neural network model is greater than or equal to the evaluation value of the previous iteratively trained neural network model, stop iterative training.

[0052] Specifically, the processing unit first obtains historical stress data and constructs a historical data set based on this data. The historical stress data reflects the stress of the pipeline support column over a past period of time, and these stress data are attached with historical importance evaluation data, which can be obtained based on historical manual evaluation and provide sufficient reference data for the training of the neural network model. The processing unit samples the historical data set into a training subset and a test subset according to a preset ratio. The training subset is used to train the neural network model, and the test subset is used to verify the effect and generalization ability of the model. The processing unit obtains a pre-selected neural network model and iteratively trains the model according to the training subset. During the training process, the model continuously adjusts its parameters (such as weights and biases) to reduce the prediction error and thus learn the patterns in the data. The trained neural network model is evaluated based on the test subset, and the performance of the model is judged by calculating evaluation values (such as loss function values or accuracies, etc.) to ensure the prediction ability of the model on new data. The processing unit decides whether to continue training based on the evaluation value. When the evaluation value of the neural network model after the current iterative training is lower than that after the previous iteration, it indicates that overfitting or slow learning progress has occurred in the current model training. The amplitude of the change in the gradient direction of the neural network model is reduced, and iterative training is continued until the preset number of iterations is reached. If the evaluation value after the current iterative training is better than the previous one, the training is stopped to ensure that the training process is not affected by ineffective iterations.

[0053] It can be understood that through neural network training, key patterns in the stress data are learned and automatically identified based on the historical stress data. The data-driven approach can dynamically adapt to different pipeline support environments, avoiding the limitations of manually setting thresholds and rules and improving the accuracy of importance evaluation. Based on the trained neural network model, the processing unit can accurately evaluate the importance of real-time stress data, thereby effectively classifying the data according to the degree of influence. This classification process provides accurate basic data for subsequent calculation of support influence factors and generation of early warnings, ensuring the accuracy and reliability of the monitoring results. Through the automated training and adjustment process, the dependence on manually set parameters is reduced, the automation level of the monitoring process is improved, and the risk of human errors is reduced.

[0054] In some embodiments of the present application, the classification unit classifies the real-time stress data in the important influence data chain based on a clustering algorithm. When constructing the stress number sequence of the same type, it includes:

[0055] Obtain the temperature data corresponding to the real-time stress data in the important influence data chain, construct each real-time stress data and the corresponding temperature data into a set of feature data, and perform normalization processing on the feature data.

[0056] Integrate all feature data into a feature data matrix, where rows represent sensor positions and columns represent corresponding feature data.

[0057] Calculate the Euclidean distance between every two data in the feature data matrix to generate a distance matrix.

[0058] Perform hierarchical clustering on the distance matrix using average linkage to obtain a classification result, and construct a same-type stress sequence based on the classification result.

[0059] Specifically, obtain the temperature data corresponding to the real-time stress data in the important influence data chain: the classification unit will obtain the temperature data associated with each real-time stress data. For each real-time stress data, combine its corresponding temperature data and construct it into a set of feature data. Each set of feature data usually contains two main parameters, namely the stress value and the temperature value. Since the dimensions and ranges of stress and temperature vary greatly, in order to make the contributions of the two to the clustering algorithm equivalent, normalization processing will convert the data into a standard range (for example, the interval from 0 to 1), eliminate the influence of different dimensions, and enable the clustering algorithm to be more accurate during processing. All processed feature data will be integrated into a feature data matrix. The rows of this matrix represent sensor positions, and each row corresponds to the feature data collected at a specific sensor position; the columns represent feature data, that is, the stress and temperature data at each position. The feature data matrix will be used as the input data for the clustering algorithm to help the classification unit classify sensor positions according to the similarity of stress and temperature. The Euclidean distance is a method used to measure the similarity between two data points. The classification unit calculates the Euclidean distance between every two data in the feature data matrix. The calculated Euclidean distance matrix will represent the similarity degree between feature data points. The smaller the distance, the more similar the data. After obtaining the Euclidean distance matrix, perform hierarchical clustering on the data using average linkage (Mean Linkage). Determine the merging or splitting method by calculating the average distance between every two clusters. Each data point is initially regarded as a separate cluster. According to the distance matrix, select the two closest clusters to merge. The "mean" distance between every two clusters is used in the merging process, that is, calculate the average distance between all data points between them. The hierarchical clustering result will classify the stress data and temperature data according to similarity, obtaining several same-type stress sequences. Based on the clustering result, the classification unit will organize the stress data belonging to the same class into a same-type stress sequence. These sequences contain sensor data that are similar in terms of stress and temperature characteristics and are used for further analysis and influence factor calculation.

[0060] It can be understood that by combining the clustering algorithm and the Euclidean distance, the stress and temperature data are classified according to similarity, and a meaningful stress sequence of the same type is constructed. Compared with only considering the stress data, it can more comprehensively reflect the state of the pipeline support column. By combining hierarchical clustering and mean linkage, it can flexibly cope with the dynamic changes of the pipeline support column under different temperature and pressure conditions. The stress sequence of the same type obtained after classification provides high-quality input data for the subsequent calculation of the support influence factor.

[0061] In some embodiments of the present application, when the classification unit obtains the sub-support influence factor of the stress sequence of the same type according to the stress sequence of the same type and the corresponding temperature data, it includes:

[0062]

[0063] Wherein, Yz represents the sub-support influence factor, N represents the number of real-time stress data in the stress sequence of the same type, E i represents the i-th real-time stress data in the stress sequence of the same type, Wi represents the i-th temperature data in the stress sequence of the same type, E0 represents the basic real-time stress data, and W0 represents the basic temperature data.

[0064] In some embodiments of the present application, when the classification unit obtains the support influence factor set according to all the sub-support influence factors, it includes:

[0065] Determine the median and variance of all the sub-support influence factors.

[0066] Extract the sub-support influence factors greater than the median among all the sub-support influence factors to construct the first data set.

[0067] Extract the sub-support influence factors greater than the variance among all the sub-support influence factors to construct the second data set.

[0068] Judge whether there is an intersection between the first data set and the second data set.

[0069] If so, that is, there is an intersection between the first data set and the second data set, then construct the support influence factor set according to the intersection value.

[0070] If not, that is, there is no intersection between the first data set and the second data set, then fuse the first data set and the second data set without repetition to construct the support influence factor set, where the non-repetitive fusion is to retain the non-repetitive sub-support influence factors in the first data set and the second data set, retain one of the repetitive sub-support influence factors in the first data set and the second data set, and delete the remaining repetitive sub-support influence factors.

[0071] It is understandable that by combining stress and temperature data to calculate the sub - support influence factor, the stress state of the pipeline support column is evaluated. Statistical methods (median and variance) are used to screen and analyze the sub - support influence factor, and the most representative influence factors are extracted to help judge the health status of the pipeline support column. By judging the intersection of the data sets and performing non - repetitive fusion, the interference of duplicate information is effectively avoided, making the final set of support influence factors more concise. By screening key influence factors, more accurate data support is provided for subsequent support stress early warning.

[0072] In some embodiments of the present application, when the judgment unit integrates the set of support influence factors to obtain the final influence factor of the monitored area of the pipeline, it includes: comparing the set of support influence factors with historical judgment data, where the historical judgment data includes a historical set of support influence factors and a historical final influence factor.

[0073] When there is data in the historical judgment data whose similarity to the set of support influence factors is greater than the similarity threshold, the historical final influence factor corresponding to the historical support influence factor is used as the final influence factor. When the similarity between the historical set of support influence factors in the historical judgment data and the set of support influence factors is less than or equal to the similarity threshold, the final influence factor is determined according to the set of support influence factors.

[0074] In some embodiments of the present application, when the judgment unit determines the final influence factor according to the set of support influence factors, it includes:

[0075]

[0076] Where Z represents the final influence factor, m represents the number of sub - support influence factors in the set of support influence factors, Q j represents the weight corresponding to the j - th sub - support influence factor, Yz j represents the j - th sub - support influence factor, Yz min represents the minimum sub - support influence factor, Yz max is the maximum sub - support influence factor, for all is the maximum value among them.

[0077] It is understandable that through similarity comparison, the state of the current monitored area is quickly judged based on historical data, reducing the possibility of misjudgment and improving the accuracy of the early warning system. When the historical data is similar to the current data, the historical result is directly cited, reducing the calculation amount and processing time, reducing the calculation burden, and avoiding a complex calculation process that completely depends on the current data. For changes in certain positions or under specific conditions, a more accurate health assessment is provided by calculating the final influence factor.

[0078] In some embodiments of the present application, when the determination unit determines whether to generate a support stress warning for the monitoring area based on the final influence factor, it includes: the determination unit compares the final influence factor with the influence factor threshold, and determines whether to generate a support stress warning for the monitoring area according to the comparison result.

[0079] Specifically, when the final influence factor is greater than the influence factor threshold, obtain the influence factor overflow value, determine the warning level according to the influence factor overflow value, the influence factor overflow value is the difference between the final influence factor and the influence factor threshold, and the warning level is directly proportional to the influence factor overflow value. When the final influence factor is less than or equal to the influence factor threshold, it is determined that no support stress warning is generated for the monitoring area.

[0080] It can be understood that the determination unit determines the warning level of the monitoring area according to the influence factor overflow value. Specifically, the warning level is directly proportional to the overflow value, that is, the larger the influence factor overflow value, the higher the warning level. For example, a standardized level system is set: when the overflow value is small (for example, close to the threshold), a level 1 warning is output to indicate a potential minor problem; while when the overflow value is large, a level 3 warning is output, indicating that immediate repair or inspection is required. By comparing the final influence factor with the influence factor threshold and combining the calculation of the influence factor overflow value, it is ensured that the warning decision is more accurate and reliable. When the state of the pipeline support column deviates slightly, unnecessary intervention can be reduced; while when the abnormal situation is serious, a high-level warning is automatically triggered to avoid potential major safety hazards.

[0081] In the above embodiments, by combining the stress sensor and the temperature sensor, the limitations of the traditional pipeline monitoring method are solved. Using wireless passive sensors, the high maintenance cost of active sensors that need to replace batteries regularly is avoided, and the state of the support column can be continuously monitored at key positions of the pipeline. By collecting real-time stress data and constructing a support stress data chain, and intelligently screening the data in combination with the information importance model, the data is automatically divided into important influence data chains and associated influence data chains, improving the efficiency and accuracy of data processing. By classifying important data through a clustering algorithm and combining temperature data, calculating the sub-support influence factor, and comprehensively obtaining the support influence factor set for all influence factors, a comprehensive analysis of the monitoring area is realized. Determining whether to issue a support stress warning according to the final influence factor realizes a dynamic and intelligent warning mechanism, pre-identifies potential pipeline support problems, improves the real-time performance, accuracy and automation of pipeline monitoring, and effectively reduces the workload of manual inspection.

[0082] In some embodiments, as Figure 2 shown, the embodiments of the present application also provide a pipeline support monitoring method, which is applied to the pipeline support monitoring system in the above Figure 1 , and includes:

[0083] S201. Collect the real-time stress data of the stress sensors and the temperature data of the temperature sensors, and construct the real-time stress data into a support stress data chain; the stress sensors and the temperature sensors are deployed on the surface of the support columns of the pipeline, each stress sensor is arranged in cooperation with a temperature sensor, and a plurality of stress sensors and temperature sensors are provided.

[0084] S202. Output the importance data of each real-time stress data in the support stress data chain based on the information importance model.

[0085] S203. Split the support stress data chain into an important influence data chain and an associated influence data chain according to the importance data.

[0086] S204. Classify the real-time stress data in the important influence data chain based on the clustering algorithm to construct a stress sequence of the same type.

[0087] S205. Obtain the sub-support influence factor of the stress sequence of the same type according to the stress sequence of the same type and the corresponding temperature data.

[0088] S206. Determine the sub-support influence factors corresponding to the remaining stress sequences of the same type in the important influence data chain, and obtain a support influence factor set according to all the sub-support influence factors.

[0089] S207. Integrate the support influence factor set to obtain the final influence factor of the monitored area of the pipeline, and determine whether to generate a support stress warning for the monitored area according to the final influence factor.

[0090] In some embodiments, when splitting the support stress data chain into an important influence data chain and an associated influence data chain according to the importance data, it includes:

[0091] Obtain a first initial data chain and a second initial data chain, wherein a plurality of data chain nodes and connection nodes are arranged on each initial data chain;

[0092] Generate a chain replacement mark for the real-time stress data on the support stress data chain that is greater than or equal to the importance data threshold;

[0093] Transfer all the real-time stress data with the chain replacement mark to the first initial data chain to obtain an important influence data chain;

[0094] Transfer the remaining real-time stress data on the support stress data chain to the second initial data chain to obtain an associated influence data chain.

[0095] In some embodiments, the above pipeline support monitoring method further includes:

[0096] Obtain historical stress data and construct a historical data set according to the historical stress data;

[0097] Sample the historical data set according to a preset ratio to obtain a training subset and a test subset;

[0098] Obtain a preselected neural network model, perform iterative training on the neural network model according to the training subset, evaluate the iteratively trained neural network model according to the test subset, and obtain an information importance model.

[0099] In some embodiments, the above pipeline support monitoring method further includes:

[0100] When the evaluation value of the neural network model after the current iterative training is less than the evaluation value of the neural network model after the previous iterative training, reduce the amplitude of the change of the neural network model in the gradient direction, and continue iterative training until a preset number of iterations is reached; the evaluation value is obtained by evaluating the iteratively trained neural network model according to the test subset;

[0101] If the evaluation value of the neural network model after the current iterative training is greater than or equal to the evaluation value of the neural network model after the previous iterative training, stop the iterative training.

[0102] In some embodiments, when classifying the real-time stress data in the important influence data chain based on the clustering algorithm and constructing the stress number sequence of the same type, it includes:

[0103] Obtain the temperature data corresponding to the real-time stress data in the important influence data chain, construct each real-time stress data and the corresponding temperature data into a set of feature data, and perform normalization processing on the feature data;

[0104] Integrate all the feature data into a feature data matrix, where the rows represent the sensor positions and the columns represent the corresponding feature data;

[0105] Calculate the Euclidean distance between every two data in the feature data matrix to generate a distance matrix;

[0106] Perform hierarchical clustering on the distance matrix using average linkage to obtain a classification result, and construct a stress number sequence of the same type according to the classification result.

[0107] In some embodiments, when obtaining the sub-support influence factor of the stress number sequence of the same type according to the stress number sequence of the same type and the corresponding temperature data, it includes:

[0108]

[0109] Wherein, Yz represents the sub - support influence factor, N represents the number of real - time stress data in the stress sequence of the same type, E i represents the i - th real - time stress data in the stress sequence of the same type, Wi represents the i - th temperature data in the stress sequence of the same type, E0 represents the basic real - time stress data, and W0 represents the basic temperature data.

[0110] In some embodiments, when obtaining the support influence factor set according to all sub - support influence factors, it includes:

[0111] Determine the median and variance of all sub - support influence factors;

[0112] Extract the sub - support influence factors greater than the median among all sub - support influence factors to construct a first data set;

[0113] Extract the sub - support influence factors greater than the variance among all sub - support influence factors to construct a second data set;

[0114] If there is an intersection between the first data set and the second data set, construct the support influence factor set according to the intersection value;

[0115] If there is no intersection between the first data set and the second data set, fuse the first data set and the second data set without repetition to construct the support influence factor set, where the non - repeated fusion means retaining the non - repeated sub - support influence factors in the first data set and the second data set, retaining one repeated sub - support influence factor in the first data set and the second data set, and deleting the remaining repeated sub - support influence factors.

[0116] In some embodiments, when integrating the support influence factor set to obtain the final influence factor of the monitored area of the pipeline, it includes:

[0117] Compare the support influence factor set with historical judgment data, where the historical judgment data includes a historical support influence factor set and a historical final influence factor;

[0118] When there is data in the historical judgment data whose similarity with the support influence factor set is greater than the similarity threshold, use the historical final influence factor corresponding to the historical support influence factor as the final influence factor;

[0119] When the similarity between the historical support influence factor set in the historical judgment data and the support influence factor set is less than or equal to the similarity threshold, determine the final influence factor according to the support influence factor set.

[0120] In some embodiments, when determining the final influence factor according to the support influence factor set, it includes:

[0121]

[0122] Wherein, Z represents the final influence factor, m represents the number of sub - support influence factors in the set of support influence factors, and Q j represents the weight corresponding to the j - th sub - support influence factor, and Yz j represents the j - th sub - support influence factor, and Yz min represents the minimum sub - support influence factor, and Yz max is the maximum sub - support influence factor, is for all the maximum value among them.

[0123] In some embodiments, when determining whether to generate a support stress warning for the monitoring area according to the final influence factor, it includes:

[0124] When the final influence factor is greater than the influence factor threshold, obtain the influence factor overflow value, and determine the warning level according to the influence factor overflow value. The influence factor overflow value is the difference between the final influence factor and the influence factor threshold, and the warning level is directly proportional to the influence factor overflow value;

[0125] When the final influence factor is less than or equal to the influence factor threshold, do not generate a support stress warning for the monitoring area.

[0126] In some embodiments, the above - mentioned sensor module is a wireless passive sensor.

[0127] The above mainly introduces the solution provided by the embodiments of the present application from the perspective of methods. To implement the above functions, it includes the corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0128] The embodiments of the present application can divide the function modules of the pipeline support monitoring device according to the above - mentioned method examples. For example, each function module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above - mentioned integrated module can be implemented in the form of hardware or in the form of a software function module. Optionally, the division of modules in the embodiments of the present application is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0129] As Figure 3 shown, it is a schematic structural diagram of a pipeline support monitoring device provided by an embodiment of the present application.Figure 3 The pipeline support monitoring device shown includes: a communication unit 301 and a processing unit 302;

[0130] The communication unit 301 is used to collect the real-time stress data of the stress sensors and the temperature data of the temperature sensors, and construct the support stress data chain with the real-time stress data; the stress sensors and the temperature sensors are deployed on the surface of the support columns of the pipeline, each stress sensor is arranged in cooperation with a temperature sensor, and a plurality of stress sensors and temperature sensors are provided;

[0131] The processing unit 302 is used to output the importance data of each real-time stress data in the support stress data chain based on the information importance model, and split the support stress data chain into an important influence data chain and an associated influence data chain according to the importance data;

[0132] The processing unit 302 is further used to classify the real-time stress data in the important influence data chain based on the clustering algorithm, construct the same-type stress number sequence, and obtain the sub-support influence factor of the same-type stress number sequence according to the same-type stress number sequence and the corresponding temperature data; determine the sub-support influence factor corresponding to the remaining same-type stress number sequences in the important influence data chain, and obtain the support influence factor set according to all the sub-support influence factors;

[0133] The processing unit 302 is further used to integrate the support influence factor set to obtain the final influence factor of the monitored area of the pipeline, and judge whether to generate a support stress warning for the monitored area according to the final influence factor.

[0134] In some embodiments, the processing unit 302 is specifically used for:

[0135] Obtain a first initial data chain and a second initial data chain, where a plurality of data chain nodes and connection nodes are arranged on each initial data chain;

[0136] Generate a chain-changing mark for the real-time stress data on the support stress data chain that is greater than or equal to the importance data threshold;

[0137] Transfer all the real-time stress data with the chain-changing mark to the first initial data chain to obtain the important influence data chain;

[0138] Transfer the remaining real-time stress data on the support stress data chain to the second initial data chain to obtain the associated influence data chain.

[0139] In some embodiments, the communication unit 301 is further used to obtain historical stress data and construct a historical data set according to the historical stress data;

[0140] The processing unit 302 is further used to sample the historical data set according to a preset ratio to obtain a training subset and a test subset;

[0141] The processing unit 302 is further configured to obtain a pre-selected neural network model, perform iterative training on the neural network model according to the training subset, evaluate the iteratively trained neural network model according to the test subset, and obtain an information importance model.

[0142] In some embodiments, the processing unit 302 is further configured to, when the evaluation value of the currently iteratively trained neural network model is less than the evaluation value of the neural network model after the previous iterative training, reduce the amplitude of the change of the neural network model in the gradient direction, and continue the iterative training until a preset number of iterations is reached; the evaluation value is obtained by evaluating the iteratively trained neural network model according to the test subset;

[0143] The processing unit 302 is further configured to stop the iterative training when the evaluation value of the currently iteratively trained neural network model is greater than or equal to the evaluation value of the neural network model after the previous iterative training.

[0144] In some embodiments, the processing unit 302 is specifically configured to:

[0145] Obtain the temperature data corresponding to the real-time stress data in the important influence data chain, construct each real-time stress data and the corresponding temperature data into a set of feature data, and perform normalization processing on the feature data;

[0146] Integrate all the feature data into a feature data matrix, where the rows represent the sensor positions and the columns represent the corresponding feature data;

[0147] Calculate the Euclidean distance between every two data in the feature data matrix to generate a distance matrix;

[0148] Perform hierarchical clustering on the distance matrix using average linkage to obtain a classification result, and construct a same-type stress sequence according to the classification result.

[0149] In some embodiments, the processing unit 302 is specifically configured to implement the following formula:

[0150]

[0151] Where Yz represents the sub-support influence factor, N represents the number of real-time stress data in the same-type stress sequence, Ei represents the i-th real-time stress data in the same-type stress sequence, Wi represents the i-th temperature data in the same-type stress sequence, E0 represents the basic real-time stress data, and W0 represents the basic temperature data.

[0152] In some embodiments, the processing unit 302 is specifically configured to:

[0153] Determine the median and variance of all sub-support influence factors;

[0154] Extract the sub - support impact factors greater than the median among all sub - support impact factors to construct the first data set;

[0155] Extract the sub - support impact factors greater than the variance among all sub - support impact factors to construct the second data set;

[0156] If there is an intersection between the first data set and the second data set, construct a support impact factor set according to the intersection values;

[0157] If there is no intersection between the first data set and the second data set, fuse the first data set and the second data set without duplication to construct a support impact factor set, where the non - duplicate fusion means retaining the non - duplicate sub - support impact factors in the first data set and the second data set, retaining one of the duplicate sub - support impact factors in the first data set and the second data set, and deleting the remaining duplicate sub - support impact factors.

[0158] In some embodiments, the processing unit 302 is specifically configured to:

[0159] Compare the support impact factor set with historical judgment data, where the historical judgment data includes a historical support impact factor set and a historical final impact factor;

[0160] When there is data in the historical judgment data whose similarity with the support impact factor set is greater than the similarity threshold, use the historical final impact factor corresponding to the historical support impact factor as the final impact factor;

[0161] When the similarity between the historical support impact factor set in the historical judgment data and the support impact factor set is less than or equal to the similarity threshold, determine the final impact factor according to the support impact factor set.

[0162] In some embodiments, the processing unit 302 is specifically configured to implement the following formula:

[0163]

[0164] Where Z represents the final impact factor, m represents the number of sub - support impact factors in the support impact factor set, Q j represents the weight corresponding to the j - th sub - support impact factor, Yz j represents the j - th sub - support impact factor, Yz min represents the minimum sub - support impact factor, Yz max is the maximum sub - support impact factor, for all is the maximum value among them.

[0165] In some embodiments, the processing unit 302 is specifically configured to:

[0166] When the final impact factor is greater than the impact factor threshold, obtain the impact factor overflow value, determine the warning level according to the impact factor overflow value. The impact factor overflow value is the difference between the final impact factor and the impact factor threshold, and the warning level is directly proportional to the impact factor overflow value;

[0167] When the final impact factor is less than or equal to the impact factor threshold, no support stress warning is generated for the monitoring area.

[0168] In some embodiments, the above sensor module is a wireless passive sensor.

[0169] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium includes computer-executable instructions. When the computer-executable instructions run on a computer, the computer is enabled to execute the pipeline support monitoring method provided in the above embodiments.

[0170] The embodiment of the present application also provides a computer program product. The computer program product can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement the pipeline support monitoring method provided in the above embodiments. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements do not cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

[0171] For the system provided in the above embodiments, only the above division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiments can be combined into one module, or further split into multiple sub-modules to complete all or part of the functions described above. For the names of the modules and steps involved in the embodiments of the present invention, they are only used to distinguish each module or step and are not regarded as an improper limitation of the present invention.

[0172] Those skilled in the art should be able to realize that the modules and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. The programs corresponding to the software modules and method steps can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field. To clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in the form of electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

Claims

1. A pipeline support monitoring system, characterized in that: include: A sensor module, including a stress sensor and a temperature sensor, wherein the sensor module is deployed on the surface of the support column of the pipeline, each of the stress sensors is arranged in cooperation with the temperature sensor, and a plurality of the stress sensors and the temperature sensors are arranged; A collection unit, configured to collect real-time stress data of the stress sensor and temperature data of the temperature sensor, and construct the real-time stress data into a supporting stress data chain; A processing unit is configured to output importance data of each of the real-time stress data in the supporting stress data chain based on an information importance model, and split the supporting stress data chain into an important influence data chain and an associated influence data chain according to the importance data; A classification unit is configured to classify the real-time stress data in the important influencing data chain based on a clustering algorithm, construct a stress series of the same type, and obtain a sub-support influencing factor of the stress series of the same type according to the stress series of the same type and the corresponding temperature data; the classification unit is also configured to determine the sub-support influencing factors corresponding to the remaining stress series of the same type in the important influencing data chain, and obtain a support influencing factor set according to all the sub-support influencing factors; The judgment unit is configured to integrate the support influence factor set to obtain a final influence factor of the monitoring area of ​​the pipeline, and judge whether to generate a support stress warning for the monitoring area according to the final influence factor.

2. The pipeline support monitoring system according to claim 1, characterized in that: When the processing unit splits the support stress data chain into an important influence data chain and an associated influence data chain according to the importance data, it includes: Acquire a first initial data link and a second initial data link, wherein each initial data link is provided with a plurality of data link nodes and connection nodes; Generating a chain change mark for the real-time stress data on the support stress data chain that is greater than or equal to the importance data threshold; Transferring all real-time stress data carrying a link change mark to the first initial data link to obtain the important impact data link; The remaining real-time stress data on the supporting stress data chain is transferred to the second initial data chain to obtain the associated impact data chain.

3. The pipeline support monitoring system according to claim 2, characterized in that: The processing unit is further configured to: Acquire historical stress data, and construct a historical data set based on the historical stress data; Sampling the historical data set according to a preset ratio to obtain a training subset and a test subset; A pre-selected neural network model is obtained, and the neural network model is iteratively trained according to the training subset, and the iteratively trained neural network model is evaluated according to the test subset to obtain the information importance model.

4. The pipeline support monitoring system according to claim 3, characterized in that: The processing unit is further configured to: When the evaluation value of the neural network model after the current iterative training is less than the evaluation value of the neural network model after the previous iterative training, the amplitude of the change of the neural network model in the gradient direction is reduced, and the iterative training is continued until a preset number of iterations is reached; the evaluation value is obtained by evaluating the neural network model after the iterative training according to the test subset; If the evaluation value of the neural network model after the current iterative training is greater than or equal to the evaluation value of the neural network model after the previous iterative training, the iterative training is stopped.

5. The pipeline support monitoring system according to claim 1, characterized in that: The classification unit classifies the real-time stress data in the important impact data chain based on a clustering algorithm, and constructs the same type of stress series, including: Acquire temperature data corresponding to the real-time stress data in the important influencing data chain, construct each of the real-time stress data and the corresponding temperature data into a set of characteristic data, and perform normalization processing on the characteristic data; Integrate all feature data into a feature data matrix, where rows represent sensor locations and columns represent corresponding feature data; Calculate the Euclidean distance between every two data in the feature data matrix to generate a distance matrix; The distance matrix is ​​hierarchically clustered using mean linking to obtain a classification result, and the stress series of the same type are constructed according to the classification result.

6. The pipeline support monitoring system according to claim 5, characterized in that: When the classification unit obtains the sub-support influence factor of the same type of stress series according to the same type of stress series and the corresponding temperature data, it includes: Among them, Yz represents the sub-support influence factor, N represents the number of real-time stress data in the same type of stress series, Ei represents the i-th real-time stress data in the same type of stress series, Wi represents the i-th temperature data in the same type of stress series, E0 represents the basic real-time stress data, and W0 represents the basic temperature data.

7. The pipeline support monitoring system according to claim 6, characterized in that: When the classification unit obtains a support impact factor set according to all the sub-support impact factors, it includes: Determine the median and variance of all said sub-support impact factors; Extracting the sub-support impact factors greater than the median from all the sub-support impact factors to construct a first data set; Extracting the sub-support influencing factors greater than the variance from all the sub-support influencing factors to construct a second data set; If there is an intersection between the first data set and the second data set, constructing the support impact factor set according to the intersection value; If there is no intersection between the first data set and the second data set, the first data set and the second data set are fused without duplication to construct the support influence factor set, wherein the non-duplication fusion is to retain the non-duplication sub-support influence factors in the first data set and the second data set, retain one duplication sub-support influence factor in the first data set and the second data set, and delete the remaining duplication sub-support influence factors.

8. The pipeline support monitoring system according to claim 7, characterized in that: When the judgment unit integrates the support influence factor set to obtain the final influence factor of the monitoring area of ​​the pipeline, it includes: Comparing the supporting impact factor set with historical judgment data, wherein the historical judgment data includes a historical supporting impact factor set and a historical final impact factor; When there is data in the historical judgment data whose similarity with the supporting influence factor set is greater than the similarity threshold, the historical final influence factor corresponding to the historical supporting influence factor is used as the final influence factor; When the similarity between the historical supporting influence factor set in the historical judgment data and the supporting influence factor set is less than or equal to the similarity threshold, the final influence factor is determined according to the supporting influence factor set.

9. The pipeline support monitoring system according to claim 8, characterized in that: When the judgment unit determines the final impact factor according to the supporting impact factor set, it includes: Among them, Z represents the final impact factor, m represents the number of sub-support impact factors in the supporting impact factor set, and Q j represents the weight corresponding to the j-th sub-support impact factor, Yz j represents the j-th sub-support impact factor, Yz min represents the minimum sub-support influence factor, Yz max is the maximum sub-support impact factor, For all The maximum value in .

10. The pipeline support monitoring system according to claim 9, characterized in that: When the judging unit judges whether to generate a support stress warning for the monitoring area according to the final influencing factor, it includes: When the final impact factor is greater than the impact factor threshold, an impact factor overflow value is obtained, and a warning level is determined according to the impact factor overflow value, wherein the impact factor overflow value is the difference between the final impact factor and the impact factor threshold, and the warning level is proportional to the impact factor overflow value; When the final impact factor is less than or equal to the impact factor threshold, no support stress warning is generated for the monitoring area.

11. The pipeline support monitoring system according to any one of claims 1 to 10, characterized in that: The sensor module is a wireless passive sensor.

12. A pipeline support monitoring method, characterized in that: The pipeline support monitoring system applied to any one of claims 1 to 11 comprises: Collecting real-time stress data of the stress sensor and temperature data of the temperature sensor, and constructing the real-time stress data into a supporting stress data chain; the stress sensor and the temperature sensor are deployed on the surface of the supporting column of the pipeline, each of the stress sensor and the temperature sensor are arranged in cooperation, and a plurality of the stress sensors and the temperature sensors are arranged; Outputting importance data of each of the real-time stress data in the supporting stress data chain based on the information importance model, and splitting the supporting stress data chain into an important influence data chain and an associated influence data chain according to the importance data; Based on the clustering algorithm, the real-time stress data in the important influencing data chain is classified, and the same type of stress series is constructed, and the sub-support influencing factors of the same type of stress series are obtained according to the same type of stress series and the corresponding temperature data; the sub-support influencing factors corresponding to the remaining same type of stress series in the important influencing data chain are determined, and the support influencing factor set is obtained according to all the sub-support influencing factors; The support influence factor set is integrated to obtain a final influence factor of the monitoring area of ​​the pipeline, and whether to generate a support stress warning for the monitoring area is determined according to the final influence factor.

13. A pipeline support monitoring device, characterized in that: include: A processor and a memory; wherein the memory is used to store one or more programs, and the one or more programs include computer execution instructions. When the device is running, the processor executes the computer execution instructions stored in the memory to enable the pipeline support monitoring device to perform the pipeline support monitoring method as described in claim 12.

14. A computer-readable storage medium, characterized in that: When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of a pipeline support monitoring device, the pipeline support monitoring device can perform the pipeline support monitoring method according to claim 12 .

15. A computer program product, characterized in that The computer program product comprises: a computer program or instructions, which, when executed on a computer, enable the computer to execute the pipeline support monitoring method according to claim 12 .

Images