Pipeline coating aging monitoring system and method

Abstract

The invention relates to a pipeline monitoring technology, and discloses a pipeline coating aging monitoring system and method. The system is characterized in that an acquisition module acquires aging data of a pipeline monitoring point, and a judgment module compares a target signal value with preset reflected wave intensity and preset reflected wave delay to determine whether coating aging occurs at the pipeline monitoring point; the processing module determines an initial coating depth value according to the target signal value when coating aging occurs at the pipeline monitoring point, and determines a pipeline coating humidity value according to the target humidity value, the target temperature value and multiple groups of historical data; and the prediction module determines a plurality of coating depth prediction values of the pipeline monitoring point at different times, and determines a pipeline coating aging monitoring result according to the initial coating depth value and the plurality of coating depth prediction values. According to the invention, through comprehensive analysis of data, the system has a good monitoring characteristic.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline monitoring, and more particularly, to a pipeline coating aging monitoring system and method. Background Art

[0002] With the continuous advancement of industrialization and urbanization, during the transportation of oil and gas, the safety of pipelines directly affects energy supply and environmental protection. The aging of pipeline coatings is one of the main reasons for pipeline damage and corrosion. Therefore, real-time monitoring of the aging state of pipeline coatings is of great significance for extending the service life of pipelines and ensuring the safe operation of pipelines.

[0003] However, the existing pipeline coating aging monitoring technologies have limitations such as single data, insufficient monitoring accuracy, and lack of comprehensive analysis. For example, the coating aging monitoring only analyzes one of the data of coating humidity or temperature, and cannot comprehensively reflect the whole process of coating aging. Coating aging is a complex process with multiple factors and dimensions. Single data cannot accurately evaluate the health state and aging trend of the coating, which easily leads to misjudgment and cannot achieve comprehensive analysis between different parameters. Moreover, traditional monitoring mostly relies on manual detection or data from wired sensors. When the cables of wired sensors are affected by signal interference and environmental factor changes, it will affect the accuracy of monitoring data and lead to the inability to accurately reflect the aging situation of pipeline coatings. Summary of the Invention

[0004] In view of this, the present invention proposes a pipeline coating aging monitoring system and method, aiming to solve the problems of inability to achieve comprehensive analysis between different parameters and inability to accurately reflect the aging situation of pipeline coatings.

[0005] In a first aspect, a pipeline coating aging monitoring system proposed by the present invention includes:

[0006] An acquisition module, a judgment module, a processing module, and a prediction module;

[0007] The acquisition module is configured to acquire aging data of pipeline monitoring points, and the aging data includes a target humidity value, a target temperature value, and a target signal value;

[0008] The judgment module is configured to compare the target signal value with a preset reflection wave intensity and a preset reflection wave delay respectively to determine whether coating aging occurs at the pipeline monitoring point;

[0009] The processing module is configured to determine an initial coating depth value according to a target signal value when coating aging occurs at a pipeline monitoring point, determine a humidity adjustment factor according to a target humidity value, a target temperature value, and multiple sets of historical data, and determine a pipeline coating humidity value according to the target humidity value and the humidity adjustment factor; each set of historical data includes a corresponding historical target humidity value, a historical target temperature value, and a historical humidity adjustment factor.

[0010] The prediction module is configured to determine multiple coating depth prediction values at different times of the pipeline monitoring point according to the pipeline coating humidity value, historical pipeline coating humidity value data, target temperature value, historical target temperature value data, initial coating depth value, and historical initial coating depth value data, and determine a pipeline coating aging monitoring result according to the initial coating depth value and the multiple coating depth prediction values; the pipeline coating aging monitoring result is used to indicate the change trend of the initial coating depth value and the multiple coating depth prediction values over time.

[0011] Optionally, the acquisition module includes a time unit and a sensor installed at the pipeline monitoring point; the sensor is a wireless passive sensor; the time unit is used to set the acquisition frequency of the sensor; the sensor includes a humidity sensor, a temperature sensor, and an ultrasonic sensor; the humidity sensor is used to obtain the humidity data of the pipeline monitoring point, the temperature sensor is used to obtain the temperature data of the pipeline monitoring point, and the ultrasonic sensor is used to transmit an ultrasonic signal and receive the signal reflected by the pipeline coating to obtain echo signal data; the acquisition module is specifically configured to preprocess the humidity data, temperature data, and echo signal data respectively, and obtain the corresponding target humidity value based on the preprocessing result, obtain the target temperature value based on the preprocessed temperature data, and obtain the target signal value based on the preprocessed echo signal data; the preprocessing includes data cleaning and data standardization. The target signal value includes: an echo signal time value and an echo signal intensity value.

[0012] Optionally, the judgment module is specifically configured to: compare the echo signal time value with the reflection wave delay, and compare the echo signal intensity value with the reflection wave intensity; when the echo signal time value is equal to the reflection wave delay and the echo signal intensity value is equal to the reflection wave intensity, it is determined that no coating aging has occurred at the pipeline monitoring point; when there is a situation where the echo signal time value is not equal to the reflection wave delay or the echo signal intensity value is not equal to the reflection wave intensity, it is determined that coating aging has occurred at the pipeline monitoring point.

[0013] Optionally, the initial coating depth value is obtained by the following formula:

[0014]

[0015] Wherein, v represents the propagation speed of ultrasonic waves in the pipeline coating, t represents the time value of the echo signal, A0 represents the signal intensity value when the ultrasonic wave is emitted, A represents the echo signal intensity value, and d represents the initial coating depth value.

[0016] Optionally, the processing module is further configured to compare the target humidity value with multiple historical target humidity values respectively to determine whether to adjust the target humidity value.

[0017] Optionally, the processing module is specifically configured as follows: when the target humidity value is less than the minimum value among the multiple historical target humidity values, it is determined to adjust the target humidity value; when the target humidity value is greater than or equal to the minimum value among the multiple historical target humidity values, it is determined not to adjust the target humidity value, and the target humidity value is determined as the pipeline coating humidity value.

[0018] Optionally, the processing module is specifically configured as follows: taking multiple groups of historical data as the dataset to be aggregated; extracting the historical humidity adjustment factors corresponding to each group of historical data in the dataset to be aggregated, determining that the expected number of clusters k is 3, and initializing the parameters of the Gaussian distribution, calculating the probability that each group of historical data in the dataset to be aggregated belongs to each Gaussian distribution to obtain the responsibility value; obtaining the dataset corresponding to the target humidity value and the target temperature value to be adjusted according to the responsibility value, and using the dataset as the target data set; taking the mean value of the historical humidity adjustment factors in the target data set as the humidity adjustment factor of the target humidity value to be adjusted, and determining the pipeline coating humidity value as the product value of the target humidity value to be adjusted and the humidity adjustment factor.

[0019] Optionally, the prediction module is specifically configured as follows: merging the pipeline coating humidity value and the historical pipeline coating humidity value data into a coating humidity dataset, merging the target temperature value and the historical target temperature value data into a coating temperature dataset, and merging the initial coating depth value and the historical initial coating depth value data into a coating depth dataset; mining the aging association rules between the coating humidity dataset, the coating temperature dataset and the coating depth dataset and establishing an aging dataset, processing the aging dataset based on the random forest model to obtain multiple coating depth prediction values of the pipeline monitoring point at different times, setting the initial coating depth value as the base point, sorting the multiple coating depth prediction values according to the time series to obtain the time-depth function, and obtaining the pipeline coating aging monitoring result based on the time-depth function.

[0020] Optionally, the prediction module is specifically configured as follows: discretizing the data in the coating humidity dataset, the coating temperature dataset and the coating depth dataset to construct a transaction dataset; using the Apr i or i algorithm to iteratively generate frequent item sets in the transaction dataset, and screening the item sets with a support degree higher than the preset minimum threshold to generate aging association rules, and establishing an aging dataset based on the aging association rules.

[0021] Optionally, the prediction module is specifically configured to: divide the aging dataset into a model training set and a model test set, use cross-validation and combine it with grid search to find the model parameters of the random forest model, and establish a random forest model; use the model training set to fit the random forest model, substitute the model test set into the random forest model and calculate the accuracy rate of the coating depth prediction value. When the accuracy rate reaches the preset accuracy threshold, input the initial coating depth value into the random forest model for processing, obtain the depth prediction result of the current pipeline monitoring point, and perform multiple iterative predictions based on the depth prediction result to obtain multiple coating depth prediction values at different time periods; the value input into the random forest model for each iterative prediction is the value output by the random forest model in the previous iterative prediction.

[0022] Optionally, the prediction module is specifically configured to: calculate the slopes of all adjacent two points in the time-depth function; when all the slopes are less than 0, it is determined that the coating aging change trend of the pipeline monitoring point is an upward trend; when all the slopes are equal to 0, it is determined that the coating aging change trend of the pipeline monitoring point is a stable trend; when all the slopes are not all equal to 0 or less than 0, it is determined that the coating aging change trend of the pipeline monitoring point is a fluctuating trend.

[0023] Optionally, the system further includes: an early warning module; the early warning module is configured to: set the upward trend as a first-level aging early warning, set the fluctuating trend as a second-level aging early warning, and set the stable trend as a third-level aging early warning; the emergency levels of the first-level aging early warning, the second-level aging early warning, and the third-level aging early warning decrease in sequence; establish a chart of the pipeline coating humidity value, the target temperature value, and the initial coating depth value, and output the established chart in a standard output format.

[0024] This technical solution can support setting different early warning levels according to the aging trend and generating a visual report, improve the automation level of monitoring, and provide intuitive decision-making support for the maintenance of pipeline coatings.

[0025] Second aspect, a method for monitoring the aging of pipeline coatings is provided, including: collecting aging data of pipeline monitoring points, where the aging data includes a target humidity value, a target temperature value, and a target signal value; comparing the target signal value with a preset reflection wave intensity and a preset reflection wave delay respectively to determine whether coating aging occurs at the pipeline monitoring point; when coating aging occurs at the pipeline monitoring point, determining an initial coating depth value according to the target signal value, determining a humidity adjustment factor according to the target humidity value, the target temperature value, and multiple sets of historical data, and determining the pipeline coating humidity value according to the target humidity value and the humidity adjustment factor; each set of historical data includes a corresponding historical target humidity value, a historical target temperature value, and a historical humidity adjustment factor; determining multiple coating depth prediction values at different times of the pipeline monitoring point according to the pipeline coating humidity value, the historical pipeline coating humidity value data, the target temperature value, the historical target temperature value data, the initial coating depth value, and the historical initial coating depth value data, and determining the pipeline coating aging monitoring result according to the initial coating depth value and the multiple coating depth prediction values; the pipeline coating aging monitoring result is used to indicate the change trend of the initial coating depth value and the multiple coating depth prediction values over time.

[0026] Third aspect, a device for monitoring the aging of pipeline coatings 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 device for monitoring the aging of pipeline coatings runs, the processor executes the computer execution instructions stored in the memory to enable the device for monitoring the aging of pipeline coatings to execute the method for monitoring the aging of pipeline coatings in the second aspect.

[0027] Fourth aspect, a computer-readable storage medium is provided, where the computer-readable storage medium includes computer execution instructions, and when the computer execution instructions run on a computer, the computer is enabled to execute the method for monitoring the aging of pipeline coatings in the second aspect.

[0028] Fifth aspect, a computer program product is further provided, where the computer program product includes computer instructions, and when the computer instructions run on the device for monitoring the aging of pipeline coatings, the device for monitoring the aging of pipeline coatings is enabled to execute the method for monitoring the aging of pipeline coatings in the second aspect as described above.

[0029] It should be noted that the above computer instructions may be stored in whole or in part on the computer-readable storage medium. Among them, the computer-readable storage medium may be packaged together with the processor of the device for monitoring the aging of pipeline coatings, or may be separately packaged from the processor of the device for monitoring the aging of pipeline coatings. The embodiments of the present application do not make any limitations in this regard.

[0030] The descriptions of the second aspect, the third aspect, the fourth aspect, and the fifth aspect in the present application may refer to the detailed description of the first aspect.

[0031] In the embodiments of the present application, the name of the above pipeline coating aging monitoring device does not constitute a limitation to the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the functions of each device or functional 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.

[0032] The beneficial effects of the present invention are as follows: Through the collaborative action of multiple modules, the system has functions of acquisition, judgment, processing and prediction, realizing accurate monitoring of the aging state of the pipeline coating. Using the time unit and sensors to obtain the target humidity value, target temperature value and target signal value, ensuring the comprehensiveness and efficiency of the monitoring data, realizing comprehensive analysis between different parameters. By comparing with the reflection wave delay and reflection wave intensity, the aging situation of the pipeline coating can be quickly identified. Determining the humidity adjustment factor based on historical data to dynamically adjust the target humidity value, avoiding interference of factors such as environmental temperature on the target humidity value, and improving the accuracy of the pipeline coating humidity value. Based on the multi-dimensional data in the time series, the aging change trend of the coating can be accurately revealed, improving the scientific nature of pipeline operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] By reading the following detailed description of the preferred embodiments, 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 invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0034] Figure 1 It is a schematic structural diagram of a pipeline coating aging monitoring system provided by an embodiment of the present application;

[0035] Figure 2 It is a schematic structural diagram of an acquisition module provided by an embodiment of the present invention;

[0036] Figure 3 It is another schematic structural diagram of an acquisition module provided by an embodiment of the present invention;

[0037] Figure 4 It is another schematic structural diagram of a pipeline coating aging monitoring system provided by an embodiment of the present application;

[0038] Figure 5 It is a schematic flow diagram of a pipeline coating aging monitoring method provided by an embodiment of the present application;

[0039] Figure 6 It is a schematic structural diagram of a pipeline coating aging monitoring device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] Exemplary embodiments of the present disclosure will be described in more detail below 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 invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0041] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0042] In order to improve the automation level of pipeline monitoring, provide intuitive decision-making support for the maintenance of pipeline coatings, and enhance the scientific nature of pipeline operation and maintenance, the embodiments of the present application provide a pipeline coating aging monitoring system. As Figure 1 shown, it is a schematic structural diagram of a pipeline coating aging monitoring system provided by the embodiments of the present application. Figure 1 The shown pipeline coating aging monitoring system includes: a collection module 101, a judgment module 102, a processing module 103, and a prediction module 104.

[0043] The collection module 101 is the data source of the pipeline coating aging monitoring system and is configured to collect aging data of pipeline monitoring points. The aging data includes a target humidity value, a target temperature value, and a target signal value. For example, the collection module 101 can collect aging data through various types of sensors such as humidity sensors, temperature sensors, and ultrasonic sensors. The target signal value can be collected by the ultrasonic sensor based on the reflection of ultrasonic signals. A preset reflection wave delay and a preset reflection wave intensity can be preset in the judgment module 102. The judgment module 102 is configured to compare the target signal value with the reflection wave intensity and the reflection wave delay respectively to determine whether coating aging occurs at the pipeline monitoring point.

[0044] The preset reflected wave delay is expressed as the time when the ultrasonic sensor sends ultrasonic waves to a standard pipeline with the same material and the same thickness and receives the echo. The preset reflected wave intensity is expressed as the intensity when the ultrasonic sensor sends ultrasonic waves to a standard pipeline with the same material and the same thickness and receives the echo. By comparing the target signal values with the preset reflected wave intensity and the preset reflected wave delay respectively, the existing differences between them are shown, enabling the aging state of the pipeline coating to be judged quickly and intuitively, reducing manual intervention and improving the judgment efficiency.

[0045] The processing module 103 is responsible for analyzing the relationship between the target signal value and the pipeline environment and adjusting the data. It can be configured to determine the initial coating depth value according to the target signal value when coating aging occurs at the pipeline monitoring point, providing a data basis for subsequent prediction.

[0046] Moreover, considering that the humidity of the pipeline is affected by the temperature of the pipeline, resulting in an error in the target humidity value and the occurrence of extreme data deviating from the reasonable range. Therefore, the processing module 103 can also be configured to determine the humidity adjustment factor according to the target humidity value, the target temperature value and multiple groups of historical data when coating aging occurs at the pipeline monitoring point, and determine the pipeline coating humidity value according to the target humidity value and the humidity adjustment factor. Each group of historical data includes the corresponding historical target humidity value, historical target temperature value and historical humidity adjustment factor. The prediction module 104 is configured to determine multiple coating depth prediction values at different times of the pipeline monitoring point according to the pipeline coating humidity value, historical pipeline coating humidity value data, target temperature value, historical target temperature value data, initial coating depth value and historical initial coating depth value data, and determine the pipeline coating aging monitoring result according to the initial coating depth value and multiple coating depth prediction values. The pipeline coating aging monitoring result is used to indicate the change trend of the initial coating depth value and multiple coating depth prediction values over time.

[0047] Based on this, the prediction module 104 can analyze the coating aging change trend through multi-dimensional data, thereby quantifying the aging speed of the pipeline coating and ensuring the visibility and scientificity of the pipeline coating aging monitoring.

[0048] In a possible embodiment of the present application, as Figure 2 shown, it is a schematic structural diagram of an acquisition module 101 provided by an embodiment of the present application. Figure 2 The shown acquisition module 101 includes a time unit 1011 and a sensor 1012. A connection can be established between the time unit 1011 and the sensor 1012.

[0049] The time unit 1011 is used to set the acquisition frequency of the sensor. For example, the acquisition frequency can be twice a day, and can be specifically adjusted according to actual needs to ensure the time continuity and data integrity of the coating aging information of the pipeline monitoring point collected.

[0050] The sensor 1012 is a wireless passive sensor and is installed at the pipeline monitoring point.

[0051] Based on this, the present application can collect real-time data through the wireless passive sensor, achieve accurate identification of coating aging, and improve the monitoring efficiency. Moreover, based on the wireless passive sensing technology, the maintenance cost of the sensor can be reduced, while human intervention is reduced, and the reliability and applicability of the system are improved.

[0052] In one possible way, the sensor 1012 may include a humidity sensor, a temperature sensor, and an ultrasonic sensor. As Figure 3 shown, it is a schematic structural diagram of another acquisition module 101 provided by an embodiment of the present application. The time unit 1011 can be respectively connected to the humidity sensor 10121, the temperature sensor 10122, and the ultrasonic sensor 10123.

[0053] The humidity sensor 10121 is used to obtain the humidity data of the pipeline monitoring point, the temperature sensor 10122 is used to obtain the temperature data of the pipeline monitoring point, and the ultrasonic sensor 10123 is used to transmit an ultrasonic signal and receive the signal reflected by the pipeline coating to obtain echo signal data.

[0054] Furthermore, the acquisition module 101 can be specifically configured to preprocess the humidity data, the temperature data, and the echo signal data respectively, and obtain the corresponding target humidity value based on the result of the preprocessing, and obtain the target temperature value based on the preprocessed temperature data, and obtain the target signal value based on the preprocessed echo signal data. Among them, the preprocessing may include data cleaning and data standardization. The target signal value includes: the echo signal time value and the echo signal intensity value. The echo signal time value represents the time value when the ultrasonic sensor sends ultrasonic waves to the pipeline monitoring point and receives the echo. The echo signal intensity value represents the echo intensity value when the ultrasonic sensor sends ultrasonic waves to the pipeline monitoring point and the echo reflected by the pipeline coating returns.

[0055] The above humidity sensor 10121, temperature sensor 10122, and ultrasonic sensor 10123 are respectively used to monitor the humidity data, temperature data, and pipe and echo signal data of the pipeline, providing a multi-dimensional data basis for subsequent analysis. The acquisition module 101 preprocesses the humidity data, temperature data, and echo signal data. By data cleaning, the noise of the data is eliminated, and by data standardization, the influence of the dimension is eliminated, improving the data quality of the target humidity value, target temperature value, echo signal time value, and echo signal intensity value, reducing external interference, and ensuring subsequent data analysis and processing.

[0056] In some embodiments of the present application, the determination module 102 may be specifically configured to compare the echo signal time value with the reflection wave delay and compare the echo signal intensity value with the reflection wave intensity. When the echo signal time value is equal to the reflection wave delay and the echo signal intensity value is equal to the reflection wave intensity, it is determined that there is no coating aging at the pipeline monitoring point. When there is a situation where the echo signal time value is not equal to the reflection wave delay or the echo signal intensity value is not equal to the reflection wave intensity, it is determined that coating aging has occurred at the pipeline monitoring point.

[0057] In some embodiments of the present application, the initial coating depth value is obtained by the following formula:

[0058]

[0059] Wherein, v represents the propagation speed of ultrasonic waves in the pipeline coating, t represents the echo signal time value, A0 represents the signal intensity value when the ultrasonic wave is emitted, A represents the echo signal intensity value, and d represents the initial coating depth value.

[0060] The present application uses the preset reflection wave delay and reflection wave intensity as the reference data for judging the aging situation. By comparing the difference between the reference data and the collected target signal values, the coating aging state of the pipeline monitoring point can be clearly represented. Moreover, the pipeline coating aging monitoring system in the present application uses a dual-parameter comparison, avoiding misjudgment caused by a single parameter and ensuring the accuracy of the monitoring. Based on the occurrence of coating aging, the initial coating depth value is calculated, providing a reference index for the state analysis of the pipeline coating, facilitating the quantification of the aging degree of the pipeline coating, thereby reducing the risk of accidents. The automated judgment process does not require manual intervention, improving the monitoring efficiency of the pipeline coating.

[0061] In some embodiments of the present application, considering that the humidity of the pipeline is affected by the temperature of the pipeline, resulting in errors in the target humidity value and the existence of extreme data deviating from the reasonable range. Moreover, the historical target humidity value represents the humidity range of the pipeline coating at the pipeline monitoring point. When the ambient temperature rises or the temperature of the pipeline changes, it will have a temperature concentration effect on the humidity sensor, resulting in extreme situations of the target humidity value. To avoid this situation, the processing module 103 may also be configured to compare the target humidity value with multiple historical target humidity values respectively to determine whether to adjust the target humidity value. In this way, the processing module 103 can support further judgment and analysis of the target humidity value, compare it with historical data, and determine whether the current target humidity value needs to be adjusted, ensuring the accuracy of the data and avoiding the situation of data source deviation.

[0062] In some embodiments, the processing module 103 may be specifically configured to:

[0063] When the target humidity value is less than the minimum value among multiple historical target humidity values, it is determined to adjust the target humidity value. When the target humidity value is greater than or equal to the minimum value among multiple historical target humidity values, it is determined not to adjust the target humidity value, and the target humidity value is determined as the pipeline coating humidity value.

[0064] Based on this, by comparing the target humidity value with the minimum value of the historical target humidity values, this application can avoid extreme data situations and improve the accuracy of the pipeline coating humidity value.

[0065] In some embodiments of this application, the processing module 103 may be specifically configured to obtain multiple sets of historical data. The historical data includes historical target temperature value data and historical target humidity values. The historical target temperature value data includes: historical humidity adjustment factors and historical target temperature values, and the historical target humidity values correspond to the historical humidity adjustment factors. The multiple sets of historical data are used as the dataset to be aggregated. Extract the historical humidity adjustment factors corresponding to each set of historical data in the dataset to be aggregated, determine that the expected number of clusters k is 3, and initialize the parameters of the Gaussian distribution. Calculate the probability that each set of historical data in the dataset to be aggregated belongs to each Gaussian distribution to obtain the responsibility value. Obtain the dataset corresponding to the target humidity value and target temperature value to be adjusted according to the responsibility value, and use the dataset as the target data set. Use the mean value of the historical humidity adjustment factors in the target number set as the humidity adjustment factor for the target humidity value to be adjusted, and determine the pipeline coating humidity value as the product value of the target humidity value to be adjusted and the humidity adjustment factor.

[0066] In this way, when the processing module 103 determines to adjust the target humidity value, it can analyze through a clustering algorithm to find the temperature set closest to the current pipeline monitoring point, avoid the situation of data source deviation, improve the accuracy of the humidity adjustment factor, dynamically adjust the target humidity value in real time, reduce the dependence on manual experience and judgment, and improve the automation level and reliability of the system. By accurately calculating the pipeline coating humidity value, the risk of extreme data affecting subsequent judgments is avoided, ensuring the accuracy of subsequent predictions.

[0067] In some embodiments of the present application, the prediction module 104 may be specifically configured to: combine the pipeline coating humidity value and the historical pipeline coating humidity value data into a coating humidity data set, combine the target temperature value and the historical target temperature value data into a coating temperature data set, and combine the initial coating depth value and the historical initial coating depth value data into a coating depth data set. Mine the aging association rules among the coating humidity data set, the coating temperature data set, and the coating depth data set and establish an aging data set. Process the aging data set based on the random forest model to obtain multiple coating depth prediction values at different times for the pipeline monitoring points. Set the initial coating depth value as the base point, sort the multiple coating depth prediction values in time series to obtain a time-depth function, and obtain the pipeline coating aging monitoring result based on the time-depth function. Based on this, the prediction module 104 can obtain multiple coating depth prediction values through big data algorithms and machine learning models, and establish a time-depth function to analyze the aging change trend of the coating, so as to quantify the aging speed of the pipeline coating and ensure the visibility and scientific nature of the pipeline coating aging monitoring.

[0068] In some embodiments of the present application, the prediction module may be specifically configured to: discretize the data in the coating humidity data set, the coating temperature data set, and the coating depth data set to construct a transaction data set. Use the Apriori algorithm to iteratively generate frequent item sets in the transaction data set, and filter the item sets with a support degree higher than the preset minimum threshold to generate aging association rules, and establish an aging data set based on the aging association rules.

[0069] In the above embodiments of the present application, the data in the coating humidity data set, the coating temperature data set, and the coating depth data set are discretized. The coating humidity data set is divided into three intervals, namely low humidity (such as below 40%), medium humidity (such as greater than or equal to 40% and less than 70%), and high humidity (such as greater than or equal to 70%). The coating temperature data set is divided into three intervals, namely low temperature (such as below 20°C), medium temperature (such as greater than or equal to 20°C and less than 50°C), and high temperature (such as greater than or equal to 50°C). The coating depth data set is divided into two intervals, namely light depth (such as below 5 mm) and medium depth (such as greater than or equal to 5 mm). All the intervals are sequentially converted into a transaction data set. For example: {low humidity - low temperature - light depth}, {low humidity - low temperature - medium depth}, {low humidity - medium temperature - light depth}. The preset minimum threshold is 2, which can be specifically adjusted according to requirements, so as to obtain the aging association rules. For example: when the low humidity is 28% and the medium temperature is 37°C, the medium depth of 7 mm always appears. Furthermore, an aging data set can be established according to the interval data of all the aging association rules. And using the Apriori algorithm not only improves the accuracy of data analysis, but also provides a scientific basis for the precise monitoring of pipeline coatings.

[0070] In some embodiments of the present application, the prediction module 104 may further be configured to: divide the aging dataset into a model training set and a model test set, use cross-validation in combination with grid search to find the model parameters of the random forest model, and establish a random forest model. Fit the random forest model with the model training set, substitute the model test set into the random forest model and calculate the accuracy rate of the coating depth prediction value. When the accuracy rate reaches the preset accuracy rate threshold, input the initial coating depth value into the random forest model for processing, obtain the depth prediction result of the current pipeline monitoring point, and perform multiple iterative predictions based on the depth prediction result to obtain multiple coating depth prediction values at different time periods. Wherein, the value input into the random forest model for each iterative prediction is the value output by the random forest model in the previous iterative prediction.

[0071] Considering that the aging dataset records the operating conditions of the pipeline monitoring points at different time periods. Divide the aging dataset into a model training set and a model test set, and use 80% of the data as the model training set and the remaining data as the model test set, which can ensure that the model training set and the model test set can contain data of various operating conditions. At the same time, use cross-validation in combination with grid search to find the model parameters of the random forest model. Cross-validation divides the data into several parts and trains the random forest model multiple times to verify its stability. Grid search searches for model parameter combinations, such as the number of trees, the depth of the trees, etc. Using the optimized parameters, fit the random forest model with the model training set data, thereby reducing the risk of overfitting and improving the accuracy and stability of the random forest model.

[0072] Moreover, considering that the accuracy rate is an important criterion for evaluating the performance of the random forest model, substitute the model test set data into the already trained random forest model, and calculate the accuracy rate of the coating depth prediction value obtained by the random forest model. After the random forest model reaches the preset accuracy rate threshold, substitute the initial coating depth value into the random forest model to obtain the depth prediction result, and substitute the depth prediction result into the random forest model to continue the prediction. For example, it can be cyclically substituted 10 times in sequence to obtain multiple coating depth prediction values at different time periods. The number of cyclic substitutions (i.e., the number of iterative predictions) can be adjusted according to actual needs.

[0073] In the above embodiments of the present application, through the combination of cross-validation and grid search, the optimization of the random forest model parameters is ensured, and the stability and reliability of the random forest model on the aging dataset are improved. After the random forest model reaches the preset accuracy rate threshold, it can predict the initial coating depth value in real time, provide multiple coating depth prediction values, which is beneficial to timely discovering potential problems and improving the reliability of monitoring.

[0074] In some embodiments of the present application, the prediction module 104 may be specifically configured to calculate the slopes of all adjacent points in the time-depth function. When all the slopes are less than 0, it is determined that the coating aging change trend of the pipeline monitoring point is an upward trend. When all the slopes are equal to 0, it is determined that the coating aging change trend of the pipeline monitoring point is a stable trend. When all the slopes are not all equal to 0 or less than 0, it is determined that the coating aging change trend of the pipeline monitoring point is a fluctuating trend.

[0075] Among them, the time-depth function is obtained by sorting multiple coating depth prediction values in a time series with the initial coating depth value as the base point. The slope between two adjacent points in the time-depth function is the difference between the coating depth prediction values of every two adjacent time points divided by the time interval between them. The slope represents the change rate of the pipeline coating depth in each time period.

[0076] If all the slopes are less than 0, it means that the coating depth continuously decreases over time and the aging situation becomes more serious. Then it is determined that the coating aging change trend is an upward trend. If all the slopes are not all equal to 0 or less than 0, it is determined as a fluctuating trend. The fluctuating trend means that there are certain fluctuations in the coating aging process, which may be affected by environmental factors or other unexpected situations. At this time, it is necessary to closely monitor the changes in the coating. If all the slopes are equal to 0, it means that the coating depth remains unchanged in the future for a period of time, that is, the pipeline coating is in a relatively stable state, and it is determined as a stable trend.

[0077] In some embodiments of the present application, in combination Figure 1 , as Figure 4 shown, it is a schematic structural diagram of another pipeline coating aging monitoring system provided by the embodiments of the present application. The pipeline coating aging monitoring system further includes: an early warning module 105. The early warning module 105 may be configured to set an aging early warning level according to the coating aging change trend and establish a visual early warning report. In this way, the early warning module 105 can provide intuitive early warning information through comprehensive analysis of the coating aging trend, thereby generating a visual early warning report, which is beneficial for relevant maintenance personnel to make decisions on pipeline monitoring points.

[0078] The aging early warning levels include a first-level aging early warning, a second-level aging early warning, and a third-level aging early warning. The emergency levels of the first-level aging early warning, the second-level aging early warning, and the third-level aging early warning decrease in sequence. For example, the first-level aging early warning indicates serious coating aging. The second-level aging early warning indicates fluctuations in the aging process, and it is necessary to pay attention and take preventive measures. The third-level aging early warning indicates that the coating state is stable, and the intervention can be appropriately delayed.

[0079] The warning module 105 can be specifically configured to set an upward trend as a first-level aging warning, a fluctuating trend as a second-level aging warning, a stable trend as a third-level aging warning, and establish a chart for the pipeline coating humidity value, target temperature value, and initial coating depth value, and output the established chart in a standard output format.

[0080] Optionally, the standard output format of the chart can be in the form of a spreadsheet (Excel) or a presentation (PowerPoint, PPT) format.

[0081] Based on this, the present application can help relevant personnel intuitively understand the actual situation of the current pipeline coating, make scientific and reasonable decisions based on the aging warning level, improve the accuracy and response efficiency of pipeline coating monitoring, and through real-time monitoring and trend analysis of coating aging, potential risks can be discovered in advance and actions can be taken, thereby improving the safety of the pipeline and ensuring the long-term stable operation of the pipeline.

[0082] As Figure 5 shown, it is a schematic flow chart of a pipeline coating aging monitoring method provided by an embodiment of the present application. Figure 5 The shown pipeline coating aging monitoring method can be executed by a pipeline coating aging monitoring device. The pipeline coating aging monitoring device can be configured with software units for implementing the functions of each module of the above-mentioned pipeline coating aging monitoring system. Such as software units for implementing the acquisition module, judgment module, processing module, prediction module, and warning module. Figure 5 The shown pipeline coating aging monitoring method includes: S201 - S204.

[0083] S201. Collect aging data of pipeline monitoring points.

[0084] Among them, the aging data includes a target humidity value, a target temperature value, and a target signal value.

[0085] S202. Compare the target signal value with a preset reflection wave intensity and a preset reflection wave delay respectively to determine whether coating aging occurs at the pipeline monitoring point.

[0086] S203. When coating aging occurs at the pipeline monitoring point, determine the initial coating depth value according to the target signal value, determine the humidity adjustment factor according to the target humidity value, target temperature value, and multiple sets of historical data, and determine the pipeline coating humidity value according to the target humidity value and the humidity adjustment factor.

[0087] Among them, each set of historical data includes the corresponding historical target humidity value, historical target temperature value, and historical humidity adjustment factor.

[0088] S204. Determine multiple predicted coating depth values at different times for the pipeline monitoring point based on the pipeline coating humidity value, historical pipeline coating humidity value data, target temperature value, historical target temperature value data, initial coating depth value, and historical initial coating depth value data, and determine the pipeline coating aging monitoring result based on the initial coating depth value and the multiple predicted coating depth values.

[0089] Among them, the pipeline coating aging monitoring result is used to indicate the change trend of the initial coating depth value and the multiple predicted coating depth values over time.

[0090] In some embodiments of the present application, the pipeline coating aging monitoring device can collect aging data through sensors installed at the pipeline monitoring point. The sensors are wireless passive sensors. The time unit is used to set the acquisition frequency of the sensors. The sensors include a humidity sensor, a temperature sensor, and an ultrasonic sensor. The humidity sensor is used to obtain the humidity data of the pipeline monitoring point, the temperature sensor is used to obtain the temperature data of the pipeline monitoring point, and the ultrasonic sensor is used to transmit ultrasonic signals and receive the signals reflected by the pipeline coating to obtain echo signal data.

[0091] Based on this, when the pipeline coating aging monitoring device executes S201 above, that is, when the pipeline coating aging monitoring device collects the aging data of the pipeline monitoring point, an optional implementation manner provided by the embodiments of the present application includes: S2011.

[0092] S2011. Preprocess the humidity data, temperature data, and echo signal data respectively, and obtain the corresponding target humidity value based on the preprocessing results, and obtain the target temperature value based on the preprocessed temperature data, and obtain the target signal value based on the preprocessed echo signal data.

[0093] Among them, the preprocessing includes data cleaning and data standardization. The target signal value includes: echo signal time value and echo signal intensity value.

[0094] In some embodiments of the present application, when the pipeline coating aging monitoring device executes S202 above, that is, when the pipeline coating aging monitoring device compares the target signal value with the preset reflection wave intensity and the preset reflection wave delay respectively to determine whether there is coating aging at the pipeline monitoring point, an optional implementation manner provided by the embodiments of the present application includes: S2021 - S2023.

[0095] S2021. Compare the echo signal time value with the reflection wave delay, and compare the echo signal intensity value with the reflection wave intensity.

[0096] S2022. When the echo signal time value is equal to the reflection wave delay and the echo signal intensity value is equal to the reflection wave intensity, it is determined that there is no coating aging at the pipeline monitoring point.

[0097] S2023. When the echo signal time value is not equal to the reflection wave delay or the echo signal intensity value is not equal to the reflection wave intensity, it is determined that the coating at the pipeline monitoring point is aged.

[0098] In some embodiments of the present application, the initial coating depth value is obtained from the following formula:

[0099]

[0100] Wherein, v represents the propagation speed of ultrasonic waves in the pipeline coating, t represents the echo signal time value, A0 represents the signal intensity value at the time of ultrasonic wave emission, A represents the echo signal intensity value, and d represents the initial coating depth value.

[0101] In some embodiments of the present application, the pipeline coating aging monitoring method may further include: S205.

[0102] S205. Compare the target humidity value with multiple historical target humidity values respectively to determine whether to adjust the target humidity value.

[0103] In some embodiments of the present application, when the pipeline coating aging monitoring device executes the above S205, that is, when the pipeline coating aging monitoring device compares the target humidity value with multiple historical target humidity values respectively to determine whether to adjust the target humidity value, an optional implementation manner provided by the embodiments of the present application includes: S2051 - S2052.

[0104] S2051. When the target humidity value is less than the minimum value among multiple historical target humidity values, it is determined to adjust the target humidity value.

[0105] S2052. When the target humidity value is greater than or equal to the minimum value among multiple historical target humidity values, it is determined not to adjust the target humidity value, and the target humidity value is determined as the pipeline coating humidity value.

[0106] In some embodiments of the present application, when the pipeline coating aging monitoring device executes the above S203, that is, when the pipeline coating aging monitoring device determines the humidity adjustment factor according to the target humidity value, the target temperature value and multiple sets of historical data, and determines the pipeline coating humidity value according to the target humidity value and the humidity adjustment factor, an optional implementation manner provided by the embodiments of the present application includes: S2031 - S2034.

[0107] S2031. Use multiple sets of historical data as the dataset to be aggregated.

[0108] S2032. Extract the historical humidity adjustment factors corresponding to each group of historical data in the dataset to be aggregated, determine that the expected number of clusters k is 3, initialize the parameters of the Gaussian distribution, calculate the probability that each group of historical data in the dataset to be aggregated belongs to each Gaussian distribution, and obtain the responsibility values.

[0109] S2033. Obtain the dataset corresponding to the target humidity value and the target temperature value to be adjusted according to the responsibility values, and use the dataset as the target dataset.

[0110] S2034. Use the mean value of the historical humidity adjustment factors in the target dataset as the humidity adjustment factor for the target humidity value to be adjusted, and determine the pipeline coating humidity value by the product value of the target humidity value to be adjusted and the humidity adjustment factor.

[0111] In some embodiments of the present application, when the pipeline coating aging monitoring device executes the above S204, an optional implementation manner provided by the embodiments of the present application includes: S2041 - S2044.

[0112] S2041. Combine the pipeline coating humidity value and the historical pipeline coating humidity value data into a coating humidity dataset, combine the target temperature value and the historical target temperature value data into a coating temperature dataset, and combine the initial coating depth value and the historical initial coating depth value data into a coating depth dataset.

[0113] S2042. Mine the aging association rules among the coating humidity dataset, the coating temperature dataset and the coating depth dataset, and establish an aging dataset.

[0114] S2043. Process the aging dataset based on the random forest model to obtain multiple coating depth prediction values at different times for the pipeline monitoring point.

[0115] S2044. Set the initial coating depth value as the base point, sort the multiple coating depth prediction values according to the time series to obtain the time - depth function, and obtain the pipeline coating aging monitoring result based on the time - depth function.

[0116] In some embodiments of the present application, when the pipeline coating aging monitoring device executes the above S2042, an optional implementation manner provided by the embodiments of the present application includes: S20421 - S20422.

[0117] S20421. Discretize the data in the coating humidity dataset, the coating temperature dataset and the coating depth dataset to construct a transaction dataset.

[0118] S20422. Use the Apriori algorithm to iteratively generate frequent item sets in the transaction dataset, screen the item sets with support degrees higher than the preset minimum threshold to generate aging association rules, and establish an aging dataset based on the aging association rules.

[0119] In some embodiments of the present application, when the pipeline coating aging monitoring device executes the above S2043, an optional implementation manner provided by the embodiments of the present application includes: S20431 - S20433.

[0120] S20431. Divide the aging data set into a model training set and a model test set, use cross - validation and combine it with grid search to find the model parameters of the random forest model, and establish a random forest model.

[0121] S20432. Fit the random forest model with the model training set, substitute the model test set into the random forest model and calculate the accuracy rate of the coating depth prediction value.

[0122] S20433. When the accuracy rate reaches the preset accuracy threshold, input the initial coating depth value into the random forest model for processing, obtain the depth prediction result of the current pipeline monitoring point, and perform multiple iterative predictions based on the depth prediction result to obtain multiple coating depth prediction values at different time periods.

[0123] Among them, the value input into the random forest model for each iterative prediction is the value output by the random forest model in the previous iterative prediction.

[0124] In some embodiments of the present application, when the pipeline coating aging monitoring device executes the above S2044, that is, when the pipeline coating aging monitoring device obtains the pipeline coating aging monitoring result based on the time - depth function, an optional implementation manner provided by the embodiments of the present application includes: S20441 - S20444.

[0125] S20441. Calculate the slopes of all adjacent points in the time - depth function.

[0126] S20442. When all the slopes are less than 0, it is determined that the coating aging change trend of the pipeline monitoring point is an upward trend.

[0127] S20443. When all the slopes are equal to 0, it is determined that the coating aging change trend of the pipeline monitoring point is a stable trend.

[0128] S20444. When all the slopes are not all equal to 0 or less than 0, it is determined that the coating aging change trend of the pipeline monitoring point is a fluctuating trend.

[0129] In some embodiments of the present application, the pipeline coating aging monitoring further includes: S206 - S207.

[0130] S206. Set the upward trend as a first - level aging warning, set the fluctuating trend as a second - level aging warning, and set the stable trend as a third - level aging warning.

[0131] Among them, the urgency levels of the first-level aging warning, the second-level aging warning, and the third-level aging warning decrease in sequence.

[0132] S207. Establish a chart for the pipeline coating humidity value, the target temperature value, and the initial coating depth value, and output the established chart in a standard output format.

[0133] Based on the above embodiments of the present application, the beneficial effects of the present invention are as follows: Through the synergistic effect of multiple modules, the system has functions of acquisition, judgment, processing, prediction, and warning, realizing precise monitoring of the aging state of the pipeline coating. Using time units and sensors to obtain the target humidity value, the target temperature value, and the target signal value ensures the comprehensiveness and efficiency of the monitoring data, realizes comprehensive analysis between different parameters. By comparing with the reflection wave delay and the reflection wave intensity, the aging situation of the pipeline coating can be quickly identified. Dynamically adjust the target humidity value based on the clustering algorithm and historical data, and determine the humidity adjustment factor through the temperature set, avoiding interference from factors such as environmental temperature on the target humidity value and improving the accuracy of the pipeline coating humidity value. Use the Apr i or i algorithm to mine aging association rules, and combine with the random forest model to obtain the predicted coating depth values at different time points, thereby generating a time-depth function to reveal the coating aging trend, improving the automation level of monitoring. Set different warning levels according to the aging trend and generate a visual report, providing intuitive decision-making support for the maintenance of the pipeline coating and improving the scientific nature of pipeline operation and maintenance.

[0134] The above mainly introduces the solution provided by the embodiments of the present application from the perspective of methods. To implement the above functions, the pipeline coating aging monitoring device 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 form 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.

[0135] The embodiments of the present application can divide the functional modules of the pipeline coating aging monitoring device according to the above method examples. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. Optionally, the division of modules in the embodiments of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0136] Such asFigure 6 As shown in the figure, it is a schematic structural diagram of a pipeline coating aging monitoring device provided by an embodiment of the present application. Figure 6 The pipeline coating aging monitoring device shown in the figure includes: a collection unit 301, a judgment unit 302, a processing unit 303, and a prediction unit 304;

[0137] The collection unit 301 is configured to collect aging data of the pipeline monitoring point, and the aging data includes a target humidity value, a target temperature value, and a target signal value;

[0138] The judgment unit 302 is configured to compare the target signal value with a preset reflection wave intensity and a preset reflection wave delay respectively to determine whether there is coating aging at the pipeline monitoring point;

[0139] The processing unit 303 is configured to, when there is coating aging at the pipeline monitoring point, determine an initial coating depth value according to the target signal value, determine a humidity adjustment factor according to the target humidity value, the target temperature value, and multiple sets of historical data, and determine the pipeline coating humidity value according to the target humidity value and the humidity adjustment factor; each set of historical data includes a corresponding historical target humidity value, a historical target temperature value, and a historical humidity adjustment factor.

[0140] The prediction unit 304 is configured to determine multiple coating depth prediction values of the pipeline monitoring point at different times according to the pipeline coating humidity value, the historical pipeline coating humidity value data, the target temperature value, the historical target temperature value data, the initial coating depth value, and the historical initial coating depth value data, and determine the pipeline coating aging monitoring result according to the initial coating depth value and the multiple coating depth prediction values; the pipeline coating aging monitoring result is used to indicate the change trend of the initial coating depth value and the multiple coating depth prediction values over time.

[0141] Optionally, the collection unit 301 includes a time unit and a sensor installed at the pipeline monitoring point; the sensor is a wireless passive sensor; the time unit is used to set the collection frequency of the sensor; the sensor includes a humidity sensor, a temperature sensor, and an ultrasonic sensor; the humidity sensor is used to obtain the humidity data of the pipeline monitoring point, the temperature sensor is used to obtain the temperature data of the pipeline monitoring point, and the ultrasonic sensor is used to transmit an ultrasonic signal and receive the signal reflected by the pipeline coating to obtain echo signal data; the collection unit 301 is specifically configured to preprocess the humidity data, the temperature data, and the echo signal data respectively, and obtain the corresponding target humidity value based on the result of the preprocessing, and obtain the target temperature value based on the preprocessed temperature data, and obtain the target signal value based on the preprocessed echo signal data; the preprocessing includes data cleaning and data standardization. The target signal value includes: an echo signal time value and an echo signal intensity value.

[0142] Optionally, the determination unit 302 is specifically configured to: compare the echo signal time value with the reflection wave delay, and compare the echo signal intensity value with the reflection wave intensity; when the echo signal time value is equal to the reflection wave delay and the echo signal intensity value is equal to the reflection wave intensity, it is determined that there is no coating aging at the pipeline monitoring point; when there is a situation where the echo signal time value is not equal to the reflection wave delay or the echo signal intensity value is not equal to the reflection wave intensity, it is determined that there is coating aging at the pipeline monitoring point.

[0143] Optionally, the initial coating depth value is obtained by the following formula:

[0144]

[0145] Wherein, v represents the propagation speed of ultrasonic waves in the pipeline coating, t represents the echo signal time value, A0 represents the signal intensity value when the ultrasonic wave is emitted, A represents the echo signal intensity value, and d represents the initial coating depth value.

[0146] Optionally, the processing unit 303 is further configured to compare the target humidity value with multiple historical target humidity values respectively to determine whether to adjust the target humidity value.

[0147] Optionally, the processing unit 303 is specifically configured to: when the target humidity value is less than the minimum value of multiple historical target humidity values, it is determined to adjust the target humidity value; when the target humidity value is greater than or equal to the minimum value of multiple historical target humidity values, it is determined not to adjust the target humidity value, and the target humidity value is determined as the pipeline coating humidity value.

[0148] Optionally, the processing unit 303 is specifically configured to: use multiple groups of historical data as the dataset to be aggregated; extract the historical humidity adjustment factor corresponding to each group of historical data in the dataset to be aggregated, determine that the expected number of clusters k is 3, and initialize the parameters of the Gaussian distribution, calculate the probability that each group of historical data in the dataset to be aggregated belongs to each Gaussian distribution, and obtain the responsibility value; obtain the dataset corresponding to the target humidity value and the target temperature value to be adjusted according to the responsibility value, and use the dataset as the target data set; use the mean value of the historical humidity adjustment factors in the target data set as the humidity adjustment factor of the target humidity value to be adjusted, and determine the pipeline coating humidity value by the product value of the target humidity value to be adjusted and the humidity adjustment factor.

[0149] Optionally, the prediction unit 304 is specifically configured to: combine the pipeline coating humidity value and the historical pipeline coating humidity value data into a coating humidity data set, combine the target temperature value and the historical target temperature value data into a coating temperature data set, and combine the initial coating depth value and the historical initial coating depth value data into a coating depth data set; mine the aging association rules between the coating humidity data set, the coating temperature data set, and the coating depth data set and establish an aging data set, process the aging data set based on the random forest model, obtain multiple coating depth prediction values at different times for the pipeline monitoring point, set the initial coating depth value as the base point, sort the multiple coating depth prediction values according to the time series, obtain the time-depth function, and obtain the pipeline coating aging monitoring result based on the time-depth function.

[0150] Optionally, the prediction unit 304 is specifically configured to: discretize the data in the coating humidity data set, the coating temperature data set, and the coating depth data set, and construct a transaction data set; use the Apriori algorithm to iteratively generate frequent item sets in the transaction data set, and filter out the item sets with support higher than the preset minimum threshold to generate aging association rules, and establish an aging data set based on the aging association rules.

[0151] Optionally, the prediction unit 304 is specifically configured to: divide the aging data set into a model training set and a model test set, use cross-validation and combine it with grid search to find the model parameters of the random forest model, and establish a random forest model; use the model training set to fit the random forest model, substitute the model test set into the random forest model and calculate the accuracy rate of the coating depth prediction value, when the accuracy rate reaches the preset accuracy rate threshold, input the initial coating depth value into the random forest model for processing, obtain the depth prediction result of the current pipeline monitoring point, and perform multiple iterative predictions based on the depth prediction result to obtain multiple coating depth prediction values at different time periods; the value input into the random forest model for each iterative prediction is the value output by the random forest model in the previous iterative prediction.

[0152] Optionally, the prediction unit 304 is specifically configured to: calculate the slope of all adjacent points in the time-depth function; when all the slopes are less than 0, it is determined that the coating aging change trend of the pipeline monitoring point is an upward trend; when all the slopes are equal to 0, it is determined that the coating aging change trend of the pipeline monitoring point is a stable trend; when all the slopes are not equal to 0 or less than 0, it is determined that the coating aging change trend of the pipeline monitoring point is a fluctuating trend.

[0153] Optionally, the system further includes: a warning unit 305. The warning unit 305 is configured to: set an upward trend as a first-level aging warning, a fluctuating trend as a second-level aging warning, and a stable trend as a third-level aging warning; the urgency levels of the first-level aging warning, the second-level aging warning, and the third-level aging warning decrease in sequence; establish a chart for the pipeline coating humidity value, the target temperature value, and the initial coating depth value, and output the established chart in a standard output format.

[0154] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0155] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0156] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including instruction means, and the instruction means implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0158] 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 above embodiments, those of ordinary skill in the art should understand that: it is still possible to modify the specific implementation manners of the present invention or make equivalent substitutions, and any modification or equivalent substitution that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A pipeline coating aging monitoring system, characterized in that: include: Acquisition module, judgment module, processing module and prediction module; The acquisition module is configured to acquire aging data of pipeline monitoring points, wherein the aging data includes a target humidity value, a target temperature value, and a target signal value; The judgment module is configured to compare the target signal value with a preset reflected wave intensity and a preset reflected wave delay respectively to determine whether coating aging occurs at the pipeline monitoring point; The processing module is configured to determine an initial coating depth value according to the target signal value when coating aging occurs at the pipeline monitoring point, determine a humidity adjustment factor according to the target humidity value, the target temperature value and multiple groups of historical data, and determine a pipeline coating humidity value according to the target humidity value and the humidity adjustment factor; each group of historical data includes a corresponding historical target humidity value, a historical target temperature value and a historical humidity adjustment factor; The prediction module is configured to determine a plurality of coating depth prediction values ​​of the pipeline monitoring point at different times according to the pipeline coating humidity value, the historical pipeline coating humidity value data, the target temperature value, the historical target temperature value data, the initial coating depth value and the historical initial coating depth value data, and determine a pipeline coating aging monitoring result according to the initial coating depth value and the plurality of coating depth prediction values; the pipeline coating aging monitoring result is used to indicate a changing trend of the initial coating depth value and the plurality of coating depth prediction values ​​over time.

2. The pipeline coating aging monitoring system according to claim 1, characterized in that: The acquisition module includes a time unit and a sensor installed at the pipeline monitoring point; the sensor is a wireless passive sensor; The time unit is used to set the acquisition frequency of the sensor; The sensors include a humidity sensor, a temperature sensor and an ultrasonic sensor; The humidity sensor is used to obtain humidity data of the pipeline monitoring point, the temperature sensor is used to obtain temperature data of the pipeline monitoring point, and the ultrasonic sensor is used to transmit ultrasonic signals and receive signals reflected by the pipeline coating to obtain echo signal data; The acquisition module is specifically configured to preprocess the humidity data, the temperature data and the echo signal data respectively, and obtain a target humidity value based on the preprocessed humidity data, obtain a target temperature value based on the preprocessed temperature data, and obtain a target signal value based on the preprocessed echo signal data; The preprocessing includes data cleaning and data standardization; The target signal value includes: an echo signal time value and an echo signal strength value.

3. The pipeline coating aging monitoring system according to claim 2, characterized in that: The determination module is specifically configured as follows: Comparing the echo signal time value with the reflected wave delay, and comparing the echo signal strength value with the reflected wave strength; When the echo signal time value is equal to the reflected wave delay, and the echo signal intensity value is equal to the reflected wave intensity, it is determined that no coating aging occurs at the pipeline monitoring point; When the echo signal time value is not equal to the reflected wave delay or the echo signal intensity value is not equal to the reflected wave intensity, it is determined that coating aging occurs at the pipeline monitoring point.

4. The pipeline coating aging monitoring system according to claim 2 or 3, characterized in that: The initial coating depth value is obtained from the following formula: Wherein, v represents the propagation speed of ultrasound in the pipeline coating, t represents the echo signal time value, A0 represents the signal strength value when ultrasound is emitted, A represents the echo signal strength value, and d represents the initial coating depth value.

5. The pipeline coating aging monitoring system according to claim 1, characterized in that: The processing module is further configured to compare the target humidity value with a plurality of historical target humidity values ​​respectively to determine whether to adjust the target humidity value.

6. The pipeline coating aging monitoring system according to claim 5, characterized in that: The processing module is specifically configured as follows: When the target humidity value is less than the minimum value among the multiple historical target humidity values, it is determined that the target humidity value should be adjusted; When the target humidity value is greater than or equal to the minimum value of the multiple historical target humidity values, it is determined that the target humidity value is not to be adjusted, and the target humidity value is determined as the pipeline coating humidity value.

7. The pipeline coating aging monitoring system according to claim 1, characterized in that: The processing module is specifically configured as follows: Using the multiple sets of historical data as data sets to be aggregated; Extract the historical humidity adjustment factor corresponding to each group of historical data in the data set to be aggregated, determine the expected number of clusters k to be 3, initialize the parameters of the Gaussian distribution, calculate the probability that each group of historical data in the data set to be aggregated belongs to each Gaussian distribution, and obtain the responsibility value; Obtaining a data set corresponding to the target humidity value and the target temperature value to be adjusted according to the responsibility value, and using the data set as a target data set; The mean value of the historical humidity adjustment factors in the target data set is used as the humidity adjustment factor of the target humidity value to be adjusted, and the product value of the target humidity value to be adjusted and the humidity adjustment factor is determined as the pipeline coating humidity value.

8. The pipeline coating aging monitoring system according to claim 1, characterized in that: The prediction module is specifically configured as follows: Merging the pipeline coating humidity value and historical pipeline coating humidity value data into a coating humidity data set, merging the target temperature value and historical target temperature value data into a coating temperature data set, and merging the initial coating depth value and historical initial coating depth value data into a coating depth data set; The aging association rules among the coating humidity data set, the coating temperature data set and the coating depth data set are mined and an aging data set is established. The aging data set is processed based on the random forest model to obtain multiple coating depth prediction values ​​of the pipeline monitoring point at different times. The initial coating depth value is set as the base point, and the multiple coating depth prediction values ​​are sorted according to the time series to obtain a time-depth function. The pipeline coating aging monitoring result is obtained based on the time-depth function.

9. The pipeline coating aging monitoring system according to claim 8, characterized in that: The prediction module is specifically configured as follows: Discretize the data in the coating humidity data set, the coating temperature data set, and the coating depth data set to construct a transaction data set; Apriori algorithm is used to iteratively generate frequent item sets in the transaction data set, and item sets with support higher than a preset minimum threshold are screened to generate the aging association rules; The aging data set is established based on the aging association rule.

10. The pipeline coating aging monitoring system according to claim 9, characterized in that: The prediction module is specifically configured as follows: The aging data set is divided into a model training set and a model test set, and the model parameters of the random forest model are found by cross-validation combined with grid search to establish a random forest model; The random forest model is fitted using the model training set, the model test set is substituted into the random forest model and the accuracy of the coating depth prediction value is calculated, when the accuracy reaches a preset accuracy threshold, the initial coating depth value is input into the random forest model for processing, the depth prediction result of the current pipeline monitoring point is obtained, and multiple iterative predictions are performed based on the depth prediction result to obtain multiple coating depth prediction values ​​in different time periods; The value of the random forest model input in each iteration prediction is the value output by the random forest model in the previous iteration prediction.

11. The pipeline coating aging monitoring system according to claim 8, characterized in that: The prediction module is specifically configured as follows: Calculating the slopes of all two adjacent points in the time-depth function; When all slopes are less than 0, it is judged that the coating aging change trend of the pipeline monitoring point is an upward trend; When all slopes are equal to 0, it is judged that the coating aging change trend of the pipeline monitoring point is a stable trend; When all the slopes are not all equal to 0 or are not all less than 0, it is determined that the coating aging change trend of the pipeline monitoring point is a fluctuating trend.

12. The pipeline coating aging monitoring system according to claim 11, characterized in that: Also includes: Early warning module; The warning module is configured to: set the rising trend as a first-level aging warning, set the fluctuating trend as a second-level aging warning, and set the stable trend as a third-level aging warning; The urgency of the first-level aging warning, the second-level aging warning and the third-level aging warning decreases in sequence; The pipeline coating moisture value, the target temperature value and the initial coating depth value are used to create a graph, and the created graph is output in a standard output format.

13. A pipeline coating aging monitoring method, characterized in that: include: Collecting aging data of pipeline monitoring points, wherein the aging data includes a target humidity value, a target temperature value, and a target signal value; Comparing the target signal value with a preset reflected wave intensity and a preset reflected wave delay respectively, to determine whether coating aging occurs at the pipeline monitoring point; When coating aging occurs at the pipeline monitoring point, an initial coating depth value is determined according to the target signal value, a humidity adjustment factor is determined according to the target humidity value, the target temperature value and multiple groups of historical data, and a pipeline coating humidity value is determined according to the target humidity value and the humidity adjustment factor; each group of historical data includes a corresponding historical target humidity value, a historical target temperature value and a historical humidity adjustment factor; According to the pipeline coating humidity value, historical pipeline coating humidity value data, the target temperature value, historical target temperature value data, the initial coating depth value and historical initial coating depth value data, multiple coating depth prediction values ​​of the pipeline monitoring point at different times are determined, and according to the initial coating depth value and the multiple coating depth prediction values, the pipeline coating aging monitoring result is determined; the pipeline coating aging monitoring result is used to indicate the changing trend of the initial coating depth value and the multiple coating depth prediction values ​​over time.

Images