Intelligent gas pipe network deformation monitoring internet of things system, method and storage medium

Abstract

This invention provides an IoT system, method, and storage medium for intelligent gas pipeline deformation monitoring, relating to the field of intelligent gas. The method is implemented based on this IoT system, in which the gas company management platform is configured to: determine a local pipeline segment of a target pipeline, identify a first deformation rate and a second deformation rate within a preset target time period, thereby determining a target deformation rate; adjust the division method of the local pipeline segment based on the target deformation rate; and determine the height change, monitoring frequency, and maintenance frequency based on the adjusted target deformation rate of the local pipeline segment, pipeline material data, and pipeline length data, thereby generating base control instructions, monitoring work orders, and maintenance work orders, which are then sent to the corresponding platforms. The storage medium stores computer instructions, which are executed by the computer upon reading them. This invention can predict the deformation rate of local pipeline segments, enabling timely monitoring, adjustment, and maintenance of pipeline network deformation.

Description

Technical Field

[0001] This specification relates to the field of smart gas, and in particular to a smart gas pipeline deformation monitoring Internet of Things system, method and storage medium. Background Technology

[0002] Once a gas pipeline is built and put into use, local sections may experience varying degrees of deformation due to gas transportation and external environmental factors. These factors include changes in gas transportation parameters and pipeline vibrations caused by gas transportation, while external environmental factors include differences in terrain and topography, uneven soil or foundation settlement, and variations in ambient temperature. Uneven deformation in multiple local sections of the same pipeline poses safety hazards, and currently, pipeline deformation monitoring often requires manual on-site inspections, which is time-consuming, labor-intensive, and lacks timely monitoring.

[0003] Therefore, it is desirable to provide an intelligent gas pipeline deformation monitoring IoT system, method, and storage medium that can assess the deformation rate of local pipeline sections in future time periods, accurately generate corresponding base control commands, monitoring work orders, and maintenance work orders, and then send them to the corresponding platforms to achieve timely monitoring, adjustment, and maintenance of pipeline deformation. Summary of the Invention

[0004] To address the problem of accurately assessing the deformation rate of local pipeline segments in future time periods in order to accurately generate corresponding instructions and work orders, this invention provides an intelligent gas pipeline deformation monitoring IoT system, method, and storage medium.

[0005] The invention includes an IoT system for monitoring deformation in intelligent gas pipeline networks. The IoT system comprises a government gas regulatory management platform, a government gas regulatory sensor network platform, a government gas regulatory object platform, a gas company sensor network platform, a gas equipment object platform, and a gas maintenance object platform. The government gas regulatory object platform includes a gas company management platform. The government gas regulatory management platform is communicatively connected to the gas company management platform via the government gas regulatory sensor network platform. The gas equipment object platform and the gas maintenance object platform are communicatively connected to the gas company management platform via the gas company sensor network platform. The gas company management platform is configured to execute an intelligent gas pipeline deformation monitoring method.

[0006] The invention includes a method for monitoring deformation in intelligent gas pipeline networks. The method is implemented based on an intelligent gas pipeline network deformation monitoring IoT system, executed by a gas company management platform within the IoT system. The method includes: determining a local pipeline segment of a target pipeline, and a first deformation rate and a second deformation rate within a preset target time period; determining a target deformation rate for the local pipeline segment based on the first and second deformation rates; adjusting the division method of the local pipeline segment based on the target deformation rate; determining the height change, monitoring frequency, and maintenance frequency of the adjusted local pipeline segment within the preset target time period based on the adjusted target deformation rate, pipeline material data, and pipeline length data; generating a base control command based on the height change and sending it to the gas equipment object platform; generating a monitoring work order based on the monitoring frequency and sending it to the gas maintenance object platform; and generating a maintenance work order based on the maintenance frequency and sending it to the gas maintenance object platform.

[0007] The invention includes a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the intelligent gas pipeline deformation monitoring method.

[0008] The beneficial effects of the above-mentioned invention include, but are not limited to: (1) by estimating the deformation rate of a local pipeline segment due to various reasons, and then adjusting the division method of the local pipeline segment according to the deformation rate, the local pipeline segment with a higher deformation rate can be controlled with finer granularity, so as to improve the control effect while saving computing resources; based on the target deformation rate, pipeline material data and pipeline length data of the adjusted local pipeline segment, the height change, monitoring frequency and maintenance frequency of the adjusted local pipeline segment within the preset target time period are accurately determined, and the corresponding base control instructions, monitoring work orders and maintenance work orders are generated and sent to the corresponding platform, so as to realize the local pipeline segment The precise adjustment of the base equipment and the timely monitoring and maintenance of local pipeline sections can effectively avoid the hidden danger of excessive deformation of local pipelines, which is conducive to maintaining the safety of the gas pipeline network; (2) Based on the historical deformation rate and historical temperature difference data, the correlation information between temperature difference data and pipeline deformation rate can be accurately constructed. Then, for local pipeline sections, the corresponding first deformation rate can be quickly determined through the correlation information and temperature difference data; (3) Adjusting the opening of the gas speed regulating valve according to the second deformation rate can accurately control the gas flow rate and gas pressure in the local pipeline section, avoid serious deformation of the local pipeline section due to excessive temperature difference, pressure fluctuation or vibration, and reduce the risk of pipeline damage. Attached Figure Description

[0009] The present invention will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same reference numerals denote the same structures, wherein:

[0010] Figure 1 This is a schematic diagram of the platform structure of an IoT system for monitoring deformation of smart gas pipelines, as shown in some embodiments of this specification.

[0011] Figure 2 This is an exemplary flowchart of a smart gas pipeline deformation monitoring method according to some embodiments of this specification;

[0012] Figure 3 This is an exemplary schematic diagram illustrating the determination of a first deformation rate according to some embodiments of this specification;

[0013] Figure 4 This is an exemplary schematic diagram of a temperature difference prediction model according to some embodiments of this specification;

[0014] Figure 5 This is an exemplary schematic diagram illustrating the determination of a second deformation rate according to some embodiments of this specification. Detailed Implementation

[0015] The accompanying drawings used in the description of the embodiments will be briefly introduced below. The drawings do not represent all embodiments.

[0016] In the embodiments of the present invention, when describing the operations performed step by step, unless otherwise specified, the order of the steps is interchangeable, the steps can be omitted, and other steps may be included in the operation process.

[0017] Figure 1 This is a schematic diagram of the platform structure of an IoT system for monitoring deformation of smart gas pipelines, as shown in some embodiments of this specification.

[0018] In some embodiments, such as Figure 1 As shown, the intelligent gas pipeline deformation monitoring IoT system 100 may include a government gas supervision and management platform 110, a government gas supervision sensor network platform 120, a government gas supervision object platform 130, a gas company sensor network platform 140, a gas equipment object platform 150, and a gas maintenance object platform 160. The government gas supervision object platform 130 may include a gas company management platform 131.

[0019] The government gas regulatory management platform 110 refers to the platform on which the government regulates and manages gas, and can be configured as a processor and / or server and storage.

[0020] The processor can process data and / or information related to the smart gas pipeline deformation monitoring IoT system 100. In some embodiments, the processor may include one or more sub-processing devices. By way of example only, the processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or any combination thereof.

[0021] In some embodiments, the processor can interact with multiple platforms included in the smart gas pipeline deformation monitoring IoT system 100, or can be configured on multiple platforms.

[0022] In some embodiments, the government gas regulatory management platform 110 can communicate with the gas company management platform 131 through the government gas regulatory sensor network platform 120.

[0023] The government gas regulatory sensor network platform 120 refers to a platform for the government to supervise and manage gas-related sensor network information, and can be configured as communication equipment and gateways.

[0024] In some embodiments, the government gas regulatory sensor network platform 120 can be used for communication and interaction between the government gas regulatory management platform 110 and the gas company management platform 131.

[0025] The government gas regulatory platform 130 refers to the platform for generating sensing information and executing control information. In some embodiments, the government gas regulatory platform 130 may include a gas company management platform 131.

[0026] The gas company management platform 131 refers to a comprehensive management platform for relevant information of the gas company, which can be configured as a processor and / or server and storage.

[0027] In some embodiments, the gas company management platform 131 can be configured to: determine a local pipeline segment of a target pipeline, and a first deformation rate and a second deformation rate within a preset target time period; determine a target deformation rate of the local pipeline segment based on the first and second deformation rates; adjust the division method of the local pipeline segment based on the target deformation rate; determine the height change, monitoring frequency, and maintenance frequency of the adjusted local pipeline segment within the preset target time period based on the adjusted target deformation rate, pipeline material data, and pipeline length data; generate a base control command based on the height change and send it to the gas equipment object platform; generate a monitoring work order based on the monitoring frequency and send it to the gas maintenance object platform; and generate a maintenance work order based on the maintenance frequency and send it to the gas maintenance object platform. For more information on this part, please refer to [link to relevant documentation]. Figure 2 Related descriptions.

[0028] In some embodiments, the gas company management platform 131 is connected upward to the government gas regulatory management platform 110 via the government gas regulatory sensor network platform 120, and downward to the gas equipment object platform 150 and the gas maintenance object platform 160 via the gas company sensor network platform 140.

[0029] The gas company sensor network platform 140 refers to the comprehensive management platform for the gas company's sensor information, which can be configured as a communication network and gateway, etc. In some embodiments, the gas company sensor network platform 140 can be used for communication and interaction between the gas company management platform 131 and the gas equipment object platform 150 and the gas maintenance object platform 160.

[0030] The gas equipment platform 150 refers to a functional platform for real-time monitoring and intelligent control of gas pipeline networks. For example, the gas equipment platform 150 includes various sensors (temperature sensors, vibration sensors, etc.) installed inside the gas pipeline and base equipment installed outside the gas pipeline.

[0031] A base device refers to a support for a gas pipeline, deployed beneath each local pipeline section. The base device can be an electrically controlled device, such as a bracket containing an electromagnetic spring. In some embodiments, when the pipeline bends downwards, the height of the base device can be lowered to prevent compression of the pipeline; when the pipeline bends upwards, the height of the base device can be raised to provide support for the pipeline and effectively slow down further deformation.

[0032] The gas maintenance platform 160 refers to a platform for interaction with gas workers. Gas workers are personnel engaged in work related to gas pipeline networks, such as safety officers, maintenance workers, and storage and transportation workers. In some embodiments, the gas maintenance platform 160 includes at least one interactive device, such as a mobile phone or computer used by gas workers.

[0033] In some embodiments of this specification, the IoT system for monitoring deformation of smart gas pipelines can form a closed loop of information operation between various functional platforms and operate in a coordinated and regular manner under the unified management of the gas company's management platform, thereby realizing the informatization and intelligence of smart gas pipeline deformation monitoring.

[0034] Figure 2 This is an exemplary flowchart of a smart gas pipeline deformation monitoring method according to some embodiments of this specification. In some embodiments, process 200 can be implemented based on a smart gas pipeline deformation monitoring IoT system 100 and can be executed by a gas company management platform 131. For example, it can be executed by a processor in the gas company management platform 131. Figure 2 As shown, process 200 includes the following steps.

[0035] Step 210: Determine the first deformation rate and the second deformation rate of a local section of the target pipeline within a preset target time period.

[0036] The target pipeline refers to the gas pipeline whose deformation is to be predicted. For example, an open-air gas pipeline.

[0037] A local pipe segment refers to multiple pipe segments formed by dividing a target pipe into sections. In some embodiments, the division of local pipe segments can include various methods. For example, the processor can divide the target pipe into multiple local pipe segments of a preset length.

[0038] A preset target time period refers to a future time period from the current moment. For example, the next week or the next month after the current moment.

[0039] The first deformation rate refers to the rate of deformation of the pipeline under the influence of natural environmental factors. Environmental parameters related to pipeline deformation can include ambient temperature, humidity, and other factors related to the pipeline's location. These environmental parameters can be monitored and acquired by sensors deployed outside the gas pipeline.

[0040] The deformation rate can be represented by the ratio of the pipeline deformation to the preset target time period. The pipeline deformation can be characterized by the angle of the pipeline bending deformation, the length of the pipeline expansion and contraction deformation, etc.

[0041] The second deformation rate refers to the rate of deformation of the pipeline under the influence of gas transported inside. Gas parameters related to pipeline deformation can include gas flow rate, gas temperature, and gas pressure. These gas parameters can be monitored and acquired by sensors deployed inside the gas pipeline.

[0042] In some embodiments, the processor may determine the first deformation rate and the second deformation rate of a local pipe segment within a preset target time period in a variety of ways.

[0043] For example, the processor can obtain the first deformation rate of the local pipe segment during a preset target time period based on the current ambient temperature, ambient humidity, and pipe material data of the local pipe segment through the first vector database.

[0044] The pipe material data may include the pipe material and pipe wall thickness.

[0045] The first vector database may include multiple first feature vectors and corresponding first labels for the first feature vectors. The first feature vectors can be constructed from historical ambient temperature, historical ambient humidity, and historical pipe material data corresponding to a local pipe segment at a historical target time. The first label corresponding to the first feature vector can be the actual first deformation rate of the local pipe segment at the historical target time period.

[0046] The sample local pipeline segment can be any historical local pipeline segment of the historical target pipeline. The historical target time refers to the same historical time as the current time. The historical target time period refers to the historical time period that starts from the historical target time and has the same duration as the preset target time period.

[0047] The first label can be represented by the ratio of historical pipeline deformation obtained by manual measurement to the duration of the historical target period, and can be manually labeled.

[0048] The processor can construct a first target vector based on the ambient temperature, ambient humidity and pipe material data of a local pipe segment at the current moment, and determine one or more first feature vectors with a first similarity greater than a preset similarity threshold by searching the first vector database, calculate the mean of the first labels corresponding to the one or more first feature vectors, and determine the first deformation rate corresponding to the first target vector.

[0049] For example, the processor can obtain the second deformation rate of a local pipe segment during a preset target time period based on the gas flow rate, gas temperature, gas pressure, and pipe material data of the local pipe segment at the current moment through a second vector database.

[0050] The second vector database can include multiple second feature vectors and their corresponding second labels. The second feature vectors can be constructed from historical gas flow velocity, historical gas temperature, historical gas pressure, and historical pipe material data for a local pipe segment at a historical target time. The second label corresponding to the second feature vector can be the actual second deformation rate of the local pipe segment at the historical target time period. The method for obtaining the second label is similar to that of the first label.

[0051] The processor can construct a second target vector based on the gas flow rate, gas temperature, gas pressure, and pipe material data of a local pipe segment at the current moment, and obtain the second deformation rate by searching the second vector database. This process is similar to obtaining the first deformation rate by searching the first vector database, and will not be described in detail here.

[0052] In some embodiments, the processor can generate correlation information between temperature difference data and deformation rate based on historical deformation rate and historical temperature difference data of a local pipe segment of the target pipe; and determine a first deformation rate based on the average temperature difference data of the local pipe segment within a preset target time period and the correlation information. Further explanation of this part can be found in [link to relevant documentation]. Figure 3 Related descriptions.

[0053] In some embodiments, the processor may acquire monitoring data sequences and vibration data sequences of a local pipe segment; based on the monitoring data sequences and vibration data sequences, a second deformation rate is determined. Further details on this section can be found in [link to relevant documentation]. Figure 5 Related descriptions.

[0054] Step 220: Determine the target deformation rate of the local pipe segment based on the first deformation rate and the second deformation rate.

[0055] The target deformation rate refers to the estimated deformation rate of a local pipeline segment based on the combined effects of multiple factors.

[0056] In some embodiments, the processor can perform a weighted summation of the first deformation rate and the second deformation rate of the local pipe segment to obtain the target deformation rate of the local pipe segment.

[0057] In some embodiments, the weights of the first deformation rate and the second deformation rate can be preset manually based on experience.

[0058] In some embodiments, the processor can also determine the distribution of deformation sources in a local pipe segment based on vibration data sequences, elevation data, and topographic data; based on the deformation source distribution, determine the weights of a first deformation rate and a second deformation rate, and perform a weighted sum of the first and second deformation rates to determine the target deformation rate. Further details on this part can be found in [link to relevant documentation]. Figure 5 Related descriptions.

[0059] Step 230: Adjust the division method of local pipe segments based on the target deformation rate.

[0060] In some embodiments, for local pipe segments with a target deformation rate greater than a first preset threshold, the processor can further divide them, including but not limited to average division; for multiple consecutive local pipe segments with a target deformation rate not exceeding the first preset threshold, the processor can merge adjacent local pipe segments whose target deformation rate difference is less than a second preset threshold into one local pipe segment. The first and second preset thresholds can both be preset manually based on experience, with the first preset threshold being greater than the second preset threshold.

[0061] Step 240: Based on the target deformation rate, pipe material data, and pipe length data of the adjusted local pipe section, determine the height change, monitoring frequency, and maintenance frequency of the adjusted local pipe section within the preset target time period.

[0062] In some embodiments, for multiple re-divided and adjusted local pipe segments, the processor can recalculate the target deformation rate in accordance with steps 210-220.

[0063] Pipe length data refers to the length of a local pipe section.

[0064] The change in height can be represented by the difference in pipe height of a local pipe section within a preset target time period. If the pipe height increases, the change in height is recorded as a positive value. The pipe height can be represented by the height of the center point of the local pipe section above the ground.

[0065] Monitoring frequency refers to the frequency at which deformation monitoring is performed on local pipeline sections.

[0066] Maintenance frequency refers to the frequency of maintenance and inspection of a local section of pipeline.

[0067] In some embodiments, the gas company management platform can determine the height change, monitoring frequency, and maintenance frequency of the adjusted local pipeline segment within a preset target time period by querying a preset table, based on the target deformation rate, pipeline material data, and pipeline length data of the adjusted local pipeline segment.

[0068] The preset table can include the target deformation rate of a local pipe section, pipe material data, pipe length data, and the corresponding height change, monitoring frequency, and maintenance frequency of the local pipe section within a preset target time period. The preset table can be set by technicians based on experience.

[0069] Step 250: Generate base control instructions based on the height change and send them to the gas equipment object platform.

[0070] The base control commands may include adjusting the height of the base equipment based on changes in height.

[0071] In some embodiments, the processor can generate base control instructions based on the height variation and according to a preset control instruction template.

[0072] In some embodiments, the processor in the gas company's management platform can send base control commands to the gas equipment object platform through the gas company's sensor network platform, so that the base equipment can make adjustments according to the base control commands.

[0073] Step 260: Generate a monitoring work order based on the monitoring frequency and send it to the gas maintenance object platform.

[0074] A monitoring work order may include the local pipeline section to be monitored, the corresponding monitoring frequency, and the pipeline monitor.

[0075] In some embodiments, the processor can generate monitoring work orders based on the monitoring frequency and according to a preset monitoring work order template.

[0076] In some embodiments, the processor in the gas company's management platform can send monitoring work orders to the gas maintenance object platform through the gas company's sensor network platform, so that pipeline monitors can perform pipeline inspection and monitoring according to the monitoring work orders.

[0077] Step 270: Generate a maintenance work order based on the maintenance frequency and send it to the gas maintenance object platform.

[0078] A maintenance work order may include the local section of pipe to be repaired, the corresponding maintenance frequency, and the pipe repairman.

[0079] In some embodiments, the processor can generate maintenance work orders based on the maintenance frequency and according to a preset maintenance work order template.

[0080] In some embodiments, the processor in the gas company's management platform can send maintenance work orders to the gas maintenance object platform through the gas company's sensor network platform, so that pipeline maintenance workers can carry out pipeline maintenance according to the maintenance work orders.

[0081] In some embodiments of this specification, by estimating the deformation rate of a local pipeline segment due to various reasons, and then adjusting the division method of the local pipeline segment according to the deformation rate, the local pipeline segment with a high deformation rate can be controlled with finer granularity, thereby improving the control effect while saving computing resources. Based on the target deformation rate of the adjusted local pipeline segment, pipeline material data, and pipeline length data, the height change, monitoring frequency, and maintenance frequency of the adjusted local pipeline segment within a preset target time period are accurately determined, and corresponding base control instructions, monitoring work orders, and maintenance work orders are generated and sent to the corresponding platform. This enables precise adjustment of the base equipment of the local pipeline segment, as well as timely monitoring, adjustment, and maintenance of the local pipeline segment, effectively avoiding the hidden danger of excessive deformation of the local pipeline, and is conducive to maintaining the safety of the gas pipeline network.

[0082] Figure 3 This is an exemplary schematic diagram illustrating the determination of a first deformation rate according to some embodiments of this specification.

[0083] In some embodiments, such as Figure 3 As shown, the processor can generate correlation information between temperature difference data and deformation rate of the target pipeline based on historical deformation rate and historical temperature difference data of historical local pipeline segments of the target pipeline; for local pipeline segments of the target pipeline, the first deformation rate is determined based on the average temperature difference data and correlation information of the local pipeline segments within a preset target time period.

[0084] The historical local pipeline segment of the target pipeline refers to the local pipeline segment of the target pipeline in the historical deformation monitoring.

[0085] Historical deformation rate can be represented by the ratio of historical pipeline deformation of a local pipeline segment to the duration of the corresponding historical time period. The historical pipeline deformation and the corresponding historical time period can be obtained based on the target pipeline's historical deformation monitoring records.

[0086] Temperature difference data refers to the temperature difference between the outer walls of a pipe at both ends of a local pipe section. Historical temperature difference data for a historical time period can be represented by the average of the temperature difference data at the start and end of that historical time period. Historical temperature difference data can also be obtained based on the historical deformation monitoring records of the target pipe.

[0087] Correlation information refers to information reflecting the correspondence between temperature difference data and deformation rate. In some embodiments, correlation information can be represented by a curve. The horizontal axis of the correlation information curve can be the temperature difference data, and the vertical axis can be the deformation rate.

[0088] In some embodiments, for a target pipeline, the processor can construct a numerical point from historical deformation rate and historical temperature difference data corresponding to a historical local pipeline segment within a historical time period; sort multiple numerical points in ascending order according to historical temperature difference data; perform curve fitting on the numerical points; and use the fitted curve as the correlation information between temperature difference data and deformation rate. The curve fitting method can include fitting based on a fitting model (e.g., multinomial regression model, etc.) using a fitting algorithm (e.g., least squares method, etc.).

[0089] In some embodiments, the processor can find the corresponding first deformation rate based on the average temperature difference data of a local pipe segment within a preset target time period and according to the associated information.

[0090] The average temperature difference data of a local pipeline segment within a preset target time period can be represented by the average of the temperature difference data of the local pipeline segment at the beginning of the preset target time period and the temperature difference data at the end of the preset target time period.

[0091] In some embodiments, the processor can select one or more historical temperature difference data points corresponding to a historical target time period from historical temperature difference data, and determine the average temperature difference data of the local pipe segment within the preset target time period from the one or more historical temperature difference data points. More information about historical target time periods can be found at [link to relevant documentation]. Figure 2 The relevant description in step 210.

[0092] In some embodiments, the processor can obtain topographic data of a local pipeline segment based on the government's gas regulatory management platform; based on the current temperature difference data, elevation data and topographic data of the local pipeline segment, the processor can determine the average temperature difference data of the local pipeline segment within a preset target time period through a temperature difference prediction model, wherein the temperature difference prediction model is a machine learning model.

[0093] Geomorphological data can include soil type, vegetation type, vegetation quantity, building density, etc., around a local pipeline section. Geomorphological data can be represented in vector form.

[0094] In some embodiments, the gas company's management platform can directly retrieve topographic data of a local pipeline section from the government's gas regulatory management platform through the government's gas regulatory sensor network.

[0095] Current temperature difference data refers to the temperature difference of a local pipe section at the current moment. This data can be obtained by the processor based on monitoring data uploaded by temperature sensors installed at both ends of the local pipe section.

[0096] Elevation data refers to the altitude of a local pipeline section. Elevation data can be obtained by monitoring an altimeter installed on that section of the pipeline.

[0097] Figure 4 This is an exemplary schematic diagram of a temperature difference prediction model according to some embodiments of this specification.

[0098] In some embodiments, such as Figure 4 As shown, the processor can determine the average temperature difference of a local pipeline segment within a preset time period based on the current temperature difference data, elevation data 420, and topographic data of the local pipeline segment, using a temperature difference prediction model.

[0099] In some embodiments, the temperature difference prediction model can be a machine learning model, such as a neural network (NN).

[0100] In some embodiments, such as Figure 4 As shown, the input to the temperature difference prediction model can include the current temperature difference data, elevation data, and topographic data of a local pipeline segment, and the output of the temperature difference prediction model can be the average temperature difference data of the local pipeline segment within a preset time period.

[0101] In some embodiments, the temperature difference prediction model can be trained in a variety of ways. For example, a processor can train the temperature difference prediction model using multiple training samples with training labels.

[0102] In some embodiments, the training samples of the temperature difference prediction model may include base samples and augmented samples. The base samples include sample temperature difference data, sample elevation data, and sample topographic data of a sample local pipe segment. The augmented samples include historical temperature difference data, historical elevation data, and historical topographic data of the local pipe segment. The sample loss weight of the augmented samples in the loss function is greater than that of the base samples in the loss function.

[0103] The sample temperature difference data, sample elevation data, and sample topography data for a local pipeline segment refer to the historical temperature difference data, historical elevation data, and historical topography data for that local pipeline segment at the historical target time, respectively. The first training label corresponding to the base sample is the actual average temperature difference data of the local pipeline segment during the historical target time period. The first training label can be manually obtained and labeled based on historical data.

[0104] The augmented samples include historical temperature difference data, historical elevation data, and historical topographic data of a local pipe segment at a historical target time. The second training label corresponding to the augmented samples is the actual average temperature difference data of the local pipe segment during the historical target time period. The second training label can be obtained and labeled manually based on historical data.

[0105] The base sample corresponds to historical data of a local segment of any historical target pipeline. The enhanced sample corresponds to historical data of a local segment of the current target pipeline. For more information on sample local pipeline segments, historical target times, and historical target time periods, please refer to [link to relevant documentation]. Figure 2 The relevant description in step 210.

[0106] In some embodiments, the temperature difference prediction model can be obtained by training multiple base samples with a first training label. The processor can input multiple base samples with the first training label into the initial temperature difference prediction model, construct a loss function based on the output of the initial temperature difference prediction model and the first training label, and iteratively update the initial temperature difference prediction model based on the loss function. When a preset condition is met, the model training is complete, resulting in a trained temperature difference prediction model. The preset condition may be loss function convergence, the number of iterations reaching a threshold, etc. The iterative update method may include, but is not limited to, gradient descent.

[0107] In some embodiments, the temperature difference prediction model can also be obtained by training multiple augmented samples with second training labels and multiple base samples with first training labels together.

[0108] In some embodiments, when training a temperature difference prediction model using multiple augmented samples and multiple base samples, the sample loss weight of the augmented samples in the loss function is greater than that of the base samples in the loss function.

[0109] In some embodiments of this specification, the generalization ability of the temperature difference prediction model can be improved by training the model with augmented samples and base samples. In addition, by increasing the weight of the augmented samples, the temperature difference prediction model pays more attention to the data of local pipe segments of the target pipe during training, thereby improving the accuracy and reliability of the model.

[0110] In some embodiments, such as Figure 4 As shown, the input to the temperature difference prediction model also includes the vibration data sequence of local pipe sections.

[0111] The vibration data sequence can be composed of pipeline vibration data sampled at multiple historical sampling times prior to the current moment, arranged in chronological order. The pipeline vibration data can include vibration intensity, vibration frequency, etc., of a specific pipeline section. This data can be acquired by vibration sensors installed on the local pipeline section.

[0112] The historical period consisting of multiple historical sampling moments prior to the current moment is denoted as the target sampling period. That is, in the current deformation monitoring, the target sampling period is before the current moment, and the preset target period is after the current moment; in historical deformation monitoring, the historical sampling period is before the historical target moment, and the historical target period is after the historical target moment; the target sampling period corresponds to the historical sampling period, and the historical sampling period is the same historical period as the target sampling period.

[0113] In some embodiments, the base sample also includes a sequence of sample vibration data of a local pipe segment, and the enhancement sample also includes a sequence of historical vibration data of a local pipe segment for training the temperature difference prediction model.

[0114] In some embodiments of this specification, vibration of a local pipe section may cause minor deformation of the pipe, thereby affecting the temperature difference between the two ends of the pipe. By adding vibration data sequences as model input, the temperature difference prediction model can better capture the relationship between vibration data and deformation rate, making the model's prediction of temperature difference data more accurate.

[0115] In some embodiments, after the temperature difference prediction model has been trained for a preset number of rounds, the processor can adjust the learning rate of the temperature difference prediction model based on a decay factor. The preset number of rounds is determined based on the topographical and elevation differences between local pipe sections.

[0116] In some embodiments, the processor can calculate the vector distance between the topographic data of adjacent local pipe segments of the target pipe, and calculate the standard deviation of multiple vector distances, which is then determined as the topographic difference. The vector distance can be Euclidean distance, etc.

[0117] In some embodiments, the processor can calculate the standard deviation of the elevation data of all local pipe segments in the target pipe and determine it as the elevation difference.

[0118] In some embodiments, the processor can determine a preset number of rounds based on topographic and elevation differences between local pipe segments of the target pipeline. For example, the processor can perform a weighted summation of topographic and elevation differences to obtain the preset number of rounds.

[0119] In some embodiments, the attenuation factor can be in the range of 0 to 1 and can be set manually based on experience.

[0120] In some embodiments, after the temperature difference prediction model has been trained for a preset number of rounds, the processor can multiply the learning rate of the temperature difference prediction model by a decay factor and continue to train the temperature difference prediction model according to the adjusted learning rate.

[0121] In some embodiments of this specification, by multiplying the learning rate by a decay factor after a preset number of training rounds, the model can converge quickly in the early stages of training and finely adjust the parameters in small steps in the later stages of training. This effectively avoids oscillations or failure to converge during training, thereby improving the accuracy and stability of the temperature difference prediction model.

[0122] In some embodiments of this specification, based on the current temperature difference data, elevation data, and topographic data of a local pipeline segment, a trained temperature difference prediction model can be used to quickly and accurately predict future temperature difference changes. This is beneficial for identifying local pipeline segments with significant temperature differences in advance, so that appropriate measures can be taken in advance.

[0123] In some embodiments of this specification, based on historical deformation rate and historical temperature difference data, the correlation information between temperature difference data and pipeline deformation rate is accurately constructed. Thus, for a local pipeline segment, the corresponding first deformation rate can be quickly determined through the correlation information and temperature difference data.

[0124] Figure 5 This is an exemplary schematic diagram illustrating the determination of a second deformation rate according to some embodiments of this specification.

[0125] In some embodiments, such as Figure 5 As shown, the processor can acquire monitoring data sequences and vibration data sequences of a local pipe segment; based on the monitoring data sequences and vibration data sequences, it determines the second deformation rate.

[0126] The monitoring data sequence can be composed of pipeline gas data sampled at multiple historical sampling times prior to the current moment, arranged chronologically. This pipeline gas data may include gas temperature, gas flow rate, and gas pressure within a specific pipeline section. The pipeline gas data can be acquired by sensors installed inside the specific pipeline section. For more information on multiple historical sampling times prior to the current moment, please refer to [link to relevant documentation]. Figure 4 And its explanation.

[0127] In some embodiments, for the current local pipe segment, the processor can determine the second deformation rate through cluster analysis based on the monitoring data sequence and the vibration data sequence.

[0128] The processor can construct multiple clustering vectors based on multiple historical monitoring data sequences and historical vibration data sequences corresponding to multiple sample local pipe segments in multiple historical sampling periods, and mark the actual second deformation rate corresponding to the sample local pipe segment in the historical target period as the clustering label corresponding to the clustering vector.

[0129] The processor can construct a current vector based on the monitoring data sequence and vibration data sequence of the current local pipe segment; it can cluster multiple cluster vectors and the current vector to obtain multiple clusters, and determine the cluster containing the current vector as the target cluster; it can calculate the mean of the cluster labels corresponding to all cluster vectors in the target cluster, and determine this mean as the second deformation rate corresponding to the current local pipe segment. The clustering methods include, but are not limited to, the K-Means clustering algorithm.

[0130] In some embodiments of this specification, by combining monitoring data and vibration data, the operating status of the pipeline can be evaluated from multiple perspectives, making the prediction of the deformation rate of local pipeline sections more accurate.

[0131] In some embodiments, such as Figure 5 As shown, the processor can also determine the deformation source distribution of a local pipeline segment based on vibration data sequences, elevation data, and topographic data; based on the deformation source distribution, it determines the weight of the first deformation rate and the weight of the second deformation rate, and then calculates the weighted sum of the first deformation rate and the second deformation rate to determine the target deformation rate.

[0132] The distribution of deformation sources can include the degree of influence of environmental parameters and gas parameters on the deformation of local pipeline sections. More information on environmental parameters and gas parameters can be found in [link to relevant documentation]. Figure 2 The relevant description of step 210.

[0133] In some embodiments, the processor can construct multiple regression datasets based on multiple vibration data sequences of a sample local pipeline segment over multiple historical sampling periods, and elevation and geomorphological data at multiple historical target times; use the actual deformation rate of the sample local pipeline segment during the historical target periods as the regression label corresponding to the regression data; construct multiple regression equations based on the multiple regression datasets and their corresponding regression labels; use a regression algorithm to fit the weight coefficients corresponding to the vibration data sequences, elevation data, and geomorphological data of the local pipeline segment using the multiple regression equations; determine the degree of influence of gas parameters on the deformation of the local pipeline segment using the weight coefficients of the vibration data sequences; and determine the degree of influence of environmental parameters on the deformation of the local pipeline segment by summing the weight coefficients of the elevation data and geomorphological data. The regression algorithm may include, but is not limited to, linear regression, multinomial regression, and support vector regression.

[0134] For example, the regression equation is shown below:

[0135]

[0136] in,( , , ) is the first There are 1 regression data point, and the corresponding regression label is 1. ,Right now , , Representing the first Vibration data sequences, elevation data, and geomorphological data in the regression data; , and These represent the weighting coefficients for the vibration data sequence, elevation data, and geomorphological data, respectively. This represents the degree to which gas parameters affect the deformation of local pipeline sections. This represents the degree to which environmental parameters affect the deformation of a local pipeline section.

[0137] In some embodiments, the processor can determine the degree of influence of gas parameters on the deformation of a local pipeline segment as a weighting coefficient of the second deformation rate; determine the degree of influence of environmental parameters on the deformation of a local pipeline segment as a weighting coefficient of the first deformation rate; and weight the first deformation rate and the second deformation rate according to their respective weighting coefficients to obtain the target deformation rate.

[0138] In some embodiments of this specification, combining vibration data, elevation data, and topographic data helps to assess the degree of influence of different factors on pipeline deformation, identify the dominant factors in pipeline deformation, and thus accurately predict the target deformation rate of local pipeline segments.

[0139] In some embodiments, the processor can adjust the opening of the gas speed regulating valve in a local pipeline segment based on the second deformation rate.

[0140] The opening degree of a gas speed regulating valve refers to the degree to which a valve that regulates the gas flow rate within a local pipeline section is open, and can be expressed as a percentage from 0% to 100%.

[0141] In some embodiments, in response to a second deformation rate of a local pipe segment exceeding a third preset threshold, the processor may adjust and reduce the opening of the gas speed regulating valve to reduce the gas flow rate in the local pipe segment until the second deformation rate is less than the third preset threshold.

[0142] In some embodiments, the third preset threshold is negatively correlated with the vibration frequency in the pipe vibration data of a local pipe segment. More information on pipe vibration data can be found at [link to relevant documentation]. Figure 4 Related descriptions.

[0143] In some embodiments of this specification, adjusting the opening of the gas speed regulating valve according to the second deformation rate can accurately control the gas flow rate and gas pressure in a local pipeline section, avoiding severe deformation of the local pipeline section due to excessive temperature difference, pressure fluctuation or vibration, and reducing the risk of pipeline damage.

[0144] Some embodiments of this specification also provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the intelligent gas pipeline deformation monitoring method described in any of the above embodiments.

[0145] The embodiments described in this invention are merely illustrative and do not limit the scope of the invention. Various modifications and alterations that can be made by those skilled in the art under the guidance of this invention are still within its scope.

[0146] Furthermore, certain features, structures, or characteristics in one or more embodiments of the present invention can be appropriately combined.

[0147] If there is any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the appended materials of this invention and the content described in this invention, the descriptions, definitions, and / or terminology used in this invention shall prevail.

Claims

1. A smart gas pipeline deformation monitoring IoT system, characterized in that, The Internet of Things (IoT) system includes a government gas supervision and management platform, a government gas supervision object platform, a gas equipment object platform, and a gas maintenance object platform; The government's gas regulatory platform includes a gas company management platform; The gas company management platform is configured as follows: Determine the first deformation rate and the second deformation rate of a local section of the target pipeline within a preset target time period; the first deformation rate is the pipeline deformation rate under the influence of natural environmental factors, and the second deformation rate is the pipeline deformation rate under the influence of internal gas transportation. Based on the first deformation rate and the second deformation rate, the target deformation rate of the local pipe section is determined; Based on the target deformation rate, the division method of the local pipe segment is adjusted; Based on the target deformation rate, pipe material data, and pipe length data of the adjusted local pipe segment, the height change, monitoring frequency, and maintenance frequency of the adjusted local pipe segment within the preset target time period are determined. Based on the height change, a base control command is generated and sent to the gas equipment object platform; A monitoring work order is generated based on the monitoring frequency and sent to the gas maintenance object platform; A maintenance work order is generated based on the maintenance frequency and sent to the gas maintenance object platform.

2. The Internet of Things system according to claim 1, characterized in that, The gas company management platform is further configured as follows: Based on the historical deformation rate and historical temperature difference data of the target pipeline's local pipeline segments, the correlation information between the temperature difference data and deformation rate of the target pipeline is generated. For the local pipe segment of the target pipe, the first deformation rate is determined based on the average temperature difference data of the local pipe segment within the preset target time period and the associated information.

3. The Internet of Things system according to claim 2, characterized in that, The gas company management platform is further configured as follows: Based on the government's gas regulatory management platform, the topographic data of the local pipeline section is obtained; Based on the current temperature difference data, elevation data, and topographic data of the local pipeline segment, the average temperature difference data of the local pipeline segment within the preset target time period is determined by a temperature difference prediction model, wherein the temperature difference prediction model is a machine learning model.

4. The Internet of Things system according to claim 1, characterized in that, The gas company management platform is further configured as follows: Obtain the monitoring data sequence and vibration data sequence of the local pipeline section; The second deformation rate is determined based on the monitoring data sequence and the vibration data sequence.

5. The Internet of Things system according to claim 1, characterized in that, The Internet of Things system also includes a government gas regulatory sensor network platform and a gas company sensor network platform; The government gas regulatory management platform is connected to the gas company management platform through the government gas regulatory sensor network platform, and the gas equipment object platform and the gas maintenance object platform are connected to the gas company management platform through the gas company sensor network platform.

6. A method for monitoring deformation in intelligent gas pipeline networks, characterized in that, The method is based on a smart gas pipeline deformation monitoring Internet of Things (IoT) system. This IoT system includes a government gas regulatory management platform, a government gas regulatory sensor network platform, a government gas regulatory object platform, a gas company sensor network platform, a gas equipment object platform, and a gas maintenance object platform; the government gas regulatory object platform includes a gas company management platform. The method is executed by the gas company's management platform and includes: Determine the first deformation rate and the second deformation rate of a local section of the target pipeline within a preset target time period; the first deformation rate is the pipeline deformation rate under the influence of natural environmental factors, and the second deformation rate is the pipeline deformation rate under the influence of internal gas transportation. Based on the first deformation rate and the second deformation rate, the target deformation rate of the local pipe section is determined; Based on the target deformation rate, the division method of the local pipe segment is adjusted; Based on the target deformation rate, pipe material data, and pipe length data of the adjusted local pipe segment, the height change, monitoring frequency, and maintenance frequency of the adjusted local pipe segment within the preset target time period are determined. Based on the height change, a base control command is generated and sent to the gas equipment object platform; A monitoring work order is generated based on the monitoring frequency and sent to the gas maintenance object platform; A maintenance work order is generated based on the maintenance frequency and sent to the gas maintenance object platform.

7. The method according to claim 6, characterized in that, The determination of the first deformation rate and the second deformation rate of the local pipe segment of the target pipe within a preset target time period includes: Based on the historical deformation rate and historical temperature difference data of the target pipeline's local pipeline segments, the correlation information between the temperature difference data and deformation rate of the target pipeline is generated. For the local pipe segment of the target pipe, the first deformation rate is determined based on the average temperature difference data of the local pipe segment within the preset target time period and the associated information.

8. The method according to claim 7, characterized in that, The method further includes: Based on the government's gas regulatory management platform, the topographic data of the local pipeline section is obtained; Based on the current temperature difference data, elevation data, and topographic data of the local pipeline segment, the average temperature difference data of the local pipeline segment within the preset target time period is determined by a temperature difference prediction model, wherein the temperature difference prediction model is a machine learning model.

9. The method according to claim 6, characterized in that, The determination of the first deformation rate and the second deformation rate of a local pipe segment of the target pipe within a preset target time period also includes: acquiring the monitoring data sequence and vibration data sequence of the local pipe segment; The second deformation rate is determined based on the monitoring data sequence and the vibration data sequence.

10. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes the method as described in any one of claims 6 to 9.

Images