Heat distribution pipeline safety risk assessment method, system, equipment and program

Abstract

The invention discloses a heat distribution pipeline safety risk assessment method, system, device and program, and relates to the technical field of risk assessment, and the method comprises the steps: obtaining heat distribution pipeline data; the heat distribution pipeline data comprises static data and time sequence data of a heat distribution pipeline; wherein the time sequence data comprises mechanical vibration data; preprocessing the heat distribution pipeline data; feature extraction is carried out based on the preprocessed heat distribution pipeline data, and static data features and time series data features are obtained; inputting the static data features and the time series data features into a machine learning fusion model, and outputting a risk probability; calculating vibration fatigue damage based on the mechanical vibration data characteristics; performing risk correction on the risk probability based on the vibration fatigue damage to obtain a corrected risk probability; and determining a risk level based on the corrected risk probability. Through the processing scheme disclosed by the invention, the real risk state of the pipeline can be reflected, and the risk level can be accurately evaluated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of risk assessment, in particular to a heat pipe safety risk assessment method, system, device and program. BACKGROUND

[0002] With the rapid development of urban heating industry in China, the heat industry involves heat source production, pipeline transportation, heat user supply and other links, and each link has potential safety risks. Especially, as an important urban infrastructure, the operation safety of heat pipe is directly related to the life of residents, public safety and social stability. Once a failure accident occurs, it may cause heat leakage, personnel scalding, equipment damage and even secondary disasters, which will have a serious impact on society.

[0003] In recent years, safety accidents caused by aging, corrosion and external damage of heat pipes have occurred from time to time, such as heat loss caused by pipe rupture and damage to surrounding facilities, which makes the safety of heat pipes face more and more severe challenges. Therefore, it is imperative to strengthen the safety risk assessment of urban heat pipes, which is of great significance to ensure the safe and stable operation of urban heating systems.

[0004] The existing technology has obvious limitations in heat pipe risk assessment, mainly in the following aspects: First, the evaluation dimension is single and difficult to fully reflect the risk. Traditional methods focus on static characteristics (such as material, service life) or single dynamic parameters (such as pressure), ignoring the correlation between static inherent properties and dynamic operating state.

[0005] Second, the model adaptability is insufficient, and the time sequence correlation capturing ability is weak. The existing technology often uses models such as logistic regression and static decision tree, which are difficult to handle the time dependence of time series data such as temperature and vibration.

[0006] Third, the weight mechanism is rigid and lacks dynamic adaptability. Most fusion models use fixed weights and do not consider the difference in working condition fluctuations. When the pipe vibration is severe, it will still be calculated according to the fixed weight, which will underestimate the proportion of dynamic risk and cause early warning lag.

[0007] Fourth, the key risk sources are not fully covered, and the mechanical vibration factor is ignored. Traditional evaluation focuses on temperature and pressure, and pays insufficient attention to mechanical impact parameters such as vibration acceleration. Vibration caused by loose supports and unbalanced equipment is often an important inducement for pipe fatigue cracking, resulting in blind spots in risk tracing.

[0008] It can be seen that the existing heat pipe risk assessment method has obvious disadvantages and needs to be further improved. How to create a new heat pipe risk assessment method has become the goal of the current industry improvement. SUMMARY

[0009] Therefore, the embodiment of the present disclosure provides a heat pipe safety risk assessment method, which at least partially solves the problems in the prior art.

[0010] In a first aspect, the embodiment of the present disclosure provides a heat pipe safety risk assessment method, which comprises the following steps: Obtaining heat pipe data; the heat pipe data comprises static data and time series data of the heat pipe; wherein the time series data comprises mechanical vibration data; Pretreating the heat pipe data; Extracting features based on the pretreated heat pipe data to obtain static data features and time series data features; Inputting the static data features and the time series data features into a machine learning fusion model to output a risk probability; Calculating vibration fatigue damage based on the mechanical vibration data features; Risk correcting the risk probability based on the vibration fatigue damage to obtain a corrected risk probability; Determining a risk level based on the corrected risk probability.

[0011] According to a specific implementation manner of the embodiment of the present disclosure, the pretreating the heat pipe data comprises filling missing values, removing outliers and standardizing the heat pipe data; The method further comprises: Verifying the authenticity of the static data; Aligning the time series data; Performing signal smoothing on the mechanical vibration data.

[0012] According to a specific implementation manner of the embodiment of the present disclosure, the extracting features based on the pretreated heat pipe data to obtain static data features and time series data features comprises: Extracting static data features, comprising: Using the standardized values of the pretreated static data as the static data features; Calculating the coupling features of the heat pipe material and the service life based on the following formula: ; Wherein, is the coupling features of the heat pipe material and the service life; is the standardized value of the yield strength of the pipe material; is the standardized value of the service life of the pipe; and 0.5 is the attenuation coefficient; Extracting time series data features, comprising: Calculating vibration-fault correlation features based on the following formula: ; wherein, is a vibration-failure correlation feature; is the number of fatigue cracks of similar pipelines in the past 3 years; is the average vibration fatigue damage of the pipeline in the past 30 days; is the fatigue damage threshold.

[0013] According to a specific implementation manner of the embodiment of the present disclosure, the method further comprises: establishing an LSTM model and an XGBoost model; inputting the time series data features into the LSTM model to output a first probability value ; inputting the static data features into the XGBoost model to output a second probability ; fusing the first probability and the second probability based on the following formula: ; wherein, is a fusion probability; is an LSTM model weight, is an XGBoost model weight, and ; is an LSTM model probability; is an XGBoost model probability.

[0014] According to a specific implementation manner of the embodiment of the present disclosure, the method further comprises: optimizing the weights α and β through cross-validation. The method of optimizing the weights α and β through cross-validation comprises: selecting pipeline sample historical data containing known failure and normal labels; dividing the sample historical data into a training set and a validation set; calculating different weights corresponding fusion probabilities , and selecting the α and β that make the prediction accuracy the highest as initial weights.

[0015] According to a specific implementation manner of the embodiment of the present disclosure, the method of calculating the vibration fatigue damage based on the mechanical vibration data features comprises: calculating the vibration fatigue damage based on the following formula: ; wherein, vibration fatigue damage; vibration load level number; vibration level sequence number; vibration fatigue damage; cycle number of vibration at the level; vibration fatigue damage; material fatigue life corresponding to vibration at the level; The material fatigue life is calculated based on the following formula : ; wherein, is the material symmetric cyclic fatigue limit; is the material fatigue index, which can be obtained by consulting industry standards; vibration fatigue damage; stress amplitude corresponding to vibration at the level.

[0016] According to a specific implementation manner of the embodiment of the present disclosure, the risk probability is corrected based on the vibration fatigue damage, to obtain a corrected risk probability, which comprises: when the vibration fatigue damage , the risk correction is performed based on the following formula: ; wherein, is the corrected risk probability; is the risk probability; is the vibration correction coefficient, ; The vibration correction coefficient is calculated based on the following formula : ; wherein, is the vibration fatigue damage; when the vibration fatigue damage , the vibration correction coefficient , .

[0017] In a second aspect, the embodiment of the present disclosure provides a heat pipe safety risk assessment system, which comprises: a data acquisition module configured to acquire heat pipe data; the heat pipe data comprises static data and time series data of the heat pipe; wherein the time series data comprises mechanical vibration data; a preprocessing module configured to preprocess the heat pipe data; a feature extraction module configured to perform feature extraction based on the preprocessed heat pipe data, to obtain static data features and time series data features; The machine learning module is configured to input static data features and time series data features into a machine learning fusion model, output a risk probability, calculate a vibration fatigue damage based on the mechanical vibration data features, and correct the risk probability based on the vibration fatigue damage to obtain a corrected risk probability. The risk judgment module is configured to determine a risk level based on the corrected risk probability.

[0018] In a third aspect, the embodiments of the present disclosure further provide an electronic device, which comprises: at least one processor; and a memory in communication with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, cause the at least one processor to perform the heat pipe safety risk assessment method in the first aspect or any implementation manner of the first aspect.

[0019] In a fourth aspect, the embodiments of the present disclosure further provide a non-transitory computer-readable storage medium storing computer instructions, which, when executed by at least one processor, cause the at least one processor to perform the heat pipe safety risk assessment method in the first aspect or any implementation manner of the first aspect.

[0020] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product, which comprises a computer program stored on a non-transitory computer-readable storage medium, and the computer program comprises program instructions, which, when executed by a computer, cause the computer to perform the heat pipe safety risk assessment method in the first aspect or any implementation manner of the first aspect.

[0021] The heat pipe safety risk assessment method in the embodiments of the present disclosure comprehensively reflects the real risk state of the pipe through multi-dimensional risk assessment fusion. The XGBoost model is adapted to static features to accurately capture the cumulative effects of long-term aging and material decay. The LSTM model is good at processing time series data to effectively identify short-term dynamic risks such as temperature sudden change, pressure fluctuation, and vibration anomaly. The two types of models cooperate to improve the assessment accuracy. Through feature extraction such as vibration acceleration, frequency, and amplitude, the forward-looking of risk early warning is improved, and an intuitive risk probability is output, which facilitates the operation and maintenance personnel to quickly locate the risk source, take measures in advance, reduce the accident rate, and provide strong support for the safety operation and maintenance of the heat pipe. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 A heat pipe safety risk assessment method flowchart is provided for the embodiments of the present disclosure. Figure 2 A flow chart of a heat pipe safety risk assessment method provided by an embodiment of the present disclosure is shown in FIG. 1. Figure 3 A structural schematic diagram of a heat pipe safety risk assessment system provided by an embodiment of the present disclosure is shown in FIG. 2. Figure 4 A schematic diagram of an electronic device provided by an embodiment of the present disclosure is shown in FIG. 3. DETAILED DESCRIPTION

[0023] The embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0024] The above and other aspects of the present disclosure will become more apparent by describing in detail embodiments thereof with reference to the attached drawings in which:

[0025] It should be noted that aspects described herein can be embodied in a wide variety of forms and that any specific structure and / or function described herein is merely illustrative and not restrictive. Based on the disclosure provided herein, one skilled in the art should appreciate that an aspect described herein can be implemented independent of any other aspects, and that two or more aspects can be combined in any suitable manner. Further, the aspects can be implemented using other structures and / or functionalities in addition to or other than those described herein.

[0026] In addition, in the following description, specific details are given to provide a thorough understanding of examples. However, one skilled in the relevant art will understand that the aspects described herein can be practiced without

[0027] Figure 1 A schematic diagram of a heat pipe safety risk assessment method provided by an embodiment of the present disclosure is shown in FIG. 1.

[0028] Figure 2 A structural schematic diagram of a heat pipe safety risk assessment system provided by an embodiment of the present disclosure is shown in FIG. 2. Figure 1 A flow chart of a heat pipe safety risk assessment method provided by an embodiment of the present disclosure is shown in FIG. 1.

[0029] As shown in FIG. 1, the heat pipe safety risk assessment method provided by the embodiment of the present disclosure includes the following steps: Figure 1As shown, at step S110, heat pipe data is acquired; the heat pipe data includes static data and time series data of the heat pipe.

[0030] More specifically, the static data includes: nominal diameter, design wall thickness, actual residual wall thickness, material yield strength and service life of the heat pipe; the time series data includes: real-time temperature of the medium in the heat pipe, real-time pressure of the medium, soil corrosion rate and mechanical vibration data, the mechanical vibration data includes: instantaneous vibration acceleration, vibration frequency and vibration amplitude of the outer wall of the pipe.

[0031] The heat pipe data further includes: the number of cracks generated by vibration of the pipe with the same material and working condition in the past three years.

[0032] The specific information of the collected data is shown in Table 1.

[0033] Table 1: Heat pipe data

[0034] The specific acquisition method of the heat pipe data can include sensor collection, manual collection, data query and table research, etc., and is not the focus of the present application, and will not be described here.

[0035] In the embodiment of the present application, the acquired data further includes other data necessary for calculation, which is not limited here.

[0036] More specifically, next turn to step S120.

[0037] At step S120, the heat pipe data is preprocessed.

[0038] In the embodiment of the present application, preprocessing the heat pipe data includes: filling missing values, removing outliers and standardizing the heat pipe data; the method further includes: verifying the authenticity of the static data; aligning the time series data; and performing signal smoothing processing on the mechanical vibration data.

[0039] More specifically, the missing value filling includes: the missing value filling of the time series data uses forward filling, that is, using the valid observation value at the previous time of the missing value to fill the current missing value; the static data uses the mean value of the same type of pipe, and when there is no same batch data, the recommended value of the industry standard is used.

[0040] The outlier removal includes: removing outliers based on the 3σ criterion for time series data and static data.

[0041] The standardization processing includes: Parameters positively correlated with risk (i.e. the greater the value, the lower the risk), such as the design wall thickness of the heat pipe, the actual residual wall thickness, and the yield strength of the material, are standardized based on the following formula:

[0042] wherein, is the standardized value; is the actual value of the parameter, is the industry safety lower limit of the parameter; is the industry safety upper limit of the parameter; and can be obtained by consulting industry standard documents.

[0043] Parameters negatively correlated with risk (i.e. the greater the value, the higher the risk), such as the service life of the heat pipe, the real-time temperature of the medium, the real-time pressure of the medium, the soil corrosion rate, the instantaneous vibration acceleration of the pipe outer wall, the vibration frequency and amplitude, and the historical failure, are standardized based on the following formula:

[0044] wherein, is the standardized value; is the actual value of the parameter, is the industry safety lower limit of the parameter; is the industry safety upper limit of the parameter; and can be obtained by consulting industry standard documents.

[0045] Static data is a property inherent to the pipe, and if there is an input error, it can easily lead to misjudgment of the material's resistance to risk.

[0046] Therefore, it is necessary to verify the authenticity of the static data, which specifically includes: cross-comparing the collected static data with the pipe design drawings, factory reports, and historical detection records. When the deviation of the pipe nominal diameter from the design drawing is more than ±5mm, it is considered a authenticity error, and the sample needs to be re-sampled; when the deviation of the yield strength of the material from the factory report is more than ±10MPa, it is considered a authenticity error, and the sample needs to be re-sampled; when the actual residual wall thickness is greater than 0.5mm / year compared with the last detection value, it is considered a authenticity error, and the sample needs to be re-sampled, and the detection equipment precision needs to be reviewed.

[0047] Machine learning models need to unify time series data with the same time granularity, and time axis misalignment can lead to feature-time matching errors.

[0048] Therefore, it is necessary to align the time series data, which specifically includes the following steps: The high-frequency data (medium real-time temperature, medium real-time pressure) is down-sampled according to the hourly average, and is aligned with the time axis of the low-frequency data (soil corrosion rate); The entire time series data is divided into continuous and non-overlapping time windows in units of hours, and each window corresponds to 1 hour; all sampling values in a single window are extracted; The hourly average of each window is calculated as the down-sampled characteristic value.

[0049] The hourly average of the data is calculated according to the following formula:

[0050] Among them, is the average value of the data in the i-th hour window; is the sampling frequency of 1 hour; is all the sampling values of the data in the time window; is the serial number of the sampling; in the present application, the data sampling frequency for calculating the hourly average is higher than 1 time per hour.

[0051] The mechanical vibration data is subjected to signal smoothing processing, including: the mechanical vibration data is subjected to signal smoothing processing by a five-point sliding average method.

[0052] Next, go to step S130.

[0053] At step S130, feature extraction is performed based on the preprocessed heat pipe data to obtain static data features and time series data features.

[0054] In the embodiments of the present application, the feature extraction based on the preprocessed heat pipe data to obtain static data features and time series data features includes: Static data feature extraction includes: The standardized value of the preprocessed static data is used as the static data feature; The coupling feature of the heat pipe material and the service life is calculated based on the following formula: ; Among them, is the coupling feature of the heat pipe material and the service life; is the standardized value of the yield strength of the pipe material; is the standardized value of the pipe service life; 0.5 is the attenuation coefficient, which is obtained according to experience; Time series data feature extraction includes: The vibration-fault correlation feature is calculated based on the following formula: ; Among them,​ is a vibration-failure correlation feature; is the number of fatigue cracks of the same type of pipeline in the past 3 years, which is obtained by statistical historical data; is the average vibration fatigue damage of the pipeline in the past 30 days; is a fatigue damage threshold. Taking 3 years as the fatigue life benchmark, the contribution degree of the vibration damage intensity in the past 30 days to the vibration-failure correlation is the damage benchmark, realizing the scale connection of long-term fatigue life and short-term damage statistics.

[0055] is the coupling relationship between the damage rate and the failure time scale, and a fatigue damage threshold is introduced, when = fatigue damage threshold, the contribution of vibration fatigue to failure enters the significant correlation interval, which is used as a benchmark to measure the vibration-failure correlation strength of different pipelines. Experts in the field refer to API 579-1 / ASME FFS-1 “Fitness for Service”, ASME B31.8S “Gas Pipeline System Integrity Management” and other standards to determine that the 5 months before the pipeline accumulates to the critical damage state due to vibration fatigue is the critical point at which vibration fatigue has a significant driving effect on failure. That is, , the benchmark value is 0.2.

[0056] Next, go to step S140.

[0057] At step S140, the static data features and the time series data features are input into a machine learning fusion model to output a risk probability.

[0058] In the embodiment of the present application, the static data features and the time series data features are input into a machine learning fusion model to output a risk probability, which includes: establishing an LSTM model and an XGBoost model; inputting the time series data features into the LSTM model to output a first probability value ; inputting the static data features into the XGBoost model to output a second probability ; and fusing the first probability and the second probability based on the following formula:

[0059] wherein, is the fusion probability; is the LSTM model weight, is the XGBoost model weight, and ; is the LSTM model probability; is the XGBoost model probability.

[0060] ​More specifically, the single LSTM model cannot effectively handle static features (such as wall thickness does not change over time), and the single XGBoost model cannot handle time series fluctuations (such as instantaneous peak values of vibration); the fusion model can take into account both types of features, and the weighting weight can adapt to the intensity of time series fluctuations, improving the accuracy of risk probability calculation.

[0061] The model architecture is established, specifically including the following steps: 1. Establishing LSTM model and XGBoost model.

[0062] The LSTM model includes an input layer, an LSTM layer, a fully connected layer, and an output layer.

[0063] The input layer is 288x3, that is, each input sample contains 288 consecutive time point data (corresponding to 24 hours, with 1 sample collected every 5 minutes), and each time step contains 3 features: standardized value of medium temperature, standardized value of medium pressure, and standardized value of mechanical vibration acceleration; The LSTM layer has 64 neurons, and the dropout is set to 0.2 to prevent overfitting.

[0064] The fully connected layer has 32 neurons, which compresses the feature dimension from 64 to 32, simplifying subsequent calculations; The output layer has a sigmoid activation function, and the output probability is , which represents the probability of pipeline failure within the next 1 hour. When the output value is closer to 1, it indicates that the model has a higher confidence in judging "risk occurrence", and when it is closer to 0, it indicates that the confidence in "low risk" is higher.

[0065] 2. XGBoost model hyperparameter settings: learning rate set to 0.1, tree depth set to 3, estimators set to 100, and loss function set to log loss; Input static features (remaining wall thickness standardized value, material yield strength standardized value, service life standardized value, vibration-failure correlation feature, material-year coupling feature) into the XGBoost model, and output static risk probability .

[0066] Among them, the vibration-failure correlation feature belongs to static features. Static features refer to features that change slowly and do not fluctuate frequently over time, usually reflecting the inherent properties or long-term cumulative state of the pipeline. is the average vibration fatigue damage of this pipeline in the past 30 days, although it is based on 30-day data, but its statistical period is "month", which is much lower than real-time dynamic data (such as second-level vibration acceleration), and is a static summary of monthly vibration damage, rather than real-time fluctuation values. is a long-term quantitative correlation of vibration fatigue accumulation and failure occurrence, which will not change frequently with the vibration fluctuation of hours, days, and has the stability of static characteristics.

[0067] 3. Single static risk or dynamic risk cannot comprehensively evaluate the safety of the pipeline, for example: the pipeline with excellent static properties ( =0.2) but severe real-time vibration ( =0.8) may have a high actual risk; the pipeline with poor static properties ( =0.8) but stable real-time operation ( =0.2) may have a lower short-term risk.

[0068] Therefore, the outputs of the LSTM model and the XGBoost model need to be fused based on the following formula:

[0069] wherein, is the fusion probability; is the LSTM model weight, is the XGBoost model weight, and ; is the LSTM model probability; is the XGBoost model probability.

[0070] The weights α and β are optimized by cross-validation, including the following steps: Select the pipeline sample historical data containing known failure and normal labels; Divide the sample historical data into a training set and a validation set (7:3); Test the fusion probability corresponding to different α (0.1~0.9) , calculate the accuracy rate of the fusion probability and the actual label; Select the α and β that make the prediction accuracy the highest as the initial weights.

[0071] The accuracy rate of and the actual label is calculated based on the following method:

[0072] wherein, is the prediction accuracy; is the actual failure and predicted failure; is the actual normal and predicted normal; is the actual normal but predicted failure; is the actual failure but predicted normal.

[0073] Cross-validation can avoid the bias of subjective weight setting, ensure that the fusion result is optimal in historical data, and provide a benchmark for subsequent dynamic adjustment.

[0074] The weights α and β are dynamically adjusted, specifically including the following steps: When the standard deviation of the time sequence feature fluctuates more than 0.3, the influence of real-time running fluctuations (such as sudden temperature rise, pressure pulse, vibration impact) on the current risk is more significant, and the weight is increased (increased by 0.1); . When the standard deviation of the time sequence feature does not fluctuate more than 0.3, the pipeline operation is stable, and the long-term influence of static inherent properties (such as wall thickness, material aging) is more critical, and the weight is increased (increased by 0.1). .

[0075] 4. Train and verify the model: Collect 1000 pieces of heat pipe data (including 200 pieces of fault data), and divide them into training set, verification set and test set according to the ratio of 7:2:1; Train the machine learning fusion model based on the training set; Verify the machine learning fusion model based on the verification set, and when the prediction accuracy (P) of the test set is ≥0.92 and the F1 score is ≥0.9, the verification is passed. .

[0076] Test the machine learning fusion model based on the test set.

[0077] Calculate the F1 score based on the following method:

[0078] Wherein, is the proportion of actual faults in predicted faults, . is the proportion of correctly predicted actual faults in actual faults, .

[0079] Next, go to step S150.

[0080] At step S150, the vibration fatigue damage is calculated based on the mechanical vibration data features.

[0081] In the embodiment of the application, the vibration fatigue damage is calculated based on the mechanical vibration data features, including: The vibration fatigue damage is calculated based on the following formula:

[0082] Wherein, is the vibration fatigue damage; For the number of vibration load categories, the vibration load level is divided based on industry standards and vibration acceleration amplitude range, for example, less than 5 m / s 2 is classified as level one, between 5-15 m / s 2 is rated as level two, and greater than 15 m / s 2 is rated as level three. is the vibration load index. is the actual number of times of the first category vibration load; is the fatigue limit number corresponding to the first category vibration load. The material fatigue life is calculated based on the following formula :

[0083] wherein, is the material symmetric cycle fatigue limit, which can be obtained by consulting industry standards, for example, Q235 steel MPa; is the material fatigue index, which can be obtained by consulting industry standards; is the stress amplitude of the first vibration load.

[0084] Next, go to step S160.

[0085] At step S160, the risk probability is risk-corrected based on the vibration fatigue damage, to obtain a corrected risk probability.

[0086] More specifically, when the vibration fatigue damage is greater than 0, the risk correction is based on the following formula:

[0087] wherein, is the corrected risk probability; is the risk probability; is the vibration correction coefficient, . The vibration correction coefficient is calculated based on the following formula :

[0088] wherein, is the vibration fatigue damage.

[0089] When the vibration fatigue damage is less than 0, the vibration correction coefficient , .

[0090] The machine learning output is The vibration fatigue damage is not quantified separately, and the pipeline with high vibration damage has higher actual risk under the same P, The long-term damage of vibration on the pipeline can be accurately reflected, The deviation can be corrected, and the vibration risk can be avoided from being underestimated.

[0091] Next, go to step S170.

[0092] At step S170, the risk level is determined based on the corrected risk probability.

[0093] More specifically, the risk level determination is based on the preset risk level threshold, when the low risk is determined; when the medium risk is determined; when the high risk is determined; and when the extremely high risk is determined.

[0094] In the embodiment of the present application, the method further comprises: When the low risk is determined, the vibration acceleration is detected once a month, and the data is recorded; When the medium risk is determined, the rubber shock absorber is installed at the connection between the pump group and the pipeline; When the high risk is determined, the vibration section pipeline is replaced by a thick-walled pipeline, and a shock absorber is installed; When the extremely high risk is determined, the vibration section pipeline is shut down urgently, replaced by a fatigue-resistant material, and operated after re-pressurization.

[0095] The new fault data is supplemented to the training set, and the machine learning model is retrained and the threshold is optimized every quarter.

[0096] The safety risk assessment method for heat supply pipelines provided by the present application comprehensively reflects the real risk state of the pipeline through multi-dimensional risk assessment fusion. Through the XGBoost model adapting to static characteristics, the cumulative effects of long-term aging and material decay are accurately captured. Through the LSTM model which is good at processing time series data, short-term dynamic risks such as temperature sudden change, pressure fluctuation and vibration anomaly are effectively identified. The two types of models cooperate to improve the evaluation accuracy. Through the extraction of vibration acceleration, frequency and amplitude and other characteristics, the forward-looking of risk early warning is improved, and the intuitive risk probability is output, which is convenient for operation and maintenance personnel to quickly locate the risk source, take measures in advance, reduce the accident rate, and provide strong support for the safety operation and maintenance of heat supply pipelines.

[0097] Figure 3 The safety risk assessment system 300 for heat supply pipelines provided by the present application is shown, which comprises a data acquisition module 310, a preprocessing module 320, a feature extraction module 330, a machine learning module 340 and a risk judgment module 350.

[0098] The data acquisition module 310 is configured to acquire heat pipe data; the heat pipe data comprises static data and time series data of a heat pipe; and the time series data comprises mechanical vibration data. The preprocessing module 320 is configured to preprocess the heat pipe data. The feature extraction module 330 is configured to perform feature extraction based on the preprocessed heat pipe data, to obtain static data features and time series data features. The machine learning module 340 is configured to input the static data features and the time series data features into a machine learning fusion model, to output a risk probability; calculate a vibration fatigue damage based on the mechanical vibration data features; and perform risk correction on the risk probability based on the vibration fatigue damage, to obtain a corrected risk probability. The risk judgment module 350 is configured to determine a risk level based on the corrected risk probability.

[0099] Referring to Figure 4 The present disclosure also provides an electronic device 40, which comprises: at least one processor; and a memory in communication connection with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the heat pipe safety risk assessment method in the foregoing method embodiments.

[0100] The present disclosure also provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the heat pipe safety risk assessment method in the foregoing method embodiments.

[0101] The present disclosure also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the heat pipe safety risk assessment method in the foregoing method embodiments.

[0102] Reference is made below to Figure 4 which shows a structural schematic diagram of an electronic device 40 suitable for implementing the embodiments of the present disclosure. The electronic device in the embodiments of the present disclosure can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet PCs), PMPs (Portable Multimedia Players), vehicle terminals (such as vehicle navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 4The electronic device shown is merely one example, and should not be taken as limiting the scope of functionality or use of embodiments of the disclosure.

[0103] As Figure 4 shown, the electronic device 40 can include a processing device (e.g., a central processor, a graphics processor, etc.) 401 that can perform various suitable actions and processes according to programs stored in a read-only memory (ROM) 402 or loaded into a random access memory (RAM) 403 from a storage device 408. Various programs and data required for operation of the electronic device 40 are also stored in the RAM 403. The processing device 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0104] In general, the following devices can be connected to the I / O interface 405: input devices 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 408 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 409. The communication devices 409 can allow the electronic device 40 to communicate wirelessly or wired with other devices to exchange data. While the electronic device 40 is shown with various devices, it should be understood that not all of the shown devices are required to be implemented or present. More or fewer devices can alternatively be implemented or present.

[0105] In particular, according to embodiments of the disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the disclosure include a computer program product comprising a computer program carrying computer program code for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication devices 409, or installed from the storage devices 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the methods of embodiments of the disclosure are performed.

[0106] It should be noted that the computer-readable medium in the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer-readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the computer-readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, a RF (radio frequency) or the like, or any suitable combination of the above.

[0107] The computer-readable medium described above can be contained in the electronic device described above; or can exist separately and not be assembled into the electronic device.

[0108] The computer-readable medium described above carries one or more programs, when the one or more programs are executed by the electronic device, the electronic device is caused to: obtain at least two Internet protocol addresses; send a node evaluation request including the at least two Internet protocol addresses to a node evaluation device, wherein the node evaluation device selects an Internet protocol address from the at least two Internet protocol addresses and returns; receive the Internet protocol address returned by the node evaluation device; wherein the obtained Internet protocol address indicates an edge node in a content distribution network.

[0109] Alternatively, the computer readable medium described above carries one or more programs, which when executed by the electronic device, cause the electronic device to: receive a node evaluation request comprising at least two internet protocol addresses; select an internet protocol address from the at least two internet protocol addresses; and return the selected internet protocol address; wherein the received internet protocol address indicates an edge node in a content distribution network.

[0110] Computer program code for carrying out operations of the present disclosure can be written in any one or more of a variety of programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as the "C" programming language or similar programming languages. The program code may

[0111] The flow diagrams and the block diagrams in the drawings are meant as possible implementations of systems, methods, and computer program products according to the present disclosure. In this regard, each block in the flow diagrams and the block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0112] The units described in the embodiments of the present disclosure can be implemented by means of software, or by means of hardware. Among them, the name of the unit does not constitute a limitation to the unit itself in some cases. For example, the first acquisition unit can also be described as "a unit for acquiring at least two internet protocol addresses".

[0113] It should be understood that parts of the present disclosure can be implemented by hardware, software, firmware, or a combination thereof.

[0114] The above description is merely that of a specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present disclosure, and such changes or replacements should be covered within the protection scope of the present disclosure.

Claims

1. A heat pipe safety risk assessment method, characterized by, The method comprises the following steps: acquiring heat pipe data; the heat pipe data comprises static data and time series data of the heat pipe; wherein the time series data comprises mechanical vibration data; preprocessing the heat pipe data; extracting features based on the preprocessed heat pipe data to obtain static data features and time series data features; inputting the static data features and the time series data features into a machine learning fusion model to output a risk probability; calculating a vibration fatigue damage based on the mechanical vibration data features; risk correcting the risk probability based on the vibration fatigue damage to obtain a corrected risk probability; judging a risk level based on the corrected risk probability.

2. The heat line safety risk assessment method according to claim 1, wherein The preprocessing of the heat pipe data comprises missing value filling, abnormal value elimination and standardization processing of the heat pipe data; The method further comprises: conducting a reality test on the static data; aligning the time series data; conducting signal smoothing processing on the mechanical vibration data.

3. The heat line safety risk assessment method according to claim 1, wherein The feature extraction based on the preprocessed heat pipe data to obtain static data features and time series data features comprises: extracting static data features, comprising: using the standardized values of the preprocessed static data as the static data features; calculating a coupling feature of the heat pipe material and the service life based on the following formula: ； wherein, is the coupling characteristic of the heat pipe material and the service life; is the normalized value of the yield strength of the pipe material; is the normalized value of the service life of the pipe; and 0.5 is the attenuation coefficient. extracting time series data features, comprising: calculating a vibration-fault correlation feature based on the following formula: ； wherein, is a vibration-failure correlation feature; is the number of fatigue cracks in similar pipelines in the last 3 years; is the average vibration fatigue damage of the pipeline in the last 30 days; is the fatigue damage threshold.

4. The heat line safety risk assessment method according to claim 1, wherein, The inputting of the static data features and the time series data features into the machine learning fusion model to output a risk probability comprises: establishing an LSTM model and an XGBoost model; inputting the time series data features into an LSTM model, outputting a first probability value ; inputting the static data features into an XGBoost model, outputting a second probability ; The first probability is fused with the second probability based on the following equation: and the second probability is fused: ； wherein, is the fusion probability; is the LSTM model weight, is the XGBoost model weight, and ; is the LSTM model probability; is the XGBoost model probability.

5. The heat line safety risk assessment method according to claim 4, wherein The method further comprises optimizing the weights α and β through cross-validation; The optimization of the weights α and β through cross-validation comprises: selecting pipe sample historical data containing known faults and normal labels; dividing the sample historical data into a training set and a validation set; Computing different weights Corresponding fusion probability Select the α, β that make the prediction accuracy highest as the initial weights.

6. The heat line safety risk assessment method according to claim 1, wherein, The calculation of a vibration fatigue damage based on the mechanical vibration data features comprises: calculating the vibration fatigue damage based on the following formula: ； wherein, is the vibration fatigue damage; is the vibration load rank number; is the rank vibration sequence number; is the first is the cycle number of rank vibration for 24 hours; is the first is the material fatigue life corresponding to the rank vibration; The material fatigue life is calculated based on the following equation : ； wherein, is the material symmetrical cycle fatigue limit; is the material fatigue index, which can be obtained by consulting industry standards; is the first is the stress amplitude corresponding to the vibration of the first grade.

7. The heat line safety risk assessment method according to claim 1, wherein, The risk correction of the risk probability based on the vibration fatigue damage to obtain a corrected risk probability comprises: When the vibration fatigue damage is corrected for risk based on the following formula: ； wherein, is the modified risk probability; is the risk probability; is the vibration correction coefficient, ; The vibration correction coefficient is calculated based on the following equation : ； wherein is the vibrational fatigue damage; when the vibration fatigue damage vibration correction coefficient , .

8. A heat pipe safety risk assessment system, characterized by, The system comprises: a data acquisition module configured to acquire heat pipe data; the heat pipe data comprises static data and time series data of the heat pipe; wherein the time series data comprises mechanical vibration data; a preprocessing module configured to preprocess the heat pipe data; a feature extraction module configured to extract features based on the preprocessed heat pipe data to obtain static data features and time series data features; a machine learning module configured to input the static data features and the time series data features into a machine learning fusion model to output a risk probability; calculate a vibration fatigue damage based on the mechanical vibration data features; and risk correct the risk probability based on the vibration fatigue damage to obtain a corrected risk probability; a risk judgment module configured to judge a risk level based on the corrected risk probability.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein The memory stores instructions capable of being executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the heat pipe safety risk assessment method according to any one of claims 1 to 7.

10. A computer program product, characterised in that, The computer program product comprises a computer program stored on a non-transitory computer readable storage medium, and the computer program comprises program instructions, and the program instructions, when executed by a computer, enable the computer to perform the heat pipe safety risk assessment method according to any one of claims 1 to 7.

Images