CN112032568A - Prediction algorithm and prediction method of leakage risk degree of buried gas pipeline - Google Patents

Abstract

The invention belongs to the technical field of gas pipeline maintenance, and in particular relates to an algorithm and a method for predicting the leakage risk of buried gas pipelines. The leakage risk prediction algorithm of buried gas pipelines includes: collecting data; The leakage risk model of buried gas pipeline is constructed by vector; according to the leakage risk model of buried gas pipeline and the parameters of the corresponding position on the buried gas pipeline, the leakage risk of the buried gas pipeline at the corresponding position can be obtained in real time; according to the buried gas pipeline leakage risk of the corresponding position A preventive maintenance strategy for pipeline leakage risk generation; the invention can overcome the shortcomings of strong subjectivity and randomness in the judgment and early warning of buried gas pipeline leakage risk based on monitoring data, and is beneficial to the detection of buried gas pipeline leakage accidents Carry out advance protection and predictive maintenance. Predictive maintenance has better economics and reduces the labor cost of buried gas pipeline maintenance.

Description

Prediction algorithm and prediction method of leakage risk degree of buried gas pipeline

technical field

The invention belongs to the technical field of gas pipeline maintenance, and in particular relates to a leakage risk prediction algorithm and a prediction method of a buried gas pipeline.

Background technique

Buried gas pipeline leakage cannot be found intuitively and obviously, especially when trace leakage occurs, it is not easy to find. When a leak occurs, a series of secondary disasters such as explosions are likely to occur, resulting in serious personal casualties and property losses. Buried pipelines are concealed projects with 24-hour uninterrupted operation. Routine inspections can only ensure "surface" safety, and the internal situation is poorly understood, resulting in insufficient information and difficult management. Ultrasonic real-time monitoring of gas pipeline data can only be used for overhead pipelines, and sufficient information cannot be obtained for buried pipelines.

At present, the commonly used detection methods for buried gas pipelines include manual inspection and intelligent inspection based on the Internet of Things technology. The post-event maintenance method uses buried gas pipelines until leakage occurs, and then repairs them. In case of serious leakage, it may cause huge losses.

Condition maintenance based on condition monitoring is currently being developed. According to the information provided by the measured values obtained by condition monitoring, experts use the knowledge and experience they have about buried pipelines to make inferences and judgments. maintenance recommendations. Due to the use of a large number of human interventions such as experts, this method has a large workload, high labor costs, and poor economy; at the same time, there are problems of strong subjectivity and large randomness.

Therefore, it is urgent to develop a new prediction algorithm and prediction method for the leakage risk of buried gas pipelines to solve the above problems.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide an algorithm and a method for predicting the leakage risk of buried gas pipelines.

In order to solve the above technical problems, the present invention provides an algorithm for predicting the leakage risk of buried gas pipelines, which includes: collecting data; establishing a corresponding vector according to the corresponding data; building a leakage risk model of the buried gas pipeline according to the corresponding vector; The leakage risk model of the underground gas pipeline and the parameters of the corresponding position on the buried gas pipeline are used to obtain the leakage risk of the buried gas pipeline in the corresponding position in real time; the preventive maintenance strategy is generated according to the leakage risk of the buried gas pipeline in the corresponding position.

所述PH值变化率为：

其中，F_0j为埋地燃气管道刚刚安装或确认管道状态为正常时的对应第j个节点的应力测量平均值，F_i为第i个记录的应力值，FR_i为第i个记录的应力变化率，PH_0j为埋地燃气管道刚刚安装或确认管道状态为正常时的对应第j个节点的PH值测量平均值，PH_i为第i个记录的PH值，PHR_i为第i个记录的PH值变化率。Further, the method for collecting data includes: collecting stress value and pH value, and calculating the stress change rate and pH value change rate according to the corresponding stress value and pH value, that is, the stress change rate is:

The rate of change of the pH value is:

Among them, F _0j is the average stress measurement of the corresponding jth node when the buried gas pipeline is just installed or the state of the pipeline is confirmed to be normal, F _i is the stress value of the ith record, and FR _i is the stress of the ith record. Rate of change, PH _0j is the measured average value of the pH value of the jth node when the buried gas pipeline is just installed or the state of the pipeline is confirmed to be normal, PH _i is the pH value of the i-th record, and PHR _i is the i-th record. rate of change in pH.

Further, the method for establishing a corresponding vector according to the corresponding data includes: quantifying the characteristic stress change rate FR _i , the pH value change rate PHR _i , the quantization interval is 0.1, and the use time of the buried gas pipeline is rounded by year.

S.ty_i(w.x_i+b)≥1-ξ_i；ξ_i≥0i＝1,2,......,N；其中，x⁽¹⁾为量化后的应力变化率，x⁽²⁾为量化后的PH值变化率，x⁽³⁾为量化后的燃气管道使用时间，向量w的分量是向量x相应分量的系数，C为惩罚系数；x_i为第i个训练数据向量；y_i为x_i的类标记，当y_i为-1时表示埋地燃气管道出现泄露，当y_i为1时表示埋地燃气管道状态正常；N为训练数据数目；ξ为松弛变量；ξ_i为第i个训练数据的松弛变量；b为偏置；则最优化模型的解为：w^*；

其中，w^*为最优分类超平面的法向量；

为拉格朗日乘子向量中对偶问题的解的第i个元素。Further, the method for establishing a corresponding vector according to the corresponding data further includes: establishing a data vector: x=(x ⁽¹⁾ , x ⁽²⁾ , x ⁽³⁾ ); establishing a coefficient vector: w=(w ⁽¹⁾ , w ⁽²⁾ , w ⁽³⁾ ); construct the optimal model, namely

S.ty _i (wx _i +b)≥1-ξ _i ; ξ _i ≥0i=1,2,...,N; where, x ⁽¹⁾ is the quantized stress change rate, x ^{( 2)} is the rate of change of PH value after quantization, x ⁽³⁾ is the use time of the gas pipeline after quantization, the component of vector w is the coefficient of the corresponding component of vector x, C is the penalty coefficient; x _i is the ith training data vector ; y _i is the class label of _xi , when y _i is -1, it means that the buried gas pipeline leaks, and when y _i is 1, it means that the buried gas pipeline is in normal state; N is the number of training data; ξ is the slack variable; ξ _i is the slack variable of the i-th training data; b is the bias; the solution of the optimal model is: w ^* ;

Among them, w ^* is the normal vector of the optimal classification hyperplane;

is the ith element of the solution to the dual problem in the vector of Lagrangian multipliers.

其中，N_A为类别y＝1的样本数；N_B为类别y＝-1的样本数；μ_B为出现埋地燃气管道泄露数据在w^*向量轴投影后所得到的数据的均值；μ_A为埋地燃气管道状态正常数据在w^*向量轴投影后所得到的数据的均值；δ_A为埋地燃气管道状态正常数据在w^*向量轴投影后所得到的数据的标准差；δ_B为出现埋地燃气管道泄露数据在w^*向量轴投影后所得到的数据的标准差；

Further, the method for constructing the leakage risk model of buried gas pipelines according to the corresponding vectors includes: obtaining data obtained by projecting stress values and PH values on the normal vector, and the occurrence of buried gas pipeline leakage and the state of buried gas pipelines. The mean and variance of two normal data categories, namely

Among them, NA is the number of samples of category y ₌ 1; _{NB is the number of samples of category y=-1; μ B is} the mean value of the data obtained after the data of buried gas pipeline leakage is projected on the w ^* vector axis; μ _A is the mean value of the data obtained after the normal data of the buried gas pipeline state is projected on the w ^* vector axis; δ _A is the standard deviation of the data obtained after the normal data of the buried gas pipeline state is projected on the w ^* vector axis; δ _B The standard deviation of the data obtained after the projection of the buried gas pipeline leakage data on the w ^* vector axis;

其中，H(Z_C|Z_A)为在给定Z_A条件下，Z_C的条件熵；H(μ_B|Z_A)为在给定Z_A条件下，μ_B的条件熵；埋地燃气管道危险度V越小表示埋地燃气管道泄露概率越小，埋地燃气管道危险度V越大表示埋地燃气管道泄露概率越大。Further, according to the buried gas pipeline leakage risk model and the parameters of the corresponding position on the buried gas pipeline, the method for obtaining the leakage risk of the buried gas pipeline in the corresponding position in real time includes: setting x _A to be all samples of y=1 The sum of data, Z _A is the projection of x _A on the w ^* vector axis, and the current data is set as x _c , that is, Zc = w ^* x _c ; when wx _c ≤ μ _A + δ _A , the buried gas pipeline hazard V is 0; when wx _c ≥μ _B -δ _B , the risk degree V of buried gas pipeline is 1; when μ _A +δ _A ≤wx _c ≤μ _B -δ _B , the risk degree V of buried gas pipeline is:

Among them, H(Z _C | Z _A ) is the conditional entropy of Z _C under the given Z _A condition; H(μ _B | Z _A ) is the conditional entropy of μ _B under the given Z _A condition; The smaller the risk degree V of the gas pipeline is, the smaller the leakage probability of the buried gas pipeline is, and the higher the risk degree V of the buried gas pipeline is, the greater the leakage probability of the buried gas pipeline is.

Further, the method for generating the preventive maintenance strategy according to the leakage risk degree of the buried gas pipeline at the corresponding location includes: controlling the inspection time interval according to the risk degree of the buried gas pipeline, that is, T=VT ₁ +(1-V)T ₀ ; T is the inspection time interval that should be used for the current buried gas pipeline under the current risk degree V, T ₀ is the reference inspection time interval for the current buried gas pipeline when the risk degree V is 0, and T ₁ is the current buried gas pipeline. The gas pipeline is the reference inspection time interval when the risk degree V is 1.

In another aspect, the present invention provides a method for predicting the leakage risk of buried gas pipelines, which includes: collecting data and sending it to a cloud server and/or a processor module; the cloud server and/or the processor module determine the buried gas according to the data Pipeline hazard.

Further, the cloud server and/or the processor module are suitable for judging the risk degree of the buried gas pipeline by adopting the above-mentioned prediction algorithm for the leakage risk degree of the buried gas pipeline.

The beneficial effect of the present invention is that the present invention can overcome the shortcomings of strong subjectivity and randomness in the judgment and early warning of the leakage risk of buried gas pipelines manually based on monitoring data, and is conducive to early prevention of leakage accidents of buried gas pipelines And predictive maintenance, compared with post-event maintenance, predictive maintenance has better economics, while reducing the labor cost of buried gas pipeline maintenance.

Other features and advantages of the present invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention.

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below, and are described in detail as follows in conjunction with the accompanying drawings.

Description of drawings

In order to illustrate the specific embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

Fig. 1 is the flow chart of the buried gas pipeline leakage risk degree prediction algorithm of the present invention;

FIG. 2 is a flow chart of the method for predicting the leakage risk of buried gas pipelines according to the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. example. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Example 1

FIG. 1 is a flow chart of the leakage risk prediction algorithm of the buried gas pipeline according to the present invention.

In this embodiment, as shown in FIG. 1 , this embodiment provides an algorithm for predicting the leakage risk of buried gas pipelines, which includes: collecting data; establishing corresponding vectors according to corresponding data; building buried gas pipelines according to corresponding vectors Leakage risk model; according to the leakage risk model of buried gas pipeline and the parameters of the corresponding position on the buried gas pipeline, the leakage risk of the buried gas pipeline at the corresponding location can be obtained in real time; the leakage risk of the buried gas pipeline at the corresponding location can be generated to prevent Sexual maintenance strategy.

In this embodiment, this embodiment can overcome the shortcomings of strong subjectivity and randomness in the manual judgment and early warning of buried gas pipeline leakage based on monitoring data, and is conducive to early prevention of buried gas pipeline leakage accidents And predictive maintenance, compared with post-event maintenance, predictive maintenance has better economics, while reducing the labor cost of buried gas pipeline maintenance.

所述PH值变化率为：

其中，F_0j为埋地燃气管道刚刚安装或确认管道状态为正常时的对应第j个节点的应力测量平均值，F_i为第i个记录的应力值，FR_i为第i个记录的应力变化率，PH_0j为埋地燃气管道刚刚安装或确认管道状态为正常时的对应第j个节点的PH值测量平均值，PH_i为第i个记录的PH值，PHR_i为第i个记录的PH值变化率。In this embodiment, the method for collecting data includes: collecting stress value and pH value, and calculating the stress change rate and pH value change rate according to the corresponding stress value and pH value, that is, the stress change rate is:

The rate of change of the pH value is:

Among them, F _0j is the average stress measurement of the corresponding jth node when the buried gas pipeline is just installed or the state of the pipeline is confirmed to be normal, F _i is the stress value of the ith record, and FR _i is the stress of the ith record. Rate of change, PH _0j is the measured average value of the pH value of the jth node when the buried gas pipeline is just installed or the state of the pipeline is confirmed to be normal, PH _i is the pH value of the i-th record, and PHR _i is the i-th record. rate of change in pH.

In this embodiment, the method for establishing a corresponding vector according to the corresponding data includes: quantifying the characteristic stress change rate FR _i , the pH value change rate PHR _i , the quantization interval is 0.1, and the use time of the buried gas pipeline is determined by year all.

S.ty_i(w.x_i+b)≥1-ξ_i；ξ_i≥0i＝1,2,......,N；其中，x⁽¹⁾为量化后的应力变化率，x⁽²⁾为量化后的PH值变化率，x⁽³⁾为量化后的燃气管道使用时间，向量w的分量是向量x相应分量的系数，C为惩罚系数；x_i为第i个训练数据向量；y_i为x_i的类标记，当y_i为-1时表示埋地燃气管道出现泄露，当y_i为1时表示埋地燃气管道状态正常；N为训练数据数目；ξ为松弛变量；ξ_i为第i个训练数据的松弛变量；b为偏置；则最优化模型的解为：w^*；

其中，w^*为最优分类超平面的法向量；

为拉格朗日乘子向量中对偶问题的解的第i个元素。In this embodiment, the method for establishing a corresponding vector according to the corresponding data further includes: establishing a data vector: x=(x ⁽¹⁾ , x ⁽²⁾ , x ⁽³⁾ ); establishing a coefficient vector: w=(w ⁽¹⁾ , w ⁽²⁾ , w ⁽³⁾ ); build an optimization model, that is

S.ty _i (wx _i +b)≥1-ξ _i ; ξ _i ≥0i=1,2,...,N; where, x ⁽¹⁾ is the quantized stress change rate, x ^{( 2)} is the rate of change of PH value after quantization, x ⁽³⁾ is the use time of the gas pipeline after quantization, the component of vector w is the coefficient of the corresponding component of vector x, C is the penalty coefficient; x _i is the ith training data vector ; y _i is the class label of _xi , when y _i is -1, it means that the buried gas pipeline leaks, and when y _i is 1, it means that the buried gas pipeline is in normal state; N is the number of training data; ξ is the slack variable; ξ _i is the slack variable of the i-th training data; b is the bias; the solution of the optimal model is: w ^* ;

Among them, w ^* is the normal vector of the optimal classification hyperplane;

is the ith element of the solution to the dual problem in the vector of Lagrangian multipliers.

In this embodiment, the method for constructing a leakage risk model of a buried gas pipeline according to a corresponding vector includes: obtaining the data obtained by projecting the stress value and the PH value on the normal vector, and the occurrence of leakage and buried gas pipeline leakage in the buried gas pipeline. The mean and variance of the two data categories in the normal state of the ground gas pipeline, namely

其中，N_A为类别y＝1的样本数；N_B为类别y＝-1的样本数；μ_B为出现埋地燃气管道泄露数据在w^*向量轴投影后所得到的数据的均值；μ_A为埋地燃气管道状态正常数据在w^*向量轴投影后所得到的数据的均值；δ_A为埋地燃气管道状态正常数据在w^*向量轴投影后所得到的数据的标准差；δ_B为出现埋地燃气管道泄露数据在w^*向量轴投影后所得到的数据的标准差；

Among them, NA is the number of samples of category y ₌ 1; _{NB is the number of samples of category y=-1; μ B is} the mean value of the data obtained after the data of buried gas pipeline leakage is projected on the w ^* vector axis; μ _A is the mean value of the data obtained after the normal data of the buried gas pipeline state is projected on the w ^* vector axis; δ _A is the standard deviation of the data obtained after the normal data of the buried gas pipeline state is projected on the w ^* vector axis; δ _B The standard deviation of the data obtained after the projection of the buried gas pipeline leakage data on the w ^* vector axis;

其中，H(Z_C|Z_A)为在给定Z_A条件下，Z_C的条件熵；H(μ_B|Z_A)为在给定Z_A条件下，μ_B的条件熵；埋地燃气管道危险度V越小表示埋地燃气管道泄露概率越小，埋地燃气管道危险度V越大表示埋地燃气管道泄露概率越大。In this embodiment, the method for obtaining the leakage risk degree of the buried gas pipeline at the corresponding position in real time according to the leakage risk model of the buried gas pipeline and the parameters of the corresponding position on the buried gas pipeline includes: setting x _A as all y = 1 sum of sample data, Z _A is the projection of x _A on the w ^* vector axis, set the current data to be x _c , that is, Zc = w ^* x _c ; when wx _c ≤ μ _A + δ _A , the buried gas pipeline The risk degree V is 0; when wx _c ≥ μ _B -δ _B , the buried gas pipeline risk degree V is 1; when μ _A +δ _A ≤wx _c ≤μ _B -δ _B , the buried gas pipeline risk degree V is:

Among them, H(Z _C | Z _A ) is the conditional entropy of Z _C under the given Z _A condition; H(μ _B | Z _A ) is the conditional entropy of μ _B under the given Z _A condition; The smaller the risk degree V of the gas pipeline is, the smaller the leakage probability of the buried gas pipeline is, and the higher the risk degree V of the buried gas pipeline is, the greater the leakage probability of the buried gas pipeline is.

In this embodiment, the risk V of the buried gas pipeline is a number ranging from 0 to 1. The closer to 0, the lower the risk, and the closer to 1, the greater the risk. The user can perform preventive maintenance according to the risk. .

In this embodiment, the method for generating a preventive maintenance strategy according to the leakage risk degree of buried gas pipelines at a corresponding location includes: controlling the inspection time interval according to the risk degree of buried gas pipelines, that is, T=VT ₁ +(1-V ) T ₀ ; T is the inspection time interval that the current buried gas pipeline should adopt under the current risk degree V, T ₀ is the reference inspection time interval when the risk degree V is 0 for the current buried gas pipeline, and T ₁ is For the current buried gas pipeline, it is the benchmark inspection time interval when the risk degree V is 1.

In this embodiment, when the risk degree V>γ, an early warning is activated and a comprehensive inspection is performed. γ is the early warning threshold, and the range is 0.3-0.4. The user can choose the threshold setting within this range. The above warning threshold is in a reasonable range, which is a good compromise between avoiding false alarms and avoiding false alarms.

Example 2

FIG. 2 is a flow chart of the method for predicting the leakage risk of buried gas pipelines according to the present invention.

On the basis of Embodiment 1, as shown in FIG. 2 , this embodiment provides a method for predicting leakage risk of buried gas pipelines, which includes: collecting data and sending it to a cloud server and/or a processor module; the cloud server and /or the processor module judges the danger of the buried gas pipeline according to the data.

In this embodiment, the cloud server and/or the processor module are adapted to use the buried gas pipeline leakage risk prediction algorithm as provided in Embodiment 1 to determine the buried gas pipeline risk.

To sum up, the present invention can overcome the shortcomings of strong subjectivity and randomness in the manual judgment and early warning of buried gas pipeline leakage based on monitoring data, and is conducive to early protection and prediction of buried gas pipeline leakage accidents. Compared with post-event maintenance, predictive maintenance is more economical, and at the same time reduces the labor cost of buried gas pipeline maintenance.

In the several embodiments provided in this application, it should be understood that the disclosed system and method can also be implemented in other manners. The system embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the Figures illustrate the architecture, functionality, and possible implementations of systems, methods and computer program products according to various embodiments of the present invention. operate. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

In addition, each functional module in each embodiment of the present invention may be integrated to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

Taking the above ideal embodiments according to the present invention as inspiration, and through the above description, relevant personnel can make various changes and modifications without departing from the technical idea of the present invention. The technical scope of the present invention is not limited to the content in the specification, and the technical scope must be determined according to the scope of the claims.

Claims (9)

1. a buried gas pipeline leakage risk prediction algorithm, is characterized in that, comprises: Data collection; Create a corresponding vector according to the corresponding data; Build the leakage risk model of buried gas pipelines according to the corresponding vectors; According to the leakage risk model of the buried gas pipeline and the parameters of the corresponding position on the buried gas pipeline, the leakage risk of the buried gas pipeline at the corresponding position can be obtained in real time; Generate preventive maintenance strategies based on the leakage risk of buried gas pipelines at corresponding locations. 2. The buried gas pipeline leakage risk prediction algorithm according to claim 1, characterized in that, The method for collecting data includes: Collect the stress value and pH value, and calculate the stress change rate and pH value change rate according to the corresponding stress value and pH value, namely The rate of change of the stress is:

The rate of change of the pH value is:

Among them, F _0j is the average stress measurement of the corresponding jth node when the buried gas pipeline is just installed or the state of the pipeline is confirmed to be normal, F _i is the stress value of the ith record, and FR _i is the stress of the ith record. Rate of change, PH _0j is the measured average value of the pH value of the jth node when the buried gas pipeline is just installed or the state of the pipeline is confirmed to be normal, PH _i is the pH value of the i-th record, and PHR _i is the i-th record. rate of change in pH. 3. The buried gas pipeline leakage risk prediction algorithm according to claim 2, characterized in that, The method for establishing a corresponding vector according to the corresponding data includes: The characteristic stress change rate FR _i and the PH value change rate PHR _i are quantified, and the quantification interval is 0.1, and the use time of the buried gas pipeline is rounded according to the year. 4. The buried gas pipeline leakage risk prediction algorithm according to claim 3, characterized in that, The method for establishing a corresponding vector according to the corresponding data also includes: Create a data vector: x=(x ⁽¹⁾ , x ⁽²⁾ , x ⁽³⁾ ); Establish coefficient vector: w = (w ⁽¹⁾ , w ⁽²⁾ , w ⁽³⁾ ); Build the optimal model, that is

St y _i (wx _i +b)≥1-ξ _i ; ξ _i ≥ 0 i=1,2,...,N; Among them, x ⁽¹⁾ is the quantized stress change rate, x ⁽²⁾ is the quantized PH value change rate, x ⁽³⁾ is the quantized gas pipeline service time, and the component of the vector w is the corresponding component of the vector x. coefficient, C is the penalty coefficient; _xi is the ith training data vector; _yi is the class label of _xi , when _yi is -1, it means that the buried gas pipeline leaks, and when _yi is 1, it means buried The gas pipeline is in normal state; N is the number of training data; ξ is the slack variable; ξ _i is the slack variable of the i-th training data; b is the bias; Then the solution of the optimal model is: w ^* ;

Among them, w ^* is the normal vector of the optimal classification hyperplane;

is the ith element of the solution to the dual problem in the vector of Lagrangian multipliers. 5. The buried gas pipeline leakage risk prediction algorithm according to claim 4, characterized in that, The method for constructing a leakage risk model of buried gas pipelines according to corresponding vectors includes: Obtain the data obtained by projecting the stress value and PH value on the normal vector, and the mean and variance of the two data categories of leakage of buried gas pipeline and normal state of buried gas pipeline, namely

Among them, NA is the number of samples of category y ₌ 1; _{NB is the number of samples of category y=-1; μ B is} the mean value of the data obtained after the data of buried gas pipeline leakage is projected on the w ^* vector axis; μ _A is the mean value of the data obtained after the normal data of the buried gas pipeline state is projected on the w ^* vector axis; δ _A is the standard deviation of the data obtained after the normal data of the buried gas pipeline state is projected on the w ^* vector axis; δ _B The standard deviation of the data obtained after the projection of the buried gas pipeline leakage data on the w ^* vector axis;

6. The buried gas pipeline leakage risk prediction algorithm according to claim 5, characterized in that, The method for obtaining the leakage risk degree of the buried gas pipeline at the corresponding position in real time according to the leakage risk model of the buried gas pipeline and the parameters of the corresponding position on the buried gas pipeline includes: Let x _A be the sum of all y=1 sample data, Z _A is the projection of x _A on the w ^* vector axis, and let the current data be x _c , that is Zc=w ^* _xc ; When wx _c ≤μ _A +δ _A , the risk degree V of buried gas pipeline is 0; When wx _c ≥ μ _B -δ _B , the risk degree V of buried gas pipeline is 1; When μ _A +δ _A ≤wx _c ≤μ _B -δ _B , the risk degree V of buried gas pipeline is:

Among them, H(Z _C |Z _A ) is the conditional entropy of Z _C under the condition of given Z _A ; H(μ _B |Z _A ) is the conditional entropy of μ _B under a given Z _A condition; The smaller the risk degree V of the buried gas pipeline is, the lower the leakage probability of the buried gas pipeline is, and the higher the risk degree V of the buried gas pipeline is, the greater the leakage probability of the buried gas pipeline is. 7. The buried gas pipeline leakage risk prediction algorithm according to claim 6, characterized in that, The method for generating a preventive maintenance strategy according to the leakage risk of a buried gas pipeline at a corresponding location includes: The inspection time interval is controlled according to the risk degree of the buried gas pipeline, namely T=VT ₁ +(1-V)T ₀ ; T is the inspection time interval that should be used for the current buried gas pipeline under the current risk degree V, T ₀ is the reference inspection time interval for the current buried gas pipeline when the risk degree V is 0, and T ₁ is the current buried gas pipeline. The gas pipeline is the reference inspection time interval when the risk degree V is 1. 8. A method for predicting the leakage risk of buried gas pipelines, comprising: Collect data and send to cloud server and/or processor module; The cloud server and/or the processor module judges the danger level of the buried gas pipeline according to the data. 9. The method for predicting leakage risk of buried gas pipelines according to claim 8, wherein, The cloud server and/or the processor module are suitable for judging the risk degree of the buried gas pipeline by adopting the leakage risk degree prediction algorithm of the buried gas pipeline according to any one of claims 1-7.

Images