Gas supply reliability detection method and device for natural gas pipeline network based on cross entropy theory

Abstract

A method and device for detecting the reliability of gas supply of a natural gas pipeline network based on the cross entropy theory, the method comprising: obtaining user demand prediction and user classification results according to the demand side analysis of the target natural gas pipeline network; performing reliability evaluation on a preset area of ​​the target natural gas pipeline network according to a historical failure database to obtain input data for system state transition simulation; simulating the state transition process of the target natural gas pipeline network through a temporal Monte Carlo method based on the cross entropy according to the input data to obtain a temporal state transition sequence; obtaining the gas supply of the target natural gas pipeline network after the state transition according to the gas usage characteristics of the users contained in each demand point and the calculation results of the temporal state transition sequence; and obtaining gas supply reliability detection data of the target natural gas pipeline network according to the user demand prediction results and the gas supply analysis.

Description

Technical Field

[0001] The present invention relates to the field of natural gas pipeline network maintenance, and in particular to a natural gas pipeline network gas supply reliability detection method and device based on cross entropy theory. Background Art

[0002] The random process simulation of the system operating state and the calculation of gas supply under various operating states are the key to the study of gas supply reliability of natural gas pipeline networks. Sequential Monte Carlo simulation is often used to simulate system state transitions in system reliability evaluation because it can provide unbiased estimates of system reliability indicators that are closely related to time. However, the huge state space of the natural gas pipeline network, the time-varying nonlinear operating state changes, and the large time lag and nonlinear system characteristics determine that the traditional sequential Monte Carlo method has a speed bottleneck in solving the gas supply reliability of the natural gas pipeline network. For the calculation of the gas supply volume of the pipeline network, the maximum flow method, steady-state hydraulic simulation, and offline hydraulic database are mainly used, but none of them fully consider the fluctuation characteristics of natural gas demand and the influence of user importance.

[0003] Based on this, this study proposed a large-scale and complex natural gas pipeline network gas supply reliability detection method and device based on cross entropy theory to make up for the shortcomings of existing research. Summary of the invention

[0004] The present invention aims to provide a method and device for detecting the gas supply reliability of a natural gas pipeline network based on the cross entropy theory, so as to effectively evaluate and detect the reliability of the natural gas pipeline network.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for detecting the gas supply reliability of a natural gas pipeline network based on the cross-entropy theory, the method comprising: obtaining user demand prediction and user classification results according to the demand-side analysis of the target natural gas pipeline network; performing reliability evaluation on a preset area of ​​the target natural gas pipeline network according to a historical failure database to obtain input data for a system state transition simulation; simulating the state transition process of the target natural gas pipeline network according to the input data by a temporal Monte Carlo method based on the cross-entropy to obtain a temporal state transition sequence; obtaining the gas supply of the target natural gas pipeline network after the state transfer according to the gas usage characteristics of the users contained in each demand point and the calculation results of the temporal state transition sequence; and obtaining gas supply reliability detection data of the target natural gas pipeline network according to the results of the user demand prediction, the user classification results and the gas supply analysis.

[0006] In the above-mentioned natural gas pipeline network gas supply reliability detection method based on cross entropy theory, preferably, the method further includes: based on the definition of gas supply reliability, constructing a gas supply reliability characterization function of the natural gas pipeline network according to the two dimensions of gas volume and time; obtaining the demand of the target natural gas pipeline network according to the result of the user demand prediction, and obtaining the gas supply reliability detection data of the target natural gas pipeline network by calculating the gas supply reliability characterization function according to the demand, the user characteristic data in the user classification result and the gas supply.

[0007] In the above-mentioned natural gas pipeline network gas supply reliability detection method based on the cross entropy theory, preferably, constructing the gas supply reliability characterization function of the natural gas pipeline network according to the two dimensions of gas volume and time includes: constructing the gas supply reliability characterization function according to the time dimension includes:

[0008]

[0009]

[0010] The gas supply reliability characterization function constructed based on the gas volume dimension includes:

[0011]

[0012]

[0013] In the above formula, the superscript i represents the i-th demand point in the network, LODE i , LODP i ,EGNS i and ERNS i They represent the expected time value, time probability, expected gas volume and the ratio of the reduction volume to the total demand of the i-th demand point, respectively. The subscript j represents the j-th simulation, N is the total number of simulations, T is the task time, and C i (t) represents the degree to which the pipe network system cannot meet the demand on day t, and its calculation formula is: X i (t) and D i (t) are the gas supply of the natural gas pipeline network to the i-th demand point and the demand of the i-th demand point on the t-th day respectively.

[0014] In the above-mentioned natural gas pipeline network gas supply reliability detection method based on cross entropy theory, preferably, obtaining user demand forecast results based on demand-side analysis of the target natural gas pipeline network includes: obtaining the user's gas usage characteristics based on the demand-side analysis of the target natural gas pipeline network, and using one of the time series model, support vector machine and long short-term memory artificial neural network model to construct a gas demand forecasting model.

[0015] In the above-mentioned natural gas pipeline network gas supply reliability detection method based on cross entropy theory, preferably, the user classification result is obtained according to the demand side analysis of the target natural gas pipeline network: based on the user's gas usage data, the gas volume, fluctuation and gas usage habit indicators are used to analyze the user's gas usage characteristics, and the demand guarantee attributes of each user are determined; according to the demand guarantee attributes of each user, the users are divided into fully guaranteed users, users who can be slightly reduced, users who can be reduced and users who can be interrupted.

[0016] In the above-mentioned natural gas pipeline network gas supply reliability detection method based on cross entropy theory, preferably, sampling the state transition process of the pipeline network through a time series Monte Carlo method based on cross entropy, and obtaining the time series state transition sequence also includes: obtaining the unit resampling distortion transfer rate through an optimization algorithm; randomly simulating the system operation state during the state transfer process according to the resampling distortion transfer rate, and obtaining the time series state transfer sequence through the probability density sampling state transfer process.

[0017] In the above-mentioned natural gas pipeline network gas supply reliability detection method based on cross entropy theory, preferably, obtaining the gas supply of the target natural gas pipeline network after the state transfer according to the gas usage characteristics of the users contained in each demand point and the calculation results of the time series state transfer sequence includes: constructing the pipeline network gas supply objective function, the pipeline network flow constraint function, the pipeline network pressure constraint function and the pipeline network hydraulic constraint function according to the topological structure of the target natural gas pipeline network and the gas usage characteristics of the users; according to the pipeline network gas supply objective function, the pipeline network flow constraint function, the pipeline network pressure constraint function and the pipeline network hydraulic constraint function, and considering the impact of failure on the pipeline network gas supply capacity, calculating to obtain the pipeline network flow distribution data, that is, the gas supply of the target natural gas pipeline network after the state transfer.

[0018] The present invention also provides a natural gas pipeline network gas supply reliability detection device based on cross entropy theory, the device comprising a market demand analysis module, a unit reliability estimation module, a state transition simulation module, a gas supply volume calculation module and a detection and analysis module; the market demand analysis module is used to obtain user demand prediction and user classification results according to the demand side analysis of the target natural gas pipeline network; the unit reliability estimation module is used to perform reliability assessment on a preset area of ​​the target natural gas pipeline network according to a historical failure database to obtain input data for system state transition simulation; the state transition simulation module is used to simulate the state transition process of the target natural gas pipeline network according to the input data through a temporal Monte Carlo method based on cross entropy to obtain a temporal state transition sequence; the gas supply volume calculation module is used to obtain the gas supply of the target natural gas pipeline network after the state transfer according to the gas consumption characteristics of each demand point and the calculation result of the temporal state transition sequence; the detection and analysis module is used to obtain gas supply reliability detection data of the target natural gas pipeline network according to the result of the user demand prediction, the user classification result and the gas supply volume analysis.

[0019] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0020] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the above method.

[0021] The beneficial technical effects of the present invention are: based on the basic data provided on site, the topological structure diagram of the natural gas pipeline network and the failure and maintenance data of the pipeline and compressor unit are obtained, and the state transition process of the target natural gas pipeline network is quickly simulated based on the cross-entropy temporal Monte Carlo method to determine the temporal state transition sequence of the pipeline network within the mission time; combined with the pipeline network gas supply calculation model considering user characteristics and hydraulic calculation, the gas supply reliability of the pipeline network is evaluated, and the weak points and key links of the gas supply are identified, and the flow distribution plan and gas supply reliability enhancement measures under emergency conditions are proposed. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of the present application, and do not constitute a limitation of the present invention. In the drawings:

[0023] Figure 1 A schematic flow chart of a method for detecting gas supply reliability of a natural gas pipeline network based on the cross entropy theory provided in one embodiment of the present invention;

[0024] Figure 2 A schematic diagram of the principle of a natural gas pipeline network gas supply reliability detection method based on the cross entropy theory provided by an embodiment of the present invention;

[0025] Figure 3 A schematic diagram of a calculation flow of gas supply reliability detection data provided by an embodiment of the present invention;

[0026] Figure 4 A schematic diagram of a state transition core provided by an embodiment of the present invention;

[0027] Figure 5 A schematic diagram of system state transition provided by an embodiment of the present invention;

[0028] Figure 6 A schematic diagram of a calculation flow of the gas supply volume of a target natural gas pipeline network provided by an embodiment of the present invention;

[0029] Figure 7 A schematic diagram of the structure of a natural gas pipeline network gas supply reliability detection device based on the cross entropy theory provided by an embodiment of the present invention;

[0030] Figure 8A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will describe the implementation methods of the present invention in detail with reference to the accompanying drawings and embodiments, so that the implementation process of how the present invention applies technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly. It should be noted that as long as there is no conflict, the various embodiments of the present invention and the various features in the embodiments can be combined with each other, and the technical solutions formed are all within the protection scope of the present invention.

[0032] In addition, the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be performed in an order different from that shown here.

[0033] Please refer to Figure 1 As shown, the present invention provides a method for detecting gas supply reliability of a natural gas pipeline network based on cross entropy theory, the method comprising:

[0034] S101: Obtain user demand forecast and user classification results based on demand side analysis of the target natural gas pipeline network

[0035] S102: Perform reliability assessment on the preset area of ​​the target natural gas pipeline network based on the historical failure database to obtain input data for system state transition simulation

[0036] S103: According to the input data, the state transition process of the target natural gas pipeline network is simulated by a time series Monte Carlo method based on cross entropy to obtain a time series state transition sequence

[0037] S104: Obtaining the gas supply of the target natural gas pipeline network after state transfer according to the gas consumption characteristics of the users included in each demand point and the calculation result of the time series state transfer sequence;

[0038] S105: Obtaining gas supply reliability detection data of a target natural gas pipeline network according to the user demand prediction result, the user classification result and the gas supply volume analysis.

[0039] In the above embodiment, the principle process of the natural gas pipeline network gas supply reliability detection method provided by the present invention is mainly as follows: first, an indicator for quantifying the reliability of the natural gas pipeline network gas supply is proposed; second, based on the demand side analysis, the predicted value of the natural gas demand is obtained and the user characteristics and user levels are determined; then, based on the failure database, the reliability of the important units of the pipeline network is estimated to obtain the input of the system state transition simulation; finally, based on the time series Monte Carlo method, combined with the cross entropy technology, the system state transition process is sampled, and the uncertainty of the pipeline network state, user characteristics and hydraulically calculated pipeline network gas supply are considered, and the established indicators are used to evaluate the reliability of the natural gas pipeline network gas supply. Therefore, the uncertainty and timing of the operating state of the natural gas pipeline network, the volatility of market demand, user characteristics, as well as the pipeline network's transmission capacity, gas source supply capacity, user demand, node flow, pressure constraints and pipeline network hydraulic calculations are comprehensively considered. For details, please refer to Figure 2 As shown, the specific implementation method of each step will be described one by one in the subsequent embodiments and will not be described in detail here.

[0040] Please refer to Figure 3 As shown, in one embodiment of the present invention, the process of establishing the gas supply reliability index in the gas supply reliability detection method of the natural gas pipeline network based on the cross entropy theory may include:

[0041] S401 is based on the definition of gas supply reliability and constructs a gas supply reliability characterization function of the natural gas pipeline network according to the two dimensions of gas volume and time;

[0042] S402 obtains the demand of the target natural gas pipeline network according to the result of the user demand prediction, and obtains the gas supply reliability detection data of the target natural gas pipeline network according to the demand, the user classification result and the gas supply through the gas supply reliability characterization function.

[0043] In actual work, the gas supply reliability characterization function of the natural gas pipeline network constructed based on the two dimensions of gas volume and time can include the expected value calculation function and probability function constructed in the time dimension, and the expected value function and ratio function constructed in the gas volume dimension. The specific formula is as follows:

[0044] The loss of demand expectation (LODE) includes:

[0045]

[0046] The expectation of the loss of demand probability (LODP) contains:

[0047]

[0048] The expected reduction in demand due to the system's inability to meet demand in a given time interval (The expected natural gas not supplied EGNS) includes:

[0049]

[0050] The expected ratio of the natural gas not supplied (ERNS) in a given time interval includes:

[0051]

[0052] In the above formula, the superscript i represents the i-th demand point in the network, LODE i , LODP i ,EGNS i and ERNS i They represent the expected time value, time probability, expected gas volume and the ratio of the reduction volume to the total demand of the i-th demand point, respectively. The subscript j represents the j-th simulation, N is the total number of simulations, T is the task time, and C i (t) represents the degree to which the pipe network system cannot meet the demand on day t, and its calculation formula is: X i (t) and D i (t) are the gas supply of the natural gas pipeline network to the i-th demand point and the demand of the i-th demand point on the t-th day respectively.

[0053] In one embodiment of the present invention, obtaining a user demand prediction model according to the demand side analysis of the target natural gas pipeline network includes: according to the demand volatility characteristics of each user on the demand side of the target natural gas pipeline network, using one of the time series model, support vector machine and long short-term memory artificial neural network model to build a gas demand prediction model. Specifically, through the demand side analysis, the market demand within the task cycle can be predicted and the importance of each demand point (distribution point) can be determined. Natural gas users are classified according to the purpose of gas use, mainly including four types of gas users, CNG users, power plant users and industrial users. Generally speaking, each distribution point of the natural gas pipeline network includes multiple and multiple natural gas users. The gas usage characteristics and fluctuation characteristics of each user are different, so different evaluation methods need to be used to predict their market demand. In view of the volatility characteristics of user demand, the present invention uses a time series model, a support vector machine and a long short-term memory artificial neural network (LSTM) model as a user demand prediction method for modeling, and the scope of use of each method is shown in Table 1 below.

[0054] Table 1

[0055]

[0056] In one embodiment of the present invention, the user classification result is obtained according to the demand-side analysis of the target natural gas pipeline network: based on the user's gas consumption data, the gas volume, fluctuation and gas consumption habit indicators are used to analyze the user's gas consumption characteristics, and the demand guarantee attributes of each user are determined; according to the demand guarantee attributes of each user, the users are divided into fully guaranteed users, users who can be slightly reduced, users who can be reduced and users who can be interrupted. In actual work, natural gas users are mainly classified according to the user's demand guarantee attributes, which are divided into four levels: users who need to be fully guaranteed, users who can be slightly reduced, users who can be reduced and users who can be interrupted. The key to grading according to the user's demand guarantee attributes lies in how to determine the user's demand guarantee attributes. The present invention performs data analysis based on experience, and determines its demand guarantee attributes in combination with the user's own attributes. Specifically, the model construction principles of users at all levels are as follows:

[0057] 1) City gas users:

[0058] In the absence of specific data on the proportion of residential and non-residential gas consumption among urban gas users, a volatility index can be established, and an intelligent algorithm can be used to perform cluster analysis based on the volatility of users to determine the demand protection attributes of urban gas users. Some small industrial distribution users have greater volatility compared to residential and commercial users, and this characteristic can be reflected in the cluster analysis. Therefore, users with smaller gas consumption and greater unevenness can be artificially regarded as users who can be reduced in small amounts. Compared with users who can be reduced, this type of user includes residential users, so the degree of reduction should not be too high.

[0059] 2) CNG users:

[0060] Since CNG users account for a small proportion and most of them are for civil and commercial use, they are users that need full protection.

[0061] 3) Power plant users:

[0062] According to the function of the power plant itself, the demand protection attribute of the power plant is determined according to the season. In spring, the continuous natural gas power plant is a user that needs full protection, the peak-shaving power plant is an interruptible user, and the backup energy power plant is a user that can be reduced. In summer, the continuous natural gas power plant, the peak-shaving power plant and the backup energy power plant are all users that need full protection. In autumn, the continuous natural gas power plant is a user that needs full protection, the peak-shaving power plant is an interruptible user, and the backup energy power plant is a user that can be reduced. In winter, the continuous natural gas power plant is a user that needs full protection, the peak-shaving power plant is an interruptible user, and the backup energy power plant is an interruptible user.

[0063] 4) Direct supply to industry:

[0064] It has attributes such as interruptibility and non-interruptibility. Due to the lack of such data, the interruptibility attribute is determined by data analysis and assumptions. In the process of analyzing the existing data, from the perspective of gas consumption trends, industrial users are roughly divided into the following categories: users who use gas continuously are defined as users who need full protection, users whose sales volume is 0 for more than 7 days in a certain period are defined as users who can be interrupted, and users whose gas consumption unevenness is higher than 1 for 10 consecutive days in a certain period are defined as users who can be reduced.

[0065] The current methods for evaluating the reliability of natural gas pipelines mainly include failure data statistics and methods based on structural reliability. In one embodiment of the present invention, the failure data statistics method can be used to calculate the reliability parameters of natural gas pipelines for unit reliability analysis. Based on GBT 29167-2012, EGIG and PHMSA, it is known that the failure probability of large-pore leakage and rupture in natural gas pipelines is 1×10 -4 ~2×10 -4 (km·a) -1 For the compressor station, the present invention simplifies the natural gas station into a booster system composed of multiple compressor units, and uses the GO method to calculate the failure probability of the compressor station, thereby obtaining the failure rate and maintenance rate of the compressor station.

[0066] In one embodiment of the present invention, the state transition process of the pipeline network is sampled by a sequential Monte Carlo method based on cross entropy, and obtaining a sequential state transition sequence also includes: minimizing the cross entropy by iterative learning to obtain the probability density; sampling the state transition process according to the probability density to obtain the sequential state transition sequence. Furthermore, obtaining the sequential state transition sequence according to the probability density sampling state transfer process may also include: obtaining the unit resampling distortion transfer rate through an optimization algorithm; performing random simulation of the system operating state during the state transfer process according to the resampling distortion transfer rate, and obtaining the sequential state transfer sequence through the probability density sampling state transfer process. In actual work, when the sequential Monte Carlo method is used, the sampling efficiency is often low when the state space of the pipeline network system is huge and the unit reliability is high. To this end, the present invention improves the system state sampling efficiency and the system reliability calculation speed based on the cross entropy theory; the specific implementation process is as follows:

[0067] Consider the general transfer process: the system at time t 1 Transition to state x 1 , then the system is determined at time t 2 The next transition occurs and enters state x 2 The probability transition kernel is (such as Figure 4 shown):

[0068] K((x 2 ,t 2 )|(x 1 ,t 1 ))=T(t 2 |t 1 ,x 1 )·C(x 2 |t 2 ,x 1 );

[0069] In the above formula, T(t 2 |t 1 ,x 1 ) is the given system at time t 1 The last transition occurs and enters state x 1 Under the condition, the system is 2 The conditional probability of the next transfer occurring at time ; C(x 2 |t 2 ,x 1 ) is given by the initial state of the system is x 1 , at time t 2 Enter state x under the condition of state transition 2Conditional probability. Considering the assumption that the operating characteristics of the natural gas pipeline network system obey the Markov process, the present invention adopts sequential Monte Carlo simulation to describe the state transition process of the pipeline network system, and takes the variance coefficient of the sample less than a certain constant as the Monte Carlo convergence criterion. And let f(x; α) be the probability density function of the random variable x required for reliability evaluation, and its parameter is α (i.e., unit reliability parameter). Under the sequential Monte Carlo simulation mechanism, the random variable x is the system state sequence of the system within the mission time.

[0070] Let S(x) be the loss mapping function corresponding to sample x. Based on different gas supply reliability indicators, the loss mapping function has different calculation formulas. Then the general expression of the reliability zero-variance sampling probability density function is h(x; β):

[0071]

[0072] In the formula, E f (S(x)) is the mathematical expectation of S(x) under the probability density f(x; α), and it is clear that E f (S(x)) and h(x; β) are a pair of interdependent quantities to be determined. To resolve this contradiction, h(x; β) can be estimated: if f(x; γ) and f(x; α) are from the same distribution family, and γ≠α, then the Kullback-Leibler (KL) distance between f(x; γ) and h(x; β), also known as cross entropy, can be minimized through iterative learning to solve for γ. The process is as follows.

[0073] First, create the iteration expression shown below.

[0074]

[0075] In common problems, the function to be maximized in the above equation is convex and differentiable with respect to γ, so the solution to the above equation can be obtained by solving the system of equations with respect to γ:

[0076]

[0077] Where: γ (k) The superscript represents the kth iteration, usually let γ (1) =α; N is the number of Monte Carlo simulations; is the probability density function The samples represent the state sequence of the system within the task time; is a state sequence sample Corresponding to the loss mapping function, for different gas supply reliability indicators, the loss mapping function has different calculation formulas.

[0078] Actual iterative solution γ(k) When the original unit transfer rate is used as the initial transfer rate of iteration, the event The probability of occurrence is very small (that is, unreliable gas supply is a low-probability event), especially when the evaluation period is short, it is a rare event. Therefore, the present invention obtains the unit resampling distortion transfer rate by establishing a two-stage enhanced optimization algorithm to avoid the problem that the loss mapping function is too often taken as zero during iterative solution, resulting in difficulty in starting the algorithm. The two-stage enhanced optimization algorithm here refers to: the first stage completes the accelerated training of the low-probability state transition sequence samples; the second stage performs enhanced optimization on the resampling distortion transfer rate obtained in the first stage. Then, based on the resampling distortion transfer rate, the system operating state is randomly simulated to obtain the state sequence of the system within the task time, as shown in the following formula:

[0079] x={(x 0 ,t 0 ),(x 1 ,t 1 ),...,(x m ,t m ),(t 0 +T)};

[0080] In the above formula, (x i , t i ) indicates that the i-th state transition occurs at t i time, and the system state after the transfer is x i ,(x 0 ,t 0 ) is the current system state, T is the task time, (t 0 +T) indicates the time of the last transfer, and its schematic diagram is as follows Figure 5 shown.

[0081] Finally, combining the natural gas pipeline network supply calculation model under complex effects and the market demand forecast gas volume, the loss mapping function is calculated and resampled and offset corrected to output the reliability evaluation results while satisfying the convergence condition.

[0082] Please refer to Figure 6 As shown, in one embodiment of the present invention, the gas supply of the target natural gas pipeline network after the state transfer is obtained according to the gas consumption characteristics of the users included in each demand point and the calculation result of the time series state transfer sequence, including:

[0083] S601 constructs a pipeline network gas supply objective function, a pipeline network flow constraint function, a pipeline network pressure constraint function, and a pipeline network hydraulic constraint function according to the topological structure of the target natural gas pipeline network and the gas consumption characteristics of users;

[0084] S602 calculates and obtains the pipeline flow distribution data, i.e., the gas supply of the target natural gas pipeline network after the state transfer, based on the pipeline network gas supply objective function, the pipeline network flow constraint function, the pipeline network pressure constraint function and the pipeline network hydraulic constraint function, and taking into account the impact of failure on the pipeline network gas supply capacity.

[0085] In actual work, after obtaining the system operation state transition process, the next step is how to calculate the gas supply of the system in various states. The present invention transforms the problem of solving the gas supply of each demand point in any operation state of the natural gas pipeline network into an optimization problem. The specific model is as follows:

[0086] Objective function: During the mission time, the total weighted gas volume supplied by the natural gas pipeline network to each demand point is maximized, as shown below.

[0087]

[0088] In the above formula, T is the task time; day, t is the time, day; D is the set of demand points; d is the virtual sink; Q 1 id (t) represents the gas volume that needs to be fully guaranteed for the user in the i-th demand point supplied by the pipeline network at time t, 10 4 m 3 / day;Q 2 id (t) indicates that at time t, the gas volume of the user can be slightly reduced in the pipeline network supply to the i-th demand point, 10 4 m 3 / day;Q 3 id (t) represents the amount of gas that can be reduced by the pipeline network in supplying the i-th demand point at time t, 10 4 m 3 / day;Q 4 id (t) represents the amount of gas that can be interrupted for the user at the i-th demand point supplied by the pipeline network at time t, 10 4 m 3 / day; They are the weights of users at each level. Obviously, the higher the user level, the greater the user importance and the higher the weight. This study uses the analytic hierarchy process to determine the weights of users at each level. It is believed that the level of fully guaranteed users is the highest, and the levels of users who can be reduced in small quantities, users who can be reduced and users who can be interrupted are lower in turn. The weight calculation results are 0.9576, 0.0245, 0.0120 and 0.0059.

[0089] Constraints:

[0090] 1) Pipeline network flow constraints:

[0091] The sum of traffic entering a node is equal to the sum of traffic leaving it.

[0092]

[0093] In the above formula, Q ij (t) represents the flow from the i-th node to the j-th node at time t, 10 4 Nm 3 / day; (i,j) and (j,l) represent the pipeline between node i and node j and the pipeline between node j and node l respectively; V represents the set of nodes in the graph, including gas source points, stations and demand points; E represents the set of natural gas pipelines

[0094] The flow direction constraint of a bidirectional pipe means that there is at most one flow direction in the pipe.

[0095]

[0096] In the above formula, E b Represents a collection of bidirectional pipes, y ij (t) is the binary decision variable that controls the flow direction of the bidirectional pipeline at time t.

[0097] The sum of the gas volumes obtained by users at each distribution point is equal to the gas volume obtained by the distribution point.

[0098]

[0099] In the formula represents the gas volume supplied by the pipeline network to the i-th demand point at time t, 10 4 m 3 / day.

[0100] 2) Constraints on gas supply capacity

[0101] The supply flow rate of the gas source point is less than the gas supply capacity of the gas source.

[0102]

[0103] In the formula is the gas flow rate of the i-th gas source at the t-th time, 10 4 Nm 3 / day, is the gas supply capacity of the ith gas source on day t, 10 4 Nm 3 / day.

[0104] 3) Demand constraints

[0105] The flow rate supplied to the demand point is less than the demand at the demand point.

[0106]

[0107] In the formula represents the gas demand at the ith demand point at time t, 10 4 m 3 / day;

[0108] 4) Pipeline capacity constraints

[0109]

[0110] In the formula represents the minimum safe flow rate of pipeline (i, j), 10 4 m 3 / day; represents the maximum transport capacity of pipeline (i, j), 10 4 m 3 / day.

[0111] 5) Pipeline network pressure constraints:

[0112] Pressure constraints at each node of the pipeline network.

[0113] P i,min (t)≤P i (t)≤P i,max (t);

[0114] In the above formula, P i (t) is the pressure of the ith node at the tth moment, MPa, P i,min (t) and P i,max (t) are the upper and lower limits of the pressure at the ith node at the tth moment, in MPa.

[0115] Pressure constraints upstream and downstream of the compressor station.

[0116]

[0117] In the above formula They are the upstream pressure, downstream pressure, upstream pressure limit and downstream pressure limit of the ith compressor station at time t, in MPa.

[0118] Regulating valve chamber upstream and downstream pressure constraints (used for interface pressure regulation of pipelines with different pressure levels).

[0119]

[0120]

[0121]

[0122] In the above formula They are the upstream pressure, downstream pressure, upstream pressure limit and downstream pressure limit of the i-th regulating valve chamber at the tth moment, MPa.

[0123] 6) Pipeline network hydraulic constraints:

[0124]

[0125] In the above formula, P i (t) and P j (t) are the pressures of the i-th and j-th nodes on the t-th day, MPa, λ is the hydraulic friction coefficient, Z is the compression factor of natural gas under pipeline transportation conditions, Δ * The relative density of natural gas, T is the gas transmission temperature, K, L is the calculated length of the gas pipeline, km, D is the inner diameter of the gas pipeline, m, C 0 is a constant whose value depends on the units of each parameter. The above parameters are all parameters of the pipeline between node i and node j.

[0126] Since the hydraulic constraints of the pipe network are nonlinear and contain many unknowns, in order to simplify the constraints and facilitate model solving, an attempt is made to linearize the hydraulic constraints piecewise.

[0127] Decision variable: Pipeline flow rate Q ij , flow direction of bidirectional pipe y ij And the node pressure P at both ends of the pipeline i .

[0128] Due to the random failure and maintenance activities of the units in the system, the pipeline capacity of each arc in the pipeline network system will change, resulting in changes in the gas supply of the system. The impact of the failure of different types of units in the pipeline network system on the pipeline capacity is shown in Table 2, where the impact of pipeline and compressor failure on the pipeline capacity needs to be accurately determined by performing water-thermal simulation on the pipeline network system. The present invention does not consider the failure of each demand point.

[0129] Table 2

[0130]

[0131] Therefore, the calculation of gas supply under any state of the natural gas pipeline network can be transformed into the above-mentioned mixed integer linear programming problem. By solving this optimization problem, the gas supply of the natural gas pipeline network under any working condition can be obtained. And combined with the market demand gas volume, the established indicators are used to realize the evaluation and detection of the gas supply reliability of the natural gas pipeline network.

[0132] Please refer to Figure 7 As shown, the present invention also provides a natural gas pipeline network gas supply reliability detection device based on the cross entropy theory, the device comprises a market demand analysis module, a unit reliability estimation module, a state transition simulation module, a gas supply volume calculation module and a detection analysis module;

[0133] The market demand analysis module is used to obtain user demand forecasts and user classification results based on the demand side analysis of the target natural gas pipeline network; the unit reliability estimation module is used to perform reliability assessment on a preset area of ​​the target natural gas pipeline network based on a historical failure database to obtain input data for system state transition simulation; the state transition simulation module is used to simulate the state transition process of the target natural gas pipeline network through a temporal Monte Carlo method based on cross entropy according to the input data to obtain a temporal state transition sequence; the gas supply volume calculation module is used to obtain the gas supply volume of the target natural gas pipeline network after the state transfer based on the gas consumption characteristics of each demand point and the calculation results of the temporal state transition sequence; the detection and analysis module is used to obtain gas supply reliability detection data of the target natural gas pipeline network based on the results of the user demand prediction, the user classification results and the gas supply volume analysis.

[0134] The beneficial technical effects of the present invention are as follows: it makes up for the insufficiency of the evaluation of the gas supply reliability of the existing natural gas pipeline network, obtains the topological structure diagram of the natural gas pipeline network and the failure and maintenance data of the pipeline and compressor unit based on the basic data provided on site, and uses the temporal Monte Carlo algorithm to simulate the state transfer process of the natural gas pipeline network, determines the temporal state transfer sequence of the pipeline network within the task time, and based on the cross entropy theory, improves the sampling speed of the system operation state; and then combines the pipeline network gas supply volume calculation model considering user characteristics and hydraulic calculation to realize the evaluation of the gas supply reliability of the pipeline network, identify the weak points and key links of the gas supply, and propose the flow distribution plan and gas supply reliability enhancement measures under emergency conditions.

[0135] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0136] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the above method.

[0137] like Figure 8 As shown, the electronic device 600 may further include: a communication module 110, an input unit 120, an audio processing unit 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily have to include Figure 8 In addition, the electronic device 600 may also include Figure 8 For components not shown, reference may be made to the prior art.

[0138] like Figure 8As shown, the central processor 100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor devices and / or logic devices. The central processor 100 receives inputs and controls the operations of various components of the electronic device 600 .

[0139] The memory 140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The memory 140 may store the above-mentioned information related to the failure, and may also store a program for executing the related information. The CPU 100 may execute the program stored in the memory 140 to implement information storage or processing.

[0140] The input unit 120 provides input to the CPU 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0141] The memory 140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 140 may also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application / function storage unit 142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 600 through the central processor 100.

[0142] The memory 140 may also include a data storage unit 143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 144 of the memory 140 may include various driver programs for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0143] The communication module 110 is a transmitter / receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter / receiver) 110 is coupled to the central processor 100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0144] Based on different communication technologies, multiple communication modules 110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless local area network module, etc. The communication module (transmitter / receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide an audio output via the speaker 131 and receive an audio input from the microphone 132, thereby realizing a common telecommunication function. The audio processor 130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 130 is also coupled to the central processor 100, so that recording can be performed on the local device through the microphone 132, and the sound stored on the local device can be played through the speaker 131.

[0145] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0146] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0147] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0149] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting gas supply reliability of a natural gas pipeline network based on cross entropy theory, characterized in that: The method comprises: Obtain user demand forecast and user classification results based on demand side analysis of the target natural gas pipeline network; According to the historical failure database, reliability assessment is performed on the preset area of ​​the target natural gas pipeline network to obtain input data for system state transfer simulation; According to the input data, a time series Monte Carlo method based on cross entropy is used to simulate the state transition process of the target natural gas pipeline network to obtain a time series state transition sequence; Obtaining the gas supply of the target natural gas pipeline network after state transfer according to the gas consumption characteristics of the users included in each demand point and the calculation result of the time series state transfer sequence; Obtaining gas supply reliability detection data of a target natural gas pipeline network according to the user demand prediction result, the user classification result and the gas supply volume analysis; The state transition process of the pipeline network is sampled by a temporal Monte Carlo method based on cross entropy to obtain a temporal state transition sequence, which further includes: minimizing the cross entropy by iterative learning to obtain a probability density; and sampling the state transition process according to the probability density to obtain a temporal state transition sequence.

2. The method for detecting gas supply reliability of a natural gas pipeline network based on cross entropy theory according to claim 1 is characterized in that: Obtaining gas supply reliability detection data of a target natural gas pipeline network according to the user demand prediction result, the user classification result and the gas supply volume analysis includes: Based on the definition of gas supply reliability, a gas supply reliability characterization function of the natural gas pipeline network is constructed according to the two dimensions of gas volume and time. The demand of the target natural gas pipeline network is obtained according to the result of the user demand prediction, and the gas supply reliability detection data of the target natural gas pipeline network is obtained by calculating the gas supply reliability characterization function according to the demand, the user characteristic data in the user classification result and the gas supply.

3. The method for detecting gas supply reliability of a natural gas pipeline network based on cross entropy theory according to claim 2 is characterized in that: The gas supply reliability characterization function of the natural gas pipeline network constructed based on the two dimensions of gas volume and time includes: The gas supply reliability characterization function constructed according to the time dimension includes: The gas supply reliability characterization function constructed based on the gas volume dimension includes: In the above formula, the superscript i represents the i-th demand point in the network, LODE i , LODP i ,EGNS i and ERNS i They represent the expected time value, time probability, expected gas volume and the ratio of the reduction volume to the total demand of the i-th demand point, respectively. The subscript j represents the j-th simulation, N is the total number of simulations, T is the task time, and C i (t) represents the degree to which the pipe network system cannot meet the demand on day t, and its calculation formula is: X i (t) and D i (t) are the gas supply of the natural gas pipeline network to the i-th demand point and the demand of the i-th demand point on the t-th day respectively.

4. The method for detecting gas supply reliability of a natural gas pipeline network based on cross entropy theory according to claim 3 is characterized in that: The user demand forecasting model obtained based on the demand side analysis of the target natural gas pipeline network includes: According to the demand volatility characteristics of each user on the demand side of the target natural gas pipeline network, a gas demand forecasting model is constructed by using one of the time series model, support vector machine and long short-term memory artificial neural network model.

5. The method for detecting gas supply reliability of a natural gas pipeline network based on cross entropy theory according to claim 4 is characterized in that: The user classification results are obtained based on the demand side analysis of the target natural gas pipeline network: Based on the user's gas usage data, the gas volume, fluctuation and gas usage habit indicators are used to analyze the user's gas usage characteristics and determine the demand protection attributes of each user; According to the protection attributes of each user's needs, users are divided into fully protected users, users who can be slightly reduced, users who can be reduced, and users who can be interrupted.

6. The method for detecting gas supply reliability of a natural gas pipeline network based on cross entropy theory according to claim 5 is characterized in that: The gas supply of the target natural gas pipeline network after state transfer is obtained according to the gas consumption characteristics of the users included in each demand point and the calculation results of the time series state transfer sequence, including: According to the topological structure of the target natural gas pipeline network and the gas consumption characteristics of users, the pipeline network gas supply objective function, pipeline network flow constraint function, pipeline network pressure constraint function and pipeline network hydraulic constraint function are constructed; According to the pipeline network gas supply objective function, the pipeline network flow constraint function, the pipeline network pressure constraint function and the pipeline network hydraulic constraint function, and considering the impact of failure on the pipeline network gas supply capacity, the pipeline network flow distribution data is calculated to obtain the gas supply volume of the target natural gas pipeline network after the state transfer.

7. A natural gas pipeline network gas supply reliability detection device based on cross entropy theory, characterized in that: The device comprises a market demand analysis module, a unit reliability estimation module, a state transition simulation module, a gas supply volume calculation module and a detection analysis module; The market demand analysis module is used to obtain user demand forecasts and user classification results based on the demand side analysis of the target natural gas pipeline network; The unit reliability estimation module is used to perform reliability evaluation on a preset area of ​​the target natural gas pipeline network according to the historical failure database to obtain input data for system state transfer simulation; The state transfer simulation module is used to simulate the state transfer process of the target natural gas pipeline network according to the input data by using the time series Monte Carlo method based on cross entropy to obtain a time series state transfer sequence; sampling the state transfer process of the pipeline network by using the time series Monte Carlo method based on cross entropy to obtain the time series state transfer sequence further includes: minimizing the cross entropy by iterative learning to obtain the probability density; sampling the state transfer process according to the probability density to obtain the time series state transfer sequence; The gas supply calculation module is used to obtain the gas supply of the target natural gas pipeline network after state transfer based on the gas consumption characteristics of each demand point and the calculation results of the time series state transfer sequence; the detection and analysis module is used to obtain the gas supply reliability detection data of the target natural gas pipeline network based on the results of the user demand prediction, the user classification results and the gas supply analysis.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for causing a computer to execute the method according to any one of claims 1 to 6.

Images