Fault-visualization hydrogen-electricity coupling micro-energy grid reliability evaluation method and fault-visualization hydrogen-electricity coupling micro-energy grid reliability evaluation system

Abstract

The invention discloses a fault visualization hydrogen-electricity coupling micro energy network reliability evaluation method and system, and the method comprises the steps: obtaining a first top fault event and a first fault reason, a second top fault event and a second fault reason, and a third top fault event and a third fault reason as nodes, so as to build a reliability evaluation network model representing the relation between the nodes; determining a fault node corresponding to the to-be-evaluated fault event and an occurrence path of the to-be-evaluated fault event based on the fault occurrence probability and the constraint condition of each node according to the fault data and the risk data of the micro-energy network by adopting a statistical method; the fault occurrence probability, the fault recovery time and the average fault duration of the verified fault node are respectively used as a first reliability index, a second reliability index and a third reliability index of the fault node, and a reliability index of the hydrogen-electricity coupling micro energy grid; on the basis of realizing fault visualization, reliability evaluation is carried out on the hydrogen-electricity coupling micro-energy grid.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrogen-electricity coupled micro energy networks, and in particular to a reliability assessment method and system for hydrogen-electricity coupled micro energy networks with fault visualization. Background Art

[0002] In the process of implementing the "dual carbon goals", hydrogen energy is expected to become an important part of the energy sector. In recent years, as hydrogen energy application technology has gradually matured and the global pressure to cope with climate change continues to increase, electric-hydrogen coupling technology has continued to advance, allowing hydrogen to be quickly integrated into the entire micro-energy system.

[0003] In the prior art, the reliability assessment of the hydrogen-electricity coupled micro-energy network includes: using the operating data collected by the equipment sensors to establish a coupled mathematical model to obtain reliability indicators, using the training data to train the hybrid neural network, and monitoring the abnormal working state of the hydrogen-electricity coupled system; using linear regression and deviation analysis to improve the accuracy of data analysis, and then using the neural network algorithm to proofread the data in real time, and using the Bayesian network algorithm to enhance the optimization of the abnormal test process and improve the reliability of intelligent robot detection; combining dynamic Bayesian network time series analysis to predict and identify changes in special geological structures, and improve the accuracy of data processing and the reliability of prediction; by integrating the causal reasoning module to construct the Bayesian network structure, accurately display the complex relationship between each production and energy, and provide a solution for real-time monitoring and automatic adjustment of energy consumption. However, the prior art reliability assessment method for micro-energy networks mainly considers the overall impact of the integrated energy system, and lacks the focus on flammable, explosive, and easily diffusible hydrogen energy.

[0004] Therefore, there is an urgent need for a technical solution that can solve the problem that the existing reliability assessment method for micro-energy grids mainly considers the overall impact of the integrated energy system and lacks a key consideration for hydrogen energy with unstable physical properties. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the present invention provides a reliability assessment method and system for a hydrogen-electricity coupled micro-energy network with fault visualization, which performs a local focused assessment on the reliability of hydrogen energy with unstable physical properties within the micro-energy network, and combines the assessment results with the overall reliability assessment results of the integrated energy system. On the basis of achieving fault visualization, the reliability of the hydrogen-electricity coupled micro-energy network is accurately assessed.

[0006] The present invention adopts the following technical solution.

[0007] The present invention proposes a reliability assessment method for a hydrogen-electric coupling micro-energy network with fault visualization. The energy structure of the micro-energy network includes a hydrogen energy sub-network, an electric energy sub-network and a thermal energy sub-network. The hydrogen energy sub-network and the electric energy sub-network are coupled through an electric-hydrogen coupling element, and the electric energy sub-network and the thermal energy sub-network are coupled through an electric-thermal coupling element. The method includes: The first top-level fault event and the first fault cause of the hydrogen energy sub-network, the second top-level fault event and the second fault cause of the electric energy sub-network, and the third top-level fault event and the third fault cause of the thermal energy sub-network are obtained as nodes to establish a reliability assessment network model that characterizes the relationship between the nodes; Collect micro energy grid fault data and micro energy grid risk data; Using statistical methods, according to the fault data and risk data of the micro-energy network, the failure probability of each node in the reliability assessment network model is determined; according to the failure probability of each node and its constraints, the fault nodes corresponding to the fault event to be evaluated and the occurrence path of the fault event to be evaluated are determined based on the reliability assessment network model, and the fault visualization is performed based on the fault nodes and occurrence paths; Based on the confidence interval, the failure probability of the faulty node in the reliability evaluation network model is verified, and the failure probability of the faulty node, the fault repair time of the faulty node and the average fault duration of the faulty node after verification are used as the first reliability index, the second reliability index and the third reliability index of the faulty node respectively; The reliability of the hydrogen-electricity coupled micro-energy network is evaluated by using the first reliability index, the second reliability index, the third reliability index of the faulty node and the reliability index of the hydrogen-electricity coupled micro-energy network.

[0008] Preferably, the first top-level fault event includes: a fault event caused by hydrogen, and the first fault factor includes: a fault factor causing the fault event caused by hydrogen; The second top-level fault events include: power system collapse or outage, and the second fault factors include: fault factors that cause the power system collapse or outage; The third top-level fault events include: the thermal system loses control and cannot provide continuous heating. The third fault factors include: the fault factors that cause the thermal system to lose control and cannot provide continuous heating.

[0009] Preferably, a reliability assessment network model characterizing the relationship between nodes is established, including: Taking the first top-level fault event and the first fault cause as the root node, generate layer-by-layer layer subnode, and the electric-hydrogen coupling element is used as the first Child nodes in the layer; From Starting from the child nodes in the layer, generate layer by layer The second top-level fault event and the second fault cause of the power sub-network are taken as the first Leaf nodes in a layer; From Starting from the child nodes in the layer, generate layer by layer The second top-level fault event and the second fault cause of the power sub-network are taken as the first The leaf nodes in the layer use the electrothermal coupling element as the first The leaf nodes in the layer; among them, ; From Starting from the leaf nodes in the layer, generate layer by layer The third top-level fault event and the third fault cause of the thermal energy sub-network are taken as the first Leaf nodes in a layer; in, , , and All are positive integers.

[0010] Preferably, the relationships between nodes represented by the reliability assessment network model include: and relationship, joint relationship, and causal relationship.

[0011] Preferably, a statistical method is used to determine the failure probability of each node in the reliability assessment network model based on the failure data and risk data of the micro energy network, including: Extract characteristic information from micro energy grid fault data as prior information; According to the prior information, the fault prior distribution is obtained based on the reliability evaluation network model; Extract characteristic information from micro-energy grid risk data as posterior information; According to the posterior information and the prior distribution of faults, the posterior distribution of faults is obtained based on the reliability evaluation network model; According to the fault posterior distribution, the failure probability of each node in the reliability assessment network model is obtained.

[0012] Preferably, according to the failure probability of each node and its constraint conditions, the failure event to be evaluated and its occurrence path are determined based on the reliability evaluation network model, including: Establish the constraint conditions of the failure probability of each node to satisfy the following relationship: , In the formula, is the observed value of the fault population sample The corresponding coupling coefficient; is the observed value of the fault population sample The corresponding probability of failure; and are the observed values ​​of the fault population sample respectively. The corresponding lower and upper limits of the probability of failure occurring; When the probability of failure Greater than , it is judged as a high probability failure event ,in, is the number of tests; high probability failure events are taken as the failure events to be evaluated, and high probability failure events are obtained based on the reliability evaluation network model path of occurrence.

[0013] Preferably, the failure probability of each node in the reliability assessment network model is verified based on the confidence interval, including: The confidence interval of the fault probability of the fault node is determined according to the fault posterior distribution, and the confidence interval is used to screen the fault probability of the fault node; when the confidence interval is not less than the set interval threshold, the fault probability of the fault node is retained; otherwise, when the confidence interval is less than the set interval threshold, the fault probability of the fault node is removed.

[0014] Preferably, based on the reliability assessment network model, it is determined whether the faulty node whose fault occurrence probability has been removed is the underlying event of each sub-network; if the faulty node is a non-bottom-level event of each sub-network, then based on the occurrence path of the fault event to be evaluated, the underlying events of each sub-network corresponding to the faulty node are determined in the reliability assessment network model; according to Bayes' theorem, the failure rate of the underlying events of each sub-network corresponding to the faulty node is used to calculate the failure occurrence probability of the faulty node; conversely, if the faulty node is the underlying event of each sub-network, the failure rate of the underlying events of each sub-network is used as the failure occurrence probability of the faulty node.

[0015] Preferably, the faulty node The first reliability index, the second reliability index and the third reliability index satisfy the following relationship: , In the formula, the faulty node after verification is The probability of failure For the faulty node The first reliability indicator is the fault repair time of the faulty node. For the failed node The second reliability indicator is the average failure duration of the faulty node. For the failed node The third reliability indicator.

[0016] Preferably, the reliability index of the hydrogen-electricity coupled micro-energy network includes: the probability of the hydrogen-electricity coupled micro-energy network stopping supplying hydrogen, the probability of the hydrogen-electricity coupled micro-energy network obtaining hydrogen, and the energy expectation of hydrogen load shortage.

[0017] The present invention also proposes a fault visualized hydrogen-electricity coupled micro-energy grid reliability assessment system, comprising: Reliability assessment network establishment module, fault event visualization processing module, reliability assessment module; A reliability assessment network establishment module is used to obtain the first top-level fault event and the first fault cause of the hydrogen energy sub-network, the second top-level fault event and the second fault cause of the electric energy sub-network, and the third top-level fault event and the third fault cause of the thermal energy sub-network as nodes to establish a reliability assessment network model that characterizes the relationship between the nodes; The fault event visualization processing module is used to collect micro-energy network fault data and micro-energy network risk data; using statistical methods, according to the fault data and micro-energy network risk data of the micro-energy network, determine the fault probability of each node in the reliability evaluation network model; according to the fault probability of each node and its constraint conditions, determine the fault node corresponding to the fault event to be evaluated and the occurrence path of the fault event to be evaluated based on the reliability evaluation network model; The reliability assessment module is used to verify the failure probability of the fault node in the reliability assessment network model based on the confidence interval, and use the verified failure probability of the fault node, the fault repair time of the fault node and the average fault duration of the fault node as the first reliability index, the second reliability index and the third reliability index of the fault node respectively; the reliability of the hydrogen-electricity coupled micro-energy network is jointly evaluated by using the first reliability index, the second reliability index and the third reliability index of the fault node and the reliability index of the hydrogen-electricity coupled micro-energy network.

[0018] A terminal includes a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method.

[0019] A computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.

[0020] The beneficial effect of the present invention is that, compared with the prior art, it at least includes the reliability assessment method of the hydrogen-electric coupled micro-energy network with fault visualization of the present invention, which focuses on the impact of hydrogen energy on the reliability of the micro-energy network by constructing the fault events of hydrogen-related equipment and then constructing a model based on the Bayesian network according to the fault events of hydrogen-related equipment, so that the present method can further evaluate the reliability of the micro-energy network on the basis of the prior art. The posterior distribution of the fault is obtained by analysis, and then the high-probability fault events and event occurrence paths are obtained according to the posterior distribution, so that the present method can visualize the faults and occurrence paths, and further facilitate the reliability assessment of the micro-energy network. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of a reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization proposed by the present invention; DETAILED DESCRIPTION

[0022] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only embodiments of a part of the present invention, rather than all embodiments. Based on the spirit of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the protection scope of the present invention.

[0023] The present invention proposes a reliability assessment method for a hydrogen-electric coupling micro-energy network with fault visualization. The energy structure of the micro-energy network includes a hydrogen energy sub-network, an electric energy sub-network and a thermal energy sub-network. The hydrogen energy sub-network and the electric energy sub-network are coupled through an electric-hydrogen coupling element, and the electric energy sub-network and the thermal energy sub-network are coupled through an electric-thermal coupling element. like Figure 1 As shown, the method includes: Step 1, obtain the first top-level fault event and the first fault cause of the hydrogen energy sub-network, the second top-level fault event and the second fault cause of the electric energy sub-network, and the third top-level fault event and the third fault cause of the thermal energy sub-network as nodes to establish a reliability assessment network model that characterizes the relationship between the nodes.

[0024] Specifically, according to the production, transportation and use of hydrogen energy in the micro-energy network, the hydrogen-related equipment in the hydrogen energy sub-network includes: new energy hydrogen production equipment, distributed energy equipment, energy conversion equipment, and storage equipment.

[0025] The top-level fault events in the preferred embodiment of the present invention are shown in Table 1, and the fault causes are shown in Table 2.

[0026] Table 1 List of top-level fault events

[0027] Table 2 List of fault causes

[0028] Specifically, the first top-level fault event includes but is not limited to: a fault event caused by hydrogen, and the first fault factor includes but is not limited to: a fault factor that causes a fault event caused by hydrogen. The second top-level fault event includes but is not limited to: a power system collapse or shutdown, and the second fault factor includes but is not limited to: a fault factor that causes a power system collapse or shutdown. The third top-level fault event includes but is not limited to: a thermal system loses control and cannot continue to provide heat, and the third fault factor includes but is not limited to: a fault factor that causes a thermal system to lose control and cannot continue to provide heat.

[0029] Specifically, a reliability assessment network model is established, including: Taking the first top-level fault event and the first fault cause as the root node, generate layer-by-layer layer subnode, and the electric-hydrogen coupling element is used as the first Child nodes in the layer; In a non-limiting preferred embodiment, The first fault layer is the one that connects hydrogen energy and electric energy. For example, when facing a fuel cell, the fuel cell can cause both electric energy and hydrogen energy failures at the same time. Therefore, the fuel cell is used as the first fault layer. Child nodes in a layer.

[0030] From Starting from the child nodes in the layer, generate layer by layer The second top-level fault event and the second fault cause of the power sub-network are taken as the first The leaf nodes in the layer use the electrothermal coupling element as the first The leaf nodes in the layer; among them, .

[0031] From Starting from the leaf nodes in the layer, generate layer by layer The third top-level fault event and the third fault cause of the thermal energy sub-network are taken as the first Leaf nodes in a layer.

[0032] in, , , and All are positive integers.

[0033] The reliability assessment network model established by the present invention can characterize the various relationships between hydrogen energy sub-network failures, electric energy sub-network failures and thermal energy sub-network failures, including but not limited to: and relationship, joint relationship, causal relationship; and according to the energy structure of the micro energy network, the probability of the existence of causal relationship between the sub-network failures is the highest. Therefore, when the reliability assessment network model is established, the hydrogen energy sub-network failure is taken as the main trunk, and on the basis of the trunk, based on the causal relationship between the electric energy sub-network failure and the hydrogen energy sub-network failure, and the causal relationship between the thermal energy sub-network failure and the electric energy sub-network failure, the reliability assessment network model is generated layer by layer, and the relationship between the sub-networks represented by the model is arranged according to the actual situation of the micro energy network.

[0034] In a non-limiting preferred embodiment, a reliability assessment network model is generated layer by layer based on a Bayesian network, including: 1) The first top-level fault event and the first fault cause of the hydrogen energy sub-network, the second top-level fault event and the second fault cause of the electric energy sub-network, and the third top-level fault event and the third fault cause of the thermal energy sub-network are used as variables for reliability assessment and serve as nodes in the reliability assessment network model; 2) Based on the relationship between variables, corresponding nodes are connected with directed edges; 3) For any node, when the probability distribution of the parent node of the node is given, the conditional probability of the node is used as the probability distribution of the node.

[0035] Step 2: Collect micro energy grid fault data and micro energy grid risk data.

[0036] Specifically, micro-energy network failure data includes but is not limited to: empirical data of micro-energy network failures, historical data of micro-energy network failures, and predicted data of micro-energy network failures; micro-energy network risk data includes but is not limited to: empirical data of micro-energy network risks, historical data of micro-energy network risks, and predicted data of micro-energy network risks.

[0037] Step 3: Use statistical methods to determine the failure probability of each node in the reliability assessment network model based on the fault data and risk data of the micro energy network; determine the fault nodes corresponding to the fault event to be evaluated and the occurrence path of the fault event to be evaluated based on the reliability assessment network model according to the failure probability of each node and its constraints, and perform fault visualization based on the fault nodes and occurrence paths.

[0038] Specifically, step 3 includes: Step 3.1, extracting characteristic information from micro energy grid fault data as prior information; Those skilled in the art may adopt different feature extraction methods according to actual needs to extract relevant feature information from micro energy grid fault data.

[0039] Step 3.2, according to the prior information, the fault prior distribution is obtained based on the reliability evaluation network model; Step 3.3, extracting characteristic information from micro-energy grid risk data as posterior information; Those skilled in the art may adopt different feature extraction methods according to actual needs to extract relevant feature information from the micro energy grid risk data.

[0040] Step 3.4, according to the posterior information and the fault prior distribution, the fault posterior distribution is obtained based on the reliability evaluation network model.

[0041] Step 3.5, based on the fault posterior distribution, obtain the failure probability of each node in the reliability assessment network model.

[0042] Specifically, step 3.5 includes: set up is a sample from the fault population of Fault samples, is the observed value of each sample, and Satisfying the set probability distribution, in a non-limiting preferred embodiment, Satisfies binomial distribution , the binomial distribution describes the binomial distribution The possibility of taking values, the fault prior distribution adopts the conjugate prior distribution; Parameters in The prior distribution of is Beta distribution ,but The probability density function of Satisfies the following relationship: , In the formula, is the probability of an event occurring in a binomial distribution, is a Beta distribution, and .

[0043] Then the likelihood function satisfies the following relationship: , In the formula, is the likelihood function, is the total sample of faults The observed value of is the number of experiments, For the The interval corresponding to the observed values ​​of the fault population sample in the experiment.

[0044] Considering that the probability of human error is very small but uncertain, the probability density function satisfies the following relationship: ,

[0045] In the formula, For super parameters The value range of for The prior distribution function of for The prior distribution function of .

[0046] Then the likelihood function satisfies the following relationship: , According to Bayes' theorem, The posterior density function Satisfies the following relationship: , In the formula, for The value range of .

[0047] The posterior density function is integrated to obtain the failure probability of each node in the reliability assessment network model.

[0048] Step 3.6, based on the reliability evaluation network model, determine the nodes corresponding to the fault event to be evaluated and the occurrence path of the fault event to be evaluated.

[0049] Specifically, step 3.6 includes: Establish the constraint conditions of the failure probability of each node to satisfy the following relationship: , In the formula, is the observed value of the fault population sample The corresponding coupling coefficient; is the observed value of the fault population sample The corresponding probability of failure; and are the observed values ​​of the fault population sample respectively. The corresponding lower limit and upper limit of the probability of failure.

[0050] When the probability of failure Greater than , it is judged as a high probability failure event , taking high probability failure events as the failure events to be evaluated, and obtaining high probability failure events based on the reliability evaluation network model path of occurrence.

[0051] Extract the fault node corresponding to the fault event to be evaluated.

[0052] The present invention obtains the fault posterior distribution through analysis, and then obtains high-probability fault events and event occurrence paths based on the fault posterior distribution, so that the method can visualize the faults and occurrence paths, further facilitating the reliability assessment of the micro energy network.

[0053] Step 4: Verify the failure probability of the faulty node in the reliability assessment network model based on the confidence interval, and use the verified failure probability of the faulty node, the fault repair time of the faulty node, and the average fault duration of the faulty node as the first reliability index, the second reliability index, and the third reliability index of the faulty node, respectively.

[0054] Specifically, step 4 includes: Step 4.1, verify the failure probability of the faulty node in the reliability assessment network model based on the confidence interval.

[0055] The confidence interval of the fault probability of the fault node is determined according to the fault posterior distribution, and the confidence interval is used to screen the fault probability of the fault node; when the confidence interval is not less than the set interval threshold, the larger the confidence interval, the greater the reliability of the fault posterior distribution of the fault node, and the greater the reliability of the fault probability of the fault node, and the fault probability of the fault node is retained; conversely, when the confidence interval is less than the set interval threshold, the smaller the confidence interval, the smaller the reliability of the fault probability of the fault node, and the fault probability of the fault node is removed.

[0056] Based on the reliability assessment network model, it is determined whether the faulty node whose fault occurrence probability has been removed is the underlying event of each sub-network. If the faulty node is a non-bottom-level event of each sub-network, then based on the occurrence path of the fault event to be evaluated, the underlying events of each sub-network corresponding to the faulty node are determined in the reliability assessment network model; according to the Bayesian theorem, the failure rate of the underlying events of each sub-network corresponding to the faulty node is used to calculate the failure probability of the faulty node; conversely, if the faulty node is the underlying event of each sub-network, the failure rate of the underlying events of each sub-network is used as the failure probability of the faulty node.

[0057] In a non-limiting preferred embodiment, the parameter The value range of Find the interval corresponding to the observed value of the fault population sample in , so that the posterior probability As large as possible, and When the posterior probability is as small as possible, the loss function satisfies the following relationship: , In the formula, and are all non-negative weights, Is the interval Length, is an indicative function.

[0058] Then the posterior risk satisfies the following relationship: , In the formula, is the posterior risk, is the length of the posterior interval, is the posterior probability.

[0059] Will Treated as a random variable, binomial parameter distribution It is approximately a Beta distribution, satisfying the following relationship: , For a given sample observation and , if there are two statistics and , so that the following relationship is satisfied: , The confidence level is ; interval( , ) is the parameter Confidence interval of .

[0060] Step 4.2: The verified fault probability of the faulty node, the fault repair time of the faulty node, and the average fault duration of the faulty node are used as the first reliability index, the second reliability index, and the third reliability index of the faulty node, respectively.

[0061] Specifically, the reliability index of the faulty node is closely related to the reliability index of the hydrogen-electricity coupled micro-energy network, reflecting the reliability of hydrogen energy supply to each faulty node in the hydrogen-electricity coupled micro-energy network. The first reliability index, the second reliability index, and the third reliability index of the faulty node enable a local focused evaluation of the reliability of hydrogen energy with unstable physical properties in the micro-energy network.

[0062] The faulty node after verification The probability of failure , Fault repair time of the faulty node And the average failure duration of the failed nodes They are respectively used as the first reliability index, the second reliability index and the third reliability index of the faulty node.

[0063] In a non-limiting preferred embodiment, the fault repair time of a faulty node represents the average time from fault to normal operation, and the average fault duration of a faulty node represents the average power outage time of the faulty node in the system within a year.

[0064] Faulty Node The first reliability index, the second reliability index and the third reliability index satisfy the following relationship: , Step 5: Use the first reliability index, the second reliability index, the third reliability index of the faulty node, and the reliability index of the hydrogen-electricity coupled micro-energy network to jointly evaluate the reliability of the hydrogen-electricity coupled micro-energy network.

[0065] Specifically, the reliability index of the faulty node alone cannot fully reflect the overall hydrogen supply reliability level of the hydrogen-electricity coupled micro-energy network. Therefore, it is necessary to use the reliability index of the hydrogen-electricity coupled micro-energy network to objectively evaluate the system's ability to provide continuous power supply.

[0066] The reliability indicators of hydrogen-electricity coupled micro-energy grid include: 1) The probability of stopping hydrogen supply in the hydrogen-electricity coupled micro-energy grid , satisfying the following relationship: , In the formula, Indicates a faulty node Uptime For the failed node The hydrogen outage time when a fault occurs.

[0067] 2) The probability of obtaining hydrogen through hydrogen-electric coupling micro-energy grid , satisfying the following relationship: , 3) Duration of hydrogen outage in hydrogen-electricity coupled micro-energy grid , satisfying the following relationship: , In the formula, For the failed node The probability of hydrogen suspension.

[0068] 4) Hydrogen load shortage energy expectation , satisfying the following relationship: , In the formula, 1 means that there is loss during the operation of hydrogen energy equipment. To simulate the years, For the Year time Faulty Node The amount of hydrogen load reduction at the electricity-hydrogen coupling, is the number of years, is the number of failed nodes.

[0069] In a non-limiting preferred embodiment, technical personnel in this field can adopt a variety of evaluation methods such as scoring method, weighted sum method, hierarchical analysis method, etc., and use the first reliability index, second reliability index, third reliability index of the fault node, and the reliability index of the hydrogen-electricity coupled micro-energy network to jointly conduct reliability evaluation on the hydrogen-electricity coupled micro-energy network.

[0070] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0071] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The computer-readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0072] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0073] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute the computer-readable program instructions, thereby implementing various aspects of the present disclosure.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A reliability assessment method for a hydrogen-electricity coupled micro-energy network with fault visualization. The energy structure of the micro-energy network includes a hydrogen energy sub-network, an electric energy sub-network, and a thermal energy sub-network. The hydrogen energy sub-network and the electric energy sub-network are coupled via an electric-hydrogen coupling element, and the electric energy sub-network and the thermal energy sub-network are coupled via an electric-thermal coupling element; the characteristics are: Methods include: The first top-level fault event and the first fault cause of the hydrogen energy sub-network, the second top-level fault event and the second fault cause of the electric energy sub-network, and the third top-level fault event and the third fault cause of the thermal energy sub-network are obtained as nodes to establish a reliability assessment network model that characterizes the relationship between the nodes; Collect micro energy grid fault data and micro energy grid risk data; Using statistical methods, according to the fault data and risk data of the micro-energy network, the failure probability of each node in the reliability assessment network model is determined; according to the failure probability of each node and its constraints, the fault nodes corresponding to the fault event to be evaluated and the occurrence path of the fault event to be evaluated are determined based on the reliability assessment network model, and the fault visualization is performed based on the fault nodes and occurrence paths; Based on the confidence interval, the failure probability of the faulty node in the reliability evaluation network model is verified, and the failure probability of the faulty node, the fault repair time of the faulty node and the average fault duration of the faulty node after verification are used as the first reliability index, the second reliability index and the third reliability index of the faulty node respectively; The reliability of the hydrogen-electricity coupled micro-energy network is evaluated by using the first reliability index, the second reliability index, the third reliability index of the faulty node and the reliability index of the hydrogen-electricity coupled micro-energy network.

2. The reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization according to claim 1 is characterized in that: The first top-level fault event includes: a fault event caused by hydrogen, and the first fault factor includes: a fault factor that causes the fault event caused by hydrogen; The second top-level fault events include: power system collapse or outage, and the second fault factors include: fault factors that cause the power system collapse or outage; The third top-level fault events include: the thermal system loses control and cannot provide continuous heating. The third fault factors include: the fault factors that cause the thermal system to lose control and cannot provide continuous heating.

3. The reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization according to claim 2 is characterized in that: Establish a reliability assessment network model that characterizes the relationship between nodes, including: Taking the first top-level fault event and the first fault cause as the root node, generate layer-by-layer layer subnode, and the electric-hydrogen coupling element is used as the first Child nodes in the layer; From Starting from the child nodes in the layer, generate layer by layer The second top-level fault event and the second fault cause of the power sub-network are taken as the first Leaf nodes in a layer; From Starting from the child nodes in the layer, generate layer by layer The second top-level fault event and the second fault cause of the power sub-network are taken as the first The leaf nodes in the layer use the electrothermal coupling element as the first The leaf nodes in the layer; among them, ; From Starting from the leaf nodes in the layer, generate layer by layer The third top-level fault event and the third fault cause of the thermal energy sub-network are taken as the first Leaf nodes in a layer; in, , , and All are positive integers.

4. The reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization according to claim 3 is characterized in that: The relationships between nodes represented by the reliability assessment network model include: AND relationship, joint relationship, and causal relationship.

5. The reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization according to claim 1 is characterized in that: Using statistical methods, based on the failure data and risk data of the micro energy grid, the failure probability of each node in the reliability assessment network model is determined, including: Extract characteristic information from micro energy grid fault data as prior information; According to the prior information, the fault prior distribution is obtained based on the reliability evaluation network model; Extract characteristic information from micro-energy grid risk data as posterior information; According to the posterior information and the fault prior distribution, the fault posterior distribution is obtained based on the reliability evaluation network model; According to the fault posterior distribution, the failure probability of each node in the reliability assessment network model is obtained.

6. The reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization according to claim 5 is characterized in that: According to the failure probability of each node and its constraints, the failure events to be evaluated and their occurrence paths are determined based on the reliability evaluation network model, including: Establish the constraint conditions of the failure probability of each node to satisfy the following relationship: ， In the formula, is the observed value of the fault population sample The corresponding coupling coefficient; is the observed value of the fault population sample The corresponding probability of failure; and are the observed values ​​of the fault population sample The corresponding lower and upper limits of the probability of failure occurring; When the probability of failure Greater than , it is judged as a high probability failure event ,in, is the number of tests; high probability failure events are taken as the failure events to be evaluated, and high probability failure events are obtained based on the reliability evaluation network model path of occurrence.

7. The reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization according to claim 5 is characterized in that: The failure probability of each node in the reliability assessment network model is verified based on the confidence interval, including: The confidence interval of the fault probability of the fault node is determined according to the fault posterior distribution, and the confidence interval is used to screen the fault probability of the fault node; when the confidence interval is not less than the set interval threshold, the fault probability of the fault node is retained; otherwise, when the confidence interval is less than the set interval threshold, the fault probability of the fault node is removed.

8. The reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization according to claim 7 is characterized in that: Based on the reliability evaluation network model, determine whether the faulty node whose fault occurrence probability is removed is the bottom-level event of each sub-network; if the faulty node is a non-bottom-level event of each sub-network, then based on the occurrence path of the fault event to be evaluated, determine the bottom-level event of each sub-network corresponding to the faulty node in the reliability evaluation network model; According to Bayesian theorem, the failure probability of the faulty node is calculated using the failure rate of the underlying events of each sub-network corresponding to the faulty node; On the contrary, if the faulty node is the underlying event of each sub-network, the failure rate of the underlying event of each sub-network is used as the failure probability of the faulty node.

9. The reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization according to claim 1 is characterized in that: Faulty Node The first reliability index, the second reliability index and the third reliability index satisfy the following relationship: ， In the formula, the faulty node after verification is The probability of failure For the faulty node The first reliability indicator is the fault repair time of the faulty node. For the faulty node The second reliability indicator is the average failure duration of the faulty node. For the faulty node The third reliability indicator.

10. The reliability assessment method of hydrogen-electricity coupled micro-energy network with fault visualization according to claim 1 is characterized in that: The reliability indicators of the hydrogen-electricity coupled micro-energy grid include: the probability of the hydrogen-electricity coupled micro-energy grid stopping hydrogen supply, the probability of the hydrogen-electricity coupled micro-energy grid obtaining hydrogen, and the energy expectation of hydrogen load shortage.

11. A fault-visualized hydrogen-electricity coupled micro-energy grid reliability assessment system, characterized in that: The system includes: Reliability assessment network establishment module, fault event visualization processing module, reliability assessment module; A reliability assessment network establishment module is used to obtain the first top-level fault event and the first fault cause of the hydrogen energy sub-network, the second top-level fault event and the second fault cause of the electric energy sub-network, and the third top-level fault event and the third fault cause of the thermal energy sub-network as nodes to establish a reliability assessment network model that characterizes the relationship between the nodes; The fault event visualization processing module is used to collect micro-energy network fault data and micro-energy network risk data; using statistical methods, according to the fault data and micro-energy network risk data of the micro-energy network, determine the fault probability of each node in the reliability evaluation network model; according to the fault probability of each node and its constraint conditions, determine the fault node corresponding to the fault event to be evaluated and the occurrence path of the fault event to be evaluated based on the reliability evaluation network model; The reliability assessment module is used to verify the failure probability of the fault node in the reliability assessment network model based on the confidence interval, and use the verified failure probability of the fault node, the fault repair time of the fault node and the average fault duration of the fault node as the first reliability index, the second reliability index and the third reliability index of the fault node respectively; the reliability of the hydrogen-electricity coupled micro-energy network is jointly evaluated by using the first reliability index, the second reliability index and the third reliability index of the fault node and the reliability index of the hydrogen-electricity coupled micro-energy network.

12. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images