Modeling method and device for hydrogen leakage situation prediction model
By constructing a hydrogen leakage situation prediction model, using historical data and fuzzy neural networks, the problem of the inability to simulate the spatial and temporal evolution of hydrogen leakage events in the existing technology is solved, and the safety and accuracy of hydrogen leakage prevention and control are improved.
Patent Information
- Application Number
- CN202411235319.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-04
AI Technical Summary
The existing hydrogen leakage prevention and control system cannot effectively simulate the space-time evolution of hydrogen leakage incidents, limiting the improvement of the safety of hydrogen leakage prevention and control.
By obtaining the measurement data of historical hydrogen leakage events and preset leakage risk indicator information, a risk indicator data matrix is constructed, the weights of each leakage risk indicator are calculated, the relative risk identification results are determined, and the preset fuzzy neural network is trained. Establish a hydrogen leakage situation prediction model.
It has realized the effective simulation of the space-time evolution of hydrogen leakage events, improved the safety of hydrogen leakage prevention and control, and can formulate prevention and control strategies more targeted, which has improved the accuracy and reliability of prevention and control.
Smart Images

Figure CN119091997A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of hydrogen energy safety prevention and control, and in particular to a method and device for modeling a hydrogen leakage situation prediction model. Background Art
[0002] Mobile hydrogen power generation devices have the advantages of zero carbon, low noise, and high efficiency, and are the future development direction of emergency power supply. However, at present, there is a lack of safety monitoring and control methods for hydrogen leakage in mobile hydrogen power generation devices in complex scenarios. The risk of gas cloud explosion caused by hydrogen tank leakage is difficult to assess, and the corresponding prevention and control strategies and means are also imperfect, which has become a bottleneck restricting the large-scale application of mobile hydrogen power generation devices in the future.
[0003] The existing hydrogen leakage prevention and control system mainly prevents hydrogen leakage by installing a certain number of hydrogen concentration sensors, hydrogen leakage warning hosts and other equipment in a certain space. However, this prevention and control method can only accurately display the real-time hydrogen leakage situation through the data collected by the sensors after the leakage incident occurs, and cannot effectively simulate the temporal and spatial evolution of the hydrogen leakage incident, making it impossible for staff to formulate more targeted hydrogen leakage prevention and control strategies, limiting the further improvement of the safety of hydrogen leakage prevention and control. Summary of the invention
[0004] The present application provides a method and device for modeling a hydrogen leakage situation prediction model, which is used to solve the technical problem that the existing hydrogen leakage prevention and control cannot effectively simulate the temporal and spatial evolution of hydrogen leakage events, limiting the further improvement of the safety of hydrogen leakage prevention and control.
[0005] In order to solve the above technical problems, the first aspect of the present application provides a method for modeling a hydrogen leakage situation prediction model, comprising:
[0006] Obtain measurement data of historical hydrogen leakage events, preset leakage risk indicator information, and hierarchical system information between different leakage risk indicators;
[0007] Calculating first weights of each item of leakage risk indicator information respectively according to the measurement data;
[0008] According to the hierarchical system information, an indicator judgment matrix corresponding to each level is constructed, wherein the indicator judgment matrix contains the importance comparison results between any indicators in the risk indicator set;
[0009] According to the indicator judgment matrix, the second weight of each leakage risk indicator information is calculated respectively;
[0010] Determine the relative distance between each leakage risk indicator and the worst solution of the indicator according to the risk indicator data matrix and the first weight, and obtain a relative risk identification result according to the relative distance and the second weight;
[0011] According to the relative risk identification result and the measurement data, a preset fuzzy neural network is trained to obtain a hydrogen leakage situation prediction model.
[0012] Preferably, the step of calculating the first weight of each leakage risk indicator information respectively according to the risk indicator data matrix by using an entropy weight method specifically includes:
[0013] Normalizing the elements of the risk indicator data matrix;
[0014] Based on the normalized element values and the preset indicator entropy value calculation formula, the entropy value of each leakage risk indicator information is calculated;
[0015] According to the entropy value of each item of leakage risk indicator information and in combination with a preset entropy value weight calculation formula, a first weight corresponding to each item of leakage risk indicator information is obtained.
[0016] Preferably, before respectively calculating the second weights of each leakage risk indicator information according to the indicator judgment matrix by means of a hierarchical analysis method, the method further includes:
[0017] According to the maximum eigenvalue and matrix order of the indicator judgment matrix, combined with the preset consistency ratio calculation formula, the consistency check result of the indicator judgment matrix is obtained. If the consistency check result passes, the second weight of each leakage risk indicator information is calculated separately according to the indicator judgment matrix through the hierarchical analysis method.
[0018] Preferably, the determining the relative distance between each leakage risk indicator and the worst solution of the indicator by using the good-bad solution distance method based on the standardized matrix and the first weight specifically includes:
[0019] Determine the optimal solution and the worst solution of each leakage risk indicator information according to each element in the standardized matrix;
[0020] According to the optimal solution and the worst solution, combined with the first weight, the distance values between each indicator data of the same leakage risk indicator information and the optimal solution and the worst solution are calculated to obtain the optimal solution distance and the worst solution distance respectively;
[0021] The relative distance degree between the leakage risk index and the worst solution of the index is determined according to the ratio of the worst solution distance to the sum of the optimal solution distance and the worst solution distance.
[0022] Preferably, the hydrogen leakage situation prediction result obtained by the hydrogen leakage situation prediction model in combination with the measured data obtained by field measurement specifically includes:
[0023] The measured data obtained from on-site actual measurement are obtained, the measured data are input into the hydrogen leakage situation prediction model, and the hydrogen leakage situation prediction result is obtained through the operation of the hydrogen leakage situation prediction model.
[0024] Preferably, the calculating the first weight of each item of leakage risk indicator information respectively according to the measurement data specifically includes:
[0025] Constructing a risk indicator data matrix according to the measurement data and the leakage risk indicator information;
[0026] According to the risk indicator data matrix, the first weights of each item of leakage risk indicator information are calculated respectively by using the entropy weight method.
[0027] Preferably, constructing an indicator judgment matrix corresponding to each level according to the hierarchical system information specifically includes:
[0028] According to the hierarchical system information, risk indicators at the same level are classified into the same risk indicator set to obtain several risk indicator sets, and then indicator judgment matrices corresponding to each risk indicator set are constructed respectively.
[0029] Preferably, according to the risk indicator data matrix and the first weight, determining the relative distance between each leakage risk indicator and the worst solution of the indicator, and obtaining the relative risk identification result according to the relative distance and the second weight specifically includes:
[0030] The risk indicator data matrix is subjected to data standardization processing to obtain a standardized matrix, and then the relative distance degree between each leakage risk indicator and the worst solution of the indicator is determined based on the standardized matrix and the first weight through the superior-inferior solution distance method, and the relative distance degree is multiplied by the second weight to obtain a relative risk identification result.
[0031] Preferably, the step of training a preset fuzzy neural network according to the relative risk identification result and the measurement data to obtain a hydrogen leakage situation prediction model specifically includes:
[0032] A fault tree is decomposed according to the highest risk event of hydrogen leakage in the relative risk identification result to obtain several basic component failure events of the highest risk event, and then the measurement data, the basic component failure events and the highest risk event of hydrogen leakage are used as training sets to train a preset fuzzy neural network to obtain a hydrogen leakage situation prediction model that includes the correlation relationship between basic component failure events and measurement data and the correlation relationship between measurement data and hydrogen leakage risk events.
[0033] At the same time, the second aspect of the present application provides a hydrogen leakage situation prediction model modeling device, comprising:
[0034] A historical data acquisition unit, used to acquire measurement data of historical hydrogen leakage events, preset leakage risk indicator information, and hierarchical system information between different leakage risk indicators;
[0035] A first weight calculation unit, used to calculate first weights of each item of leakage risk indicator information respectively according to the measurement data;
[0036] A second matrix construction unit is used to construct an indicator judgment matrix corresponding to each level according to the hierarchical system information, wherein the indicator judgment matrix contains the importance comparison results between any indicators in the risk indicator set;
[0037] A second weight calculation unit, used to calculate the second weight of each leakage risk indicator information according to the indicator judgment matrix;
[0038] A relative risk identification unit, used to determine the relative distance between each leakage risk indicator and the worst solution of the indicator according to the risk indicator data matrix and the first weight, and obtain a relative risk identification result according to the relative distance and the second weight;
[0039] The prediction model generating unit is used to train a preset fuzzy neural network according to the relative risk identification result and the measurement data to obtain a hydrogen leakage situation prediction model.
[0040] It can be seen from the above technical solutions that this application has the following advantages:
[0041] The scheme of the present application first obtains the measurement data of historical hydrogen leakage events, the preset leakage risk indicator information and the hierarchical system information between different leakage risk indicators, and then constructs a risk indicator data matrix according to the measurement data and the leakage risk indicator information, and respectively calculates the first weight of each leakage risk indicator information by the entropy weight method, and then classifies the risk indicators of the same level into the same risk indicator set according to the hierarchical system information, so as to respectively construct the indicator judgment matrix corresponding to each risk indicator set, and then respectively calculates the second weight of each leakage risk indicator information by the hierarchical analysis method, and then, based on the first weight and the second weight, the relative distance degree between each leakage risk indicator and the worst solution of the indicator is determined by the superior and inferior solution distance method, and the relative distance degree is multiplied by the second weight to obtain the relative risk identification result, and the fault tree is decomposed according to the highest risk event of hydrogen leakage in the relative risk identification result to obtain several basic component failure events of the highest risk event, and then the measurement data, the basic component failure event and the highest risk event of hydrogen leakage are used as training sets to train the preset fuzzy neural network to obtain a hydrogen leakage situation prediction model including the correlation relationship between the basic component failure event and the measurement data and the correlation relationship between the measurement data and the hydrogen leakage risk event. In actual application, it is only necessary to use on-site sensors and input the collected measured data into the established hydrogen leakage situation prediction model. By calculating the prior knowledge in the hydrogen leakage situation prediction model, the hydrogen leakage situation prediction result can be obtained. This solves the technical problem that the existing hydrogen leakage prevention and control cannot effectively simulate the spatiotemporal evolution of concentration after the occurrence of hydrogen leakage, which limits the further improvement of the safety of hydrogen leakage prevention and control. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0043] Figure 1 A schematic flow chart of an embodiment of a method for modeling a hydrogen leakage situation prediction model provided in the present application.
[0044] Figure 2 A logic block diagram of the overall process of an embodiment of a hydrogen leakage situation prediction modeling method provided in this application.
[0045] Figure 3 It is the risk hierarchy system information between hydrogen leakage risk indicators.
[0046] Figure 4A schematic structural diagram of an embodiment of a hydrogen leakage situation prediction model building device provided in the present application. DETAILED DESCRIPTION
[0047] The present application provides a method and device for modeling a hydrogen leakage situation prediction model, which is used to solve the technical problem that the existing hydrogen leakage prevention and control cannot effectively simulate the temporal and spatial evolution of hydrogen leakage events, limiting the further improvement of the safety of hydrogen leakage prevention and control.
[0048] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described below are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0049] First, a detailed description of an embodiment of a hydrogen leakage prediction modeling method provided by the first aspect of the present application is as follows:
[0050] See also Figures 1 to 3 , a hydrogen leakage situation prediction model modeling method provided in this embodiment includes:
[0051] Step 101: Obtain measurement data of historical hydrogen leakage events, preset leakage risk indicator information, and hierarchical system information of information between different leakage risk indicators.
[0052] It should be noted that first, the risk events, systems and risk indicators that need to be assessed are determined, such as the hydrogen leakage risk event library of hydrogen fuel emergency power supply vehicles, the risk system and its corresponding scenarios and fault categories. Then, a risk matrix model is established. The description of the risk matrix varies according to the risk, and the score data of the two indicators of risk possibility and severity are included.
[0053] Step 102: Calculate the first weight of each leakage risk indicator information according to the measurement data.
[0054] It should be noted that the constructed risk indicator data matrix can be expressed by the following formula (1):
[0055] (1)
[0056] Among them, the matrix The number of rows m represents the number of risk events, and the number of columns n represents the number of indicators in the risk matrix, which is generally 2, namely the severity and possibility of risk.
[0057] Based on the obtained risk indicator data matrix, the first weight of each leakage risk indicator information is calculated by the entropy weight method. .
[0058] More specifically, using formula (2) The data were normalized.
[0059] (2)
[0060] In the formula, is the value of the jth evaluation indicator of the ith evaluated risk event. for Normalized value.
[0061] Then use formula (3) to calculate the entropy value of the jth evaluation index ,have
[0062]
[0063] Finally, use formula (4) to calculate the weight of the jth index ,Right now
[0064]
[0065] Step 103: construct an indicator judgment matrix corresponding to each level according to the hierarchical system information.
[0066] Among them, the indicator judgment matrix contains the importance comparison results between any indicators in the risk indicator set.
[0067] It should be noted that after using the entropy weight method to complete the weighting of the risk matrix indicators, the hierarchical analysis method is used to weight the risk indicators of the risk system.
[0068] (1) First, classify and summarize the indicators of the risk system to form multi-level indicators, and compare the indicators of the same level in pairs to form a judgment matrix. . As shown in the following formula (5).
[0069]
[0070] In the formula, represents n risk indicators of the same level, Indicators Relative to the indicator Its value is usually determined by the nine-level scale method, as shown in Table 1.
[0071] Table 1 Nine-level scale and its meaning
[0072]
[0073] In some embodiments, the judgment matrix is obtained After that, the consistency of the judgment matrix can be checked to avoid logical errors in comparison. The consistency test is to compare the consistency ratio CR with 0.1. If CR < 0.1, the consistency test passes, otherwise the judgment matrix needs to be readjusted. The calculation method of CR value is shown in formula (6).
[0074]
[0075] Among them, CI is the consistency index, and its value can be obtained by formula (7). RI is the average random consistency index, and its common values are shown in Table 2.
[0076]
[0077] In the formula, is the judgment matrix The maximum eigenvalue of , n is the number of indices and also the matrix order.
[0078] Table 2 RI value table
[0079]
[0080] When the consistency check of the judgment matrix passes, the process may jump to step 105 to continue the subsequent weight calculation.
[0081] Step 104: Calculate the second weight of each leakage risk indicator information according to the indicator judgment matrix.
[0082] It should be noted that the geometric mean method is used for calculation, and the calculation formula is shown in formula (8).
[0083]
[0084] in, is the indicator weight of the indicator at this level. After obtaining the weight, in order to facilitate data processing, the weight is normalized by formula (9) to obtain the normalized weight value .
[0085]
[0086] Finally, if there are multiple levels of indicators, the weight of each level of indicators is calculated and the total weight is calculated by formula (10): .
[0087]
[0088] in, is the weight of the first-level indicator relative to the target layer, is the weight of the secondary indicator relative to the primary indicator.
[0089] Step 105: Determine the relative distance between each leakage risk indicator and the worst solution of the indicator according to the risk indicator data matrix and the first weight, and obtain the relative risk identification result according to the relative distance and the second weight.
[0090] It should be noted that the original data must first be consistent, that is, processed in a positive way. The relevant literature on the positive processing method has been described in detail, so it will not be repeated here. From the perspective of risk classification, the indicator data of the risk matrix is obviously a very large-scale data with the same trend. Therefore, the data is processed in a positive way according to formula (11). After obtaining the positive data, the data needs to be standardized according to formula (12) to construct a standardized matrix .
[0091]
[0092] In the formula, and They represent the minimum and maximum values of the data under the j-th indicator respectively.
[0093]
[0094] After obtaining the standardized matrix, the data scores are sorted using the superior-inferior solution distance method using equations (13)-(15). However, the traditional method only considers the weight of the indicator in which the data itself is located. Corresponding to the risk matrix, that is, only the weights of the two indicators of the risk matrix are considered, and the weights of the risk system indicators are not considered. Therefore, this embodiment improves it by adding the risk system weight to improve the calculation method. The improved method is shown in equation (16).
[0095]
[0096]
[0097]
[0098] In the formula, and They represent the distance between the evaluation object and the worst solution and the optimal solution respectively. In the risk matrix, they are the distance between the minimum and maximum values of the two indicator data. represents the j-th risk matrix indicator, and They respectively represent the minimum and maximum value of the risk data under the j-th indicator. The value indicates the relative distance from the worst solution. The larger the value, the farther the research object is from the worst solution. Corresponding to the risk matrix, it can be understood as the relative distance from the minimum value of the risk indicator data. The larger the value, the higher the risk level.
[0099]
[0100] Step 106: According to the relative risk identification result and the measurement data, a preset fuzzy neural network is trained to obtain a hydrogen leakage situation prediction model.
[0101] It should be noted that according to the relative risk identification results obtained in the previous step, the highest relative risk event is determined, and the explosion event caused by hydrogen leakage (i.e. the highest relative risk event identified by the improved risk matrix method) is used as the top event to perform a fault tree analysis on the hydrogen leakage explosion event, and the key basic events (component failure, etc.) of the hydrogen leakage explosion event are determined through the dynamic Bayesian network by consulting the data; the mechanism analysis of the key basic events (key components) is carried out, and the failure model of the key components is established, and the key state parameters that cause the failure of the key components are determined, and the association model between the failure state parameters of the key components and hydrogen leakage is established, so as to obtain the hydrogen leakage situation prediction model. The obtained hydrogen leakage situation prediction model can be implanted in the on-site terminal, and then the relevant parameters are measured by using the corresponding sensors arranged on-site, and the measured parameters are input into the failure model to determine the failure state of the components, thus completing the construction of the hydrogen leakage risk identification module.
[0102] The following are specific scenario examples provided in this application, as follows: Taking the event of metal corrosion in batteries as an example, the entropy weight method (EWM) in the improved risk matrix method is first used to determine the weight offset of its severity and possibility, and then the analytical layer processing method (AHP) is used to determine the relative weight of the power generation scenario. Finally, combined with the determined indicator weight value, the superiority and inferior solution distance method (TOPSIS) method is used to calculate the risk score, and after comparing the scores, it is determined that the risk level is the highest.
[0103] Then the failure causes of metal corrosion in the battery are analyzed, the failure characteristics of the two components are extracted, and the fuzzy neural network is trained based on the relationship between component failure and hydrogen leakage.
[0104] The trained model is then deployed on site to perform status perception of hydrogen leakage in hydrogen fuel cell application scenarios.
[0105] In the hydrogen fuel cell system, there are hydrogen storage tanks, valves, hydrogen pipelines and hydrogen fuel cells. The improved risk matrix was used to determine that valves and pipelines are most likely to have hydrogen leakage;
[0106] Then, the failure causes of valves and pipelines were analyzed, the failure characteristics of these two components were extracted, and the fuzzy network was trained to train the correlation between component failure and hydrogen leakage.
[0107] The trained model is then deployed on site to perform status perception of hydrogen leakage in hydrogen fuel cell application scenarios.
[0108] Conduct numerical calculation and simulation analysis on the temporal and spatial evolution of hydrogen concentration under various circumstances of hydrogen leakage in the computer;
[0109] Use some numerical simulation results to train graph convolutional neural networks, PINN neural networks, etc. for hydrogen leakage in hydrogen-related scenarios, and use other numerical simulation results as test sets to improve the model prediction speed and accuracy;
[0110] Deploy the trained AI model at hydrogen-related sites;
[0111] At hydrogen-related sites, hydrogen concentration sensors, temperature and humidity sensors, and wind speed and direction sensors are used to measure flow field information, and the temporal and spatial evolution of hydrogen concentration can be visualized after hydrogen leakage is detected;
[0112] Complete the temporal and spatial evolution model of hydrogen concentration monitoring;
[0113] By inputting information from multiple sensors into the graph neural network, we can make full use of the complex relationships between various environmental factors to improve the accuracy and reliability of predictions. For example, the graph neural network can identify the characteristic patterns of changes in hydrogen concentration under specific wind speed and temperature conditions, and provide early warning of potential leakage risks. At the same time, the graph neural network model can dynamically adjust the prediction of hydrogen diffusion behavior under different environmental conditions, providing a scientific basis for emergency response.
[0114] Hydrogen leakage sensors are placed at the hydrogen storage bottle mouth, passenger compartment and fuel cell engine system where hydrogen is easy to accumulate and leak, to monitor the hydrogen content in the car in real time. Once hydrogen leakage occurs, immediate response measures are taken to ensure the safety of passengers. Moreover, when the hydrogen volume fraction detected by any sensor exceeds 10%, 25% and 50% of the lower explosion limit of hydrogen (the volume content of hydrogen in the air is 4%), the monitor will issue level I, level II and level III sound and light alarm signals respectively. Specific control measures are shown in Table 3:
[0115] Table 3 Hydrogen leakage safety situation level table
[0116]
[0117] With reference to the national emergency plan for public emergencies, and combined with the characteristics of factors such as hydrogen leakage and external environment, the security level of network security situation is divided into 5 levels, and the weights and characteristics of each level are quantitatively described using values in the [0,1] interval.
[0118] Combined with the characteristics of fuzzy neural network with strong learning ability and fuzzy information processing, this method is used to effectively identify hydrogen leaks of different concentrations. An FNN model with an input layer, a fuzzy layer, a fuzzy reasoning layer, a compensation operation layer and an output layer is established. The number of input layer nodes is determined by the on-site hydrogen leakage concentration data detected by the hydrogen sensor under different environments, and corresponds to the nodes one by one; the number of fuzzy layer nodes is determined by the number of input variables and their fuzzy subsets; the number of fuzzy reasoning layer and compensation operation layer nodes are determined by the number of rules m; the number of output layer nodes is 1.
[0119] Safety situation assessment and intelligent prediction are carried out based on the hydrogen leakage concentration data detected by hydrogen sensors in different environments. The numerical simulation model under fault conditions is used to simulate the system status database under different fault modes, fault locations, and fault degrees. Based on the hydrogen release characteristics and hydrogen equipment safety prediction mechanism, a hydrogen safety situation awareness system is constructed.
[0120] The above is a detailed description of an embodiment of a hydrogen leakage situation prediction model modeling method provided by the present application. The following is a detailed description of an embodiment of a hydrogen leakage situation prediction model modeling device provided by the present application.
[0121] See also Figure 4 , a hydrogen leakage situation prediction model building device provided in this embodiment includes:
[0122] A historical data acquisition unit 201 is used to acquire measurement data of historical hydrogen leakage events, preset leakage risk indicator information, and hierarchical system information between different leakage risk indicators;
[0123] A first weight calculation unit 202, used to calculate first weights of various leakage risk indicator information respectively according to the measurement data;
[0124] The second matrix construction unit 203 is used to construct an indicator judgment matrix corresponding to each level according to the hierarchical system information, wherein the indicator judgment matrix contains the importance comparison results between any indicators in the risk indicator set;
[0125] A second weight calculation unit 204 is used to calculate the second weight of each leakage risk indicator information according to the indicator judgment matrix;
[0126] The relative risk identification unit 205 is used to determine the relative distance between each leakage risk indicator and the worst solution of the indicator according to the risk indicator data matrix and the first weight, and obtain the relative risk identification result according to the relative distance and the second weight;
[0127] The prediction model generating unit 206 is used to train a preset fuzzy neural network according to the relative risk identification result and the measurement data to obtain a hydrogen leakage situation prediction model.
[0128] Preferably, the first weight calculation unit 202 is specifically used for:
[0129] Normalize the elements of the risk indicator data matrix;
[0130] Based on the normalized element values and the preset indicator entropy value calculation formula, the entropy value of each leakage risk indicator information is calculated;
[0131] According to the entropy value of each leakage risk indicator information, combined with a preset entropy value weight calculation formula, a first weight corresponding to each leakage risk indicator information is obtained.
[0132] Preferably, it also includes:
[0133] The consistency check unit 2040 is used to obtain the consistency check result of the indicator judgment matrix based on the maximum eigenvalue and matrix order of the indicator judgment matrix, combined with a preset consistency ratio calculation formula. If the consistency check result passes, the second weight of each leakage risk indicator information is calculated separately according to the indicator judgment matrix through the hierarchical analysis method.
[0134] Preferably, the relative risk identification unit 205 is specifically used for:
[0135] A relative risk identification unit is used to perform data standardization processing on the risk indicator data matrix to obtain a standardized matrix;
[0136] According to each element in the standardized matrix, determine the optimal and worst solutions for each leakage risk indicator information;
[0137] According to the optimal solution and the worst solution, combined with the first weight, the distance values between the various indicator data of the same leakage risk indicator information and the optimal solution and the worst solution are calculated to obtain the optimal solution distance and the worst solution distance respectively;
[0138] According to the ratio of the worst solution distance to the sum of the optimal solution distance and the worst solution distance, the relative distance between the leakage risk index and the worst solution of the index is determined.
[0139] Preferably, the hydrogen leakage situation prediction model is combined with the measured data obtained by field measurement to obtain the hydrogen leakage situation prediction results, which specifically include:
[0140] The measured data obtained from on-site actual measurement are obtained, and the measured data are input into the hydrogen leakage situation prediction model. The hydrogen leakage situation prediction result is obtained through the operation of the hydrogen leakage situation prediction model.
[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the terminals, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0142] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0143] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0144] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0146] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0147] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0148] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for modeling a hydrogen leakage prediction model, characterized in that: include: Obtain measurement data of historical hydrogen leakage events, preset leakage risk indicator information, and hierarchical system information between different leakage risk indicators; Calculating first weights of each item of leakage risk indicator information respectively according to the measurement data; According to the hierarchical system information, an indicator judgment matrix corresponding to each level is constructed, wherein the indicator judgment matrix contains the importance comparison results between any indicators in the risk indicator set; According to the indicator judgment matrix, the second weight of each leakage risk indicator information is calculated respectively; Determine the relative distance between each leakage risk indicator and the worst solution of the indicator according to the risk indicator data matrix and the first weight, and obtain a relative risk identification result according to the relative distance and the second weight; According to the relative risk identification result and the measurement data, a preset fuzzy neural network is trained to obtain a hydrogen leakage situation prediction model.
2. The method for modeling a hydrogen leakage prediction model according to claim 1, characterized in that: The step of calculating the first weight of each leakage risk indicator information respectively according to the risk indicator data matrix by using the entropy weight method specifically includes: Normalizing the elements of the risk indicator data matrix; Based on the normalized element values and the preset indicator entropy value calculation formula, the entropy value of each leakage risk indicator information is calculated; According to the entropy value of each item of leakage risk indicator information and in combination with a preset entropy value weight calculation formula, a first weight corresponding to each item of leakage risk indicator information is obtained.
3. The method for modeling a hydrogen leakage prediction model according to claim 1, characterized in that: The step of calculating the second weight of each leakage risk indicator information respectively according to the indicator judgment matrix by using the hierarchical analysis method also includes: According to the maximum eigenvalue and matrix order of the indicator judgment matrix, combined with the preset consistency ratio calculation formula, the consistency check result of the indicator judgment matrix is obtained. If the consistency check result passes, the second weight of each leakage risk indicator information is calculated separately according to the indicator judgment matrix through the hierarchical analysis method.
4. The method for modeling a hydrogen leakage prediction model according to claim 1, characterized in that: The step of determining the relative distance between each leakage risk indicator and the worst solution of the indicator according to the standardized matrix and the first weight by using the superior-inferior solution distance method specifically includes: Determine the optimal solution and the worst solution of each leakage risk indicator information according to each element in the standardized matrix; According to the optimal solution and the worst solution, combined with the first weight, the distance values between each indicator data of the same leakage risk indicator information and the optimal solution and the worst solution are calculated to obtain the optimal solution distance and the worst solution distance respectively; The relative distance degree between the leakage risk index and the worst solution of the index is determined according to the ratio of the worst solution distance to the sum of the best solution distance and the worst solution distance.
5. The method for modeling a hydrogen leakage situation prediction model according to claim 1, characterized in that: The hydrogen leakage situation prediction model is combined with the measured data obtained by field measurement to obtain the hydrogen leakage situation prediction result, which specifically includes: The measured data obtained from on-site actual measurement are obtained, the measured data are input into the hydrogen leakage situation prediction model, and the hydrogen leakage situation prediction result is obtained through the operation of the hydrogen leakage situation prediction model.
6. The method for modeling a hydrogen leakage prediction model according to claim 1, characterized in that: The calculating the first weight of each leakage risk indicator information respectively according to the measurement data specifically includes: Constructing a risk indicator data matrix according to the measurement data and the leakage risk indicator information; According to the risk indicator data matrix, the first weights of each item of leakage risk indicator information are calculated respectively by using the entropy weight method.
7. The method for modeling a hydrogen leakage situation prediction model according to claim 1, characterized in that: The step of constructing an indicator judgment matrix corresponding to each level according to the hierarchical system information specifically includes: According to the hierarchical system information, risk indicators at the same level are classified into the same risk indicator set to obtain several risk indicator sets, and then indicator judgment matrices corresponding to each risk indicator set are constructed respectively.
8. The method for modeling a hydrogen leakage prediction model according to claim 1, characterized in that: According to the risk indicator data matrix and the first weight, the relative distance between each leakage risk indicator and the worst solution of the indicator is determined, and according to the relative distance and the second weight, the relative risk identification result is obtained, which specifically includes: The risk indicator data matrix is subjected to data standardization processing to obtain a standardized matrix, and then the relative distance degree between each leakage risk indicator and the worst solution of the indicator is determined based on the standardized matrix and the first weight through the superior-inferior solution distance method, and the relative distance degree is multiplied by the second weight to obtain a relative risk identification result.
9. The method for modeling a hydrogen leakage situation prediction model according to claim 1, characterized in that: The step of training a preset fuzzy neural network according to the relative risk identification result and the measurement data to obtain a hydrogen leakage situation prediction model specifically includes: A fault tree is decomposed according to the highest risk event of hydrogen leakage in the relative risk identification result to obtain several basic component failure events of the highest risk event, and then the measurement data, the basic component failure events and the highest risk event of hydrogen leakage are used as training sets to train a preset fuzzy neural network to obtain a hydrogen leakage situation prediction model that includes the correlation relationship between basic component failure events and measurement data and the correlation relationship between measurement data and hydrogen leakage risk events.
10. A hydrogen leakage prediction model building device, characterized in that: include: A historical data acquisition unit, used to acquire measurement data of historical hydrogen leakage events, preset leakage risk indicator information, and hierarchical system information between different leakage risk indicators; A first weight calculation unit, used to calculate first weights of each item of leakage risk indicator information respectively according to the measurement data; A second matrix construction unit is used to construct an indicator judgment matrix corresponding to each level according to the hierarchical system information, wherein the indicator judgment matrix contains the importance comparison results between any indicators in the risk indicator set; A second weight calculation unit, used to calculate the second weight of each leakage risk indicator information according to the indicator judgment matrix; A relative risk identification unit, used to determine the relative distance between each leakage risk indicator and the worst solution of the indicator according to the risk indicator data matrix and the first weight, and obtain a relative risk identification result according to the relative distance and the second weight; The prediction model generating unit is used to train a preset fuzzy neural network according to the relative risk identification result and the measurement data to obtain a hydrogen leakage situation prediction model.
Citation Information
Patent Citations
Optimal selection method of saline water layer CO2 geological storage injection scheme based on AHP-EWM-TOPSIS
CN118468603A
Method for optimally selecting flood-control operation scheme based on temporal convolutional network
US20230196076A1
Cited By
Prediction and control method and system for fuel cell hydrogen accident
CN120089763A
