Method for determining glass curtain wall performance and related device

Abstract

An embodiment of the present application provides a method and related device for determining the performance of a glass curtain wall. The method includes: obtaining a static Bayesian network for detecting the performance of the glass curtain wall; determining the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall; obtaining the relationship between the state changes of the components of the glass curtain wall; determining the transition conditional probability of the static Bayesian network according to the relationship between the state changes of the components, the failure rate of the components, and the repair rate of the components; determining a dynamic Bayesian network according to the transition conditional probability, the static conditional probability, and the static Bayesian network; and determining the performance information of the glass curtain wall according to the dynamic Bayesian network. It is possible to obtain the performance information of the glass curtain wall based on the determined dynamic Bayesian network, improving the accuracy when determining the performance information of the glass curtain wall.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a method for determining the performance of a glass curtain wall and related devices. Background Art

[0002] With the development of the cruise ship building industry, there are more and more designs of installing glass curtain walls on ships. With the increasing number of glass curtain walls put into use and the growth of their service life, various safety problems that occur during the installation and use of glass curtain walls have received more and more attention. In fact, there is still a lack of research on the design of glass curtain walls in cruise ships, and various conditions such as dynamic loads and erosion at sea are more complex than on land. Therefore, further research on the safety of glass curtain walls is more needed.

[0003] At present, there is little research on the safety performance evaluation of glass curtain walls, mainly based on static risk assessment or multi-criteria decision-making methods, without considering the influence of the change of evaluation indicators over time. Moreover, in fact, each component in the glass curtain wall system does not have only two absolute states of "safe" and "failed", but there are multiple degradation states, resulting in low accuracy in performance analysis. Summary of the Invention

[0004] An embodiment of this application provides a method for determining the performance of a glass curtain wall and related devices, which can obtain the performance information of the glass curtain wall based on a determined dynamic Bayesian network, improving the accuracy when determining the performance information of the glass curtain wall.

[0005] The first aspect of the embodiment of this application provides a method for determining the performance of a glass curtain wall, and the method includes:

[0006] Obtain a static Bayesian network, which is used to detect the performance of the glass curtain wall;

[0007] Determine the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall;

[0008] Obtain the relationship between the state changes of the components of the glass curtain wall;

[0009] Determine the transition conditional probability of the static Bayesian network according to the relationship between the state changes of the components, the failure rate of the components, and the repair rate of the components;

[0010] Determine a dynamic Bayesian network according to the transition conditional probability, the static conditional probability, and the static Bayesian network;

[0011] Determine the performance information of the glass curtain wall according to the dynamic Bayesian network.

[0012] In combination with the first aspect, in a possible implementation manner, the obtaining of the static Bayesian network includes:

[0013] Obtain multiple component information of the glass curtain wall;

[0014] Perform logical analysis and processing on the multiple component information to obtain the logical relationships between the components corresponding to each component information in the multiple component information;

[0015] Determine a fault tree according to the logical relationships between the components corresponding to each component information in the multiple component information;

[0016] Determine the static Bayesian network according to the fault tree.

[0017] In combination with the first aspect, in a possible implementation manner, the determining of the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall includes:

[0018] Obtain a multi-state degradation model;

[0019] Determine the static conditional probability of the static Bayesian network according to the multi-state degradation model and the degradation probability of the components of the glass curtain wall.

[0020] In combination with the first aspect, in a possible implementation manner, the determining of the static conditional probability of the static Bayesian network according to the multi-state degradation model and the degradation probability of the components of the glass curtain wall includes:

[0021] The static conditional probability can be determined through the multi-state degradation model and the degradation probability shown in the following formula:

[0022]

[0023] where is called the degradation probability of component X i The set of parent nodes of component Y in the Bayesian network is π(Y), P(Y|π(Y)) is the static conditional probability of the occurrence of component Y, and component X i is the parent node of component Y.

[0024] In combination with the first aspect, in a possible implementation manner, the method further includes:

[0025] Obtain the mutual information between the components of the glass curtain wall;

[0026] Obtain the mutual information between the components of the glass curtain wall through the method shown in the following formula:

[0027]

[0028] Among them, I(T, X) is the mutual information between component X and component T, P(t, x) is the joint probability distribution function of component T and component X, P(T) is the marginal distribution probability of component T, and P(X) is the marginal probability distribution function of component X respectively.

[0029] The second aspect of the embodiments of the present application provides a device for determining the performance of a glass curtain wall. The device includes:

[0030] A first acquisition unit, configured to acquire a static Bayesian network, where the static Bayesian network is used to detect the performance of the glass curtain wall;

[0031] A first determination unit, configured to determine the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall;

[0032] A second acquisition unit, configured to acquire the relationship of component state changes of the glass curtain wall;

[0033] A second determination unit, configured to determine the transition conditional probability of the static Bayesian network according to the component state change relationship, the failure rate of the components, and the repair rate of the components;

[0034] A third determination unit, configured to determine a dynamic Bayesian network according to the transition conditional probability, the static conditional probability, and the static Bayesian network;

[0035] A fourth determination unit, configured to determine the performance information of the glass curtain wall according to the dynamic Bayesian network.

[0036] Combined with the second aspect, in a possible implementation manner, the first acquisition unit is used to:

[0037] Acquire multiple component information of the glass curtain wall;

[0038] Perform logical analysis processing on the multiple component information to obtain the logical relationship between components corresponding to each component information in the multiple component information;

[0039] Determine a fault tree according to the logical relationship between components corresponding to each component information in the multiple component information;

[0040] Determine the static Bayesian network according to the fault tree.

[0041] Combined with the second aspect, in a possible implementation manner, the first determination unit is used to:

[0042] Acquire a multi-state degradation model;

[0043] Determine the static conditional probability of the static Bayesian network according to the multi-state degradation model and the degradation probability of the components of the glass curtain wall.

[0044] In combination with the second aspect, in a possible implementation manner, in terms of determining the static conditional probability of the static Bayesian network according to the multi-state degradation model and the degradation probability of the components of the glass curtain wall, the first determining unit is configured to:

[0045] The static conditional probability can be determined through the multi-state degradation model and the degradation probability shown in the following formula:

[0046]

[0047] wherein, is called the degradation probability of component X i in the Bayesian network, the set of parent nodes of component Y is π(Y), P(Y|π(Y)) is the static conditional probability of the occurrence of component Y, and component X i is the parent node of component Y.

[0048] In combination with the second aspect, in a possible implementation manner, the device is further configured to:

[0049] Obtain the mutual information between the components of the glass curtain wall;

[0050] The mutual information between the components of the glass curtain wall is obtained through the method shown in the following formula:

[0051]

[0052] wherein, I(T,X) is the mutual information between component X and component T, P(t,x) is the joint probability distribution function of component T and component X, P(T) is the marginal distribution probability of component T, and P(X) are the marginal probability distribution functions of component X respectively.

[0053] A third aspect of the embodiments of the present application provides a terminal, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are interconnected. Among them, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiments of the present application.

[0054] A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application.

[0055] A fifth aspect of the embodiments of the present application provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0056] Implementing the embodiments of the present application has at least the following beneficial effects:

[0057] Obtain a static Bayesian network for performing performance detection on a glass curtain wall. Determine the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall. Obtain the relationship between the state changes of the components of the glass curtain wall. Determine the transition conditional probability of the static Bayesian network according to the relationship between the component state changes, the failure rate of the components, and the repair rate of the components. Determine a dynamic Bayesian network according to the transition conditional probability, the static conditional probability, and the static Bayesian network. Determine the performance information of the glass curtain wall according to the dynamic Bayesian network. Therefore, the performance information of the glass curtain wall can be obtained based on the determined dynamic Bayesian network, improving the accuracy of determining the performance information of the glass curtain wall. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0059] Figure 1A FIG. is a schematic flowchart of a method for determining the performance of a glass curtain wall provided by an embodiment of the present application;

[0060] Figure 1B FIG. is a state transition diagram of a component provided by an embodiment of the present application;

[0061] Figure 1C An embodiment of the present application provides a schematic diagram of a dynamic Bayesian network model of a glass curtain wall;

[0062] Figure 1D An embodiment of the present application provides a schematic diagram of a fault tree;

[0063] Figure 1E An embodiment of the present application provides a schematic diagram of a static Bayesian network model of a glass curtain wall;

[0064] Figure 1F An embodiment of the present application provides a schematic diagram of the reliability of a glass curtain wall;

[0065] Figure 1G An embodiment of the present application provides a schematic diagram of the reliability of a glass curtain wall;

[0066] Figure 1H An embodiment of the present application provides a schematic diagram of the contribution of the safety performance of a component;

[0067] Figure 2 It is a schematic diagram of the structure of a terminal provided by an embodiment of the present application;

[0068] Figure 3 An embodiment of the present application provides a schematic diagram of the structure of a device for determining the performance of a glass curtain wall. Detailed implementation manners

[0069] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0070] The terms "first", "second", etc. in the specification and claims of the present application and the above accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0071] Referring to "embodiment" in the present application means that a specific feature, structure or characteristic described in combination with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments.

[0072] Please refer to Figure 1A , Figure 1A It is a schematic diagram of the process of a method for determining the performance of a glass curtain wall provided by an embodiment of the present application. As Figure 1A shown, the method includes:

[0073] 101. Obtain a static Bayesian network, where the static Bayesian network is used to detect the performance of a glass curtain wall.

[0074] A static Bayesian network can be obtained based on the logical relationships between components obtained through logical analysis and processing of the component information of multiple components of a glass curtain wall.

[0075] When performing logical analysis, the logical relationships can be determined based on the association relationships between components. The components of a glass curtain wall can include a glass panel (C1), an adhesive (C2), an opening window (C3), and a support member (C4). Of course, it can also be divided into other components. Here, it is only for illustrative purposes and is not specifically limited. The occurrence of a fault in any one of the components of the glass curtain wall will cause a fault in the glass curtain wall.

[0076] 102. Determine the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall.

[0077] The static conditional probability can be determined based on a multi-state degradation model and the degradation probability.

[0078] 103. Obtain the relationship between the state changes of the components of the glass curtain wall.

[0079] The states of the components of the glass curtain wall include: state No, first degradation state DS1, second degradation state DS2, and state Yes. Among them, state No refers to the fault-free or normal working state, and state Yes refers to the fault or failure state. Each component is initially in the working state (No). As time goes by, it may enter the first (DS1) or second (DS2) degradation state, or it may enter the fault state (Yes).

[0080] As Figure 1B shown, Figure 1B a state transition diagram is provided. λ 1 、λ 2 、λ 3 、λ 4 、λ 5 、λ 6， are the failure rates for the transitions between multiple states of the component, and μ 1 、μ 2 、μ 3 、μ 4 、μ 5 are the repair rates for the transitions between multiple states of the component. The above failure probabilities and repair rates can be expressed by the following formulas:

[0081] λ 3 =λ 4 =λ 6 ,

[0082] λ 1 +λ 4 +λ 5 =λ,

[0083] λ 1 : λ 4 : λ 5 = 1:3:6,

[0084] μ 1 = μ 4 ,

[0085] μ 2 = μ 5 ,

[0086] μ 1 + μ 2 + μ 3 = μ,

[0087] μ 1 : μ 2 : μ 3 = 1:2:7,

[0088] where λ is the prior failure probability and μ is the prior repair rate.

[0089] 104. Determine the transition conditional probability of the static Bayesian network according to the relationship between the component state changes, the failure rate of the component, and the repair rate of the component.

[0090] When determining the transition conditional probability, different component states can correspond to different conditional transition probabilities, and the transition conditional probability can be specifically determined through the following conversion relation table:

[0091] Table 1 is the conversion relation table between continuous nodes without considering repair. Table 1

[0092]

[0093] Table 2 is the conversion relation table between continuous nodes considering complete repair:

[0094] Table 2

[0095]

[0096] Table 3 is the conversion relation table between continuous nodes considering incomplete repair:

[0097] Table 3

[0098]

[0099]

[0100] Table 4 is the conversion relation table between continuous nodes considering incomplete repair and preventive maintenance:

[0101] Table 4

[0102]

[0103] 105. Determine a dynamic Bayesian network based on the transfer conditional probability, the static conditional probability, and the static Bayesian network.

[0104] The logical relationships between components in the static Bayesian network can be adjusted according to the static conditional probability to obtain an adjusted static Bayesian network, and the logical relationships can be extended according to the transfer conditional probability to obtain a dynamic Bayesian network.

[0105] As Figure 1C shown, Figure 1C shows a schematic diagram of a dynamic Bayesian network model of a glass curtain wall.

[0106] 106. Determine the performance information of the glass curtain wall according to the dynamic Bayesian network.

[0107] Operations can be performed according to the dynamic Bayesian network to obtain the performance information of the glass curtain wall at different times, and the performance information can be safety performance information, etc.

[0108] Specifically, for example: As Figure 1C shown, component nodes C1, C2, C3, and C4 are all in their normal working states (No = 100%) at the initial time t = 0. As the prior probability of the Bayesian network, combined with the transfer conditional probability obtained in the previous steps considering different maintenance modes, calculate the prior probabilities of the corresponding nodes C5, C6, C7, and C7 at time t 1 under different maintenance modes. Then, combined with the static conditional probability distribution, by the chain rule, the joint probability distribution between nodes is The probability of node X i is The occurrence probability P 2 of the glass curtain wall system being safe and fault-free (state is No) for node X2 is calculated through the above formula. Without considering maintenance, the calculated probability P 2 is the reliability of the system, and the probabilities P 2 calculated under different maintenance modes represent the availability of the system. Analyze the impact of different maintenance modes on the safety performance of the system to guide the formulation of maintenance strategies.

[0109] In a possible implementation manner, a possible method for obtaining a static Bayesian network includes:

[0110] A1. Obtain multiple component information of the glass curtain wall;

[0111] A2. Perform logical analysis and processing on the multiple component information to obtain the logical relationships between components corresponding to each component information in the multiple component information;

[0112] A3. Determine a fault tree according to the logical relationships between the components corresponding to each piece of component information among the multiple pieces of component information;

[0113] A4. Determine the static Bayesian network according to the fault tree.

[0114] Component information can be obtained from a database. The components can include a glass panel (C1), an adhesive (C2), an opening window (C3), and a support member (C4).

[0115] Specifically, logical analysis and processing can be performed according to the association relationships between the components. The association relationships can be understood as whether the components are nested, connected, etc. Logical combinations can be made according to the logical relationships to obtain a fault tree. For example, Figure 1D as shown, Figure 1D shows a schematic diagram of a fault tree. Among them, X is a glass curtain wall. This fault tree can be understood as: if any one of the components C1 - C4 fails, the glass curtain wall will fail. Logical mapping can be performed according to the fault tree to obtain a Bayesian network. The specific static Bayesian network is as Figure 1E shown.

[0116] In a possible implementation manner, a method for determining the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall includes:

[0117] B1. Obtain a multi - state degradation model;

[0118] B2. Determine the static conditional probability of the static Bayesian network according to the multi - state degradation model and the degradation probability of the components of the glass curtain wall.

[0119] The multi - state degradation model can be obtained from a database or the Internet. Of course, it can also be obtained through other means.

[0120] Probability calculations can be performed according to the multi - state degradation model and the degradation probability to obtain the static conditional probability.

[0121] In a possible implementation manner, a method for determining the static conditional probability of the static Bayesian network according to the multi - state degradation model and the degradation probability of the components of the glass curtain wall includes:

[0122] The static conditional probability can be determined through the multi - state degradation model and the degradation probability shown in the following formula:

[0123]

[0124] where, is called component Xi The degradation probability. In the Bayesian network, the set of parent nodes of component Y is π(Y), and P(Y|π(Y)) is the static conditional probability of the occurrence of component Y. Component X i is the parent node of component Y.

[0125] In a possible implementation manner, the embodiments of the present application can also obtain the mutual information between components to determine the importance degree of the components relative to the glass curtain wall according to the mutual information, as follows:

[0126] Obtain the mutual information between the components of the glass curtain wall;

[0127] Obtain the mutual information between the components of the glass curtain wall through the method shown in the following formula:

[0128]

[0129] where I(T,X) is the mutual information between component X and component T, P(t,x) is the joint probability distribution function of component T and component X, P(T) is the marginal distribution probability of component T, and P(X) is the marginal probability distribution function of component X respectively.

[0130] Mutual information is the total potential for reducing the uncertainty of X based on the initial uncertainty of T when node X is unknown. Mutual information measures the degree of information sharing between T and X, that is, to what extent one of all nodes can reduce the uncertainty of another node.

[0131] In a specific embodiment, the embodiments of the present application also provide a specific method for determining the performance of the glass curtain wall, as follows:

[0132] 1. Based on the identification and analysis of the cruise ship glass curtain wall system, construct a fault tree model and transform it into a Bayesian network structure, as Figure 1E shown.

[0133] 2. Determine the failure rate, mean repair time, and degradation probability of the four components of the glass curtain wall system as evaluation data, as shown in Table 5.

[0134] Table 5 Data list of the basic components of the glass curtain wall system

[0135]

[0136] 3. Through the obtained degradation probability data, based on the multi-state degradation model, calculate the static conditional probability of the system at a certain time. Through the failure rate and mean repair time data, substitute them into the node conversion relationship calculation models under different repair modes shown in Tables 1 - 4 to establish the transition conditional probabilities at different times, thereby expanding the static Bayesian network into a dynamic Bayesian network model, asFigure 1C as shown

[0137] 4. Through forward inference of the dynamic Bayesian network, calculate and analyze the quantitative safety performance of the glass curtain wall system within 30 weeks.

[0138] The reliability of the glass curtain wall system is as Figure 1F shown, and the availability under complete repair, incomplete repair, and the mode of incomplete repair and preventive maintenance is as Figure 1G shown. Over time, both reliability and availability will decrease. The reliability drops to approximately 0.99754 in the 30th week. For the systems with complete repair, incomplete repair, and incomplete repair and preventive maintenance, the availability in the 30th week is 0.99809, 0.99796, and 0.99843 respectively. It can be seen from the figure that the difference in availability between complete repair and incomplete repair is small, both are higher than the reliability of the system, and slightly lower than the availability under incomplete repair and preventive maintenance. The results show that in a short period of time, repair and maintenance can significantly improve the system performance, incomplete repair will not significantly reduce the system performance compared with complete repair, and preventive maintenance can slightly improve the performance of the structure compared with incomplete repair.

[0139] The contribution of each component of the glass curtain wall to the system safety performance is as Figure 1H shown. Among them, the component C1 glass panel and C2 adhesive have a great impact on the structural failure, and the contribution of other components to the system failure is small. Therefore, in order to improve the performance and safety of the glass curtain wall and prevent potential accidents, in actual safety management, more attention should be paid to the glass panel and the adhesive.

[0140] Consistent with the above embodiments, please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a terminal provided by an embodiment of the present application. As shown in the figure, it includes a processor, an input device, an output device, and a memory. The processor, input device, output device, and memory are interconnected. Among them, the memory is used to store a computer program, and the computer program includes program instructions. The processor is configured to call the program instructions. The above program includes instructions for performing the following steps;

[0141] Obtain a static Bayesian network, which is used to detect the performance of the glass curtain wall;

[0142] Determine the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall;

[0143] Obtain the relationship between the state changes of the components of the glass curtain wall;

[0144] Determine the transition conditional probability of the static Bayesian network according to the component state change relationship, the failure rate of the component, and the repair rate of the component;

[0145] Determine a dynamic Bayesian network according to the transition conditional probability, the static conditional probability, and the static Bayesian network;

[0146] Determine the performance information of the glass curtain wall according to the dynamic Bayesian network.

[0147] The above mainly introduces the solution of the embodiment of the present application from the perspective of the execution process on the method side. It can be understood that in order for the terminal to implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combined with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0148] The embodiment of the present application can divide the functions of the terminal according to the above method examples. For example, each function unit can be divided corresponding to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of a software function unit. It should be noted that the division of units in the embodiment of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0149] Consistent with the above, please refer to Figure 3 , Figure 3 which is a schematic structural diagram of a glass curtain wall performance determination device provided by an embodiment of the present application. As Figure 3 shown, the device includes:

[0150] A first acquisition unit 301, configured to acquire a static Bayesian network, where the static Bayesian network is used to detect the performance of a glass curtain wall;

[0151] A first determination unit 302, configured to determine the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall;

[0152] A second acquisition unit 303, configured to acquire the component state change relationship of the glass curtain wall;

[0153] The second determination unit 304 is configured to determine the transition conditional probability of the static Bayesian network according to the component state change relationship, the failure rate of the component, and the repair rate of the component;

[0154] The third determination unit 305 is configured to determine a dynamic Bayesian network according to the transition conditional probability, the static conditional probability, and the static Bayesian network;

[0155] The fourth determination unit 306 is configured to determine the performance information of the glass curtain wall according to the dynamic Bayesian network.

[0156] In a possible implementation manner, the first acquisition unit 301 is configured to:

[0157] Acquire multiple component information of the glass curtain wall;

[0158] Perform logical analysis processing on the multiple component information to obtain the logical relationship between components corresponding to each component information in the multiple component information;

[0159] Determine a fault tree according to the logical relationship between components corresponding to each component information in the multiple component information;

[0160] Determine the static Bayesian network according to the fault tree.

[0161] In a possible implementation manner, the first determination unit 302 is configured to:

[0162] Acquire a multi-state degradation model;

[0163] Determine the static conditional probability of the static Bayesian network according to the multi-state degradation model and the degradation probability of the components of the glass curtain wall.

[0164] In a possible implementation manner, in terms of determining the static conditional probability of the static Bayesian network according to the multi-state degradation model and the degradation probability of the components of the glass curtain wall, the first determination unit 302 is configured to:

[0165] The static conditional probability can be determined through the multi-state degradation model and the degradation probability shown by the following formula:

[0166]

[0167] Wherein, is called the degradation probability of component X i The set of parent nodes of component Y in the Bayesian network is π(Y), P(Y|π(Y)) is the static conditional probability of component Y occurring, and component X i is the parent node of component Y.

[0168] In a possible implementation, the device further uses:

[0169] Obtain the mutual information between components of the glass curtain wall;

[0170] Obtain the mutual information between components of the glass curtain wall by the method shown in the following formula:

[0171]

[0172] where I(T,X) is the mutual information between component X and component T, P(t,x) is the joint probability distribution function of component T and component X, P(T) is the marginal distribution probability of component T, and P(X) are the marginal probability distribution functions of component X respectively

[0173] The embodiments of the present application further provide a computer storage medium. Among them, the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute some or all of the steps of any one of the glass curtain wall performance determination methods described in the foregoing method embodiments.

[0174] The embodiments of the present application further provide a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute some or all of the steps of any one of the glass curtain wall performance determination methods described in the foregoing method embodiments.

[0175] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0176] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0177] In several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0178] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0179] In addition, each functional unit in the various embodiments of the application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software program modules.

[0180] If the above-mentioned integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. And the aforementioned memory includes: USB flash drives, read-only memories (ROM), random access memories (RAM), mobile hard disks, magnetic disks, or optical discs and other media that can store program codes.

[0181] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, read-only memories, random access memories, magnetic disks, or optical discs, etc.

[0182] The above has introduced the embodiments of the present application in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for determining the performance of a glass curtain wall, characterized in that, the method includes: Obtain a static Bayesian network, which is used for detecting the performance of the glass curtain wall; Determine the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall; Obtain the relationship between the state changes of the components of the glass curtain wall; Determine the transition conditional probability of the static Bayesian network according to the component state change relationship, the failure rate of the components and the repair rate of the components; Determine a dynamic Bayesian network according to the transition conditional probability, the static conditional probability and the static Bayesian network; Determine the performance information of the glass curtain wall according to the dynamic Bayesian network.

2. The method according to claim 1, characterized in that, the obtaining of the static Bayesian network includes: Obtain information of multiple components of the glass curtain wall; Perform logical analysis and processing on the information of the multiple components to obtain the logical relationship between the components corresponding to each component information in the information of the multiple components; Determine a fault tree according to the logical relationship between the components corresponding to each component information in the information of the multiple components; Determine the static Bayesian network according to the fault tree.

3. The method according to claim 1 or 2, characterized in that, the determining of the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall includes: Obtain a multi-state degradation model; Determine the static conditional probability of the static Bayesian network according to the multi-state degradation model and the degradation probability of the components of the glass curtain wall.

4. The method according to claim 3, characterized in that, the determining of the static conditional probability of the static Bayesian network according to the multi-state degradation model and the degradation probability of the components of the glass curtain wall includes: The static conditional probability can be determined through the multi-state degradation model and the degradation probability shown by the following formula: Among them, is called component X i is the degradation probability. The set of parent nodes of component Y in the Bayesian network is π(Y), and P(Y|π(Y)) is the static conditional probability of the occurrence of component Y. Component X i is the parent node of component Y.

5. The method according to claim 4, characterized in that, the method further includes: Obtain the mutual information between the components of the glass curtain wall; Obtain the mutual information between the components of the glass curtain wall through the method shown by the following formula: where I(T,X) is the mutual information between component X and component T, P(t,x) is the joint probability distribution function of component T and component X, P(T) is the marginal distribution probability of component T, and P(X) is the marginal probability distribution function of component X.

6. A device for determining the performance of a glass curtain wall, characterized in that, the device includes: A first obtaining unit, configured to obtain a static Bayesian network, which is used for detecting the performance of the glass curtain wall; A first determining unit, configured to determine the static conditional probability of the static Bayesian network according to the degradation probability of the components of the glass curtain wall; A second obtaining unit, configured to obtain the relationship between the state changes of the components of the glass curtain wall; A second determining unit, configured to determine the transition conditional probability of the static Bayesian network according to the component state change relationship, the failure rate of the components and the repair rate of the components; A third determination unit, configured to determine a dynamic Bayesian network according to the transfer conditional probability, the static conditional probability, and the static Bayesian network; A fourth determination unit, configured to determine the performance information of the glass curtain wall according to the dynamic Bayesian network.

7. The apparatus according to claim 6, wherein, the first acquisition unit is configured to: acquire a plurality of component information of the glass curtain wall; perform logical analysis processing on the plurality of component information to obtain the logical relationship between components corresponding to each component information in the plurality of component information; determine a fault tree according to the logical relationship between components corresponding to each component information in the plurality of component information; determine the static Bayesian network according to the fault tree.

8. The apparatus according to claim 6 or 7, wherein, the first determination unit is configured to: acquire a multi-state degradation model; determine the static conditional probability of the static Bayesian network according to the multi-state degradation model and the degradation probability of the components of the glass curtain wall.

9. A terminal, wherein, comprising a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1-5.

10. A computer-readable storage medium, wherein, the computer-readable storage medium stores a computer program, the computer program includes program instructions, and the program instructions, when executed by a processor, cause the processor to execute the method according to any one of claims 1-5.

Images