Bridge technical performance prediction method, device, equipment, storage medium and product

Abstract

The present application discloses a method, device, equipment, storage medium and product for predicting the technical performance of a bridge, and relates to the technical field of network-level bridge maintenance. The method includes: obtaining the state parameters of the network-level bridge, and determining the current bridge performance distribution of the network-level bridge through the state parameters; constructing the Markov degradation matrix of the network-level bridge based on the historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes the historical state degradation data of the network-level bridge and the historical state degradation data of related bridges, and the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold; predicting the future technical performance of the network-level bridge after a preset period of time through the current bridge performance distribution and the Markov degradation matrix. Therefore, the present application realizes the prediction of the future technical performance of the bridge, and the prediction results can provide a decision-making basis for bridge maintenance.

Description

Technical Field

[0001] The present application relates to the field of network-level bridge maintenance technology, and in particular to a method, device, equipment, storage medium and product for predicting the technical performance of a bridge. Background Art

[0002] After being put into use, bridges will inevitably be damaged by many factors, causing damage to the bridge's construction and consuming the service life of the building. In order to ensure the health of the bridge, the bridge maintenance party will regularly inspect the bridge, such as testing key bridge indicators including vibration, deformation, cracks and corrosion, so as to obtain the technical performance status of the bridge structure, but this traditional detection method currently lacks foresight and is difficult to provide a basis for bridge maintenance in advance.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a method, device, equipment, storage medium and product for predicting the technical performance of a bridge, aiming to solve the technical problem that the current traditional detection method lacks foresight.

[0005] To achieve the above purpose, the present application proposes a method for predicting the technical performance of a bridge, which includes:

[0006] Acquire state parameters of a network-level bridge, and determine a current bridge performance distribution of the network-level bridge through the state parameters;

[0007] Constructing a Markov degradation matrix of the network-level bridge based on historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes historical state degradation data of the network-level bridge and historical state degradation data of related bridges, wherein the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold;

[0008] The future technical performance of the network-level bridge after a preset period of time is predicted through the current bridge performance distribution and the Markov degradation matrix.

[0009] Optionally, the step of constructing the Markov degradation matrix of the network-level bridge based on historical bridge technical performance degradation data includes:

[0010] For any preset bridge technical performance, the total number of bridge technical performances degraded after a preset time period in the historical bridge technical performance degradation data, and the number of degradation results of each degradation result after the degradation after the preset time period are counted;

[0011] Based on the total number and the degradation number of each degradation result, the degradation probability of each degradation result is calculated to obtain a set of degradation probabilities of the technical performance of the bridge;

[0012] After traversing each preset bridge technical performance, a collection of degradation probabilities is obtained and combined into the Markov degradation matrix.

[0013] Optionally, before the step of constructing the Markov degradation matrix of the network-level bridge based on historical bridge technical performance degradation data, the method includes:

[0014] Acquire bridge characteristics of the network-level bridge, wherein the bridge characteristics of the network-level bridge include at least one of the service life of the network-level bridge, the building structure of the network-level bridge, the material property of the network-level bridge, the design life of the network-level bridge, the traffic load of the network-level bridge, and the geographical environment in which the network-level bridge is located;

[0015] Clustering the network-level bridges based on the bridge characteristics to obtain the belonging clusters of the network-level bridges;

[0016] Relevant bridges whose similarity with the network-level bridge is greater than a preset threshold are selected from the belonging cluster.

[0017] Optionally, the step of selecting relevant bridges from the belonging cluster whose similarity to the network-level bridge is greater than a preset threshold comprises:

[0018] Based on the bridge characteristics of each other bridge in the belonging cluster and the bridge characteristics of the network-level bridge, calculating the distance between each other bridge and the network-level bridge, and using the distance as the similarity between each other bridge and the network-level bridge;

[0019] Other bridges whose similarity to the network-level bridge is greater than a preset threshold are selected from the other bridges as related bridges of the network-level bridge.

[0020] Optionally, the step of determining the current bridge performance distribution of the network-level bridge by using the state parameter comprises:

[0021] Extracting the state characteristics of the grid-level bridge from the state parameters, wherein the state characteristics include at least one of the crack width of the grid-level bridge, the vibration frequency of the grid-level bridge, and the displacement of the grid-level bridge;

[0022] The state characteristics are preprocessed and input into a preset performance evaluation model to obtain the current bridge performance distribution of the network-level bridge.

[0023] Optionally, the step of predicting the future technical performance of the network-level bridge after a preset period of time by using the current bridge performance distribution and the Markov degradation matrix includes:

[0024] For any current technical performance in the current bridge performance distribution, obtaining a degradation probability of the current technical performance corresponding to each degradation result based on the Markov degradation matrix;

[0025] Based on the degradation probability of each degradation result and the state probability of the current technical performance in the current bridge performance distribution, the occurrence probability of each degradation result corresponding to the current technical performance is calculated;

[0026] After traversing each current technical performance, the comprehensive occurrence probability of each degradation result is calculated;

[0027] The degradation result with the highest comprehensive probability of occurrence is used as the future technical performance of the network-level bridge after a preset period of time.

[0028] In addition, to achieve the above-mentioned purpose, the present application also proposes a bridge technical performance prediction device, the bridge technical performance prediction device comprising:

[0029] A determination module, used to obtain state parameters of a network-level bridge, and determine a current bridge performance distribution of the network-level bridge through the state parameters;

[0030] A construction module, used to construct a Markov degradation matrix of the network-level bridge based on historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes historical state degradation data of the network-level bridge and historical state degradation data of related bridges, and the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold;

[0031] The prediction module is used to predict the future technical performance of the network-level bridge after a preset period of time through the current bridge performance distribution and the Markov degradation matrix.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the technical performance prediction method of the bridge as described above.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the technical performance prediction method of the bridge as described above are implemented.

[0034] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the technical performance prediction method of the bridge as described above.

[0035] One or more technical solutions proposed in this application have at least the following technical effects:

[0036] In this embodiment, the state parameters of the network-level bridge will be obtained, and the current bridge performance distribution of the network-level bridge will be determined through the state parameters; the Markov degradation matrix of the network-level bridge will be constructed based on the historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes the historical state degradation data of the network-level bridge and the historical state degradation data of the related bridges, and the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold; through the current bridge performance distribution and the Markov degradation matrix, the future technical performance of the network-level bridge after a preset time period is predicted. That is, in this embodiment, the current bridge performance distribution of the network-level bridge will be determined through the state parameters of the network-level bridge, and the Markov degradation matrix of the network-level bridge will be constructed using the historical bridge technical performance degradation data including the historical state degradation data of the network-level bridge and the historical state degradation data of the related bridges. It can be understood that the related bridges are bridges similar to the network-level bridges, and the data used to construct the Markov degradation matrix of the network-level bridge is expanded. Avoid the impact of accidental state degradation events of network-level bridges on the Markov degradation matrix, so that the Markov degradation matrix of the network-level bridge is representative, thereby improving the accuracy of the prediction results obtained through the Markov degradation matrix. Finally, the Markov degradation matrix is ​​used to predict the future technical performance of the network-level bridge after a preset period of time from the current bridge performance distribution. Therefore, this application realizes the prediction of the future technical performance of the bridge, and the prediction results can provide a decision-making basis for bridge maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0038] 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0039] Figure 1 This is a flow chart of the first embodiment of the method for predicting the technical performance of a bridge in the present application;

[0040] Figure 2 This is a flow chart of the second embodiment of the method for predicting the technical performance of a bridge in the present application;

[0041] Figure 3 This is a flow chart of the third embodiment of the method for predicting the technical performance of a bridge in the present application;

[0042] Figure 4 A schematic diagram of the structure of a bridge technical performance prediction device in the bridge technical performance prediction method of the present application;

[0043] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the method for predicting the technical performance of a bridge in an embodiment of the present application.

[0044] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0046] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0047] The main solution of the embodiment of the present application is: obtaining the state parameters of the network-level bridge, and determining the current bridge performance distribution of the network-level bridge through the state parameters; constructing the Markov degradation matrix of the network-level bridge based on the historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes the historical state degradation data of the network-level bridge and the historical state degradation data of related bridges, and the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold; predicting the future technical performance of the network-level bridge after a preset period of time through the current bridge performance distribution and the Markov degradation matrix.

[0048] After a bridge is put into use, it will inevitably be damaged by many factors, causing damage to the bridge's construction and consuming the service life of the building. At present, the Bridge Health Monitoring System (BHM) is a key technology for evaluating the technical performance of bridges. It can be used to monitor the technical performance of bridge structures in real time, including key indicators such as vibration, deformation, cracks and corrosion. However, this traditional detection method lacks foresight and it is difficult to provide early warning to provide a basis for bridge maintenance measures.

[0049] This embodiment provides a solution, which determines the current bridge performance distribution of the network-level bridge through the state parameters of the network-level bridge, and uses historical bridge technical performance degradation data including historical state degradation data of the network-level bridge and historical state degradation data of related bridges to construct the Markov degradation matrix of the network-level bridge. It can be understood that the related bridge is a bridge similar to the network-level bridge, which expands the data used to construct the Markov degradation matrix of the network-level bridge. Avoiding the influence of accidental state degradation events of the network-level bridge on the Markov degradation matrix makes the Markov degradation matrix of the network-level bridge representative, thereby improving the accuracy of the prediction results obtained by the Markov degradation matrix. Finally, the Markov degradation matrix is ​​used to predict the future technical performance of the network-level bridge after a preset period of time starting from the current bridge performance distribution. Therefore, the present application realizes the prediction of the future technical performance of the bridge, and the prediction results can provide a decision-making basis for bridge maintenance.

[0050] Based on this, the embodiment of the present application provides a method for predicting the technical performance of a bridge, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for predicting the technical performance of a bridge according to the present application.

[0051] The technical performance prediction method of the bridge comprises steps S10 to S30:

[0052] Step S10, obtaining state parameters of a network-level bridge, and determining a current bridge performance distribution of the network-level bridge through the state parameters;

[0053] It should be noted that the above-mentioned network-level bridges are bridges that need to be evaluated for technical performance. The network-level bridges can be representative bridges in a certain bridge group or a certain bridge group, and the state parameters of the network-level bridges can be collected by sensors (such as strain sensors, displacement sensors, vibration sensors, etc.) set on the network-level bridges. Correspondingly, the collected state parameters can be time series data of strain, displacement and vibration. In addition, the state parameters can also be environmental change data (such as temperature time series, humidity time series), and traffic load data, etc.

[0054] Exemplarily, after obtaining the state parameters of the network-level bridge, the current bridge performance distribution of the network-level bridge can be obtained based on the obtained state parameters. It is worth noting that in practical applications, the technical performance of the bridge can be divided into intact, good, general, poor and failure, etc. Among them, the division of technical performance can be set by technical personnel according to actual needs, and is not limited here. The current bridge performance distribution refers to the probability of each technical performance. For example, for a newly built bridge, its current bridge performance distribution should theoretically be intact (100%), good (0%), general (0%), poor (0%) and failure (0%). For the current bridge performance distribution process, it can be to evaluate the current technical performance of the network-level bridge through an existing bridge health monitoring system. Alternatively, the state parameters are compared with the pre-set evaluation rules to obtain the score of each evaluation indicator, and then the comprehensive score is obtained according to the evaluation of each evaluation indicator, and the current bridge performance distribution is obtained according to the comprehensive score. Alternatively, the state parameters are input into a pre-trained evaluation model, and the result output by the output layer of the evaluation model is the probability of each technical performance, thereby obtaining the current bridge performance distribution.

[0055] Step S20, constructing a Markov degradation matrix of the network-level bridge based on historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes historical state degradation data of the network-level bridge and historical state degradation data of related bridges, and the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold;

[0056] It should be noted that in this example, the historical bridge technical performance degradation data used to construct the Markov degradation matrix includes not only the historical state degradation data of the network-level bridges, but also the historical state degradation data of the related bridges. A related bridge refers to a bridge whose similarity with the network-level bridge is greater than a preset threshold. The similarity between bridges can be obtained by comparing the features between bridges. For example, after the feature vectors of the two bridges are quantized, the similarity of the two vectors is calculated using the cosine similarity algorithm. The historical state degradation data refers to the changes in the technical performance of the bridge (network-level bridge or related bridge) itself or the components in the bridge over time. For example, after a preset period of time, a bridge (or a component in a bridge) degrades from technical performance A to technical performance B.

[0057] Exemplarily, the Markov degradation matrix of the network-level bridge is constructed through historical bridge technical performance degradation data. Among them, the elements in the Markov degradation matrix correspond to the probability of a technical performance transition, such as the probability of technical performance A degenerating to technical performance B. For example, the probability of each degradation result can be calculated by counting the number of each degradation result in the historical bridge technical performance degradation data, thereby completing the construction of the Markov degradation matrix. It is worth noting that the specific process of constructing the Markov degradation matrix can also refer to the existing solution, so it will not be repeated here.

[0058] It is understandable that, since the historical bridge technical performance degradation data includes not only the historical state degradation data of the network-level bridges, but also the historical state degradation data of the related bridges, the data used to construct the Markov degradation matrix is ​​expanded. The influence of the accidental state degradation events of the network-level bridges on the Markov degradation matrix is ​​avoided, so that the Markov degradation matrix of the network-level bridge is representative, thereby improving the accuracy of the prediction results obtained by the Markov degradation matrix.

[0059] Step S30, predicting the future technical performance of the network-level bridge after a preset period of time through the current bridge performance distribution and the Markov degradation matrix.

[0060] It should be noted that the data period selected when constructing the Markov degradation matrix (for example, the data period can be one year, and correspondingly, the state degradation is the change in the technical performance of the bridge after one year) is usually less than or equal to the above-mentioned preset time length.

[0061] Exemplarily, the vector formed by the current bridge performance distribution is multiplied by the Markov degradation matrix to obtain the future technical performance of the network-level bridge after a preset time. For example, if the data period selected when constructing the Markov degradation matrix is ​​1 year, and the above preset time is 1 year, then the result of multiplying the vector formed by the current bridge performance distribution and the Markov degradation matrix is ​​the future technical performance. If the above preset time is 2 years, the multiplication result needs to be multiplied again by the Markov degradation matrix to obtain the future technical performance after the preset time. Therefore, the specific calculation method can be set according to actual needs.

[0062] It can be understood that in this embodiment, the state parameters of the network-level bridge will be obtained, and the current bridge performance distribution of the network-level bridge will be determined through the state parameters; the Markov degradation matrix of the network-level bridge will be constructed based on the historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes the historical state degradation data of the network-level bridge and the historical state degradation data of the related bridges, and the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold; through the current bridge performance distribution and the Markov degradation matrix, the future technical performance of the network-level bridge after a preset time period is predicted. That is, in this embodiment, the current bridge performance distribution of the network-level bridge will be determined through the state parameters of the network-level bridge, and the Markov degradation matrix of the network-level bridge will be constructed using the historical bridge technical performance degradation data including the historical state degradation data of the network-level bridge and the historical state degradation data of the related bridges. It can be understood that the related bridges are bridges similar to the network-level bridges, and the data used to construct the Markov degradation matrix of the network-level bridge is expanded. Avoid the impact of accidental state degradation events of network-level bridges on the Markov degradation matrix, so that the Markov degradation matrix of the network-level bridge is representative, thereby improving the accuracy of the prediction results obtained through the Markov degradation matrix. Finally, the Markov degradation matrix is ​​used to predict the future technical performance of the network-level bridge after a preset period of time from the current bridge performance distribution. Therefore, this application realizes the prediction of the future technical performance of the bridge, and the prediction results can provide a decision-making basis for bridge maintenance.

[0063] In a feasible implementation manner, the step of constructing the Markov degradation matrix of the network-level bridge based on the historical bridge technical performance degradation data includes steps S21 to S23:

[0064] Step S21, for any preset bridge technical performance, counting the total number of bridge technical performance degradations after a preset time in the historical bridge technical performance degradation data, and the number of degradations of each degradation result after the degradation after the preset time;

[0065] Step S22, based on the total number and the degradation number of each degradation result, calculating the degradation probability of each degradation result, and obtaining a set of degradation probabilities of the technical performance of the bridge;

[0066] Step S23, after traversing each preset bridge technical performance, a set of degradation probabilities is obtained and combined into the Markov degradation matrix.

[0067] It should be noted that the above-mentioned preset bridge technical performance can be intact, good, general, poor and failed. And in this embodiment, in the process of constructing the Markov degradation matrix of the network-level bridge, the degradation of each bridge technical performance in the historical bridge technical performance degradation data will be statistically analyzed, and the statistical process of each bridge technical performance is basically similar, so in this embodiment, one of the bridge technical performances will be used as an example for explanation.

[0068] Exemplarily, for any preset bridge technical performance, the total number of bridge technical performance degradation data after the preset time is counted. There are many types of degradation, such as assuming that the bridge technical performance is intact, and the degradation type can be from intact to good, from intact to general, from intact to poor, and from intact to failure. And the number of degradations of each degradation result after each degradation after the preset time is counted, such as the number of intact degradations to good, etc. Then, according to the total number and the degradation number of each degradation result, the degradation probability of each degradation result is calculated to obtain the degradation probability collection of the bridge technical performance. For example, for any degradation result, the degradation number of the degradation result is divided by the total number to obtain the degradation probability of the degradation result. Similarly, taking the bridge technical performance as intact as an example, if the total number is a, and the number of intact degradations to good degradations is b, then b / a is the degradation probability of intact degradation to good degradation. The degradation probability of different degradation results of each bridge technical performance can be obtained in the above manner, and then the degradation probability set of each bridge technical performance is combined into the above Markov degradation matrix.

[0069] In a feasible implementation manner, the step of predicting the future technical performance of the network-level bridge after a preset period of time by using the current bridge performance distribution and the Markov degradation matrix includes steps S31 to S34:

[0070] Step S31, for any current technical performance in the current bridge performance distribution, obtaining the degradation probability of the current technical performance corresponding to each degradation result based on the Markov degradation matrix;

[0071] Step S32, based on the degradation probability of each degradation result and the state probability of the current technical performance in the current bridge performance distribution, calculate the occurrence probability of each degradation result corresponding to the current technical performance;

[0072] Step S33, after traversing each current technical performance, counting the comprehensive occurrence probability of each degradation result;

[0073] Step S34, taking the degradation result with the highest comprehensive occurrence probability as the future technical performance of the network-level bridge after a preset period of time.

[0074] It should be noted that the current bridge performance distribution may include multiple current technical performances and the probability of each current technical performance. In this application, the processing process for each technical performance in the current bridge performance distribution is the same, so in this embodiment, one of them will be used as an example for description.

[0075] Exemplarily, for any current technical performance in the current bridge performance distribution, the Markov degradation matrix records the degradation probability of the current technical performance corresponding to each degradation result, that is, the degradation probability from the current technical performance to each degradation result. The state probability of the current technical performance in the current bridge performance distribution is multiplied by the degradation probability of the current technical performance corresponding to each degradation result in the Markov degradation matrix, and the occurrence probability of each degradation result relative to the current technical performance can be obtained. After traversing each current technical performance, for any degradation result, the occurrence probability of the degradation result is accumulated to obtain the comprehensive occurrence probability of the degradation result. Correspondingly, the comprehensive occurrence probability of each degradation result can be obtained in this way. Finally, the degradation result with the highest comprehensive occurrence probability is used as the future technical performance of the network-level bridge after a preset period of time.

[0076] Reference Figure 2 , is a flow chart of the second embodiment of the present application proposed based on the first embodiment of the present application. In this embodiment, the same or similar contents as the above embodiment can refer to the above contents, so they are not repeated here. Before the step of constructing the Markov degradation matrix of the network-level bridge based on the historical bridge technical performance degradation data, the method includes steps S100 to S300:

[0077] Step S100, obtaining bridge characteristics of the network-level bridge, wherein the bridge characteristics of the network-level bridge include at least one of the service life of the network-level bridge, the building structure of the network-level bridge, the material property of the network-level bridge, the design life of the network-level bridge, the traffic load of the network-level bridge, and the geographical environment in which the network-level bridge is located;

[0078] Step S200, clustering the network-level bridges based on the bridge characteristics to obtain the belonging clusters of the network-level bridges;

[0079] Step S300: selecting related bridges from the belonging cluster whose similarity with the network-level bridge is greater than a preset threshold.

[0080] It should be noted that, in this embodiment, in order to ensure the effectiveness of constructing the Markov degradation matrix of the network-level bridges based on the historical bridge technical performance degradation data, in this embodiment, the historical state degradation data of related bridges whose similarity with the network-level bridges is greater than a preset threshold will be selected to expand the historical bridge technical performance degradation data.

[0081] Exemplarily, the bridge characteristics of the network-level bridge are obtained, and the bridge characteristics of the network-level bridge include at least one of the service life of the network-level bridge, the building structure of the network-level bridge, the material properties of the network-level bridge, the design life of the network-level bridge, the traffic load of the network-level bridge, and the geographical environment in which the network-level bridge is located. In addition, the bridge characteristics of the network-level bridge may also include the construction unit and the design unit of the network-level bridge. The specific bridge characteristics can be set by the technicians according to the actual needs, and will not be repeated here.

[0082] Then, the network-level bridges are clustered based on the bridge characteristics of the network-level bridges, such as by using the K-means clustering algorithm. Before clustering, the bridge characteristics can be preprocessed (such as vectorization, so as to calculate the distance between bridges in the vector space, so as to cluster the bridges). During clustering, the network-level bridges can participate in clustering with other bridges to form different clusters, or other bridges can first complete clustering to obtain different clusters, and then determine to cluster the network-level bridges to determine which cluster the network-level bridge should belong to. Finally, the cluster to which the network-level bridge belongs is the belonging cluster. Select related bridges from the belonging cluster whose similarity with the network-level bridge is greater than a preset threshold. For example, all bridges in the belonging cluster can be used as related bridges of the network-level bridge.

[0083] In a feasible implementation manner, the step of selecting related bridges from the belonging cluster whose similarity with the network-level bridge is greater than a preset threshold includes steps S310 to S320:

[0084] Step 310, based on the bridge characteristics of each other bridge in the belonging cluster and the bridge characteristics of the network-level bridge, calculate the distance between each other bridge and the network-level bridge, and use the distance as the similarity between each other bridge and the network-level bridge;

[0085] Step 320: Select other bridges whose similarity with the network-level bridge is greater than a preset threshold from the other bridges as related bridges of the network-level bridge.

[0086] Exemplarily, the distance between each other bridge and the network-level bridge is calculated based on the bridge characteristics of each other bridge in the belonging cluster and the bridge characteristics of the network-level bridge. For example, for any other bridge, the bridge characteristics of the other bridge and the bridge characteristics of the network-level bridge can be vectorized to obtain two feature vectors, and then the distance between the two feature vectors is calculated using the Euclidean distance method. The distance between the two feature vectors is the similarity between the other bridge and the network-level bridge. Finally, other bridges whose similarity with the network-level bridge is greater than a preset threshold are selected from each other bridge as related bridges of the network-level bridge. It can be understood that in this embodiment, the network-level bridges are clustered from multiple angles (i.e., bridge characteristics), and related bridges similar to the network-level bridges (i.e., similarity greater than a preset threshold) are selected from the belonging clusters of the network-level bridges to ensure the effectiveness of constructing the Markov degradation matrix of the network-level bridge including the historical bridge technical performance degradation data of the related bridges, and to ensure the accuracy of the prediction results.

[0087] Reference Figure 3 , is a flow chart of the third embodiment of the present application proposed based on the first embodiment and the second embodiment of the present application. In this embodiment, the same or similar contents as the above embodiments can refer to the above contents, so they are not repeated here. The step of determining the current bridge performance distribution of the network-level bridge by the state parameter includes step S11~step S12:

[0088] Step S11, extracting the state characteristics of the network-level bridge from the state parameters, wherein the state characteristics include at least one of the crack width of the network-level bridge, the vibration frequency of the network-level bridge, and the displacement of the network-level bridge;

[0089] Step S12, pre-processing the state characteristics and inputting them into a preset performance evaluation model to obtain the current bridge performance distribution of the network-level bridges.

[0090] It should be noted that, in this embodiment, a method for evaluating the current bridge performance distribution of network-level bridges is also provided.

[0091] Exemplarily, the state characteristics of the network-level bridge are extracted from the state parameters, and the state characteristics include at least one of the crack width of the network-level bridge, the vibration frequency of the network-level bridge, and the displacement of the network-level bridge. In addition, the state characteristics may also include the service life of the network-level bridge, etc. After the state characteristics are preprocessed to form an input requirement that meets the preset performance evaluation model, they are input into the preset performance evaluation model, and the output result of the preset performance evaluation model is the current bridge performance distribution of the network-level bridge. Among them, the preset performance evaluation model can be a neural network model, and it has been pre-trained with training samples, such as the training samples include sample characteristics and sample labels, such as the sample characteristics can be the state characteristics of a bridge, and the sample labels are the technical performance of the bridge, such as intact, good, general, poor, and failed.

[0092] The present application provides a device for predicting the technical performance of a bridge, wherein the vehicle is equipped with a single neuron controller, referring to Figure 4 , the technical performance prediction device of the bridge comprises:

[0093] A determination module 10 is used to obtain state parameters of a network-level bridge and determine a current bridge performance distribution of the network-level bridge through the state parameters;

[0094] A construction module 20 is used to construct a Markov degradation matrix of the network-level bridge based on historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes historical state degradation data of the network-level bridge and historical state degradation data of related bridges, and the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold;

[0095] The prediction module 30 is used to predict the future technical performance of the network-level bridge after a preset period of time through the current bridge performance distribution and the Markov degradation matrix.

[0096] Optionally, the building module 20 is further used for:

[0097] For any preset bridge technical performance, the total number of bridge technical performances degraded after a preset time period in the historical bridge technical performance degradation data, and the number of degradation results of each degradation result after the degradation after the preset time period are counted;

[0098] Based on the total number and the degradation number of each degradation result, the degradation probability of each degradation result is calculated to obtain a set of degradation probabilities of the technical performance of the bridge;

[0099] After traversing each preset bridge technical performance, a collection of degradation probabilities is obtained and combined into the Markov degradation matrix.

[0100] Optionally, the technical performance prediction device of the bridge further includes a selection module 40, and the selection module 40 is used to:

[0101] Acquire bridge characteristics of the network-level bridge, wherein the bridge characteristics of the network-level bridge include at least one of the service life of the network-level bridge, the building structure of the network-level bridge, the material property of the network-level bridge, the design life of the network-level bridge, the traffic load of the network-level bridge, and the geographical environment in which the network-level bridge is located;

[0102] Clustering the network-level bridges based on the bridge characteristics to obtain the belonging clusters of the network-level bridges;

[0103] Relevant bridges whose similarity with the network-level bridge is greater than a preset threshold are selected from the belonging cluster.

[0104] Optionally, the selection module 40 is further used for:

[0105] Based on the bridge characteristics of each other bridge in the belonging cluster and the bridge characteristics of the network-level bridge, calculating the distance between each other bridge and the network-level bridge, and using the distance as the similarity between each other bridge and the network-level bridge;

[0106] Other bridges whose similarity to the network-level bridge is greater than a preset threshold are selected from the other bridges as related bridges of the network-level bridge.

[0107] Optionally, the determining module 10 is further configured to:

[0108] Extracting the state characteristics of the grid-level bridge from the state parameters, wherein the state characteristics include at least one of the crack width of the grid-level bridge, the vibration frequency of the grid-level bridge, and the displacement of the grid-level bridge;

[0109] The state characteristics are preprocessed and input into a preset performance evaluation model to obtain the current bridge performance distribution of the network-level bridge.

[0110] Optionally, the prediction module 30 is further used for:

[0111] For any current technical performance in the current bridge performance distribution, obtaining a degradation probability of the current technical performance corresponding to each degradation result based on the Markov degradation matrix;

[0112] Based on the degradation probability of each degradation result and the state probability of the current technical performance in the current bridge performance distribution, the occurrence probability of each degradation result corresponding to the current technical performance is calculated;

[0113] After traversing each current technical performance, the comprehensive occurrence probability of each degradation result is calculated;

[0114] The degradation result with the highest comprehensive probability of occurrence is used as the future technical performance of the network-level bridge after a preset period of time.

[0115] The technical performance prediction device for a bridge provided in the present application adopts the technical performance prediction method for a bridge in the above-mentioned embodiment, aiming to solve the technical problem that the current traditional detection method lacks foresight. Compared with the prior art, the beneficial effects of the technical performance prediction device for a bridge provided in the embodiment of the present application are the same as the beneficial effects of the technical performance prediction method for a bridge provided in the above-mentioned embodiment 1, and the other technical features in the technical performance prediction device for a bridge are the same as the features disclosed in the above-mentioned embodiment method, which will not be described in detail here.

[0116] The present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the technical performance prediction method of the bridge in the above-mentioned embodiment 1.

[0117] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic devices in the embodiments of the present application may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), PMPs (Portable Media Players: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0118] like Figure 5As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0119] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0120] The electronic device provided by the present application adopts the technical performance prediction method of the bridge in the above embodiment, which can solve the technical problem that the longitudinal control algorithm cannot provide a good control effect while being easy to apply the real-time control of the vehicle. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as the beneficial effects of the technical performance prediction method of the bridge provided by the above embodiment, and the other technical features in the electronic device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0121] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0122] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0123] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the technical performance prediction method of the bridge in the above-mentioned embodiment.

[0124] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0125] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0126] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by an electronic device, the electronic device: obtains the state parameters of the network-level bridge, and determines the current bridge performance distribution of the network-level bridge through the state parameters; constructs the Markov degradation matrix of the network-level bridge based on historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes the historical state degradation data of the network-level bridge and the historical state degradation data of related bridges, and the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold; predicts the future technical performance of the network-level bridge after a preset period of time through the current bridge performance distribution and the Markov degradation matrix.

[0127] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0128] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0129] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0130] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned bridge technical performance prediction method, and can solve the technical problem that the existing data display method is difficult to intuitively and clearly complete data visualization. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the bridge technical performance prediction method provided in the above-mentioned embodiment, and will not be repeated here.

[0131] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned method for predicting the technical performance of a bridge when executed by a processor.

[0132] The computer program product provided in this application can solve the technical problem of predicting the technical performance of bridges. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the method for predicting the technical performance of bridges provided in the above embodiments, which will not be described in detail here.

[0133] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for predicting the technical performance of a bridge, characterized in that: The technical performance prediction method of the bridge includes: Acquire state parameters of a network-level bridge, and determine a current bridge performance distribution of the network-level bridge through the state parameters; Constructing a Markov degradation matrix of the network-level bridge based on historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes historical state degradation data of the network-level bridge and historical state degradation data of related bridges, wherein the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold; Predicting the future technical performance of the network-level bridge after a preset period of time through the current bridge performance distribution and the Markov degradation matrix; Wherein, before the step of constructing the Markov degradation matrix of the network-level bridge based on the historical bridge technical performance degradation data, the method includes: Acquire bridge characteristics of the network-level bridge, wherein the bridge characteristics of the network-level bridge include the service life of the network-level bridge, the building structure of the network-level bridge, the material properties of the network-level bridge, the design life of the network-level bridge, the traffic load of the network-level bridge, and the geographical environment in which the network-level bridge is located; Clustering the network-level bridges based on the bridge characteristics to obtain the belonging clusters of the network-level bridges; Selecting related bridges from the belonging cluster whose similarity with the network-level bridge is greater than a preset threshold; The step of selecting related bridges from the belonging cluster whose similarity with the network-level bridge is greater than a preset threshold comprises: Based on the bridge features of each other bridge in the belonging cluster and the bridge features of the network-level bridge, the distance between each other bridge and the network-level bridge is calculated, and the distance is used as the similarity between each other bridge and the network-level bridge, wherein the distance is the distance between bridges in the vector space after the bridge features are vectorized; Other bridges whose similarity to the network-level bridge is greater than a preset threshold are selected from the other bridges as related bridges of the network-level bridge.

2. The method for predicting the technical performance of a bridge according to claim 1, characterized in that: The step of constructing the Markov degradation matrix of the network-level bridge based on the historical bridge technical performance degradation data comprises: For any preset bridge technical performance, the total number of bridge technical performances degraded after a preset time period in the historical bridge technical performance degradation data, and the number of degradation results of each degradation result after the degradation after the preset time period are counted; Based on the total number and the degradation number of each degradation result, the degradation probability of each degradation result is calculated to obtain a set of degradation probabilities of the technical performance of the bridge; After traversing each preset bridge technical performance, a collection of degradation probabilities is obtained and combined into the Markov degradation matrix.

3. The method for predicting the technical performance of a bridge according to claim 1, characterized in that: The step of determining the current bridge performance distribution of the network-level bridge by the state parameter comprises: Extracting the state characteristics of the grid-level bridge from the state parameters, wherein the state characteristics include at least one of the crack width of the grid-level bridge, the vibration frequency of the grid-level bridge, and the displacement of the grid-level bridge; The state characteristics are preprocessed and input into a preset performance evaluation model to obtain the current bridge performance distribution of the network-level bridge.

4. The method for predicting the technical performance of a bridge according to claim 1, characterized in that: The step of predicting the future technical performance of the network-level bridge after a preset period of time by using the current bridge performance distribution and the Markov degradation matrix includes: For any current technical performance in the current bridge performance distribution, obtaining a degradation probability of the current technical performance corresponding to each degradation result based on the Markov degradation matrix; Based on the degradation probability of each degradation result and the state probability of the current technical performance in the current bridge performance distribution, the occurrence probability of each degradation result corresponding to the current technical performance is calculated; After traversing each current technical performance, the comprehensive occurrence probability of each degradation result is calculated; The degradation result with the highest comprehensive probability of occurrence is used as the future technical performance of the network-level bridge after a preset period of time.

5. A device for predicting the technical performance of a bridge, characterized in that: The technical performance prediction device of the bridge comprises: A determination module, used to obtain state parameters of a network-level bridge, and determine a current bridge performance distribution of the network-level bridge through the state parameters; A construction module, used to construct a Markov degradation matrix of the network-level bridge based on historical bridge technical performance degradation data, wherein the historical bridge technical performance degradation data includes historical state degradation data of the network-level bridge and historical state degradation data of related bridges, and the related bridges are bridges whose similarity with the network-level bridge is greater than a preset threshold; A prediction module, used to predict the future technical performance of the network-level bridge after a preset period of time through the current bridge performance distribution and the Markov degradation matrix; Before constructing the Markov degradation matrix of the network-level bridge based on the historical bridge technical performance degradation data, the method includes: Acquire bridge characteristics of the network-level bridge, wherein the bridge characteristics of the network-level bridge include the service life of the network-level bridge, the building structure of the network-level bridge, the material properties of the network-level bridge, the design life of the network-level bridge, the traffic load of the network-level bridge, and the geographical environment in which the network-level bridge is located; Clustering the network-level bridges based on the bridge characteristics to obtain the belonging clusters of the network-level bridges; Selecting related bridges from the belonging cluster whose similarity with the network-level bridge is greater than a preset threshold; The step of selecting, from the belonging cluster, related bridges whose similarity to the network-level bridge is greater than a preset threshold comprises: Based on the bridge features of each other bridge in the belonging cluster and the bridge features of the network-level bridge, the distance between each other bridge and the network-level bridge is calculated, and the distance is used as the similarity between each other bridge and the network-level bridge, wherein the distance is the distance between bridges in the vector space after the bridge features are vectorized; Other bridges whose similarity to the network-level bridge is greater than a preset threshold are selected from the other bridges as related bridges of the network-level bridge.

6. An electronic device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for predicting the technical performance of a bridge according to any one of claims 1 to 4.

7. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for predicting the technical performance of a bridge according to any one of claims 1 to 4 are implemented.

8. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for predicting the technical performance of a bridge according to any one of claims 1 to 4 are implemented.

Images