An intelligent generation method of bridge parameters based on standard correction and probability statistics

Abstract

This invention relates to the field of bridge engineering design technology, specifically a method for intelligently generating bridge parameters based on code correction and probabilistic statistics. Before forming a reliable sample database, this method translates key clauses in bridge design codes concerning structural parameters into data rules. Samples containing physical parameters and / or indices of components that exceed the code's allowable range (i.e., do not meet the data rules) are removed, resulting in a code-corrected sample database. Probabilistic statistical methods are then used to calculate confidence intervals for indices to filter samples in the database. The remaining samples that meet the requirements are considered reliable, forming the reliable sample database. Finally, target population parameters, input by the user and of the same type as the overall parameters, are obtained, and the expected value matrix of the target bridge's physical parameters is calculated. This invention improves the efficiency of bridge engineering design by combining code correction and probabilistic statistical methods to achieve intelligent screening of existing samples, thereby making bridge design results more accurate.

Description

[0001] This application is a divisional application of application number CN202410728864.9, filed on 2024 / 06 / 06, and entitled "Interactive Generative Bridge Parameter Design Method, System and Storage Medium". Technical Field

[0002] This invention relates to the field of bridge engineering design technology, specifically a method for intelligent generation of bridge parameters based on standard correction and probabilistic statistics. Background Technology

[0003] Bridge engineering is an important part of transportation infrastructure, and bridge engineering design is also a key and challenging aspect of the entire transportation infrastructure construction process.

[0004] Concrete beam bridges are a common type of bridge in engineering. Due to their advantages such as flexible layout, clear stress, and simple construction, they are widely used in various projects, resulting in a large number of existing bridge design drawings. The traditional design method for concrete beam bridges requires engineering technicians to analyze the design functional requirements and load level requirements based on engineering design specifications, and combine basic geological survey data and surrounding environment factors to conduct structural selection, stress analysis, and structural design. They need to repeatedly calculate to obtain a set of reasonable bridge design parameters, and then use drawing tools to display this set of design parameters in a graphical and textual way on the drawings, forming a complete set of bridge structural design drawings including bridge layout drawings, bridge cross-section drawings, structural drawings, reinforcement drawings, etc. This set of bridge structural design drawings needs to show in detail all the structural styles, dimensions, and quantity information of the bridge structure, so that construction personnel can construct according to the drawings and build the actual bridge from the drawing information. There are two main pain points and difficulties in the whole process: (1) how to construct a set of safe, reliable, economical and reasonable bridge design parameters; (2) how to use these parameter sets to quickly draw a complete set of bridge structural design drawings.

[0005] Regarding question (2), the traditional design method using CAD drawing relies on manual drawing, resulting in a large workload and a lot of repetitive work. Currently, some parametric drawing software has been developed on the market that can automatically generate drawings by inputting a large number of detailed design parameters, thus solving the problem of parameter drawing. However, completing this process requires professional engineering designers to input a large amount of design information of bridge components in advance, including dimensional information, reinforcement information, quantity information, etc. The amount of input data is huge and professional. Regarding question (1), how to construct a set of safe, reliable, economical and reasonable bridge design parameters still relies entirely on professional bridge designers to complete it by relying on experience, analysis and calculation, reference suggestions, etc. This process is the most concentrated manifestation of bridge design intelligence and is also the basic link to ensure the safety, reliability and economic applicability of bridges. However, the process of experience inheritance and knowledge accumulation is long and complicated. Currently, there is a lack of intelligent design schemes that can intelligently generate bridge design parameters according to user needs. Bridge engineering design has achieved parameter drawing to a certain extent, but it has not yet developed in terms of intelligent design. Summary of the Invention

[0006] To address the technical problem of automatically generating design parameters for concrete beam bridges based on user needs in existing technologies, this invention provides an intelligent method for generating bridge parameters based on standard correction and probabilistic statistics.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] This invention discloses an intelligent method for generating bridge parameters based on standard correction and probabilistic statistics, comprising the following steps:

[0009] S1. From the bridge structural design drawings of multiple concrete beam bridges with the same bridge type and cross-sectional shape, obtain the overall parameters and physical parameter matrix of the bridge expressed by each sample, i.e., the bridge structural design drawings, and encapsulate them into a dataset of the corresponding sample, thereby forming a reliable sample database with the datasets of multiple samples; wherein, step S1 includes step S12, parsing the drawings: parsing the bridge design information expressed by the characters and symbols in the drawings and converting them into a standard dataset, thereby sequentially obtaining the overall parameters, physical parameter matrix, and parameter index set of the bridge expressed by the bridge structural design drawings;

[0010] Before forming the trusted sample database in step S1, the following specific steps are also included:

[0011] The bridge design code is structurally decomposed, and the key clauses involving structural parameters in the bridge design code are translated into data rules. Samples containing physical parameters and / or indicators of components that exceed the allowable range of the code and do not meet the data rules are removed, resulting in a sample database D1 that has been corrected by the code.

[0012] The confidence interval Z of the index with a given confidence probability is calculated using probability and the index confidence interval Z is used to screen the samples in the sample database D1. When each index exceeds the corresponding index confidence interval Z, the sample containing that index is removed from the sample database D1. The remaining samples in D1 that meet the requirements are the reliable samples, thus forming the reliable sample database D2.

[0013] S2. Obtain the target overall parameters that are input by the user and are of the same type as the overall parameters, and calculate the expected value matrix E1 of the physical parameters of the target bridge using the following formula:

[0014]

[0015] In the formula, γ v P is the reference coefficient for the v-th sample; V is the total number of samples in the reliable sample database; v This represents the physical parameter matrix in the v-th sample.

[0016] As a further improvement to the above scheme, the expression for the confidence interval Z of the index is as follows:

[0017]

[0018] In the formula, μ and σ represent the sample mean and standard deviation of each indicator q in the indicator set Q, respectively; q α2 These represent the quantiles of the standard normal distribution. Φ -1 (·) is the inverse function of the standard normal distribution function; α is the preset confidence probability, α∈[0,1]; n0 is the number of samples in the sample database D1.

[0019] As a further improvement to the above scheme, before step S12, step S1 further includes:

[0020] S11. Identify drawings: Identify and retrieve bridge structural design drawings in specific file formats from the database by extracting keywords, and identify the block components in the drawings;

[0021] Among them, the bridge structure design atlas is a series of construction drawings L' for bridge structures, represented as: L'={l1,…,l N}; N is the total number of drawing numbers in the bridge structural design atlas; l i Let i be the i-th construction drawing series, i∈[1,N]; each construction drawing series represents a series of drawings of the same category, consisting of one or more construction drawings, represented as: l i ={s 1i ,…,s ni}; In the formula, the subscript ni represents the total number of pages in the i-th construction drawing series; s niThis refers to the nth page of the i-th construction drawing series; a series of drawings of the same category are drawings with the same drawing name and number but different page numbers; the categories of each construction drawing include: table of contents, design specifications, bridge layout drawing, quantity table, bridge site plan, engineering geological longitudinal section drawing, standard cross section drawing, general structural drawing, steel strand layout drawing, longitudinal beam reinforcement structural drawing, transverse beam reinforcement structural drawing, support layout drawing, and construction flowchart; the components of the drawing blocks on each page of the construction drawing include: graphic blocks, graphic annotations, tables, notes, and drawing frames.

[0022] As a further improvement to the above scheme, step S12 includes the following specific steps:

[0023] S121. Based on the file name of the bridge structure design atlas and the keywords of the drawing names in the drawing frame, as well as the graphic form in the bridge layout drawing, the bridge types are classified into simply supported beam bridges and continuous beam bridges.

[0024] S122. Determine the type of cross-sectional shape of the bridge as expressed in the bridge structural design atlas based on the standard cross-sectional diagram;

[0025] S123. Assign a unique identification code to bridge structural design atlas files with the same bridge type and cross-sectional shape.

[0026] S124. Based on the structural description in the construction drawings of the design specifications and the pier distribution in the bridge layout diagram, determine the bridge span composition and width range, and obtain the maximum span L0 and average width B0 as two overall parameters.

[0027] S125. Using the image parameter analysis method, the physical parameters of the components in each series of construction drawings are analyzed sequentially to form the physical parameter matrix P of the bridge expressed in the bridge structure design atlas, as shown in the following expression:

[0028]

[0029] In the formula, p ji Let M represent the physical parameters of the j-th component in the i-th construction drawing series, where j∈[1,M]. M is the number of parameters in the column with the most parameters in the N column vectors of matrix P, and 0 is added to the positions of other columns where the number of parameters is insufficient.

[0030] S126. Calculate a series of indices based on the physical parameters of each component in the physical parameter matrix P, and calculate the index set Q for the key longitudinal position of the bridge; the index set Q includes the structural design parameter index set f and the reinforcement / bundle parameter index set ρ.

[0031] As a further improvement to the above scheme, step S125 includes the following specific steps:

[0032] S1251. Preprocess the images of the construction drawings, remove interference lines, retain structural lines, dimensions and annotations, and perform layer processing on the images, dividing them into structural line layers and annotation layers.

[0033] S1252. Extract the structural line layer, obtain the structural lines through image recognition, and obtain the key points of the graphic through corner detection method;

[0034] S1253. Perform noise reduction and closure checks on the structure line layer by comparing the structure lines with the lines connecting the key points of the graphic to obtain an optimized structure line layer.

[0035] S1254. Extract the annotation layer, obtain the annotation lines, annotation text information and position information through optical character recognition, and match the annotation text with the annotation lines using positional relationship logic constraints.

[0036] S1255. Match the annotation lines with the key points of the graphics through logical constraints to obtain the logical relationship between the annotation text and the structural lines;

[0037] S1256. Obtain the physical parameter attributes of the components based on the logical relationship between the annotation text and the structural lines, and store the text data into a data list according to the component category, thereby forming a physical parameter matrix P.

[0038] As a further improvement to the above scheme, in step S2, the reference coefficient γ v The calculation formula is:

[0039]

[0040] In the formula, Let θ be the preset importance coefficient for the u-th type of population parameter, u∈[1,U], where U is the type of target population parameter; uv The weighting coefficient for the v-th sample relative to the u-th population parameter is calculated using the following formula:

[0041]

[0042] In the formula, K uv Let be the correlation coefficient between the v-th sample and the u-th target population parameter, calculated using the following formula:

[0043]

[0044] In the formula, X u The u-th target population parameter input by the user; X uv Let u be the population parameter of the vth sample.

[0045] As a further improvement to the above scheme, the following step is also included: S3. Send the expected value matrix of the physical parameters of the target bridge to the interactive terminal in tabular form.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] 1. This invention discloses an automatic intelligent method for bridge parameters based on standard correction and probabilistic statistics. This method enables the automatic generation of design parameters for concrete beam bridges and allows users to customize and modify them, improving the efficiency of bridge engineering design and changing the previous situation where professional engineers needed to model, analyze, and repeatedly calculate to determine design parameters. Furthermore, this invention proposes a method for evaluating and screening data samples from bridge structural design atlases. By combining standard correction and probabilistic statistics, non-compliant data is eliminated, achieving intelligent screening of existing samples and thus making bridge design results more accurate.

[0048] 2. This invention improves the rationality of design parameters. By using image recognition technology to identify the physical meaning of graphics and text in past drawings, and by summarizing the latest data, it can quickly grasp the patterns and professional experience of past engineering designs. This helps to accumulate knowledge and pass on experience, and changes the previous situation where excellent engineering experience was difficult to share, thus limiting the development of bridge design. Attached Figure Description

[0049] Figure 1 This is a flowchart of the interactive generative bridge parameter design method in Embodiment 1 of the present invention.

[0050] Figure 2 for Figure 1 The detailed flowchart of step S1.

[0051] Figure 3 This is a flowchart of the image parameter analysis method used in Embodiment 1 of the present invention.

[0052] Figure 4 This is a framework diagram of the interactive generative bridge parameter design system in Embodiment 2 of the present invention. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] Example 1

[0055] Please see Figure 1This embodiment provides an interactive generative bridge parameter design method, which includes the following steps, namely S1 to S3.

[0056] S1. From the bridge structural design drawings of multiple concrete beam bridges with the same bridge type and cross-sectional shape, obtain the overall parameters and physical parameter matrix of each sample, that is, the bridge expressed by the bridge structural design drawings, and encapsulate them into the corresponding sample dataset, thereby forming a reliable sample database with the datasets of multiple samples.

[0057] A physical parameter matrix consisting of component parameters of the specified categories in the drawings.

[0058] Please see Figure 2 In this embodiment, step S1 may include the following specific steps, namely S11 to S12.

[0059] S11. Identify drawings

[0060] The system identifies and retrieves bridge structural design drawings in specific file formats from the database by extracting keywords, and identifies the block components in the drawings.

[0061] The database, specified by the user, contains a large number of electronic bridge design drawings. The keywords are present in at least one of the following: file name, design description within the file, or drawing annotations; the keywords include, but are not limited to, terms related to bridge structures such as bridge, pier, cap beam, T-beam, and box girder.

[0062] Bridge structural design atlas refers to a series of construction drawings L' for bridge structures, defined as: L'={l1,…,l N}, where N is the total number of drawing numbers in the bridge structural design atlas; l i For the i-th construction drawing series, i∈[1,N].

[0063] It should be noted that each construction drawing series l i A series of drawings representing the same category, consisting of one or more construction drawings, is defined by the expression: l i ={s 1i ,…,s ni}; In the formula, the subscript ni represents the total number of pages in the i-th construction drawing series, and s ni This refers to the nth page of the i-th construction drawing series. A series of drawings of the same category refers to drawings with the same drawing name and number but different page numbers.

[0064] Each construction drawing includes a catalog, design specifications, bridge layout diagram, quantity list, bridge site plan, engineering geological longitudinal section, standard cross section, general structural diagram, steel strand layout diagram, longitudinal beam reinforcement structural diagram, cross beam reinforcement structural diagram, support layout diagram, construction flowchart, and structural diagrams of other related components.

[0065] Each page of construction drawings consists of multiple blocks, namely: graphic blocks, graphic annotations, tables, notes, and title blocks; graphic blocks consist of titles and graphics; graphic annotations consist of dimension lines and dimension values; tables consist of table names, table headers, and parameter data; notes are used to supplement and explain the overall information of the drawing; title blocks consist of the unit name, project name, drawing name, drawing number, and page number.

[0066] S12, Analysis of Drawings

[0067] The process of parsing the bridge design information expressed by the characters and symbols in the drawings and converting it into a standard dataset includes the following steps, namely steps S121 to S127.

[0068] S121. Based on the keywords contained in the file name and the drawing name in the drawing frame, as well as the graphic shape in the bridge layout drawing, classify the bridges expressed in the bridge structural design atlas into simply supported beam bridges and continuous beam bridges.

[0069] S122. Based on the standard cross-section diagram, determine the type of cross-section shape of the bridge expressed in the bridge structural design atlas, including rectangular, T-shaped, I-shaped, box-shaped, etc.

[0070] S123. Assign a unique identifier to bridge structural design atlas files with the same bridge type and cross-sectional shape.

[0071] S124. Based on the structural description in the construction drawings of the design specifications and the pier distribution in the bridge layout diagram, determine the bridge span composition and width range, and obtain the maximum span L0 and the average width B0 as two overall parameters respectively.

[0072] S125. Using the image parameter analysis method, the physical parameters of the components in each series of construction drawings are analyzed sequentially to form the physical parameter matrix P of the bridge expressed in the bridge structure design atlas, as shown in the following expression:

[0073]

[0074] In the formula, p ji Let M represent the physical parameters of the j-th component in the i-th construction drawing series, where j∈[1,M]. M is the rank of matrix P. M is the number of parameters in the column with the most parameters in the N column vectors of matrix P. If the number of parameters in other columns is insufficient, zeros are added to the positions.

[0075] Please see Figure 3 Step S125 includes the following specific steps:

[0076] S1251. Preprocess the construction drawings to remove interference lines, retain structural lines, dimensions, and annotations, and perform layer processing to divide the images into structural line layers and annotation layers.

[0077] S1252. Extract the structure line layer, obtain the structure lines through image recognition, and obtain the key points of the graphic through corner detection method.

[0078] S1253. Perform noise reduction and closure checks on the structure line layer by comparing the structure lines with the lines connecting the key points of the graphic to obtain an optimized structure line layer.

[0079] S1254. Extract the annotation layer, obtain the annotation lines, annotation text information and position information through optical character recognition (OCR), and match the annotation text with the annotation lines using positional relationship logic constraints.

[0080] S1255. Match the annotation lines with the key points of the graphics through logical constraints to obtain the logical relationship between the annotation text and the structural lines.

[0081] S1256. Obtain the physical parameter attributes of the components based on the logical relationship between the annotation text and the structural lines, and store the text data into a data list according to the component category, thereby forming a physical parameter matrix P.

[0082] S126. Calculate a series of indices based on the physical parameters of each component in the physical parameter matrix P, and calculate the index set Q for the key longitudinal position of the bridge; the index set Q includes the structural design parameter index set f and the reinforcement / bundle parameter index set ρ, i.e., Q = f∪ρ.

[0083] In this embodiment, the set of design parameters f may include the height-to-span ratio f. sh Aspect ratio f wh Upper flange thickness-to-span ratio f wts1 Lower flange thickness-to-span ratio f wts2 and web thickness span ratio f ats , expressed as f = (f sh ,f wh ,f wts1 ,f wts2 ,f ats ).

[0084] Wherein, the height-to-span ratio f sh The ratio of the bridge section height h to the single span L of the bridge is expressed as f. sh =h / L; the aspect ratio f whB is the width of the bottom of the bridge section. b The ratio of the height of the bridge section to the height of the cross section h is expressed as f. wh =B b / h; the upper flange thickness-to-span ratio f wts1 The thickness h of the upper flange of the bridge cross section f1 The ratio of the length of a single span of the bridge to the span L is expressed as f. wts1 =h f1 / L; the lower flange thickness-to-span ratio f wts2 The thickness h of the lower flange of the bridge section f2 The ratio of the length of a single span of the bridge to the span L is expressed as f. wts2 =h f2 / L; the web thickness-to-span ratio f ats The thickness h of the web of the bridge section w The ratio of the length of a single span of the bridge to the span L is expressed as f. ats =h w / L.

[0085] The set of reinforcement / tendon parameters ρ may include the total steel content ρ r ρ, the ratio of main reinforcement bars m Total beam matching rate ρ pv , expressed as ρ=(ρ r ,ρ m ,ρ pv ).

[0086] Wherein, the total steel content ρ r The total weight (m) of the bridge including steel reinforcement r With structural concrete volume V c The ratio, expressed as ρ r =m r / V c The main reinforcement ratio ρ m Let A be the area of ​​the main reinforcement of the bridge component. s With bridge cross-sectional area A c The ratio, expressed as ρ m =A s / A c The total beam-matching rate ρ pv The total weight of the bridge steel strands is m p With structural concrete volume V c The ratio, expressed as ρ pv =m p / V c .

[0087] The bridge structure design drawings that have successfully passed the aforementioned steps (i.e., identification and parsing) and obtained a unique identification code are taken as a sample. The overall parameters, component parameters in the physical parameter matrix P, and indicators in the indicator set Q obtained from the parsing of the sample are encapsulated into a corresponding dataset. The original sample database D0 is composed of the datasets of multiple samples.

[0088] In some embodiments, all samples are further screened to obtain reliable samples to form the sample database. This specifically includes the following steps: standardization correction and probabilistic statistical methods.

[0089] Standardized correction method:

[0090] The bridge design code is structurally decomposed, and the key clauses involving structural parameters in the bridge design code are translated into data rules. Samples containing component parameters and / or indicators that exceed the allowable range of the code and do not meet the data rules are removed, resulting in a sample database D1 that has been corrected by the code.

[0091] Probability and statistics method:

[0092] The confidence interval Z of the index with a given confidence probability is calculated using probability and the index confidence interval Z is used to screen the samples in the sample database D1. When each index exceeds the corresponding index confidence interval Z, the sample containing that index is removed from the sample database D1. The remaining samples in D1 that meet the requirements are the reliable samples, thus forming the reliable sample database D2.

[0093] The calculation method of the parameter confidence interval includes the following specific steps, namely (1) to (4).

[0094] (1) Calculate the mean μ and standard deviation σ of each indicator q in the indicator set Q of the sample database. Define the indicator q as following the parameters μ and σ. 2 It follows a normal distribution.

[0095] (2) Obtain the reliable probability α, α∈[0,1]; α can be determined by the user.

[0096] (3) According to the standard normal distribution function inverse function Φ -1 (x) Solve for the quantile q of the standard normal distribution. α / 2 The expression is as follows:

[0097]

[0098] In the formula, e is the natural constant; Φ(x) represents the probability that the random variable is less than or equal to x; and t is the integral variable of the standard normal distribution function.

[0099] (4) Solve for the confidence interval Z of the parameter, as shown in the following expression:

[0100]

[0101] In the formula, n0 is the number of samples in the sample database D1.

[0102] S2. Obtain the target overall parameters input by the user, and calculate the expected value matrix of the physical parameters of the target bridge based on the target overall parameters and the sample database. It should be noted that the target overall parameters and the overall parameters in the sample are of the same type. In this embodiment, there are two types, namely the maximum span and average width of the bridge.

[0103] Step S2 specifically includes the following steps:

[0104] S21. Calculate the correlation coefficient between each sample in the sample database and each target population parameter. The calculation formula is as follows:

[0105]

[0106] In the formula, K uv Let X be the correlation coefficient between the v-th sample and the u-th target population parameter, where v∈[1,V], V is the total number of samples in the sample database, and u∈[1,U], where U is the type of target population parameter; u X is the u-th target population parameter input by the user. uv Let u be the population parameter of the vth sample.

[0107] S22. Calculate the weighting coefficient of each sample relative to each population parameter in the sample database. The calculation formula is as follows:

[0108]

[0109] In the formula, θ uv is the weighting coefficient of the v-th sample relative to the u-th population parameter.

[0110] S23. Calculate the reference coefficient for each sample. The calculation formula is as follows:

[0111]

[0112] In the formula, γ v Let be the reference coefficient for the v-th sample; The preset importance coefficient for the u-th population parameter is determined by the user based on empirical values.

[0113] S24. Calculate the expected value matrix E1 of the physical parameters of the target bridge. The calculation formula is as follows:

[0114]

[0115] In the formula, P v Q represents the physical parameter matrix in the v-th sample; v Let be the set of parameter indices in the v-th sample.

[0116] S3. Send the expected physical parameters of the target bridge to the interactive terminal in tabular form.

[0117] It should be noted that users can make bridge design decisions or adjust parameters based on the expected values ​​of physical parameters displayed on the interactive platform. The interactive platform can be a mobile phone, computer, or other user terminal, providing operational and display functions for user interaction.

[0118] Example 2

[0119] This embodiment provides an interactive generative bridge parameter design system 10, which can apply the interactive generative bridge parameter design method as described in Embodiment 1.

[0120] Please see Figure 4 The design system 10 includes: a data acquisition module 101, an expectation calculation module 102, and a sending module 103.

[0121] The data acquisition module 101 is used to acquire the overall parameters and physical parameter matrix of the bridge expressed by each sample from the bridge structural design drawings of multiple concrete beam bridges with the same bridge type and cross-sectional shape, and encapsulate them into a dataset of the corresponding sample, thereby forming a reliable sample database with the datasets of multiple samples.

[0122] The expected calculation module 102 is used to obtain the target overall parameters that are input by the user and are of the same type as the overall parameters, and to calculate the expected value matrix of the physical parameters of the target bridge.

[0123] The sending module 103 is used to send the expected value matrix of the physical parameters of the target bridge to the interactive terminal in tabular form.

[0124] Example 3

[0125] This embodiment provides a computer-readable storage medium storing a computer program. When the program is executed by a processor, it can implement the steps of the interactive generative bridge parameter design method in Embodiment 1.

[0126] The storage medium can be flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage medium can be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Of course, the storage medium can also include both internal storage units and external storage devices of the computer device. In this embodiment, the memory is typically used to store the operating system and various application software installed on the computer device. Furthermore, the memory can also be used to temporarily store various types of data that have been output or will be output.

[0127] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for intelligently generating bridge parameters based on standard correction and probabilistic statistics, characterized in that, Including the following steps: S1. From the bridge structural design drawings of multiple concrete beam bridges with the same bridge type and cross-sectional shape, obtain the overall parameters and physical parameter matrix of the bridge expressed by each sample, i.e., the bridge structural design drawings, and encapsulate them into a dataset of the corresponding sample, thereby forming a reliable sample database with the datasets of multiple samples; wherein, step S1 includes step S12, parsing the drawings: parsing the bridge design information expressed by the characters and symbols in the drawings and converting them into a standard dataset, thereby sequentially obtaining the overall parameters, physical parameter matrix, and parameter index set of the bridge expressed by the bridge structural design drawings; Before forming the trusted sample database in step S1, the following specific steps are also included: The bridge design code is structurally decomposed, and the key clauses involving structural parameters in the bridge design code are translated into data rules. Samples containing physical parameters and / or indicators of components that exceed the allowable range of the code and do not meet the data rules are removed, resulting in a sample database D1 that has been corrected by the code. The confidence interval Z of the index with a given confidence probability is calculated using probability and the index confidence interval Z is used to screen the samples in the sample database D1. When each index exceeds the corresponding index confidence interval Z, the sample containing that index is removed from the sample database D1. The remaining samples in D1 that meet the requirements are the reliable samples, thus forming the reliable sample database D2. S2. Obtain the target overall parameters that are input by the user and are of the same type as the overall parameters, and calculate the expected value matrix E1 of the physical parameters of the target bridge using the following formula: In the formula, γ v P is the reference coefficient for the v-th sample; V is the total number of samples in the reliable sample database; v This represents the physical parameter matrix in the v-th sample.

2. The intelligent bridge parameter generation method based on standard correction and probabilistic statistics according to claim 1, characterized in that, The expression for the confidence interval Z of the indicator is as follows: In the formula, μ and σ represent the sample mean and standard deviation of each indicator q in the indicator set Q, respectively; q α / 2 These represent the quantiles of the standard normal distribution. Φ -1 (·) is the inverse function of the standard normal distribution function; α is the preset confidence probability, α∈[0,1]; n0 is the number of samples in the sample database D1.

3. The intelligent bridge parameter generation method based on standard correction and probability statistics according to claim 2, characterized in that, Before step S12, step S1 further includes: S11. Identify drawings: Identify and retrieve bridge structural design drawings in specific file formats from the database by extracting keywords, and identify the block components in the drawings; Among them, the bridge structure design atlas is a series of construction drawings L' for bridge structures, represented as: L'={l1,…,l N }; N is the total number of drawing numbers in the bridge structural design atlas; l i Let i be the i-th construction drawing series, i∈[1,N]; each construction drawing series represents a series of drawings of the same category, consisting of one or more construction drawings, represented as: l i ={s 1i ,…,s ni }; In the formula, the subscript ni represents the total number of pages in the i-th construction drawing series; s ni This refers to the nth page of the i-th construction drawing series; a series of drawings of the same category are drawings with the same drawing name and number but different page numbers; the categories of each construction drawing include: table of contents, design specifications, bridge layout drawing, quantity table, bridge site plan, engineering geological longitudinal section drawing, standard cross section drawing, general structural drawing, steel strand layout drawing, longitudinal beam reinforcement structural drawing, transverse beam reinforcement structural drawing, support layout drawing, and construction flowchart; the components of the drawing blocks on each page of the construction drawing include: graphic blocks, graphic annotations, tables, notes, and drawing frames.

4. The intelligent bridge parameter generation method based on standard correction and probabilistic statistics according to claim 3, characterized in that, Step S12 includes the following specific steps: S121. Based on the file name of the bridge structure design atlas and the keywords of the drawing names in the drawing frame, as well as the graphic form in the bridge layout drawing, the bridge types are classified into simply supported beam bridges and continuous beam bridges. S122. Determine the type of cross-sectional shape of the bridge as expressed in the bridge structural design atlas based on the standard cross-sectional diagram; S123. Assign a unique identification code to bridge structural design atlas files with the same bridge type and cross-sectional shape. S124. Based on the structural description in the construction drawings of the design specifications and the pier distribution in the bridge layout diagram, determine the bridge span composition and width range, and obtain the maximum span L0 and average width B0 as two overall parameters. S125. Using the image parameter analysis method, the physical parameters of the components in each series of construction drawings are analyzed sequentially to form the physical parameter matrix P of the bridge expressed in the bridge structure design atlas, as shown in the following expression: In the formula, p ji Let M represent the physical parameters of the j-th component in the i-th construction drawing series, where j∈[1,M]. M is the number of parameters in the column with the most parameters in the N column vectors of matrix P, and 0 is added to the positions of other columns where the number of parameters is insufficient. S126. Calculate a series of indices based on the physical parameters of each component in the physical parameter matrix P, and calculate the index set Q for the key longitudinal position of the bridge; the index set Q includes the structural design parameter index set f and the reinforcement / bundle parameter index set ρ.

5. The intelligent bridge parameter generation method based on standard correction and probabilistic statistics according to claim 4, characterized in that, Step S125 includes the following specific steps: S1251. Preprocess the images of the construction drawings, remove interference lines, retain structural lines, dimensions and annotations, and perform layer processing on the images, dividing them into structural line layers and annotation layers. S1252. Extract the structural line layer, obtain the structural lines through image recognition, and obtain the key points of the graphic through corner detection method; S1253. Perform noise reduction and closure checks on the structure line layer by comparing the structure lines with the lines connecting the key points of the graphic to obtain an optimized structure line layer. S1254. Extract the annotation layer, obtain the annotation lines, annotation text information and position information through optical character recognition, and match the annotation text with the annotation lines using positional relationship logic constraints. S1255. Match the annotation lines with the key points of the graphics through logical constraints to obtain the logical relationship between the annotation text and the structural lines; S1256. Obtain the physical parameter attributes of the components based on the logical relationship between the annotation text and the structural lines, and store the text data into a data list according to the component category, thereby forming a physical parameter matrix P.

6. The intelligent bridge parameter generation method based on standard correction and probabilistic statistics according to claim 1, characterized in that, In step S2, the reference coefficient γ v The calculation formula is: In the formula, Let be the preset importance coefficient of the u-th type of population parameter, u∈[1,U], where U is the type of target population parameter; θ uv The weighting coefficient for the v-th sample relative to the u-th population parameter is calculated using the following formula: In the formula, K uv Let be the correlation coefficient between the v-th sample and the u-th target population parameter, calculated using the following formula: In the formula, X u The u-th target population parameter input by the user; X uv Let u be the population parameter of the vth sample.

7. The intelligent bridge parameter generation method based on standard correction and probabilistic statistics according to claim 1, characterized in that, It also includes the step: S3. Send the expected value matrix of the physical parameters of the target bridge to the interactive terminal in tabular form.

Images