Design methods, equipment, media and program products for prestressed concrete slabs
Through the design method of prestressed concrete slabs, the cost optimization function and load prediction model are used to automatically optimize the design parameters, which solves the problems of low economy and calculation efficiency in traditional design methods and realizes efficient and economical concrete slab design.
Patent Information
- Application Number
- CN202510200011.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-21
- Publication Date
- 2025-09-09
- Estimated Expiration
- 2045-02-21
AI Technical Summary
Traditional concrete slab design methods rely on manual experience and have difficulty in achieving optimal parameter selection, resulting in poor design results in terms of economy and material utilization. In addition, the finite element analysis method has low computational efficiency and is unable to meet rapid design requirements.
The design method of prestressed concrete slabs is adopted. By obtaining the cost optimization function, iteratively optimizing the design parameters, combining the load prediction model and cost constraints, the design parameters are automatically optimized to improve efficiency and material utilization.
It achieves efficient design of prestressed concrete slabs, improves material utilization and structural economy, and reduces material costs.
Smart Images
Figure CN120046499B_ABST
Abstract
Description
Technical Field
[0001] One or more embodiments of this specification relate to the technical field of building structure design, and in particular, to a design method, device, medium, and program product for a prestressed concrete slab. Background Art
[0002] Concrete slabs, due to their excellent load-bearing capacity and durability, are widely used in the design of roof and floor panels for buildings such as industrial plants, warehouses, and parking lots. Concrete roof systems fulfill multiple roles within a building structure, including load-bearing, protection, and spatial shaping. Their design requires comprehensive consideration of factors such as structural safety, durability, and cost-effectiveness.
[0003] Traditional concrete design methods mainly rely on manual experience for structural design, which makes it difficult to select optimal parameters, resulting in poor design results in terms of economy and material utilization.
[0004] In recent years, finite element analysis (FEA) has been introduced to concrete slab design. Through numerical simulation, FEA can more accurately analyze the mechanical and deformation behavior of structures, providing a more scientific basis for design. However, concrete slab design involves a large number of parameter inputs and complex calculations, resulting in long design times and low computational efficiency, making it difficult to meet the rapid design requirements of practical projects. Summary of the Invention
[0005] In view of this, one or more embodiments of this specification provide the following technical solutions:
[0006] According to a first aspect of one or more embodiments of this specification, a design method for a prestressed concrete slab is provided, the method comprising:
[0007] Obtaining a cost optimization function for the prestressed concrete slab, the cost optimization function including a cost term and a load constraint term, the cost term using design parameters of the prestressed concrete slab as input variables, and the load constraint term using a load response of the prestressed concrete slab as input variables;
[0008] Iterate the following steps until the stopping condition is met:
[0009] Determine the current design parameters used in this iteration;
[0010] Predicting a current load response corresponding to the current design parameters based on a load prediction model;
[0011] Performing a current round of iteration on the cost optimization function using the current design parameters and the current load response to optimize the current design parameters, thereby obtaining optimized design parameters;
[0012] Updating the current design parameters to the optimized design parameters and performing the next round of iteration;
[0013] The latest optimized design parameters obtained after the iteration stops are determined as the design results of the prestressed concrete slab.
[0014] Optionally, the process of constructing the cost optimization function includes:
[0015] Cost calculation function for constructing prestressed concrete slabs;
[0016] Constructing a constrained optimization problem with the goal of minimizing the cost calculation function, wherein the constraint condition of the constrained optimization problem includes that the load response of the prestressed concrete slab does not exceed a threshold value;
[0017] The cost optimization function is constructed based on the constrained optimization problem, wherein the cost item in the cost optimization function corresponds to the cost calculation function, and the constraint item corresponds to the constraint condition.
[0018] Optionally, the training process of the load prediction model includes:
[0019] Constructing sample data for training the load prediction model, wherein the sample data uses design parameters of the prestressed concrete slab as features and load responses corresponding to the design parameters as labels;
[0020] The sample data is used to train the initial load prediction model to obtain a trained load prediction model.
[0021] Optionally, the sample data constructed for training the load prediction model includes:
[0022] Obtaining several sets of design parameters of prestressed concrete slabs;
[0023] The finite element analysis method is used to determine the load response corresponding to each set of design parameters;
[0024] The design parameters and the load responses are normalized respectively, and the sample data is constructed based on the normalized design parameters and their corresponding load responses.
[0025] Optionally, the stop condition includes:
[0026] Compared with the current design parameters used in the first round of iterations, the cost of the prestressed concrete slab corresponding to the optimized design parameters has been reduced by a preset proportion.
[0027] Optionally, the process of determining the latest optimized design parameters obtained after the iteration is stopped as the design result of the prestressed concrete slab includes:
[0028] Verifying the latest optimized design parameters;
[0029] In a case where the latest optimized design parameters pass the verification, the latest optimized design parameters are determined as the design results of the prestressed concrete slab.
[0030] According to a second aspect of one or more embodiments of this specification, a design device for a prestressed concrete slab is provided, the device comprising:
[0031] a function acquisition unit for acquiring a cost optimization function of a prestressed concrete slab, wherein the cost optimization function includes a cost term and a load constraint term, wherein the cost term uses a design parameter of the prestressed concrete slab as an input variable, and the load constraint term uses a load response of the prestressed concrete slab as an input variable;
[0032] Iterate the optimization unit and iteratively perform the following steps until the stopping condition is met:
[0033] Determine the current design parameters used in this iteration;
[0034] Predicting a current load response corresponding to the current design parameters based on a load prediction model;
[0035] Performing a current round of iteration on the cost optimization function using the current design parameters and the current load response to optimize the current design parameters, thereby obtaining optimized design parameters;
[0036] Updating the current design parameters to the optimized design parameters and performing the next round of iteration;
[0037] The result determination unit determines the latest optimized design parameters obtained after the iteration stops as the design results of the prestressed concrete slab.
[0038] According to a third aspect of one or more embodiments of this specification, an electronic device is proposed, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor implements the steps of the aforementioned method by running the executable instructions.
[0039] According to a fourth aspect of one or more embodiments of this specification, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the aforementioned method are implemented.
[0040] According to a fifth aspect of one or more embodiments of this specification, a computer program product is proposed, comprising a computer program / instruction, which implements the steps of the aforementioned method when executed by a processor.
[0041] It can be seen from the above embodiments that by adopting the above design scheme provided in this specification, a cost optimization function including cost items and load constraint items can be obtained, and the current load response corresponding to the current design parameters can be predicted. Then, the cost optimization function is iteratively solved using the current design parameters and the current load response to optimize the current design parameters to obtain optimized design parameters, and the latest optimized design parameters obtained after the iteration stops can be determined as the design results of the prestressed concrete slab. By adopting such a prestressed concrete slab design scheme, the design parameters can be automatically optimized intelligently, which can not only improve the design efficiency of the prestressed concrete slab, but also improve the utilization rate of materials and reduce the cost of materials through the iterative solution of the cost optimization function, thereby improving the economy of the structure. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 It is a schematic diagram of the architecture of a design system for prestressed concrete slabs provided by an exemplary embodiment.
[0043] Figure 2 It is a flow chart of a design method of a prestressed concrete slab provided by an exemplary embodiment.
[0044] Figure 3 This is a flowchart of a method for training a load prediction model provided by an exemplary embodiment.
[0045] Figure 4 This is a flowchart of a sample data construction method provided by an exemplary embodiment.
[0046] Figure 5 It is a flowchart of a method for constructing a cost optimization function provided by an exemplary embodiment.
[0047] Figure 6 It is a schematic diagram of an iterative solution process of a cost optimization function provided by an exemplary embodiment.
[0048] Figure 7 It is a schematic diagram of another iterative solution process of a cost optimization function provided by an exemplary embodiment.
[0049] Figure 8 It is a structural diagram of a device provided by an exemplary embodiment.
[0050] Figure 9 It is a block diagram of a design device for a prestressed concrete slab provided by an exemplary embodiment. DETAILED DESCRIPTION
[0051] Concrete slabs, due to their excellent load-bearing capacity and durability, are widely used in the design of roof and floor panels for buildings such as industrial plants, warehouses, and parking lots. Concrete roof systems fulfill multiple roles within a building structure, including load-bearing, protection, and spatial shaping. Their design requires comprehensive consideration of factors such as structural safety, durability, and cost-effectiveness.
[0052] Traditional concrete design methods mainly rely on manual experience for structural design, which makes it difficult to select optimal parameters, resulting in poor design results in terms of economy and material utilization.
[0053] In recent years, finite element analysis (FEA) has been introduced into concrete slab design. Through numerical simulation, FEA can more accurately analyze the structural stress and deformation behavior, providing a more scientific basis for design. However, the design of concrete slabs involves a large number of parameter inputs and complex calculations, resulting in long design times and low computational efficiency, making it difficult to meet the rapid design requirements of practical projects.
[0054] This specification provides a design solution for prestressed concrete slabs, which can determine the design parameters of prestressed concrete slabs based on deep learning technology, thereby improving design efficiency and material utilization, while reducing material costs and improving the economy of the structure.
[0055] The prestressed concrete slabs described in this specification may be conventional concrete slabs or UHPC (Ultra-High Performance Concrete) slabs. These slabs may have a double-T or C-shaped structure. While the design parameters for these slabs may differ, the design solutions provided in this specification may be used for all designs.
[0056] The design scheme of prestressed concrete slabs provided in this specification can be applied to electronic devices, such as: PCs (Personal Computers), mobile phones, tablet devices, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smart watches, etc.), etc. During operation, the electronic device can run the design client program of the prestressed concrete slab to realize the relevant functions of the application. For example, when the electronic device runs the design program of the prestressed concrete slab, it can be realized as a client of the design service of the prestressed concrete slab. Among them, the client application of the above-mentioned prestressed concrete slab design service can be started and run on the electronic device. The client program can be a native application installed on the electronic device, or the program on the client side can be a small program, a quick application or other similar forms. Of course, when using web technologies such as HTML5 or similar, the relevant functions can be realized through the page displayed by the browser. The browser here can be an independent browser application or a browser module embedded in certain applications.
[0057] The design scheme of prestressed concrete slabs provided in this manual can also be realized by the cooperation of electronic equipment and servers. Figure 1 The schematic diagram of the architecture of the prestressed concrete slab design system is shown. The system may include a server 11, a network 12, and several electronic devices, such as a PC (Personal Computer) 13, a mobile phone 14, etc. Figure 1 In this front-end / back-end separation architecture, the client-side prestressed concrete slab design program in the electronic device is responsible for user interaction, for example, receiving initial design parameters, maximum allowable design stress, deflection, etc. uploaded by the user. The back-end prestressed concrete slab design program in server 11 is responsible for determining the design results and returning them to the electronic device for presentation. Server 11 can be a physical server containing a standalone host, or it can be a virtual server hosted by a host cluster, and this specification does not impose any specific limitations on this.
[0058] Figure 2 It is a flow chart of a design method of a prestressed concrete slab provided by an exemplary embodiment.
[0059] Please refer to Figure 2 , the design method of the prestressed concrete slab may include the following steps:
[0060] Step 202: Obtain a cost optimization function for the prestressed concrete slab. The cost optimization function includes a cost term and a load constraint term. The cost term uses the design parameters of the prestressed concrete slab as input variables, and the load constraint term uses the load response of the prestressed concrete slab as input variables.
[0061] In this embodiment, the design parameters of the prestressed concrete slab may include material design parameters, slab design parameters, and prestressing design parameters. Taking a prestressed UHPC slab with a double-T structure as an example, the material design parameters may include: UHPC compressive strength, tensile strength, ultimate tensile strain, etc.; the slab design parameters may include: top plate thickness, web thickness, web height, longitudinal and transverse rib spacing, longitudinal and transverse rib dimensions, etc.; and the prestressing design parameters may include: prestressing strand position, prestressing steel strand diameter, and total prestressing steel strand tensioning cross-sectional area, etc.
[0062] In this embodiment, the load response of the prestressed concrete slab may include maximum stress (which may include maximum tensile stress and maximum compressive stress), maximum deflection, etc. The load response corresponds to the design parameters, and different design parameters generally correspond to different load responses.
[0063] In this embodiment, the cost optimization function may be an unconstrained optimization function, such as a Lagrangian function. The cost optimization function includes a cost term and a load constraint term. The cost term uses the design parameters of the prestressed concrete slab as input variables and may represent the cost of manufacturing the prestressed concrete slab using the corresponding design parameters, and may be the sum of the concrete slab cost and the prestressing cost. The constraint term uses the load response of the prestressed concrete slab as input variables and may represent a constraint that the load response of the prestressed concrete slab does not exceed the load response allowed by the design.
[0064] Step 204, iteratively execute the following steps until a stop condition is met: determine the current design parameters used in this round of iteration; predict the current load response corresponding to the current design parameters based on the load prediction model; use the current design parameters and the current load response to perform this round of iteration on the cost optimization function to optimize the current design parameters to obtain optimized design parameters; update the current design parameters to the optimized design parameters, and execute the next round of iteration.
[0065] In this embodiment, the cost optimization function may be iteratively solved to optimize the design parameters, thereby reducing the cost of the prestressed concrete slab while ensuring that the corresponding load response does not exceed the load response allowed by the design.
[0066] In this embodiment, a set of initial design parameters can be set in advance, and a load prediction model can be used to predict the load response corresponding to this set of initial design parameters as the initial load response. Then, this set of initial design parameters and the corresponding initial load response are used to iteratively solve the cost optimization function to update and optimize the initial design parameters to obtain optimized design parameters. If the iterative stop condition corresponding to the cost optimization function is not met, the cost optimization function can continue to be iteratively solved based on the optimized design parameters.
[0067] Among them, the load prediction model can be a trained deep learning model that can be used to predict the load response of prestressed concrete slabs, or it can be a finite element analysis model. The finite element analysis model can use the finite element analysis (FEA) method to determine the load response corresponding to the design parameters. Of course, in other examples, the load prediction model can also be other models, and this specification does not impose any special restrictions on this.
[0068] In this embodiment, the stopping condition may be that the cost of the prestressed concrete slab corresponding to the optimized design parameters has been reduced by a preset proportion compared to the current design parameters (i.e., the initial design parameters) used in the first round of iteration. That is, after the current design parameters are updated in each round of iteration to obtain the optimized design parameters, the optimized prestressed concrete slab cost corresponding to the optimized design parameters may be calculated, and then the optimized prestressed concrete slab cost is compared with the initial prestressed concrete slab cost corresponding to the initial optimized design parameters to determine whether the optimized prestressed concrete slab cost has been reduced by a preset proportion (for example, 20%, 30%, etc.) compared to the initial prestressed concrete slab cost, so as to determine whether the stopping condition is met.
[0069] In this embodiment, the stopping condition may also be that the cost optimization function has reached a preset number of iterative solutions, such as 1000 times, 2000 times, etc.
[0070] In this embodiment, the stopping condition may also be that the cost of the prestressed concrete slab corresponding to the optimized design parameters has been reduced by a preset proportion compared to the initial design parameters, and the cost optimization function has reached a preset number of iterative solutions, whichever comes first. This specification does not impose any special restrictions on this.
[0071] Step 206 : determining the latest optimized design parameters obtained after the iteration stops as the design result of the prestressed concrete slab.
[0072] Based on the iterative solution of the aforementioned step 204, the optimized design parameters obtained after the iteration stops (referred to as the latest optimized design parameters) can be determined as the target design parameters of the prestressed concrete slab, that is, the design results. Using such design results to manufacture the corresponding prestressed concrete slab can greatly improve material utilization, while reducing material costs and improving the economy of the structure.
[0073] It can be seen from the above embodiments that by adopting the above design scheme provided in this specification, a cost optimization function including cost items and load constraint items can be obtained, and the current load response corresponding to the current design parameters can be predicted. Then, the cost optimization function is iteratively solved using the current design parameters and the current load response to optimize the current design parameters to obtain optimized design parameters, and the latest optimized design parameters obtained after the iteration stops can be determined as the design results of the prestressed concrete slab. By adopting such a prestressed concrete slab design scheme, the design parameters can be automatically optimized intelligently, which can not only improve the design efficiency of the prestressed concrete slab, but also improve the utilization rate of materials and reduce the cost of materials through the iterative solution of the cost optimization function, thereby improving the economy of the structure.
[0074] The following describes the specific implementation of this specification in detail from two aspects: load prediction model and cost optimization function.
[0075] 1. Load prediction model
[0076] In this embodiment, taking the load prediction model as a deep learning model as an example, a multi-layer perceptron (MLP) neural network can be selected as the load prediction model, and then the sample data can be used to train, verify and test the initial load prediction model.
[0077] Please refer to Figure 3 , the training process of the load prediction model may include the following steps:
[0078] Step 302: construct sample data for training the load prediction model, wherein the sample data uses design parameters of the prestressed concrete slab as features and load responses corresponding to the design parameters as labels.
[0079] In this embodiment, sample data for training the load prediction model can be constructed first. Please refer to Figure 4 , the following method can be used to construct sample data.
[0080] Step 3022: Obtain several sets of design parameters of prestressed concrete slabs.
[0081] In this embodiment, multiple sets of design parameters for prestressed concrete slabs can be pre-constructed. Taking the prestressed concrete slab with a double T-shaped structure as an example, the design parameters may include: top plate thickness, web thickness, web height, top plate span, concrete slab compressive strength, prestressed steel strand position, number of prestressed steel strands, prestressed steel strand diameter, total cross-sectional area of prestressed steel strand tensioning, etc.
[0082] Step 3024: Use the finite element analysis method to determine the load response corresponding to each set of design parameters.
[0083] In this embodiment, a finite element analysis method can be used to determine the load response corresponding to each set of design parameters. For example, for each set of design parameters such as top plate thickness, web plate thickness, web plate height, top plate span, concrete slab compressive strength, prestressed steel strand position, number of prestressed steel strands, prestressed steel strand diameter, and total prestressed steel strand tensioning cross-sectional area, a finite element analysis method can be used to determine the load response of the prestressed concrete slab corresponding to these design parameters. The load response may include maximum stress, maximum deflection, etc.
[0084] For example, assuming that 200 sets of design parameters are pre-constructed, the finite element analysis method can be used to determine the 200 sets of load responses corresponding to these 200 sets of design parameters.
[0085] Step 3026: Normalize the design parameters and the load responses respectively, and construct the sample data based on the normalized design parameters and their corresponding load responses.
[0086] In this embodiment, each design parameter and load response may be normalized separately to ensure that the constructed sample is not affected by the characteristic scale, thereby being able to extract more meaningful features therefrom.
[0087] For example, when performing normalization processing, a maximum-minimum normalization method may be used for each design parameter, specifically the following formula may be used:
[0088]
[0089] Among them, x represents the value of the original design parameter, x max Represents the maximum value of the design parameter, x min represents the minimum value of the design parameter, Represents the value of the design parameter obtained after normalization. Taking the design parameter roof thickness as an example, the difference between the maximum roof thickness and the minimum roof thickness can be calculated. Then, for each roof thickness, the quotient of the roof thickness and the difference can be calculated to obtain the result after normalization of the roof thickness. Other design parameters are similar to roof thickness and are not repeated here.
[0090] For example, when performing normalization processing, for each load response, a reference value scaling normalization method may be used, specifically, the following formula may be used:
[0091]
[0092] Where y represents the value of the original load response determined by the finite element analysis method, y ref The reference value representing the load response can be pre-set and can be the maximum possible value of the load response. y represents the value of the load response obtained after normalization. Taking maximum stress as an example, a reference stress can be obtained. Then, for each maximum stress, the quotient of the maximum stress and the reference stress can be calculated to obtain the normalized result of the maximum stress. Load responses such as maximum deflection are similar to maximum stress and are not repeated here.
[0093] In this embodiment, after normalizing the design parameters and load responses, sample construction can be performed. For example, a kernel function-based Kernel PCA (Kernel Principal Component Analysis) method is used to extract corresponding features from the design parameters. Each set of design parameter features obtained can then be used as a sample feature, and the corresponding load response can be used as a sample label for the corresponding design parameter, thereby obtaining multiple sample data for training the load prediction model. Of course, in other examples, other methods can also be used to extract sample features, and this specification does not impose any special restrictions on this.
[0094] Step 304: Use the sample data to train the initial load prediction model to obtain a trained load prediction model.
[0095] Based on the aforementioned step 302 , after the sample data is constructed, the sample data may be used to train the initial load prediction model.
[0096] For example, the constructed sample data can be divided into a training set, a validation set and a test set. For example, random sampling can be used to divide the sample data into a training set, a validation set and a test set to ensure that the distribution of various design parameters among these three data sets is basically uniform.
[0097] In this embodiment, the sample data in the training set can be used to train the initial load prediction model, and then the sample data in the validation set can be used to verify the trained load prediction model. After the verification is passed, the sample data in the test set can also be used for testing.
[0098] Optionally, for the hyperparameters of the load prediction model such as the hidden layer depth, dimension, learning rate, etc., multiple groups of different hyperparameter combinations can be pre-set, and the initial load prediction model formed by each hyperparameter combination can be trained separately to obtain multiple trained load prediction models. Then, an optimal load prediction model can be selected from the multiple trained load prediction models based on the sample data in the validation set for subsequent testing. For example, the optimal load prediction model can be selected based on the sample data in the validation set using the root mean square error (RMSE) method, and this manual does not impose any special restrictions on this.
[0099] In this embodiment, the load prediction model that has passed the test is determined as the trained load prediction model for subsequent load response prediction.
[0100] It can be seen from this that this manual can train a deep learning model as a load prediction model to predict load responses. Compared with the finite element calculation method, it can greatly shorten the time cost and thus improve the design efficiency.
[0101] 2. Cost Optimization Function
[0102] 1. Construction of cost optimization function
[0103] Please refer to Figure 5 The method for constructing the cost optimization function provided in this embodiment may include the following steps:
[0104] Step 502: construct a cost calculation function for prestressed concrete slabs.
[0105] In this embodiment, when designing prestressed concrete slabs, it is often necessary to consider economic efficiency, that is, the lower the cost of the prestressed concrete slabs, the better, while meeting the needs. Especially for prestressed UHPC slabs made of UHPC material, due to their high cost, more attention should be paid to cost considerations during design.
[0106] In this embodiment, a cost calculation function for calculating the cost of prestressed concrete slabs can be constructed. The cost calculation function can be the sum of the concrete slab cost and the prestressing cost. Taking the prestressed UHPC slab with a double T-shaped structure as an example, its cost calculation function can refer to the following formula:
[0107] Q=(t1×l+t2×h)×C UHPC +S×C S
[0108] Wherein, Q represents the cost calculation function, t1 represents the top plate thickness, l represents the span, t2 represents the web plate thickness, h represents the web plate height, (t1×l+t2×h) represents the amount of UHPC, C UHPCrepresents the unit price of UHPC, S represents the total cross-sectional area of prestressed steel strands (i.e. prestressing amount), C S Represents the unit price of prestressing.
[0109] Step 504 : constructing a constrained optimization problem with the goal of minimizing the cost calculation function. The constraint condition of the constrained optimization problem includes that the load response of the prestressed concrete slab does not exceed a threshold.
[0110] Based on the aforementioned step 502, a constrained optimization problem can be constructed with the goal of minimizing the cost calculation function. The constraint conditions of the constrained optimization problem are that the load response of the prestressed concrete slab does not exceed a threshold value, for example, the maximum stress of the prestressed concrete slab does not exceed the design allowable stress threshold, the maximum deflection does not exceed the design operation deflection threshold, etc.
[0111] Still taking the prestressed UHPC board as an example, the following constrained optimization problem can be constructed:
[0112] min Q=(t1×l+t2×h)×C UHPC +S×C S
[0113] stσ max ≤[σ]
[0114] w max ≤[w]
[0115] Among them, σ max represents the maximum stress of the prestressed concrete slab, [σ] represents the design allowable stress, i.e. the stress threshold, and w max represents the maximum deflection of the prestressed concrete slab, and [w] represents the design allowable deflection, i.e. the deflection threshold.
[0116] Step 506: construct the cost optimization function based on the constrained optimization problem, wherein the cost item in the cost optimization function corresponds to the cost calculation function, and the constraint item corresponds to the constraint condition.
[0117] In this embodiment, the Lagrange multiplier method may be used to convert the constrained optimization problem in the aforementioned step 504 into an unconstrained optimization problem, and then a corresponding cost optimization function may be constructed to facilitate subsequent solution.
[0118] For example, the cost optimization function can be constructed by referring to the following formula:
[0119]
[0120] ReLU(x)=max(x,0)
[0121]
[0122] Among them, L(x,λ) represents the cost optimization function that needs to be solved, represents some design parameters, d represents the web spacing, f t Represents the tensile strength of UHPC.
[0123] t1×l+t2×h+S is the cost term of the cost optimization function, which corresponds to the aforementioned cost calculation function;
[0124] is the constraint term of the cost optimization function, which corresponds to the aforementioned constraint condition. ReLU(x) is an activation function that can be used to convert the constraint condition into a non-negative penalty term.
[0125] In the cost optimization function σ i represents the maximum stress corresponding to a prestressed concrete slab with a certain design parameter, w i Represents the maximum deflection of a prestressed concrete slab with a certain design parameter, σ i and w i The above load prediction model can be used to predict the load based on the design parameters. λ1 and λ2 represent penalty coefficients.
[0126] The number of iterative updates of the penalty coefficient may be M, and the number of updates of the design parameter may be N.
[0127] At this point, the constrained optimization problem used in the prestressed concrete slab design process has been converted into an unconstrained optimization problem, which can facilitate the iterative optimization solution of subsequent design parameters.
[0128] Of course, in other examples, the penalty coefficient may not be introduced when constructing the cost optimization function, and this specification does not impose any special restrictions on this.
[0129] 2. Iterative solution of cost optimization function
[0130] Please refer to Figure 6 and Figure 7 The iterative solution process of the cost optimization function provided in this embodiment may include the following steps:
[0131] Step 602: Acquire initial design parameters of the prestressed concrete slab as current design parameters.
[0132] In this embodiment, when solving the cost optimization function for a prestressed concrete slab, initial design parameters may be obtained. These initial design parameters may be pre-set based on design requirements. These initial design parameters are the current design parameters used in the first iteration. In other iterations, the current design parameters are the optimized design parameters updated in the previous iteration.
[0133] Step 604: Use a load prediction model to predict an initial load response corresponding to the initial design parameters as the current load response.
[0134] Based on the aforementioned step 602, after the current design parameters are obtained, the trained load prediction model may be used to predict the current load response corresponding to the current design parameters.
[0135] In the first round of iteration, the load prediction model is used to predict the initial load response corresponding to the initial design parameters as the current load response used in the first round of iteration.
[0136] When it is not the first round of iteration, the load prediction model is used to predict the current load response corresponding to the current design parameters used in this round of iteration.
[0137] Step 606: Iterate the cost optimization function using the current design parameters and the current load response to optimize the current design parameters to obtain optimized design parameters.
[0138] In this embodiment, the cost optimization function is iteratively solved based on the current design parameters and their corresponding current load responses to update and optimize the current design parameters. For example, the dual gradient ascent method can be used for solving the problem. Specifically, the optimized design parameters after each round of iterative update are:
[0139]
[0140] Among them, x (i) is the design parameter used in this iteration, x (i+1) is the updated design parameter in this round of iterative optimization, α is the step size of the design parameter update, is the gradient of the cost optimization function with respect to the design parameter x.
[0141] In another embodiment, when a penalty coefficient is used, the penalty coefficient may be iteratively updated:
[0142]
[0143] Among them, λ (j) is the penalty coefficient used in this round of iteration, λ (j+1) is the penalty coefficient after this round of iterative update, β is the step size of the penalty coefficient update, is the gradient of the cost optimization function with respect to the penalty coefficient λ, and j ranges from 1 to M.
[0144] In this embodiment, the values of the update step sizes α and β, as well as the number of design parameter updates N and the number of penalty coefficient updates M can be preset. The above-mentioned gradient calculation can be obtained by the automatic differentiation algorithm of the deep learning model, and this specification does not impose any special restrictions on this.
[0145] Step 608: Determine whether the stopping condition is met. If not, determine the optimized design parameters as the current design parameters for the next iteration and return to step 602. If satisfied, execute step 610.
[0146] In this embodiment, after the cost optimization function is iteratively solved to obtain the optimized design parameters after each round of iterative update, it can be determined whether a stop condition is met.
[0147] In one example, it may be determined whether the cost of the prestressed concrete slab corresponding to the optimized design parameters after optimization has been updated has decreased by a preset ratio compared to the cost of the prestressed concrete slab corresponding to the initial design parameters. If so, it may be determined that a stop condition is satisfied, and the iteration may be stopped, executing step 610. If the stop condition is not satisfied, for example, if the cost reduction has not reached the preset ratio, the next round of iterative solution may be continued.
[0148] Among them, the cost of the prestressed concrete slab corresponding to the design parameters can be calculated using the aforementioned cost calculation function. For example, after determining the initial design parameters, the cost calculation function can be used to calculate the corresponding initial cost and save it. After the optimized design parameters are obtained, the cost calculation function can be used to calculate the optimized cost for comparison with the initial cost.
[0149] In another example, it can be determined whether a preset number of iterative solutions has been reached. In the case of introducing a penalty coefficient, the number of iterative solutions can be an iteration threshold of the penalty coefficient. If the number of iterative solutions has not been reached, the next round of iterative solutions can be continued. If the number of iterative solutions has been reached, the iteration can be stopped and step 610 can be executed.
[0150] In another example, whether the cost has been reduced by a preset ratio can be determined while determining whether a preset number of iterative solutions has been reached. When the cost has been reduced by a preset ratio or the preset number of iterative solutions has been reached, it can be determined that the stopping condition is met. If neither is met, it can be determined that the stopping condition is not met.
[0151] Step 610 : verifying the latest optimized design parameters obtained after the iteration stops, and determining the latest optimized design parameters as the design result of the prestressed concrete slab if the latest optimized design parameters pass the verification.
[0152] Based on the judgment result of the aforementioned step 608 , if the iteration stop condition is met, it can be determined whether the load response corresponding to the latest optimized design parameter obtained after the iteration stops exceeds the corresponding threshold to verify the latest optimized design parameter.
[0153] Specifically, a finite element analysis method can be used to determine the load response corresponding to the latest optimized design parameters. Then, for each load response, the magnitude relationship between it and the corresponding load response threshold can be determined. For example, it can be determined whether the maximum stress corresponding to the latest optimized design parameters exceeds the design allowable stress (i.e., the stress threshold), and it can also be determined whether the maximum deflection corresponding to the latest optimized design parameters exceeds the design allowable deflection (i.e., the deflection threshold). If the maximum stress does not exceed the stress threshold and the maximum deflection does not exceed the deflection threshold, it can be determined that the latest optimized design parameters have passed verification, and the latest optimized design parameters can be determined as the design results of the prestressed concrete slab. If the maximum stress exceeds the stress threshold or the maximum deflection exceeds the deflection threshold, it can be determined that the latest optimized design parameters have failed verification. In this case, the initial design parameters can be re-entered to re-optimize the design parameters. This specification does not impose any special restrictions on this.
[0154] It can be seen from this that after the iteration stops and the latest optimized design parameters are obtained, this embodiment can also verify the latest optimized design parameters, and after the latest optimized design parameters pass the verification, they can be determined as the design results for the design of the prestressed concrete slab, thereby ensuring that the prestressed concrete slab structure designed using the design results is safe and complies with the design specifications.
[0155] Figure 8 This is a schematic structural diagram of a device provided by an exemplary embodiment. Figure 8 At the hardware level, the device includes a processor 802, an internal bus 804, a network interface 806, a memory 808, and a non-volatile memory 810. Of course, it may also include hardware required for other functions. One or more embodiments of this specification can be implemented based on software, such as the processor 802 reading the corresponding computer program from the non-volatile memory 810 into the memory 808 and then running it. Of course, in addition to software implementation, one or more embodiments of this specification do not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0156] Please refer to Figure 9 The design device 900 for prestressed concrete slabs can be applied to Figure 8 The device shown in the figure is used to implement the technical solution of this specification. The design device 900 of the prestressed concrete slab may include:
[0157] A function acquisition unit 902 acquires a cost optimization function for a prestressed concrete slab, wherein the cost optimization function includes a cost term and a load constraint term. The cost term uses the design parameters of the prestressed concrete slab as input variables, and the load constraint term uses the load response of the prestressed concrete slab as input variables.
[0158] The iterative optimization unit 904 iteratively performs the following steps until a stopping condition is met:
[0159] Determine the current design parameters used in this iteration;
[0160] Predicting a current load response corresponding to the current design parameters based on a load prediction model;
[0161] Performing a current round of iteration on the cost optimization function using the current design parameters and the current load response to optimize the current design parameters, thereby obtaining optimized design parameters;
[0162] Updating the current design parameters to the optimized design parameters and performing the next round of iteration;
[0163] The result determination unit 906 determines the latest optimized design parameters obtained after the iteration stops as the design result of the prestressed concrete slab.
[0164] Optionally, the process of constructing the cost optimization function includes:
[0165] Cost calculation function for constructing prestressed concrete slabs;
[0166] Constructing a constrained optimization problem with the goal of minimizing the cost calculation function, wherein the constraint condition of the constrained optimization problem includes that the load response of the prestressed concrete slab does not exceed a threshold value;
[0167] The cost optimization function is constructed based on the constrained optimization problem, wherein the cost item in the cost optimization function corresponds to the cost calculation function, and the constraint item corresponds to the constraint condition.
[0168] Optionally, the training process of the load prediction model includes:
[0169] Constructing sample data for training the load prediction model, wherein the sample data uses design parameters of the prestressed concrete slab as features and load responses corresponding to the design parameters as labels;
[0170] The sample data is used to train the initial load prediction model to obtain a trained load prediction model.
[0171] Optionally, the sample data constructed for training the load prediction model includes:
[0172] Obtaining several sets of design parameters of prestressed concrete slabs;
[0173] The finite element analysis method is used to determine the load response corresponding to each set of design parameters;
[0174] The design parameters and the load responses are normalized respectively, and the sample data is constructed based on the normalized design parameters and their corresponding load responses.
[0175] Optionally, the stop condition includes:
[0176] Compared with the current design parameters used in the first round of iterations, the cost of the prestressed concrete slab corresponding to the optimized design parameters has been reduced by a preset proportion.
[0177] Optionally, the process in which the result determination unit 906 determines the latest optimized design parameters obtained after the iteration stops as the design result of the prestressed concrete slab includes:
[0178] Verifying the latest optimized design parameters;
[0179] In a case where the latest optimized design parameters pass the verification, the latest optimized design parameters are determined as the design results of the prestressed concrete slab.
[0180] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor implements the steps of the method described in any of the above embodiments by running the executable instructions.
[0181] Based on the same concept as the above method, this specification also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.
[0182] Based on the same concept as the above method, this specification also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any of the above embodiments when executed by a processor.
Claims
1. A design method for a prestressed concrete slab, characterized in that: The method comprises: Obtaining a cost optimization function for the prestressed concrete slab, the cost optimization function including a cost term and a load constraint term, the cost term using design parameters of the prestressed concrete slab as input variables, and the load constraint term using a load response of the prestressed concrete slab as input variables; Iterate the following steps until the stopping condition is met: Determine the current design parameters used in this iteration; Predicting a current load response corresponding to the current design parameters based on a load prediction model; Performing a current round of iteration on the cost optimization function using the current design parameters and the current load response to optimize the current design parameters, thereby obtaining optimized design parameters; Updating the current design parameters to the optimized design parameters and performing the next round of iteration; The latest optimized design parameters obtained after the iteration stops are determined as the design results of the prestressed concrete slab; The construction process of the cost optimization function includes: Constructing a cost calculation function for a prestressed concrete slab, wherein the cost calculation function is the sum of the concrete slab cost and the prestressing cost, wherein the concrete slab cost is the product of the concrete slab usage and the concrete slab unit price, and the prestressing cost is the product of the prestressing usage and the prestressing unit price; Constructing a constrained optimization problem with the goal of minimizing the cost calculation function, wherein the constraints of the constrained optimization problem include that the load response of the prestressed concrete slab does not exceed a threshold value, and the load response of the prestressed concrete slab does not exceed the threshold value includes that the maximum stress of the prestressed concrete slab does not exceed the design allowable stress threshold value, and the maximum deflection does not exceed the design allowable deflection threshold value; The constrained optimization problem is converted into an unconstrained optimization problem by using the Lagrange multiplier method to construct the cost optimization function, wherein the cost term in the cost optimization function corresponds to the cost calculation function, and the constraint term corresponds to the constraint condition.
2. The method according to claim 1, characterized in that The training process of the load prediction model includes: Constructing sample data for training the load prediction model, wherein the sample data uses design parameters of the prestressed concrete slab as features and load responses corresponding to the design parameters as labels; The sample data is used to train the initial load prediction model to obtain a trained load prediction model.
3. The method according to claim 2, characterized in that The sample data constructed for training the load prediction model includes: Obtaining several sets of design parameters of prestressed concrete slabs; The finite element analysis method is used to determine the load response corresponding to each set of design parameters; The design parameters and the load responses are normalized respectively, and the sample data is constructed based on the normalized design parameters and their corresponding load responses.
4. The method according to claim 1, wherein The stop conditions include: Compared with the current design parameters used in the first round of iterations, the cost of the prestressed concrete slab corresponding to the optimized design parameters has been reduced by a preset proportion.
5. The method according to claim 1, wherein The process of determining the latest optimized design parameters obtained after the iteration stops as the design result of the prestressed concrete slab includes: Verifying the latest optimized design parameters; In a case where the latest optimized design parameters pass the verification, the latest optimized design parameters are determined as the design results of the prestressed concrete slab.
6. A design device for prestressed concrete slabs, characterized in that: The device comprises: a function acquisition unit for acquiring a cost optimization function of a prestressed concrete slab, wherein the cost optimization function includes a cost term and a load constraint term, wherein the cost term uses a design parameter of the prestressed concrete slab as an input variable, and the load constraint term uses a load response of the prestressed concrete slab as an input variable; Iterate the optimization unit and iteratively perform the following steps until the stopping condition is met: Determine the current design parameters used in this iteration; Predicting a current load response corresponding to the current design parameters based on a load prediction model; Performing a current round of iteration on the cost optimization function using the current design parameters and the current load response to optimize the current design parameters, thereby obtaining optimized design parameters; Updating the current design parameters to the optimized design parameters and performing the next round of iteration; A result determination unit determines the latest optimized design parameters obtained after the iteration stops as the design results of the prestressed concrete slab; The construction process of the cost optimization function includes: Constructing a cost calculation function for a prestressed concrete slab, wherein the cost calculation function is the sum of the concrete slab cost and the prestressing cost, wherein the concrete slab cost is the product of the concrete slab usage and the concrete slab unit price, and the prestressing cost is the product of the prestressing usage and the prestressing unit price; Constructing a constrained optimization problem with the goal of minimizing the cost calculation function, wherein the constraints of the constrained optimization problem include that the load response of the prestressed concrete slab does not exceed a threshold value, and the load response of the prestressed concrete slab does not exceed the threshold value includes that the maximum stress of the prestressed concrete slab does not exceed the design allowable stress threshold value, and the maximum deflection does not exceed the design allowable deflection threshold value; The constrained optimization problem is converted into an unconstrained optimization problem by using the Lagrange multiplier method to construct the cost optimization function, wherein the cost term in the cost optimization function corresponds to the cost calculation function, and the constraint term corresponds to the constraint condition.
7. An electronic device, characterized in that: include: processor; A memory for storing processor-executable instructions; wherein the processor implements the steps of the method according to any one of claims 1 to 5 by executing the executable instructions.
8. A computer-readable storage medium, characterized in that Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.
9. A computer program product, characterized in that The method comprises a computer program / instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.