Rolling compacted concrete compaction quality analysis method, device, equipment and storage medium

Abstract

This application proposes a method, apparatus, equipment, and storage medium for analyzing the compaction quality of roller-compacted concrete. The method includes: acquiring a first VC value and a first air content of the concrete; acquiring vibration signals during the concrete compaction process; establishing a discrete computational grid for the concrete pouring layer, and setting a second VC value and a second air content for each grid based on the first VC value and the first air content; for each computational grid, inputting the vibration signal, the corresponding second VC value, and the corresponding second air content into a pre-established limit learning machine to obtain a corresponding compaction index; wherein the limit learning machine has been pre-trained to obtain the relationship between VC value, air content, vibration signal, and compaction index; and performing concrete compaction quality analysis based on the compaction index of each computational grid. The technical solution of this application can improve the accuracy of compaction quality analysis.

Description

Technical Field

[0001] This application relates to the fields of building engineering and computer technology, and in particular to a method, apparatus, equipment and storage medium for analyzing the compaction quality of roller-compacted concrete. Background Technology

[0002] The compaction quality of block aggregates is crucial to the safety and maintenance of roller-compacted concrete dams, and the degree of compaction is a key indicator for evaluating compaction quality. In related technologies, the limited number of measurement points in compaction quality testing methods leads to incomplete assessments and poor timeliness. During compaction, multiple factors such as the environment, concrete, and vehicles dynamically change, resulting in a complex and nonlinear system, and traditional single-modal evaluation models have low accuracy. While intelligent compaction technology can achieve real-time monitoring, it ignores a large amount of data, and the limited sampling frequency easily leads to analytical distortion. Summary of the Invention

[0003] This application aims to at least partially address one of the technical problems in the related art.

[0004] In a first aspect, this application proposes a method for analyzing the compaction quality of roller-compacted concrete. The method includes: obtaining a first VC value and a first air content of the concrete; obtaining vibration signals during the concrete compaction process; establishing a discrete computational grid for the concrete pouring surface, and setting a second VC value and a second air content for each grid based on the first VC value and the first air content; for each computational grid, inputting the vibration signal, the corresponding second VC value, and the corresponding second air content into a pre-established limit learning machine to obtain a corresponding compaction index; wherein the limit learning machine has been pre-trained to obtain the relationship between the VC value, air content, vibration signal, and compaction index; and performing concrete compaction quality analysis based on the compaction index of each computational grid.

[0005] In one implementation, the extreme learning machine is pre-constructed through the following steps: linearly combining a Gaussian kernel function and a polynomial kernel function to obtain a hybrid kernel function; constructing a hybrid kernel extreme learning machine based on the hybrid kernel function; optimizing the cuckoo algorithm using a chaotic method; and fine-tuning the parameters of the hybrid kernel extreme learning machine using the optimized cuckoo algorithm to obtain the extreme learning machine.

[0006] In one implementation, setting a second VC value and a second gas content for each grid based on the first VC value and the first gas content includes: constructing a probability density model of VC value and gas content based on bootstrapping and maximum entropy estimation; and assigning a corresponding second VC value and a second gas content to each grid based on the probability density model and the first VC value.

[0007] In one implementation, the concrete compaction quality analysis based on the compaction index of each of the computational grids includes: generating a compaction quality distribution map based on the compaction index of each grid; and determining the target area where the compaction index is less than the index threshold based on the compaction quality distribution map.

[0008] In one implementation, the method further includes: obtaining the measured actual compaction index; performing fast leave-one-out cross-validation based on the actual compaction index and the compaction index; and updating the parameters of the extreme learning machine if the fast leave-one-out cross-validation fails.

[0009] In one implementation, before inputting the vibration signal, the corresponding second VC value, and the corresponding second gas content into a pre-established limit learning machine for each computational grid to obtain the corresponding compaction index, the method further includes: performing data cleaning on the vibration signal.

[0010] Secondly, this application proposes a roller-compacted concrete compaction quality analysis device, the device comprising: a first acquisition module for acquiring a first VC value and a first air content of the concrete; a second acquisition module for acquiring vibration signals during the concrete compaction process; a first processing module for establishing a discrete computational grid for the concrete pouring surface, and setting a second VC value and a second air content for each grid based on the first VC value and the first air content; a second processing module for inputting the vibration signal, the corresponding second VC value, and the corresponding second air content into a pre-established limit learning machine for each computational grid to acquire a corresponding compaction index; wherein the limit learning machine has been pre-trained to obtain the relationship between VC value, air content, vibration signal, and compaction index; and a third processing module for performing concrete compaction quality analysis based on the compaction index of each computational grid.

[0011] In one implementation, the device further includes a fourth processing module, used to pre-construct the extreme learning machine through the following steps: linearly combining a Gaussian kernel function and a polynomial kernel function to obtain a hybrid kernel function; constructing a hybrid kernel extreme learning machine based on the hybrid kernel function; optimizing the cuckoo algorithm using a chaotic method; and performing parameter tuning on the hybrid kernel extreme learning machine using the optimized cuckoo algorithm to obtain the extreme learning machine.

[0012] In one implementation, the first processing module is configured to: construct a probability density model of VC value and gas content based on bootstrapping resampling and maximum entropy estimation; and assign a corresponding second VC value and second gas content to each of the grids based on the probability density model and the first VC value.

[0013] In one implementation, the third processing module can be used to: generate a compaction quality distribution map based on the compaction index of each grid; and determine the target area where the compaction index is less than the index threshold based on the compaction quality distribution map.

[0014] In one implementation, the device further includes a fifth processing module, configured to: acquire the measured actual compaction index; perform fast leave-one cross-validation based on the actual compaction index and the compaction index; and update the parameters of the extreme learning machine if the fast leave-one cross-validation fails.

[0015] In one implementation, the first processing module can also be used to perform data cleaning on the vibration signal.

[0016] Thirdly, this application proposes an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the roller-compacted concrete compaction quality analysis method as described in the first aspect.

[0017] Fourthly, this application proposes a storage medium storing instructions that, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect.

[0018] Fifthly, this application proposes a program product comprising at least one of a program and instructions, wherein when the program and instructions are executed by an electronic device, they implement the steps of the method described in the first aspect.

[0019] The roller-compacted concrete compaction quality analysis method, apparatus, equipment, and storage medium provided in this application can configure the second VC value and second air content of each grid in an established computational grid based on the first VC value and first air content of the concrete. Based on the second VC value, second air content, and vibration signals during the concrete compaction process, the compaction index of each grid is obtained, and the concrete compaction quality analysis is performed based on the compaction index of each computational grid. This improves the accuracy of compaction quality analysis.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0022] Figure 1 This is a schematic flowchart of a method for analyzing the compaction quality of roller-compacted concrete provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a hybrid extreme learning machine provided in an embodiment of this application; Figure 3 This is a schematic diagram of an optimization process for an extreme learning machine provided in an embodiment of this application; Figure 4 This is a flowchart illustrating a chaotic cuckoo search algorithm provided in an embodiment of this application; Figure 5 This is a schematic diagram of a roller-compacted concrete compaction quality analysis system provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of a roller-compacted concrete compaction quality analysis device provided in an embodiment of this application; Figure 7 This is a schematic diagram of another roller-compacted concrete compaction quality analysis device provided in the embodiments of this application; Figure 8 This is a schematic diagram of the structure of another roller-compacted concrete compaction quality analysis device provided in the embodiments of this application; Figure 9 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0024] The following description, with reference to the accompanying drawings, describes a method and apparatus for analyzing the compaction quality of roller-compacted concrete according to embodiments of this application.

[0025] Figure 1 This is a flowchart illustrating a method for analyzing the compaction quality of roller-compacted concrete provided in an embodiment of this application. Figure 1 As shown, the method may include, but is not limited to, the following steps: S101: Obtain the first VC (Vibrating Consistency) value and the first air content of the concrete.

[0026] For example, the first VC index and first air content of unvibrated concrete are obtained.

[0027] S102: Acquire vibration signals during concrete compaction.

[0028] For example, an acceleration sensor installed on a concrete compaction device collects the acceleration signal of the concrete compaction process as the aforementioned vibration signal.

[0029] S103: Establish a calculation grid for the concrete pouring layer, and set the second VC value and second air content for each grid based on the first VC value and the first air content.

[0030] For example, the concrete pouring layer is spatially discretized and divided into several discrete computational grids according to the size and construction accuracy requirements of the pouring layer; then, based on the first VC value and the first air content of the concrete, a probability distribution is fitted, and a corresponding second VC value and second air content are set for each computational grid.

[0031] In one implementation, before inputting the vibration signal, the corresponding second VC value, and the corresponding second gas content into a pre-established limit learning machine for each computational grid to obtain the corresponding compaction index, the method further includes: performing data cleaning on the vibration signal.

[0032] For example, vibration signals are cleaned to remove abnormal data such as those generated by sudden stops, rolling jumps, and rolling drops.

[0033] S104: For each computational grid, the vibration signal, the corresponding second VC value, and the corresponding second gas content are input into a pre-established limit learning machine to obtain the corresponding compaction index.

[0034] Among them, the Extreme Learning Machine has obtained the relationship between VC value, gas content, vibration signal and compaction index through pre-training.

[0035] For example, for each computational grid, partial vibration data of the concrete compaction equipment during concrete compaction in the corresponding area of ​​the computational grid is obtained. This partial vibration data, along with the second VC value and the second air content corresponding to the computational grid, is input into a pre-built limit learning machine to obtain the predicted compaction index output by the limit learning machine.

[0036] In some embodiments, the extreme learning machine described above is constructed by introducing regularization coefficients.

[0037] As an example, please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a hybrid extreme learning machine provided in an embodiment of this application. Figure 2 As shown, the Extreme Learning Machine (ELM) consists of an input layer, a hidden layer, a hybrid kernel function, and an output layer. Vibration signals, VC values, and gas content of each grid cell can be input into the input layer to obtain the corresponding compaction parameters.

[0038] In one implementation, the aforementioned extreme learning machine is pre-built through the following steps A1-A4: A1: A hybrid kernel function is obtained by linearly combining the Gaussian kernel function and the polynomial kernel function.

[0039] A2: Constructing a hybrid kernel extreme learning machine based on hybrid kernel functions.

[0040] A3: Optimize the Cuckoo algorithm using a chaotic approach.

[0041] For example, the Cuckoo algorithm is optimized using Lévy flight and Logistic chaotic systems to improve its global and local search capabilities.

[0042] A4: The optimized Cuckoo algorithm was used to fine-tune the parameters of the hybrid kernel extreme learning machine.

[0043] For example, the optimized Cuckoo algorithm is used to perform population evolution optimization on the parameters in the hybrid kernel extreme learning machine until the maximum number of iterations or the model accuracy meets the requirements is reached.

[0044] As an example, please see Figure 3 , Figure 3 This is a schematic diagram of an optimization process for an Extreme Learning Machine provided in an embodiment of this application. Figure 3 As shown, the Gaussian kernel function and the polynomial kernel function are first linearly combined to construct a hybrid kernel function; then, a chaotic cuckoo search algorithm based on Lévy flight and Logistic chaotic system is used to intelligently optimize the hyperparameters of the kernel limit learning machine, resulting in a limit learning machine for concrete compaction quality analysis.

[0045] As an example, please see Figure 4 , Figure 4 This is a flowchart illustrating a chaotic cuckoo search algorithm provided in an embodiment of this application, as shown below. Figure 4 As shown, the algorithm first initializes parameters and randomly generates N nests through initial population chaos processing. Then, it finds the current optimal nest position sequence and uses this sequence to update the positions of the first M cuckoos. Next, it uses the Levy flight algorithm to perform global iterative updates of the nest positions. Then, it enters the better individual chaotic interference stage, comparing the nest positions with the previous generation to select a set of better nest positions, and then finds the optimal nest position for the current iteration. Finally, it checks whether the algorithm termination condition is met. If not, it returns to the optimal nest position search step to continue iterative looping. If the condition is met, it outputs the final optimal solution.

[0046] S105: Concrete compaction quality analysis based on compaction indices of each computational grid.

[0047] For example, based on the compaction index of each computing grid, areas where the compaction index is less than or equal to a preset index threshold are identified, and these areas are then compacted.

[0048] In one implementation, the concrete compaction quality analysis based on the compaction index of each computational grid includes: generating a compaction quality distribution map based on the compaction index of each grid; and determining the target area where the compaction index is less than the index threshold based on the compaction quality distribution map.

[0049] For example, based on the compaction index values ​​corresponding to the calculated grid of the concrete pouring layer, the compaction index of each grid is graded according to a preset compaction quality evaluation threshold. A color mapping method is used to color the grids of different compaction quality levels, generating a compaction quality distribution map that visually indicates the quality and spatial distribution of compaction across the entire layer. The compaction index of each grid is then compared with the compaction index threshold. If the compaction index is less than the threshold, the grid is identified as the target area.

[0050] By implementing the embodiments of this application, a second VC value and a second air content can be configured for each grid in the established computational grid based on the first VC value and the first air content of the concrete. Based on the second VC value, the second air content, and the vibration signal during the concrete compaction process, the compaction index of each grid can be obtained, and concrete compaction quality analysis can be performed based on the compaction index of each computational grid. This improves the accuracy of compaction quality analysis.

[0051] In some embodiments, the above method may further include the following steps: obtaining the measured actual compaction index; performing fast leave-one-out cross-validation based on the actual compaction index and the compaction index; and updating the parameters of the extreme learning machine if the fast leave-one-out cross-validation fails.

[0052] For example, the actual compaction index of each grid concrete is detected and obtained. The actual compaction index is compared with the compaction index output by the extreme learning machine to obtain the difference. If the difference is greater than or equal to a preset threshold, the parameters of the extreme learning machine are updated by using the Fast Leave-One-Out Cross Validation (FLOO-CV) method.

[0053] By implementing the embodiments of this application, the parameters of the extreme learning machine can be updated when the difference between the actual compaction index and the compaction index output by the extreme learning machine is greater than a preset threshold, so as to ensure the accuracy of the compaction quality analysis of roller-compacted concrete.

[0054] Please see Figure 5 , Figure 5This is a schematic diagram of the structure of a roller-compacted concrete compaction quality analysis system provided in an embodiment of this application, as shown below. Figure 5 As shown, the location and elevation data of concrete compaction operations can be acquired in real time through a high-precision GNSS (Global Navigation Satellite System) system; vibration signals during the compaction process are collected by an accelerometer and dynamic signal acquisition device installed on the vibratory roller; simultaneously, the measured concrete VC value and air content parameters are entered on-site using a PDA; finally, the multi-source data, including location and elevation, vibration signals, VC value, and air content, are uploaded to the backend system in real time through vehicle-mounted data transmission equipment and wireless communication network, thereby enabling the analysis of roller-compacted concrete compaction quality based on the above data.

[0055] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a roller-compacted concrete compaction quality analysis device provided in an embodiment of this application. Figure 6 As shown, the device 600 includes: a first acquisition module 601 for acquiring the first VC value and the first air content of concrete; a second acquisition module 602 for acquiring vibration signals during concrete compaction; a first processing module 603 for establishing a discrete computational grid for the concrete pouring surface and setting a second VC value and a second air content for each grid based on the first VC value and the first air content; a second processing module 604 for inputting the vibration signal, the corresponding second VC value, and the corresponding second air content into a pre-established extreme learning machine for each computational grid to acquire the corresponding compaction index; wherein the extreme learning machine has been pre-trained to obtain the relationship between VC value, air content, vibration signal, and compaction index; and a third processing module 605 for performing concrete compaction quality analysis based on the compaction index of each computational grid.

[0056] In one implementation, the first processing module 603 is used to: construct a probability density model of VC value and gas content based on self-bootsampling and maximum entropy estimation; and assign a corresponding second VC value and second gas content to each grid based on the probability density model and the first VC value.

[0057] In one implementation, the third processing module 605 can be used to: generate a compaction quality distribution map based on the compaction index of each grid; and determine the target area where the compaction index is less than the index threshold based on the compaction quality distribution map.

[0058] In one implementation, the first processing module 603 can also be used to perform data cleaning on the vibration signal.

[0059] In one implementation, the apparatus further includes a fourth processing module. See, as an example, [link to example]. Figure 7 , Figure 7 This is a schematic diagram of another roller-compacted concrete compaction quality analysis device provided in an embodiment of this application. Figure 7 As shown, the device 700 includes a fifth processing module 706: used to pre-construct an extreme learning machine through the following steps: linearly combining a Gaussian kernel function and a polynomial kernel function to obtain a hybrid kernel function; constructing a hybrid kernel extreme learning machine based on the hybrid kernel function; optimizing the cuckoo algorithm using a chaotic method; and fine-tuning the parameters of the hybrid kernel extreme learning machine using the optimized cuckoo algorithm to obtain the extreme learning machine. Figure 7 Modules 701-706 in Figure 6 Modules 601-605 in the series have the same structure and function.

[0060] In one implementation, the device further includes a fifth processing module. See, as an example, [link to example]. Figure 8 , Figure 8 This is a schematic diagram of another roller-compacted concrete compaction quality analysis device provided in an embodiment of this application. Figure 8 As shown, the device 800 includes a fifth processing module 806: used for: acquiring the measured actual compaction index; performing rapid leave-one-out cross-validation based on the actual compaction index and the compaction index; and updating the parameters of the extreme learning machine if the rapid leave-one-out cross-validation fails. Figure 8 Modules 801-806 in Figure 6 Modules 601-605 in the series have the same structure and function.

[0061] The apparatus of this application embodiment can configure the second VC value and second air content of each grid in the established computational grid based on the first VC value and first air content of concrete. Based on the second VC value, second air content, and vibration signals during concrete compaction, the compaction index of each grid can be obtained, and concrete compaction quality analysis can be performed based on the compaction index of each computational grid. This improves the accuracy of compaction quality analysis.

[0062] It should be noted that the foregoing explanation of the embodiment of the roller-compacted concrete compaction quality analysis method also applies to the roller-compacted concrete compaction quality analysis device of this embodiment, and will not be repeated here.

[0063] To implement the above embodiments, this application also proposes an electronic device. Please see [link to relevant documentation]. Figure 9 , Figure 9 This is a schematic diagram of the structure of the electronic device provided in an embodiment of this application. For example... Figure 9As shown, the electronic device 900 includes: a processor 901 and a memory 902 communicatively connected to the processor 901; the memory 902 stores computer-executable instructions; the processor 901 executes the computer-executable instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0064] To implement the above embodiments, this application also proposes a storage medium storing instructions that, when executed on an electronic device, cause the electronic device to perform the methods provided in the foregoing embodiments.

[0065] To implement the above embodiments, this application also proposes a program product, including at least one of a program and instructions, wherein when the program and instructions are executed by an electronic device, they implement the steps of the method provided in the foregoing embodiments.

[0066] It should be noted that the acquisition, transmission, storage, use, and processing of data in this application comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.

[0067] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0068] It is worth noting that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used the solution.

[0069] In the description of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document is merely a description of the relationship between related objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone.

[0070] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0071] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0072] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0073] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0074] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0075] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0076] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0077] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method of analyzing the compaction quality of roller compacted concrete, characterized in that, include: Obtain the first Vebe consistency (VC) value and the first air content of the concrete; Acquire vibration signals during concrete compaction; A discrete computational grid is established for the concrete pouring layer, and a second VC value and a second air content are set for each grid based on the first VC value and the first air content; For each computational grid, the vibration signal, the corresponding second VC value, and the corresponding second gas content are input into a pre-established extreme learning machine to obtain the corresponding compaction index; wherein, the extreme learning machine has been pre-trained to obtain the relationship between VC value, gas content, vibration signal, and compaction index; Concrete compaction quality analysis is performed based on the compaction index of each of the computational grids.

2. The method of claim 1, wherein, The extreme learning machine is pre-built through the following steps: By linearly combining the Gaussian kernel function and the polynomial kernel function, a hybrid kernel function is obtained; Construct a hybrid kernel extreme learning machine based on the aforementioned hybrid kernel function; The Cuckoo algorithm is optimized using a chaotic approach; The optimized Cuckoo algorithm is used to fine-tune the parameters of the hybrid kernel extreme learning machine to obtain the extreme learning machine.

3. The method according to claim 1, characterized in that, The step of setting the second VC value and second gas content of each grid based on the first VC value and the first gas content includes: Based on self-guided resampling and maximum entropy estimation, a probability density model of VC value and gas content is constructed. Based on the probability density model and the first VC value, each of the grids is assigned a corresponding second VC value and a second gas content.

4. The method according to claim 1, characterized in that, The concrete compaction quality analysis based on the compaction index of each of the computational grids includes: Based on the compaction index of each grid, a compaction quality distribution map is generated; Based on the compaction quality distribution map, the target area where the compaction index is less than the index threshold is determined.

5. The method according to claim 1, characterized in that, The method further includes: Obtain the actual measured compaction parameters; Rapid leave-one cross-validation is performed based on the actual compaction index and the compaction index. If the fast leave-one cross-validation fails, the parameters of the extreme learning machine are updated.

6. The method according to claim 1, characterized in that, Before inputting the vibration signal, the corresponding second VC value, and the corresponding second gas content into a pre-established limit learning machine for each computational grid to obtain the corresponding compaction index, the method further includes: The vibration signal is then cleaned.

7. A device for analyzing the compaction quality of roller-compacted concrete, characterized in that, include: The first acquisition module acquires the first VC value and the first air content of the concrete. The second acquisition module acquires vibration signals during the concrete compaction process; The first processing module is used to establish a discrete computational grid for the concrete pouring layer, and to set the second VC value and second air content of each grid based on the first VC value and the first air content. The second processing module is used to input the vibration signal, the corresponding second VC value, and the corresponding second gas content into a pre-established extreme learning machine for each computational grid to obtain the corresponding compaction index; wherein the extreme learning machine has been pre-trained to obtain the relationship between VC value, gas content, vibration signal and compaction index; The third processing module is used to perform concrete compaction quality analysis based on the compaction index of each of the computational grids.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.

9. A storage medium storing instructions, characterized in that, When the instructions are executed on an electronic device, the electronic device causes the electronic device to perform the method of any one of claims 1 to 6.

10. A program product comprising at least one of a program and instructions, characterized in that, When at least one of the program or instructions is executed by an electronic device, it implements the steps of the method according to any one of claims 1 to 6.

Images