CN-121980643-A - Dynamic compaction parameter optimization method, equipment and medium for multi-mode data

CN121980643ACN 121980643 ACN121980643 ACN 121980643ACN-121980643-A

Abstract

The invention relates to the technical field of construction, in particular to a dynamic compaction parameter optimization method, equipment and medium for multi-mode data. The method comprises the steps of obtaining vibration time-course data and building attribute information in a dynamic compaction construction process, dynamically inverting stratum fluctuation parameters of a construction area through a trained convolutional neural network model based on the vibration time-course data, constructing a vibration propagation attenuation correction model fusing building vibration sensitivity weights based on the stratum fluctuation parameters and the building attribute information, establishing a multi-target optimization model based on a first target and a second target aiming at a current compaction point to be constructed, and solving by adopting a multi-target optimization algorithm based on a prediction result provided by the vibration propagation attenuation correction model to obtain the optimal compaction energy and the optimal compaction point azimuth angle of the current compaction point. The invention improves the accuracy of prediction, the intelligence of decision and the adaptability to complex dynamic working conditions, thereby cooperatively optimizing the construction quality and the environmental safety.

Inventors

ZHOU CHONG
ZHUANG PEIZHI
LI HUI
LI CHAO
YUE HONGYA
MIAO JIACHENG
LIU XINGGUANG
JIA SHIKUI
ZHANG TINGTING
ZHANG HONGZHI

Assignees

山东建筑大学
山东科技大学
中科智岩(山东)科技发展有限公司
山东大学
河北龙滕重工科技有限公司

Dates

Publication Date: 20260505
Application Date: 20251224

Claims (10)

1. The dynamic compaction parameter optimization method for the multi-mode data is characterized by comprising the following steps of: obtaining vibration time course data and building attribute information in the dynamic compaction construction process; Based on the vibration time course data, dynamically inverting stratum fluctuation parameters of a construction area through a trained convolutional neural network model; constructing a vibration propagation attenuation correction model fused with the building vibration sensitivity weight based on the stratum fluctuation parameter and the building attribute information; aiming at the current tamping point to be constructed, a multi-objective optimization model is established based on a first objective and a second objective; And solving by adopting a multi-objective optimization algorithm based on a prediction result provided by the vibration propagation attenuation correction model to obtain the optimal ramming energy and the optimal ramming point azimuth angle of the current ramming point.
2. The method for optimizing dynamic compaction parameters for multi-modal data as set forth in claim 1, wherein, The first target is to maximize the predicted soil compactness increment in the current to-be-constructed ramming point influence area, and the second target is to minimize the risk weighted vibration values of all surrounding building positions.
3. The method for optimizing dynamic compaction parameters for multi-modal data as set forth in claim 1, wherein, The building attribute information comprises basic attribute information and functional attribute information, wherein the basic attribute information comprises structure type, basic form, construction age and current situation.
4. The method for optimizing dynamic compaction parameters for multi-modal data as set forth in claim 1, wherein, The dynamic inversion of stratum fluctuation parameters of a construction area through a trained convolutional neural network model based on the vibration time-course data comprises the following steps: The characteristics of vibration time-course data of multiple measuring points are arranged according to the spatial positions of the sensors to form a vibration characteristic diagram which is used as the input of a convolutional neural network encoder-decoder structure, and the output of the network is stratum fluctuation parameters including the thickness, shear wave speed, density and damping ratio of each soil layer.
5. The method for optimizing dynamic compaction parameters for multi-modal data as set forth in claim 1, wherein, The building of the vibration propagation attenuation correction model fusing the building vibration sensitivity weight based on the stratum fluctuation parameter and the building attribute information comprises the following steps: And calculating a building vibration sensitivity weight coefficient according to the building attribute information, using the building vibration sensitivity weight coefficient as a risk amplification factor, coupling the risk amplification factor into a two-dimensional non-uniform medium wave equation established based on inversion stratum parameters, and outputting the vibration propagation attenuation correction model as a risk weighted vibration value.
6. The method for optimizing dynamic compaction parameters for multi-modal data as set forth in claim 1, wherein, The establishing the multi-objective optimization model comprises the following steps: The decision variables of the multi-objective optimization model are ramming energy E and ramming point azimuth angle theta, the multi-objective optimization model is built based on safety constraint conditions and equipment constraint conditions, the multi-objective optimization model comprises a first multi-objective optimization model based on a first objective and a second multi-objective optimization model based on a second objective, The first multi-objective optimization model is expressed as: Wherein, X= [ E, θ ], Calculating a total number of grid points for the target area; The soil compactness increment at the jth grid point is obtained; The second multi-objective optimization model is expressed as: Wherein Is the number of buildings; The vibration value is weighted for risk.
7. The method for optimizing dynamic compaction parameters of multi-modal data according to claim 6, wherein the method for solving by using the multi-objective optimization algorithm is characterized by comprising the steps of adopting a constrained multi-objective particle swarm algorithm and predicting vibration values by a fast proxy model constructed by a deep neural network, outputting a Pareto optimal solution set by using the multi-objective optimization algorithm, and selecting a final implementation mode by using a multi-attribute decision method.
8. A dynamic compaction parameter optimization system for multi-modal data, comprising: the data acquisition module is used for acquiring vibration time course data and building attribute information in the dynamic compaction construction process; The parameter optimization module is used for dynamically inverting stratum fluctuation parameters of a construction area through a trained convolutional neural network model based on the vibration time course data; The multi-model optimization module is used for establishing a multi-target optimization model based on a first target and a second target aiming at the current tamping point to be constructed; and the decision analysis module is used for solving and obtaining the optimal tamping energy and the optimal tamping point azimuth angle of the current tamping point by adopting a multi-objective optimization algorithm based on the prediction result provided by the vibration propagation attenuation correction model.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 7 when the program is executed by the processor.
10. A computer-readable storage medium having instructions stored thereon that, when executed by one or more processors, cause the processors to perform the dynamic compaction parameter optimization method of multi-modal data according to any one of claims 1-7.

Description

Dynamic compaction parameter optimization method, equipment and medium for multi-mode data Technical Field The invention relates to the technical field of construction, in particular to a dynamic compaction parameter optimization method, equipment and medium for multi-mode data. Background The dynamic compaction method is a construction method for compacting deep foundations by utilizing huge impact energy generated by free falling of a heavy hammer from a high place, and is widely applied to foundation treatment of large-scale projects such as airports, ports, warehouse logistics centers and the like due to economy and high efficiency. However, strong vibration waves generated during the construction process can propagate to surrounding strata, and may cause structural damage, functional failure or resident discomfort to adjacent buildings, structures, precision instruments or underground pipelines, thus constituting significant environmental safety risks and social problems. With the advancement of urban updating and infrastructure construction, the requirements for dynamic compaction construction in existing building dense areas or environment sensitive areas are increasing, and vibration control has become a core challenge for restricting the safe and efficient application of the dynamic compaction construction. At present, the prior art scheme has obvious defects in the aspects of prediction accuracy, decision intelligence and adaptability to complex dynamic working conditions. The core contradiction of how to reach the soil compactness required by design most efficiently and economically on the premise of ensuring the absolute safety of surrounding environment in dynamic compaction construction is that the 'trial-and-error' adjustment is still highly dependent on the personal experience of constructors, and a set of scientific intelligent decision support system is lacked. Therefore, there is a need for an intelligent dynamic compaction parameter optimization method capable of improving prediction accuracy and decision. Disclosure of Invention In view of the above problems, the present disclosure provides a method, apparatus and medium for dynamic compaction parameter optimization of multi-modal data, which overcomes or at least partially solves the above problems, and aims to improve accuracy of prediction, intelligence of decision making and adaptability to complex dynamic conditions, so as to cooperatively optimize construction quality and environmental safety. The aim of the invention can be achieved by the following technical scheme: according to a first aspect of the technical scheme of the invention, a dynamic compaction parameter optimization method for multi-mode data is provided, which comprises the following steps: obtaining vibration time course data and building attribute information in the dynamic compaction construction process; Based on the vibration time course data, dynamically inverting stratum fluctuation parameters of a construction area through a trained convolutional neural network model; constructing a vibration propagation attenuation correction model fused with the building vibration sensitivity weight based on the stratum fluctuation parameter and the building attribute information; aiming at the current tamping point to be constructed, a multi-objective optimization model is established based on a first objective and a second objective; And solving by adopting a multi-objective optimization algorithm based on a prediction result provided by the vibration propagation attenuation correction model to obtain the optimal ramming energy and the optimal ramming point azimuth angle of the current ramming point. Further, the method comprises the steps of, The first target is to maximize the predicted soil compactness increment in the current to-be-constructed ramming point influence area, and the second target is to minimize the risk weighted vibration values of all surrounding building positions. Further, the method comprises the steps of, The building attribute information comprises basic attribute information and functional attribute information, wherein the basic attribute information comprises structure type, basic form, construction age and current situation. Further, the method comprises the steps of, The dynamic inversion of stratum fluctuation parameters of a construction area through a trained convolutional neural network model based on the vibration time-course data comprises the following steps: The characteristics of vibration time-course data of multiple measuring points are arranged according to the spatial positions of the sensors to form a vibration characteristic diagram which is used as the input of a convolutional neural network encoder-decoder structure, and the output of the network is stratum fluctuation parameters including the thickness, shear wave speed, density and damping ratio of each soil layer. Further, the method comprises the steps of, The building o