CN-122022539-A - Reservoir dam construction quality assessment method and device based on data-knowledge dual drive

CN122022539ACN 122022539 ACN122022539 ACN 122022539ACN-122022539-A

Abstract

The application relates to the technical field of hydraulic engineering quality assessment, in particular to a method and a device for assessing the construction quality of a reservoir dam based on data-knowledge dual drive, wherein the method comprises the steps of collecting multi-source data of the construction of the reservoir dam; and integrating the detection data and the knowledge spectrum to obtain detection data-knowledge spectrum, and evaluating the actual construction quality of the reservoir dam according to the detection data-knowledge spectrum. Therefore, the problems that the construction quality is difficult to comprehensively analyze and evaluate in real time in the related technology due to various data types, high acquisition frequency and strong instantaneity in the construction process of the reservoir dam, and the construction process is not timely monitored, the quality is lagged in control, potential safety hazards cannot be early warned and the like are solved.

Inventors

XIA WANCHUN
LI YAJUN
TIAN ZHENHUA
QIAN CHENG
GAN YONGBO
CHANG PENGFEI
JIA WEILONG

Assignees

中国地质大学（北京）
中国水利水电科学研究院

Dates

Publication Date: 20260512
Application Date: 20251210

Claims (10)

1. The method for evaluating the construction quality of the reservoir dam based on data-knowledge double driving is characterized by comprising the following steps of: collecting multi-source data of reservoir dam construction, and performing at least one of cleaning, exception handling, standardization and space-time alignment on the multi-source data to obtain processed detection data; Structuring knowledge in the field of construction quality of the reservoir dam according to the entity, attribute and relation form to construct a knowledge graph in the field of construction quality of the reservoir dam; and fusing the detection data and the knowledge graph to obtain a detection data-knowledge graph, and evaluating the actual construction quality of the reservoir dam according to the detection data-knowledge graph.
2. The method of claim 1, wherein said at least one of cleaning, exception handling, normalization, and space-time alignment of the multi-source data to obtain processed detection data comprises: adopting missing value filling and repeated value removal to carry out cleaning treatment on the multi-source data so as to obtain cleaned data; performing exception processing on the cleaned data by adopting a3 sigma criterion to obtain corrected data; carrying out standardization processing on the corrected data to obtain standardized data, and mapping the standardized data to a preset interval to generate mapping data; and carrying out space-time alignment processing on the mapping data to obtain the detection data.
3. The method of claim 1, wherein structuring knowledge of the reservoir dam construction quality area based on the form of entities, attributes and relationships to construct a knowledge graph of the reservoir dam construction quality area comprises: Utilizing a pre-trained relationship identification model to identify the relationship between the entities; based on an embedded entity matching strategy, converting text description of the entity into a vector, and calculating similarity of the vector so as to unify the relationships among the entities in different knowledge sources according to the similarity; determining the weight of the relation between the entities according to preset domain expert knowledge; and constructing the knowledge graph according to the entities, the relationships among the entities, the weights of the relationships among the entities and the attributes of the entities.
4. The method of claim 1, wherein the fusing the detection data and the knowledge-graph to obtain a detection data-knowledge-graph comprises: aligning the entities by adopting a preset rule-embedded hybrid alignment strategy to obtain aligned entities; updating the weight of the relation according to the detection data to obtain updated relation weight; searching associated knowledge in the knowledge graph by adopting preset breadth-first search and combining the ordering of the relation weights; And constructing the detection data-knowledge graph according to the aligned entities, the relation weights and the associated knowledge.
5. The method of claim 4, wherein the updated formula for the relationship weights is: , Wherein w ij is an initial relation weight, S ij is a data feature similarity, and α is an adjustment coefficient.
6. The utility model provides a reservoir dam construction quality evaluation device based on data-knowledge double drive which characterized in that includes: The processing module is used for collecting multi-source data of reservoir dam construction, and performing at least one of cleaning, exception handling, standardization and space-time alignment on the multi-source data to obtain processed detection data; The construction module is used for structuring knowledge of the construction quality field of the reservoir dam according to the entity, attribute and relation form so as to construct a knowledge graph of the construction quality field of the reservoir dam; And the evaluation module is used for fusing the detection data and the knowledge graph to obtain a detection data-knowledge graph, and evaluating the actual construction quality of the reservoir dam according to the detection data-knowledge graph.
7. The apparatus of claim 6, wherein the processing module comprises: the cleaning unit is used for cleaning the multi-source data by adopting missing value filling and repeated value removal so as to obtain cleaned data; The correction unit is used for carrying out exception processing on the cleaned data by adopting a 3 sigma criterion so as to obtain corrected data; the normalization unit is used for performing normalization processing on the corrected data to obtain normalized data, mapping the normalized data to a preset interval and generating mapping data; And the alignment unit is used for carrying out space-time alignment processing on the mapping data so as to obtain the detection data.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the data-knowledge based dual drive reservoir dam construction quality assessment method of any one of claims 1-5.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor for implementing the data-knowledge dual drive reservoir dam construction quality evaluation method according to any one of claims 1 to 5.
10. A computer program product comprising a computer program, characterized in that the computer program is executed for implementing a data-knowledge based dual drive reservoir dam construction quality assessment method according to any one of claims 1-5.

Description

Reservoir dam construction quality assessment method and device based on data-knowledge dual drive Technical Field The application relates to the technical field of hydraulic engineering quality assessment, in particular to a method and a device for assessing the construction quality of a reservoir dam based on data-knowledge dual driving. Background In the related art, the method for evaluating the construction quality of the reservoir dam mainly relies on manual inspection, fixed-point sampling and laboratory analysis, so that the strength, compactness and structural integrity of the dam construction material can be primarily judged, and the construction process is ensured to meet the design requirements. However, mass, multi-source and heterogeneous detection data including material performance parameters, structural deformation monitoring data, environmental condition data, construction process parameters and the like are generated in the construction process of the reservoir dam, so that the characteristics of various types, high acquisition frequency and high real-time performance exist, the construction quality is difficult to comprehensively analyze and evaluate in real time in the related technology, the fine monitoring and timely risk early warning of the dam construction process cannot be realized, the scientificity and the reliability of the construction quality control are affected, and the problem is to be solved. Disclosure of Invention The application provides a method and a device for evaluating construction quality of a reservoir dam based on data-knowledge dual drive, which are used for solving the problems that in the related technology, the construction quality is difficult to comprehensively analyze and evaluate in real time due to various data types, high acquisition frequency and strong instantaneity in the construction process of the reservoir dam, so that the construction process is not monitored timely, the quality control is delayed and potential safety hazards cannot be early warned. The embodiment of the first aspect of the application provides a method for evaluating the construction quality of a reservoir dam based on data-knowledge dual driving, which comprises the following steps of collecting multi-source data of reservoir dam construction, performing at least one of cleaning, exception handling, standardization and space-time alignment on the multi-source data to obtain processed detection data, structuring knowledge in the field of the construction quality of the reservoir dam according to the forms of entities, attributes and relations to construct a knowledge graph in the field of the construction quality of the reservoir dam, fusing the detection data and the knowledge graph to obtain detection data-knowledge graph, and evaluating the actual construction quality of the reservoir dam according to the detection data-knowledge graph. Through the technical means, the embodiment of the application can evaluate the actual construction quality of the reservoir dam according to the constructed detection data-knowledge graph, can realize comprehensive quantitative analysis of the construction quality, quickly identify the abnormality and potential risk in the construction process and provide scientific quality improvement suggestion, and simultaneously can support the dynamic fusion of multi-source data and knowledge, so that the evaluation result is more accurate and reliable, and provides efficient and operable support for construction management and decision-making. Optionally, in one embodiment of the present application, the processing at least one of cleaning, exception processing, standardization and space-time alignment of the multi-source data to obtain processed detection data includes cleaning the multi-source data with missing value padding and repeated value removal to obtain cleaned data, exception processing the cleaned data with 3σ rule to obtain corrected data, standardization processing the corrected data to obtain standardized data, mapping the standardized data to a preset interval to generate mapping data, and space-time alignment processing the mapping data to obtain the detection data. Through the technical means, the embodiment of the application can carry out cleaning, exception handling, standardization and space-time alignment treatment on the multi-source data so as to obtain high-quality and uniform-format data, ensure the accuracy and consistency of subsequent analysis, improve the reliability and efficiency of construction quality assessment, exception detection and risk analysis, and provide a solid data base for intelligent monitoring of the whole dam construction process. Optionally, in one embodiment of the present application, the structuring the knowledge of the construction quality field of the reservoir dam according to the forms of the entity, the attribute and the relationship to construct a knowledge graph of the construction quality f