Constructional engineering quality problem reason analysis and reasoning method based on ontology
Through the ontology-based reasoning method of quality problems, and automatic reasoning using SWRL and Drools engines, the problems of frequent and complexity of construction project quality accidents are solved, the quality control efficiency is improved, and the frequency of accidents is reduced.
Patent Information
- Application Number
- CN202410942260.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-19
AI Technical Summary
Construction project quality accidents occur frequently, and the existing technology lacks a pre-prevention mechanism, which mainly focuses on the aftermath work after the accident, resulting in frequent and complex accidents.
The ontology-based analysis and reasoning method of the cause of quality problems in construction projects is adopted, and automated reasoning and control of the causes of quality problems is achieved by building ontology models, creating knowledge bases, and introducing SWRL inference rules and Drools inference engines.
It improves the efficiency and effectiveness of project quality control, can efficiently analyze and solve quality problems during construction, and reduce the frequency of accidents.
Smart Images

Figure CN118982069A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of building engineering construction quality research, and in particular relates to an ontology-based reasoning method for analyzing causes of building engineering quality problems. Background Art
[0002] Construction project quality accidents are characterized by severity, complexity, and frequency. The severity of the accident is reflected in the following: once a construction project quality accident occurs, it is usually a major safety accident, resulting in serious casualties and property losses, and is very likely to cause major public opinion storms, seriously affecting the normal production and living order of society; the complexity of the accident is reflected in the following: construction projects cover many types of buildings, such as steel structure buildings, cast-in-place concrete structure buildings, prefabricated and assembled buildings, etc. Many types of building structures directly determine the complexity and diversity of the final products of the project. The occurrence of engineering quality accidents is hidden in the subtle nodes of each type of building, and the slightest carelessness will affect the whole body; the frequency of the accident is reflected in the following: although the construction technology and methods of construction projects are relatively mature, many construction units, construction units, supervision units, etc. lack a sense of social responsibility, and are not strict enough in terms of the quality of the project, resulting in frequent engineering quality accidents.
[0003] Traditional engineering quality management focuses on the aftermath of engineering quality accidents, lacking the foresight to focus on engineering quality control before the accident, and often regrets after a major production safety accident occurs. Therefore, targeted improvement of the quality management level of construction projects is a breakthrough for the transformation of construction project quality management from post-event management to pre-event prevention. Summary of the invention
[0004] In order to solve the above problems, the present invention provides an ontology-based reasoning method for analyzing the causes of construction project quality problems, which solves the problem that project quality management focuses on the aftermath of project quality accidents instead of focusing on project quality control before the incident.
[0005] The present invention is implemented by the following scheme: a method for analyzing and reasoning the causes of quality problems of construction projects based on ontology, comprising the steps of:
[0006] S1. Constructing the ontology model, including the following steps:
[0007] S101. Create classes of the ontology based on basic elements related to the cause analysis of construction project quality problems, and define the hierarchical relationship of the classes within the ontology;
[0008] S102, conceptually define the classes in the ontology, and add and define object attributes to form an ontology model framework;
[0009] S103, analyzing the characteristics of the classes in the ontology, and adding and defining data attributes to form an ontology model that can quantitatively describe each class;
[0010] S2. Create a knowledge base, collect multiple instances related to construction project quality issues, and classify and store the detailed data in each instance according to the classes in the ontology to form a knowledge base;
[0011] S3, introducing SWRL reasoning rules into the ontology model;
[0012] S4. Based on the rule reasoning of the Drools reasoning engine, the reasoning results are fed back into the ontology model, which specifically includes the following steps:
[0013] S401, extracting and transforming information on actual construction project quality issues that need to be inferred, and matching the transformed information with the knowledge base;
[0014] S402: Obtain detailed data after successful matching, and form an inference result of the cause of the quality problem in the ontology model.
[0015] A further improvement of the ontology-based reasoning method for analyzing the causes of quality problems in construction projects of the present invention is that the classes within the ontology include at least two class hierarchies, and the two class hierarchies correspond to basic classes and subclasses set under the basic classes, respectively. The basic classes include engineering projects, specific quality problems, quality problem representation information, and quality problem cause analysis.
[0016] A further improvement of the ontology-based reasoning method for analyzing causes of quality problems in construction projects of the present invention is that the subcategories within the engineering projects include ordinary residential projects, super-high-rise projects and commercial and residential projects; the subcategories within the specific quality problems include basement leakage, wall cracking and uneven foundation lower layer; the subcategories within the quality problem representation information include basement leakage cracks, wall cracks and foundation subsidence; the subcategories within the quality problem cause analysis include causes of basement leakage cracks, causes of wall cracks and causes of foundation subsidence.
[0017] A further improvement of the ontology-based reasoning method for analyzing the causes of quality problems in construction projects of the present invention is that the concept of the project is defined as the specific name of the construction project; the concept of the specific quality problem is defined as the quality problem existing in the construction of the project; the concept of the quality problem representation information is defined as the intuitive data representation of the project quality problem; the concept of the quality problem cause analysis is defined as analyzing the causes of the quality problem representation information.
[0018] The further improvement of the ontology-based construction project quality problem cause analysis reasoning method of the present invention is that the data attributes of the engineering project include project name, building area, project address, construction unit, construction unit, supervision unit, start date and planned completion date;
[0019] The data attributes of the specific quality problem include the quality problem number, the construction stage, construction personnel, construction materials, construction machinery, construction environment, overall description of the quality problem and quality problem management measures;
[0020] The data attributes of the quality problem appearance information include foundation sinking depth, cement mortar strength, concrete mix ratio, structure hoisting position, rust area ratio, crack width, crack depth, crack length and occurrence position;
[0021] The data attributes of the quality problem cause analysis include the project category, the occurrence stage and the occurrence location.
[0022] A further improvement of the ontology-based reasoning method for analyzing the causes of quality problems in construction projects of the present invention is that each of the object attributes is provided with a domain and a range, wherein the domain is the starting point for describing the relationship between the object attributes and is located at the upper layer of the relationship, and the range is the end point for describing the relationship between the object attributes and is located at the lower layer of the relationship, so as to clarify the relationship between the classes.
[0023] A further improvement of the ontology-based reasoning method for analyzing causes of quality problems in construction projects of the present invention is that the ontology model is constructed using Protégé software.
[0024] A further improvement of the ontology-based reasoning method for analyzing causes of quality problems in construction projects of the present invention is that the Drools reasoning engine uses a forward reasoning mechanism to implement reasoning.
[0025] Compared with the prior art, the present invention has the following beneficial effects:
[0026] The present invention establishes a reasoning model for cause analysis of construction project quality problems based on ontology, uses modeling software to sort out the classes and attributes involved in the cause analysis of construction project quality problems, and builds the basic framework of the ontology model; based on the SWRL reasoning rule language, constructs SWRL attribute and instance reasoning rules; uses the Drools reasoning engine to realize automatic reasoning of the causes of quality problems; realizes the storage and call of knowledge, which is conducive to improving the efficiency and effectiveness of quality control, and can efficiently perform cause analysis and quality control of engineering quality problems, thereby solving engineering quality problems during the construction process to reduce the frequency of engineering accidents. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1The flowchart of the reasoning process for analyzing the causes of quality problems in construction projects of the present invention is shown.
[0028] Figure 2 A schematic diagram of the ontology model framework of the present invention is shown.
[0029] Figure 3 A schematic diagram showing the one-to-one correspondence between the classes in the ontology model of the present invention and the data in the instance is shown.
[0030] Figure 4 A schematic diagram of the Drools inference engine operation interface of the present invention is shown.
[0031] Figure 5 A schematic diagram of the inference result display interface of the present invention is shown. DETAILED DESCRIPTION
[0032] In order to solve the problem that the construction quality management work focuses on the aftermath of the construction quality accident, rather than the construction quality control before the accident, the present invention provides a construction quality problem cause analysis and reasoning method based on ontology. The following is a specific embodiment combined with the accompanying drawings to further illustrate the construction quality problem cause analysis and reasoning method based on ontology.
[0033] See also Figure 1 to Figure 5 As shown, a construction project quality problem cause analysis reasoning method based on ontology includes the following steps:
[0034] S1. Constructing the ontology model, including the following steps:
[0035] S101. Create classes of the ontology based on basic elements related to the cause analysis of construction project quality problems, and define the hierarchical relationship of the classes within the ontology;
[0036] S102, conceptually define the classes in the ontology, and add and define object attributes to form an ontology model framework;
[0037] S103, analyzing the characteristics of the classes in the ontology, and adding and defining data attributes to form an ontology model that can quantitatively describe each class;
[0038] S2. Create a knowledge base, collect multiple instances related to construction project quality issues, and classify and store the detailed data in each instance according to the classes in the ontology to form a knowledge base;
[0039] S3, introduce SWRL reasoning rules into the ontology model;
[0040] S4. Based on the rule reasoning of the Drools reasoning engine, the reasoning results are fed back into the ontology model, which specifically includes the following steps:
[0041] S401, extracting (extracting the inference starting point data, i.e., the data attributes of the engineering project, specific quality problems, and quality problem representation information) and transforming the information of the actual construction project quality problems that need to be inferred, and matching the transformed information with the knowledge base;
[0042] S402: Obtain detailed data after successful matching, and form reasoning results of the causes of quality problems in the ontology model.
[0043] In this embodiment, if the matching fails, the reasoning can be automatically terminated and the instance in the knowledge base can be added.
[0044] Among them, the classes in the ontology include at least two class levels, and the two class levels correspond to the basic class and the subclasses set under the basic class respectively. The basic class includes engineering projects, specific quality problems, quality problem appearance information and quality problem cause analysis;
[0045] Among them, the subcategories within the engineering project include ordinary residential projects, super high-rise projects and commercial and residential projects; the subcategories within the specific quality problems include basement leakage, wall cracks and uneven foundation lower layer; the subcategories within the quality problem appearance information include basement leakage cracks, wall cracks and foundation sinking; the subcategories within the quality problem cause analysis include the causes of basement leakage cracks, wall cracks and foundation sinking;
[0046] According to the created ontology model framework, build an ontology class hierarchy diagram, such as Figure 2 As shown, the detailed categories under the six major categories of "reinforcement engineering", "concrete engineering", "formwork engineering", "cast-in-place structure engineering", "prestressed engineering" and "prefabricated engineering" will be constructed based on the classified construction quality control statements.
[0047] Setting up class families to further subdivide classes facilitates accurate description.
[0048] Among them, the concept of engineering project is defined as the specific name of the construction engineering project; the concept of specific quality problem is defined as the quality problem existing in the construction of the engineering project; the concept of quality problem appearance information is defined as the intuitive data representation of engineering quality problems; the concept of quality problem cause analysis is defined as the analysis of the causes of the quality problem appearance information.
[0049] Among them, object attributes are used to describe the association between classes to achieve the connection between two classes;
[0050] Each object attribute is set with a domain and a range. The domain is the starting point for describing the object attribute relationship and is located at the upper layer of the relationship. The range is the end point for describing the object attribute relationship and is located at the lower layer of the relationship, so as to realize the non-hierarchical relationship between clear classes; as shown in Table 1.
[0051] Table 1:
[0052]
[0053] Among them, data attributes are used to describe the specific data characteristics of a class, so as to achieve an accurate description of each class; by defining data attributes, the ontology Protégé modeling software can quantify the description of each class and describe the object more accurately;
[0054] The data attributes of a project include project name, building area, project address, construction unit, construction unit, supervision unit, start date, and planned completion date. The data attributes of a project are intended to convert the basic information of the project into semantic information that can be recognized by computers.
[0055] The data attributes of specific quality problems include quality problem number, construction stage, construction personnel, construction materials, construction machinery, construction environment, overall description of quality problems, and quality problem management measures; the specific quality problem category contains many manifestations of engineering quality problems, and each quality problem belongs to the common engineering quality problems existing in the current construction engineering industry;
[0056] The data attributes of the quality problem appearance information include foundation sinking depth, cement mortar strength, concrete mix ratio, structure hoisting position, rust area ratio, crack width, crack depth, crack length and location; the quality problem appearance information contains a lot of appearance information about the quality problems of specific construction projects, and the quality problem appearance information is the key information for realizing the ontology-based reasoning of the cause analysis of the quality problems of construction projects. The writing of SWRL reasoning rules will take the data attributes of the quality problem appearance information as the starting point of reasoning;
[0057] The data attributes of the quality problem cause analysis include the project category, the occurrence stage and the location of occurrence; the quality problem cause analysis is the reasoning result part of the ontology established in this embodiment, which lists the possible causes of the construction project quality problems;
[0058] Reference Figure 3 As shown in the figure, each basic class hierarchical relationship and the one-to-one correspondence with the detailed data in the instance are displayed, specifically: the engineering project in the class corresponds to the specific project name in the instance (such as XXX ordinary residential project in Dalian); the specific quality problems under the engineering project correspond to the specific problems (wall cracks) under the specific project name in the instance; the quality problem phenomenon information under the specific quality problem corresponds to the specific phenomenon (wall cracks) under the specific problem in the instance; the quality problem cause analysis under the quality problem phenomenon information corresponds to the cause analysis under the specific phenomenon in the instance (improper putty ratio, uneven scraping).
[0059] Among them, the Drools reasoning engine uses a forward reasoning mechanism to implement reasoning. When the computer can obtain the necessary semantic information to start the reasoning mechanism, Drools will process the domain rules and the factual information in the ontology, thereby realizing the reasoning work in the domain and acquiring new knowledge. The production rules used by the reasoning engine have their specific grammatical form: "WhenA, Then B". If and only if the A condition can be fully met, the new knowledge B can be acquired by executing Drools reasoning. The application of production rules also effectively avoids the reasoning errors caused by the omission of the "else" statement in traditional rules.
[0060] Among them, the ontology model is constructed using Protégé software.
[0061] In this embodiment, the SWRL rules are implemented by using the SWRL Tab plug-in to convert the OWL language and SWRL rules into the Drools reasoning engine language.
[0062] Implementing Drools reasoning requires completing the following three steps:
[0063] 1. Convert the ontology OWL language into Drools facts and convert the SWRL rules into Drools rules;
[0064] 2. Run the Drools reasoning engine to perform knowledge reasoning and generate new Drools facts;
[0065] 3. Convert the new knowledge acquired through Drools reasoning into OWL language and present it in the ontology Protégé model.
[0066] Since the SWRL Tab plug-in used to build SWRL rules can realize the conversion of OWL language and SWRL rules into Drools reasoning engine language, it is convenient for users to directly call Drools reasoning engine. Figure 4 As shown, the user clicks the "OWL+SWRL->Drools", "Run Drools" and "Drools->OWL" buttons in sequence to complete the Drools reasoning work and present the reasoning results feedback in the ontology model.
[0067] Reference Figure 5 As shown, this interface displays the results of the quality problem cause analysis and lists the various reasons that lead to quality problems during the construction phase.
[0068] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0069] The present invention is described in detail above in conjunction with the embodiments of the accompanying drawings. A person skilled in the art can make various variations of the present invention according to the above description. Therefore, certain details in the embodiments should not constitute a limitation of the present invention, and the scope of protection of the present invention shall be defined by the scope of the attached claims.
Claims
1. An ontology-based reasoning method for cause analysis of construction project quality problems. It is characterized in that The method comprises the steps of: S1. Constructing the ontology model, including the following steps: S101. Create classes of the ontology based on basic elements related to the cause analysis of construction project quality problems, and define the hierarchical relationship of the classes in the ontology; S102, conceptually define the classes in the ontology, and add and define object attributes to form an ontology model framework; S103, analyzing the characteristics of the classes in the ontology, and adding and defining data attributes to form an ontology model that can quantitatively describe each class; S2. Create a knowledge base, collect multiple instances related to construction project quality issues, and classify and store the detailed data in each instance according to the classes in the ontology to form a knowledge base; S3, introducing SWRL reasoning rules into the ontology model; S4. Based on the rule reasoning of the Drools reasoning engine, the reasoning results are fed back into the ontology model, which specifically includes the following steps: S401, extracting and transforming information on actual construction project quality issues that need to be inferred, and matching the transformed information with the knowledge base; S402: Obtain detailed data after successful matching, and form an inference result of the cause of the quality problem in the ontology model.
2. The ontology-based reasoning method for analyzing causes of construction project quality problems as claimed in claim 1, It is characterized in that The classes in the ontology include at least two class hierarchies, and the two class hierarchies correspond to a basic class and a subclass set under the basic class, respectively. The basic class includes engineering projects, specific quality problems, quality problem representation information, and quality problem cause analysis.
3. The ontology-based reasoning method for analyzing causes of quality problems in construction projects as claimed in claim 2, It is characterized in that The subcategories of the engineering projects include ordinary residential projects, super high-rise projects and commercial and residential projects; the subcategories of the specific quality problems include basement leakage, wall cracks and uneven lower foundation; the subcategories of the quality problem appearance information include basement leakage cracks, wall cracks and foundation subsidence; the subcategories of the quality problem cause analysis include the causes of basement leakage cracks, the causes of wall cracks and the causes of foundation subsidence.
4. The ontology-based reasoning method for analyzing causes of quality problems in construction projects as claimed in claim 2, It is characterized in that The concept of the engineering project is defined as the specific name of the construction project; the concept of the specific quality problem is defined as the quality problem existing in the construction of the engineering project; the concept of the quality problem appearance information is defined as the intuitive data representation of the engineering quality problem; the concept of the quality problem cause analysis is defined as analyzing the causes of the quality problem appearance information.
5. The ontology-based reasoning method for analyzing causes of quality problems in construction projects as claimed in claim 2, It is characterized in that The data attributes of the engineering project include project name, construction area, project address, construction unit, construction unit, supervision unit, start date and planned completion date; The data attributes of the specific quality problem include the quality problem number, the construction stage, construction personnel, construction materials, construction machinery, construction environment, overall description of the quality problem and quality problem management measures; The data attributes of the quality problem appearance information include foundation sinking depth, cement mortar strength, concrete mix ratio, structure hoisting position, rust area ratio, crack width, crack depth, crack length and occurrence position; The data attributes of the quality problem cause analysis include the project category, the occurrence stage and the occurrence location.
6. The ontology-based reasoning method for analyzing causes of quality problems in construction projects as claimed in claim 1, It is characterized in that Each of the object attributes is provided with a domain and a range, wherein the domain is the starting point for describing the relationship between the object attributes and is located at the upper layer of the relationship, and the range is the end point for describing the relationship between the object attributes and is located at the lower layer of the relationship, so as to clarify the relationship between the classes.
7. The ontology-based reasoning method for analyzing causes of quality problems in construction projects as claimed in claim 1, It is characterized in that The ontology model is constructed using Protégé software.
8. The ontology-based reasoning method for analyzing causes of quality problems in construction projects as claimed in claim 1, It is characterized in that The Drools reasoning engine uses a forward reasoning mechanism to implement reasoning.
