Disclosure of Invention
The invention provides an automated bridge design and optimization decision method based on a body, which aims to overcome the technical problems.
The invention provides an automated bridge design and optimization decision method based on a body, which comprises the following steps:
constructing a ontology knowledge base according to multi-domain knowledge of bridge design requirements; the multi-domain knowledge of bridge design requirements includes: bridge engineering knowledge, bridge design specifications, knowledge of the hidden carbon energy and sustainable development fields, bridge building material cost knowledge and optimization decision knowledge;
defining a plurality of classes, a hierarchy of the classes and attributes of the classes in the ontology knowledge base according to the multi-domain knowledge of the bridge design requirement, and creating instances of the classes;
establishing a bridge design semantic net rule based on the ontology knowledge base; the bridge design semantic web rule comprises: bridge safety design calculation rules, bridge hidden carbon energy calculation rules and material cost calculation rules;
establishing an optimization decision semantic network rule and a semantic query rule to optimize the calculation result of the bridge design semantic network rule;
inputting bridge design requirements, and operating the bridge design semantic net rules to obtain bridge design parameters; and operating the optimization decision semantic web rule and the semantic query rule to obtain the bridge design optimization decision parameters.
Further, the constructing the ontology knowledge base according to the multi-domain knowledge of the bridge design requirement further includes: enumerating bridge engineering domain terms according to multi-domain knowledge of the bridge design requirements; the bridge engineering field term includes: bridge design terms, implicit carbon energy terms, bridge building material cost terms, optimization decision terms, and terms in the chinese bridge specification.
Further, the plurality of classes includes: bridge knowledge-related classes and optimization decision-related classes; a class related to bridge knowledge, comprising: bridge types, bridge structural parts, bridge actions and bridge materials; optimizing decision-related classes, comprising: optimization methods, optimization problems and optimization functions.
Further, the bridge design semantic network rule and the optimization decision semantic network rule are SWRL rules; the semantic query rule is an SQWRL rule.
Further, the bridge safety design calculation rule includes: the permanent action concentration, the maximum bending moment and the variable action effect cause the rules of maximum bending moment, total bending moment, crack calculation and deflection calculation.
Further, the bridge hidden carbon energy calculation rule comprises: according to the Chinese commercial concrete mix proportion, calculating different concrete hidden carbon energy quantities through hidden carbon energy of an ICE database;
calculating the amount of hidden carbon-containing energy sources in bridge concrete according to the formula (1):
wherein V is I Is the unit length and the volume of the bridge, co i-concrete The amount of carbon energy is hidden for the concrete.
Further, the concrete cost calculation rule includes:
calculating the bridge concrete cost according to the formula (2)
In which W is I Is the weight per unit volume of bridge structure, cost i Representing the cost per square meter of concrete.
Further, establishing an optimization decision semantic web rule and a semantic query rule to optimize the calculation result of the bridge design semantic web rule, including: calculating the calculation result of the bridge design semantic net rule according to an optimization objective function of a formula (3), wherein the constraint of the optimization objective function is mid-span cracks and deflection, and the optimization objective is bridge safety, carbon emission and cost;
F(x 1 ,x 2 ,x 3 )=A 1 f (safety) +A 2 f (carbon emission) +A 3 f (cost) (3)
Wherein the variable x 1 Is the cross-sectional area, the variable x 2 For concrete types, variable x 3 Is the type of the steel bar; a is that 1 、A 2 、A 3 All are weight coefficients which can be adjusted according to the requirements of a designer.
Further, after the optimization decision semantic web rule and the semantic query rule are established, the method further comprises: and verifying the correctness of the logic relationship between the knowledge in the ontology knowledge base through a PELLET reasoner, and verifying the correctness of the bridge design semantic web rule, the optimization decision semantic web rule and the semantic query rule through a SWRL Tab plug-in.
Further, the method further comprises the following steps: introducing flow definition knowledge into the ontology knowledge base, defining a flow model by adopting BPMN, and converting the flow model into flow definition classes and attributes through ontology mapping; and visualizing the flow definition class and the attribute through an OntGraf Tab visualization plug-in.
According to the invention, based on the knowledge of the body construction, the bridge specification, the hidden carbon energy of materials, the cost, the optimization, the flow definition and other fields are introduced, the automatic design meeting the requirements of bridge consideration safety, energy consumption and cost multi-objective is realized through knowledge reasoning based on semantic net rules, and the bridge engineer is assisted to find the accurate design scheme meeting the requirements through the optimization decision model and semantic query, so that the whole process of the bridge multi-objective automatic design and optimization decision is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a diagram of an architecture of the body system of the present invention;
FIG. 3a is a diagram illustrating creation of classes and attributes in accordance with the present invention;
FIG. 3b is an exemplary diagram of an example creation of a class of the present invention;
FIG. 4 is a schematic diagram of a specification introduction system of the present invention;
FIG. 5 is a schematic diagram of an optimization decision development process of the present invention;
FIG. 6 is a log diagram of a semantic consistency check performed by the Pellet plug-in of the present invention;
FIG. 7 is a log diagram of the operation of the SWRL tab plug-in of the present invention for rule checking;
FIG. 8 is a schematic diagram of a case design simple beam of the present invention;
FIG. 9a is a diagram of the design results of the case of the present invention;
fig. 9b is a graph of the optimal decision results for the case of the present invention;
FIG. 9c is a crack histogram, which is a design result of the case of the present invention;
FIG. 9d is a histogram of deflection, which is a design result of the case of the present invention;
FIG. 9e is a design result-cost and hidden carbon energy histogram for the case of the present invention;
fig. 9f is a histogram of the optimal decision results for the case of the present invention;
FIG. 10a is an expanded SWRL rule diagram of the present invention;
FIG. 10b is a graph of the results of continuous beam reasoning using the present invention;
FIG. 11a is a diagram illustrating a flow definition by ontology mapping according to the present invention;
FIG. 11b is a schematic diagram of a flow definition in accordance with the present invention;
FIG. 11c is a flow definition visualization of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1 and fig. 2, the present embodiment provides a method for automatically designing and optimizing a bridge based on a body, which includes:
101. constructing a ontology knowledge base according to multi-domain knowledge of bridge design requirements; the multi-domain knowledge of bridge design requirements includes: bridge engineering knowledge, bridge design specifications, knowledge of the hidden carbon energy and sustainable development fields, bridge building material cost knowledge and optimization decision knowledge;
102. defining a plurality of classes, a hierarchy of the classes and attributes of the classes in the ontology knowledge base according to the multi-domain knowledge of the bridge design requirement, and creating instances of the classes;
specifically, steps 101 and 102 are processes of building an ontology base, specifically:
first: the domain and scope of the ontology is determined. The area and the field covered by the knowledge base are mainly divided into six aspects of knowledge, wherein the first aspect is basic knowledge in bridge engineering, including classification of bridges, composition of bridges and the like; the second aspect is bridge specification, including specifications of security design requirements, calculation methods and related parameters; a third aspect is knowledge about the fields of implicit carbon energy and sustainable development; four aspects are the cost of the material; the fifth aspect is optimization knowledge; the sixth aspect is empirical knowledge of the flow definition.
Second,: important terms in the ontology are enumerated. In enumerating terms, it is critical to generate terms related to bridge design, cost, hidden carbon energy, and optimization. In addition to capturing important terms in bridge engineering, such as bridge length, pier height, etc., reference is made to hundreds of terms, such as actions, action design values, etc., explicitly listed in the chinese bridge specification.
Third,: classes and class hierarchies are defined. The collected terms are classified according to a top-down mode as shown in fig. 3a, and knowledge relation construction is an important step of system framework formation.
The classes of the ontology knowledge base at least comprise classes related to bridge knowledge, optimization classes and flow definition classes. The bridge knowledge class specifically comprises a bridge type class, a bridge structural component class, a bridge action class and a bridge material class. Bridge type classes include girder bridge class, slab bridge subclass, cable-stayed bridge subclass, etc.; bridge module classes include Liang Zilei, pier subclasses, auxiliary structure subclasses, and the like; bridge action classes include permanent action subclasses and variable action subclasses; bridge materials include concrete subclasses, steel bar subclasses, steel subclasses, etc
The optimization class comprises an optimization method class, an optimization problem class and an optimization function class, and the optimization function class comprises an optimization constraint subclass, an optimization target subclass and an optimization variable subclass.
The flow definition class includes an activity subclass, a task subclass, a gateway subclass.
Fourth,: attributes of the class are defined. The attributes of the definition classes in the ontology shown in fig. 3a include a relationship attribute representing the relationship between the different classes and a data attribute defining the size of the values. Table 1 shows the middle class, hierarchy and attributes of the ontology knowledge base.
TABLE 1
Fifth,: an instance is created. As shown in fig. 3b, this step will create different bridge sections, concrete types and rebar types in the body in the form of examples, for example reinforced concrete materials, the types of concrete and rebar types being selected during the creation of the examples, and the data properties of its modulus of elasticity, density, compressive strength, hidden carbon energy and cost being manually entered.
103. Establishing a bridge design semantic net rule based on the ontology knowledge base; bridge design semantic Web rules comprising: bridge safety design calculation rules, bridge hidden carbon energy calculation rules and material cost calculation rules;
specifically, bridge design specifications are introduced into bridge safety design calculation rules, and the bridge design specifications mainly comprise three aspects, namely specifications of material characteristics, specifications of parameter selection and safety requirement specifications. Bridge specifications are implemented by adding annotation and writing rules as shown in fig. 4 to the knowledge base.
The method is specifically implemented by writing SWRL rules through SWRL Tab, wherein the SWRL rules are in the form of:
B 1 ,…,B n →A 1 ,…,A m (1)
wherein comma indicates conjunctive, A 1 ,…,A m And B 1 ,…,B n May be shaped as C (x), P (x, y), sameAs (x, y), or diffentfrom (x, y), where C is an OWL description, P is an OWL attribute, and x and y are Datalog variables, OWL instances, or OWL data values.
Table 2 is SWRL rules for security calculations.
TABLE 2
On the basis of completing the safety design, the invention has the design aim of considering the concrete hidden carbon energy. The calculation rule of the concrete hidden carbon energy is described as follows:
9 kinds of Chinese commercial concrete with different strengths are selected, each concrete gives a detailed mix ratio, and most of the adopted numerical values are taken from ICE carbon and energy inventory databases developed by Hammond and Jones of Bas university to calculate the implicit carbon energy of the nine kinds of concrete. The online tool can model up to 3 different concrete mixtures and compare their specific carbon footprints. In-line tools allow a user to input the composition of concrete, typically available from concrete design certificates provided by concrete suppliers.
Factors related to the amount of implicit carbon energy are the mix ratio of the concrete, the prefabrication or on-site fabrication, the volume of the rebar and the transportation distance. The mixing ratio of the concrete can be selected from the quick-checking manual of the cooperation of Chinese commercial concrete, the cement type is ordinary Portland cement, the volume of the reinforcing steel bar is determined according to the reinforcing steel bar amount of the bridge, the concrete manufacturing mode is prefabrication, the distance is 500KM, and the calculated results are shown in Table 3:
TABLE 3 Table 3
The concrete implicit carbon energy is calculated according to the formula (2):
wherein V is I Is the unit length and the volume of the bridge, co i-concrete The amount of carbon energy is hidden for the concrete;
the method is specifically implemented by writing SWRL rules through SWRL Tab, and the SWRL rules are calculated for the implicit carbon energy quantity in table 4.
TABLE 4 Table 4
The concrete cost calculation process is described as follows:
the cost difference of materials is mainly concerned in the calculation process of the cost of concrete. Since concrete prices in different areas of China are different, the average price of eight concrete suppliers in 10 months and 10 days in 2020 in Beijing area is used as a reference in the calculation, wherein nine concrete prices are shown in Table 5:
TABLE 5
Concrete type
|
C25
|
C30
|
C35
|
C40
|
C45
|
C50
|
C55
|
C60
|
C70
|
Cost (, RMB/m) 3 )
|
447.5
|
457.5
|
472.5
|
487.5
|
502.5
|
517.5
|
532.5
|
547.5
|
587.5 |
Concrete costs are calculated according to formula (3):
in which W is I Is the weight per unit volume of bridge structure, cost i Representing the cost per square meter of concrete.
The implementation is to write SWRL rules by SWRL Tab, table 6 is the SWRL rules for cost calculation.
TABLE 6
104. Establishing an optimization decision semantic network rule and a semantic query rule to optimize the calculation result of the bridge design semantic network rule;
specifically, as shown in fig. 5, the flow of the optimization decision is that the design results of the multiple design schemes generated in 103 are queried first, then the three design target results are normalized, and calculated by the optimization equation, specifically, the SWRL rule is written by the SWRL Tab, and table 7 is the SWRL rule calculated by the optimization decision.
TABLE 7
And establishing a semantic web query language, and extracting a bridge design structure and an optimization decision result. The SQWRL language is written through SQWRL Tab, and the SQWRL rules are shown in table 8.
TABLE 8
Calculating the calculation result of the bridge design semantic net rule according to an optimization objective function of a formula (4), wherein the constraint of the optimization objective function is mid-span cracks and deflection, and the optimization objective is bridge safety, carbon emission and cost;
F(x 1 ,x 2 ,x 3 )=A 1 f (safety) +A 2 f (carbon emission) +A 3 f (cost) (4)
Wherein the variable x 1 Is the cross-sectional area, the variable x 2 For concrete types, variable x 3 Is the type of the steel bar; a is that 1 、A 2 、A 3 All are weight coefficients which can be adjusted according to the requirements of a designer.
The semantics and rule correctness are checked, and the specific operation is to run a Pellet reasoner and a SWRL rule plug-in. Fig. 6 and 7 are diagrams of inspection completion logs, respectively.
105. Inputting bridge design requirements, and operating a bridge design semantic net rule to obtain various bridge design scheme design result parameters; operating the optimization decision semantic web rule and the semantic query rule to obtain bridge design optimization decision parameters; and operating the query language to extract design results and optimized decision results.
Specifically, taking the simple beam design as shown in fig. 8 as an example, specific design requirements are shown in table 9, and the feasibility of the method is verified by performing design calculation. Fig. 9a and 9b are a design result diagram and an optimization decision result diagram, and are described in the form of histograms of fig. 9c to 9f for making the results more objectively and clearly expressed.
TABLE 9
In this embodiment, the verification method is expandable, so as to avoid new difficulties for design engineers when using the system to design other bridge types, such as continuous beam bridges, the system establishes a relatively perfect bridge basic knowledge base, and when performing other bridge calculation, only rules need to be added through SWRL Tab. To verify the convenient expansibility of the system, the continuous beam bridge design is expanded, the details are shown in the following table 10, fig. 10a is an expanded SWRL rule, wherein SSB represents a simply supported beam SWRL rule, CBB represents a continuous beam SWRL rule, and fig. 10b is a continuous beam reasoning result diagram.
Table 10
In this embodiment, a flow definition and a flow visualization are developed. In order to enable bridge designers to better use the method for designing the bridge, the invention adds a flow definition module. The specific implementation form is that BPMN process elements are mapped into an ontology through a mapping method of the ontology, and then process visualization is achieved through OntGraf Tab. The ontology and BPMN element mapping is shown in fig. 11a, and the flow definition and flow visualization is shown in fig. 11b, 11 c.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.