CN110866332B - Complex cable assembly assembling method and system - Google Patents
Complex cable assembly assembling method and system Download PDFInfo
- Publication number
- CN110866332B CN110866332B CN201911037668.2A CN201911037668A CN110866332B CN 110866332 B CN110866332 B CN 110866332B CN 201911037668 A CN201911037668 A CN 201911037668A CN 110866332 B CN110866332 B CN 110866332B
- Authority
- CN
- China
- Prior art keywords
- cable assembly
- ontology
- cable
- similarity
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The invention discloses a complex cable assembly assembling method and a complex cable assembly assembling system, which belong to the technical field of complex cable assembly and comprise the following steps: s1: modeling cable assembly process knowledge; s2: the cable assembly is designed in a man-machine integration mode; s3: and positioning and guiding the wiring harness and preventing errors. The invention provides a multi-domain knowledge model based on an ontology, which is used for realizing consistency check and conflict resolution of the domain ontology and data and carrying out consistency detection and conflict resolution on knowledge; the method is characterized in that a man-machine integrated design prototype for assembling the cable assembly is provided, the reasonability of an automatic wiring scheme is improved by adopting a method of combining automatic computer search and knowledge decision, and a cable path with multiple constraint conditions is generated by utilizing the automatically identified cable fixed structure characteristics; and a virtual-real superposition enhanced visualization environment in a multi-mode interaction mode is established, and the real-time updating and accurate positioning of the guiding information in the operation process are realized by combining a high-precision virtual-real model registration technology.
Description
Technical Field
The invention relates to the technical field of complex cable assembly, in particular to a complex cable assembly method and system.
Background
The cable assembly is a set of assembled combination of wires, cables, connectors and accessories, and is a basic component unit for interconnecting the electrical system and the electronic equipment of complex electromechanical equipment such as aerospace, automobiles, radars and the like, for example, the EWIS (electric line interconnection system) of a commercial airplane generally has cables exceeding 100km, wherein an air passenger A380 comprises 10000 electrical connectors, and the total length of the connected cables exceeds 500km. The assembly quality of the cable assembly is an important index for measuring the performance and reliability of the complete machine of the complex electromechanical equipment, and the reliability and maintainability of the equipment are seriously influenced by the reasonability of the design and the correctness of fixing and connection. Air crash accidents of TWA800 and Swissair111 in the last 90 th century were both directly related to electrical line faults; the united states air force safety center has made statistics on faults caused by various components related to an electronic and electrical system during the period from 1989 to 1999, and found that the wire and cable accounts for up to 29%. Along with the development of the intellectualization and the optical, mechanical and electrical integration direction of equipment, the filling density of the equipment is higher and higher, so that the time and the cost of the cable assembly process are high.
The assembly of the cable assembly needs to comprehensively consider various factors such as structure, electromagnetic compatibility, cable physical property, assemblability and the like, the cable belongs to a flexible body, special requirements such as bundling and fixing exist, the number of connectors is large, the wiring space is narrow, the length of the cable cannot be accurate and the like, and the cable assembly is a general problem in the design of complex electromechanical equipment. The traditional design method is to perform simulated wiring on a prototype or a tool and determine the positions of a wire harness fixing point and a hoop so as to determine the laying path of the cable, and has the problems of long production period, high error rate and the like. In recent years, enterprises begin to comprehensively apply three-dimensional software to carry out virtual assembly of cable assemblies, design links such as wiring assembly simulation, wiring diagram and wiring harness flattening diagram generation are completed in three-dimensional CAD software such as CATIA and UG, and digitization of cable assembly technology is primarily realized. Although the mainstream CAD software has a cable virtual assembly tool, a plurality of technical problems exist in the practical application of enterprises.
For example, in the existing method, in the assembly design of the cable assembly, due to the complexity of the process, the diversity of design elements, the diversity of data and the dynamic property of the assembly process, no model can realize the dynamic evolution in the assembly process and realize the rapid planning and processing of the cable assembly at present, and the traditional mode based on prototype machine, database query and empirical rule judgment cannot cope with the process planning process of the complex cable assembly; the existing method can not integrate the process requirements of cable components such as electrical, electromagnetic compatibility, physical properties, rules and the like, and the detailed problems of semantic information characteristics and the like still lack a complete theory; and meanwhile, the logic reasoning and man-machine decision process based on knowledge is not supported.
Moreover, due to the complexity of bundling of the wire harness of the complex equipment, natural features such as the cable assembly and gestures need to be recognized in real time, and various types of information need to be guided and visualized, the existing method cannot well meet the requirements, and therefore the complex cable assembly assembling method and system are provided.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: how to improve the efficiency of the cable assembly process design and the consistency of the wiring harness positioning, meet the requirement of the parallelism design of the cable assembly of the complex electromechanical equipment, and provide a complex cable assembly method.
The invention solves the technical problems through the following technical scheme, and comprises the following steps:
s1: cable assembly process knowledge modeling
Automatically extracting ontology concepts and relations from experience field documents such as cable path rules, hoop setting rules, design wiring sequence rules and the like by adopting a machine learning method, combining cable assembly engineering semantics based on algorithms such as ontology mapping, logic conventions and the like, and completing consistency check and conflict resolution of a field ontology and data; the method comprises the following steps of filtering irrelevant attributes based on domain concept attributes, relations and the like around the characteristics of cable data, complementing and enhancing the data, and solving the problems of unbalanced data distribution and overfitting caused by sparse data; the logic protocol and state space search are combined, and the knowledge is subjected to consistency detection and conflict resolution; and then based on the field context scene, performing multi-dimensional modeling by adopting an ontology modeling tool Prot g to construct a knowledge ontology model. The method for automatically extracting the domain concepts and relations from the domain unstructured data and the domain structured data is adopted to realize the automatic construction of the domain ontology, the consistency and the integrity of multi-source data and information are improved through methods such as consistency detection and conflict resolution of object data, the problems of identification and resolution of conflicts among knowledge and knowledge updating are solved by using knowledge fusion and enhancement theories and methods, and the effectiveness and the integrity of the obtained knowledge are guaranteed.
S2: man-machine integrated design of cable assembly based on human factor engineering
Combining the general design architecture of Pahl and Beitz with the FBS model based on Gero to design an integrated design prototype; then, carrying out feature recognition on the shape of the cable assembly fixing structure; and then planning the three-dimensional path of the cable under multiple constraints.
S3: wire harness positioning guide and mistake proofing based on enhanced projection
Establishing a characteristic semantic library of a cable assembly, a cable branch, an installation tool and the like, extracting corresponding characteristics of a cable assembly object by adopting detection algorithms such as Hough and the like, and identifying the extracted characteristics in a part geometric characteristic semantic library by adopting a radial basis function neural network identification algorithm according to the quantity and proportion parameters of main characteristics and secondary characteristics to obtain a confidence sequence of a part to be identified and a library part, thereby realizing the rapid and accurate identification of the cable assembly (such as a terminal, a wire binder, a hoop and the like), a wire harness turning radius, the diameter and the like; and then, indexing a domain knowledge body based on the static and dynamic characteristic identification information, accurately registering the guide information at the visible coordinate position of an operator by using a matching coordinate system as a reference through a predefined guide information position calculation method, completing a wire harness operation guide task, simultaneously carrying out real-time analysis and decision on error-proof information such as the turning radius, the diameter and the like of the wire harness, and carrying out quality control on the wire harness assembly process.
Furthermore, in the step S2, from the perspective of ontology and cognition, the integrated design prototype includes two core contents, namely modeling and expression of domain knowledge on one hand and design reasoning and information flow on the other hand.
Further, in the step S2, the ergonomic design includes six design states, which respectively represent six knowledge fields related to the cable assembly design, namely, requirement (R), function (F), configuration (C), structure (S), details (D), and Behavior (Behavior, B), wherein the Behavior can be divided into Expected Behavior (EB) and Actual Behavior (AB).
Furthermore, the integration process of the ontology includes ontology mapping and ontology fusion, the ontology mapping is to identify the local ontology created or proposed by experts in a certain field and similar knowledge concepts in other fields, and the ontology fusion is to merge concepts with similar relationships.
Further, the integration process of the body comprises the following steps:
s211: calculating the similarity of concept names, the similarity of concept attributes, the similarity of concept relationships and the similarity of concept examples, wherein the similarity between the two concepts is calculated through Jaccard factors, and the calculation formula of the similarity of the concept names is as follows:
wherein, C A Ci And C B Cj Sets of synonyms for concepts A and B, respectively, i and j are sets C, respectively A Ci And C B Cj The 'U' operation refers to the calculation of the number of elements of a set formed by the same synonyms owned by the concepts A and B, and the 'U' operation refers to the calculation of the number of elements of a set formed by all the synonyms owned by the concepts A and B;
the similarity between the concept attributes is divided into three aspects of function, constraint and behavior, after the similarity of the three aspects is respectively obtained through the Jaccard factor, the average similarity of the concept attributes and the similarity between the concept relationships and the similarity between the concept examples are respectively calculated by utilizing the Jaccard factor;
s212: on the basis of the four similarities of the name, the attribute, the relationship and the example calculated in step S211, the relationship between the two concepts is judged by calculating the overall similarity;
s213: and storing the overall similarity in a vector, calculating the similarity between other concepts in the global ontology and the currently calculated concepts in the local ontology in the same way as the steps S211 and S212, and finally selecting the global ontology candidate concept corresponding to the maximum value from the vectors storing the similarity as the final result of the ontology mapping.
Further, in the step S2, the process of identifying the characteristic of the shape of the cable assembly fixing structure includes the following steps:
s221: by analyzing the adjacency relation of basic geometric elements of a boundary representation model (B-Rep) of a three-dimensional model of the structure and the concave-convex attributes of the basic geometric elements, establishing an adjacency graph of the characteristics and the attributes of the whole structure, and determining the geometric relation of the basic geometric elements, such as: forming multi-layer attribute shape characteristic models with different thickness and granularity and capable of describing topology, geometry and other information, and establishing a basic shape characteristic library;
B-Rep refers to a contour enveloping line frame of a structural three-dimensional model, the model is a unified structural three-dimensional model, different key functions are realized only through different explicit expression modes, and the extraction and the recording of boundary information of the structural three-dimensional model are realized;
s222: expressing and storing the three-dimensional model and the extended attribute adjacency graph of the shape characteristic in the form of an extended attribute adjacency matrix, searching and extracting the attribute adjacency matrix of the shape characteristic from the attribute adjacency matrix of the three-dimensional model by means of a multilevel attribute adjacency graph of the shape characteristic and a subgraph search algorithm of the characteristic, and comparing the searched submatrix with a matrix in a shape characteristic library through a subgraph matching algorithm to determine the type of the shape characteristic;
s223: determining the decomposition and repair strategies of the intersecting shape features by analyzing the feature traces, restoring the lost geometric elements and the adjacency relation by using geometric reasoning on the basis to further realize shape feature repair, and finally restoring the basic shape features forming the intersecting shape features.
Furthermore, the process of planning the three-dimensional path of the cable under multiple constraints comprises the following steps:
s231: starting point terminal P of cable by bi-RRT algorithm init And a terminal P goal Respectively establishing two path node trees T 1 And T 2 ，T 1 Random expansion node P new After, T 2 With P new For an expanded target node, single-step-length connection is carried out, and if the node collides with an obstacle area, the node returns to the tripped;
s232: exchange two trees, from T 2 Starting to randomly expand node P new ，T 1 To T 2 And (4) connecting in a single step, returning Connected if the two trees are Connected, as shown in FIG. 6 (b), otherwise, returning to Advanced to continue connecting in a single step, and repeating the operation until the two trees are Connected.
Furthermore, the single-step expansion needs to describe the distance between two nodes, and the cable posture is defined as:
p＝(x,y,z,α,β,γ)
p contains position coordinates and orientation coordinates, and the generalized distance function defined is shown as:
in the formula, w t Is a weight coefficient of the position coordinate, w r Is a weight coefficient of a directional coordinate, satisfies a condition w t +w r ＝1，S i And S j Is a component of the position coordinates of two adjacent points, R i And R j Is the directional coordinate component, | S i -S j | | is the Euler distance defined in a three-dimensional coordinate system, | R i -R j | defines the distance of two angles.
Furthermore, in step S3, the guiding information includes process animation, wire harness positioning information display, wire harness path, and quality detection data, the process animation visualizes the cable assembly model, the wiring path, and the assembling order in the form of three-dimensional animation, and is accurately matched with the positioning position of the wire harness tooling plate; the wire harness positioning information is divided into characteristic identification information and process specification information, is obtained by index matching and is visualized based on positioning position association; the wire harness path is a path and indication information which guide an operator in real time through arrows, identification and highlighting in the wire harness assembling process, and the quality detection data is quality problem data which are fed back to the operator for real-time identification and are used for controlling the assembling quality of the wire harness to meet the standard requirement.
The invention also provides a man-machine integrated design and guide control system for assembling the complex cable assembly, which comprises the following components:
the modeling module is used for automatically extracting ontology concepts and relations from experience domain documents by adopting a machine learning method, combining cable component assembly engineering semantics, completing consistency check and conflict resolution of domain ontologies and data, complementing and enhancing the data around the characteristics of cable data, solving the problems of unbalanced data distribution and overfitting caused by data sparseness, combining logic protocol and state space search, performing consistency detection and conflict resolution on knowledge, and then performing multi-dimensional modeling by adopting an ontology modeling tool protege based on domain context to construct a knowledge ontology model;
the human-computer integrated design module is used for combining the general design frameworks of Pahl and Beitz with the FBS model based on Gero to design an integrated design prototype; then, carrying out feature recognition on the shape of the cable assembly fixing structure; then planning the three-dimensional path of the cable under multiple constraints;
the guiding and error-preventing module is used for extracting corresponding characteristics of a cable assembly object by establishing a characteristic semantic library, identifying in the part geometric characteristic semantic library according to the quantity and the proportion parameters of main characteristics and secondary characteristics, acquiring a confidence sequence of parts of a part to be identified and the library part, indexing a domain knowledge body based on static and dynamic characteristic identification information, accurately registering the guiding information in a visible coordinate position of an operator by taking a matching coordinate system as a reference through a predefined guiding information position calculation method, completing a wiring harness operation guiding task, simultaneously performing real-time analysis and decision on error-preventing information such as a wiring harness turning radius, a diameter and the like, and performing quality control on a wiring harness assembly process;
the central processing module is used for sending instructions to other modules to complete related actions;
the modeling module, the man-machine integrated design module and the guiding and error-proofing module are all electrically connected with the central processing module.
Compared with the prior art, the invention has the following advantages:
(1) Aiming at cable assembly process knowledge, a multi-domain knowledge model based on an ontology is provided, and an ontology concept and a relation are automatically extracted from process information and data by adopting a machine learning method; based on algorithms such as ontology mapping, logic specification and the like, the consistency check and conflict resolution of the domain ontology and the data are realized by combining with the cable assembly engineering semantics, and then based on domain concept attributes, relations and the like, irrelevant attributes are filtered, and the data are complemented and enhanced; and (4) combining the logic specification with state space search, and carrying out consistency detection and conflict resolution on knowledge.
(2) Aiming at automatic cable routing planning, a man-machine integrated design prototype for cable assembly is provided, the reasonability of an automatic routing scheme is improved by adopting a method of combining automatic computer search and knowledge decision, and a bi-RRT search method is adopted, and the cable path with multiple constraint conditions is generated by utilizing the automatically identified cable fixed structure characteristics, so that the engineering reasonability of the automatic cable path routing planning scheme is met.
(3) The method comprises the steps of constructing a virtual-real superposition enhanced visualization environment in a multi-mode interaction mode, namely, finishing active enhancement superposition of guide information such as pictures, characters, animations and the like in front of an operator in a maintenance process by combining multiple interaction modes such as gestures, voice, automatic dismounting process identification and the like and a high-precision virtual-real model registration technology, and realizing real-time updating and accurate positioning of the guide information in an operation process.
Drawings
Fig. 1 is a schematic flow chart of a general technical solution of a man-machine integrated design and positioning and guiding method of a cable assembly according to a second embodiment of the present invention;
FIG. 2 is a schematic diagram of the interaction of the cable assembly design influencing factors according to the second embodiment of the present invention;
FIG. 3 is a schematic diagram of a process for constructing an ontology model according to a second embodiment of the present invention;
FIG. 4 is a schematic flow chart of the human-machine integration design based on the FBS model in the second embodiment of the present invention;
FIG. 5 is a schematic diagram of an ontology integration process in the second embodiment of the present invention;
FIG. 6 is a schematic diagram of the bi-RRT algorithm in the second embodiment of the present invention;
FIG. 7 is a schematic view of a feature recognition process for a two-wire cable assembly according to an embodiment of the present invention;
fig. 8 is a schematic block diagram of a process of online visualization of bundle-mounted guidance information in the second embodiment of the present invention.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
Example one
The embodiment provides a technical scheme: a method of assembling a complex cable assembly comprising the steps of:
s1: cable assembly process knowledge modeling
Automatically extracting ontology concepts and relations from experience domain documents such as cable path rules, hoop setting rules, design wiring sequence rules and the like by adopting a machine learning method, and finishing consistency check and conflict resolution of domain ontologies and data by combining cable assembly engineering semantics based on algorithms such as ontology mapping, logic protocols and the like; the cable data characteristics are surrounded, irrelevant attributes are filtered based on the domain concept attributes, the relations and the like, the data are complemented and enhanced, and the over-fitting problem caused by unbalanced data distribution and data sparseness is solved; the logic protocol and state space search are combined, and the knowledge is subjected to consistency detection and conflict resolution; and then based on the field context scene, performing multi-dimensional modeling by adopting an ontology modeling tool Prot g to construct a knowledge ontology model. The method for automatically extracting the domain concepts and relations from the domain unstructured data and the domain structured data is adopted to realize the automatic construction of the domain ontology, the consistency and the integrity of multi-source data and information are improved through methods such as consistency detection and conflict resolution of object data, the problems of identification and resolution of conflicts among knowledge and knowledge updating are solved by using knowledge fusion and enhancement theories and methods, and the effectiveness and the integrity of the obtained knowledge are guaranteed.
S2: man-machine integrated design of cable assembly based on human factor engineering
Combining the general design architecture of Pahl and Beitz with the FBS model based on Gero to design an integrated design prototype; then, carrying out feature recognition on the shape of the cable assembly fixing structure; and then planning the three-dimensional path of the cable under multiple constraints.
S3: wire harness positioning guide and mistake proofing based on enhanced projection
Establishing a characteristic semantic library of a cable assembly, a cable branch, an installation tool and the like, extracting corresponding characteristics of a cable assembly object by adopting detection algorithms such as Hough and the like, and identifying the extracted characteristics in a part geometric characteristic semantic library by adopting a radial basis function neural network identification algorithm according to the quantity and proportion parameters of main characteristics and secondary characteristics to obtain a confidence sequence of a part to be identified and a library part, thereby realizing the rapid and accurate identification of the cable assembly (such as a terminal, a wire binder, a hoop and the like), a wire harness turning radius, the diameter and the like; and then, indexing a domain knowledge body based on the static and dynamic characteristic identification information, accurately registering the guide information at the visible coordinate position of an operator by using a matching coordinate system as a reference through a predefined guide information position calculation method, completing a wire harness operation guide task, simultaneously carrying out real-time analysis and decision on error-proof information such as the turning radius, the diameter and the like of the wire harness, and carrying out quality control on the wire harness assembly process.
In the step S2, from the perspective of ontology and cognition, the integrated design prototype includes two core contents, which are modeling and expression of domain knowledge, design inference and information flow, respectively.
In the step S2, the ergonomic design includes six design states, which respectively represent six knowledge fields related to the cable assembly design, namely Requirement (R), function (F), configuration (C), structure (S), details (D), and Behavior (Behavior, B), wherein the Behavior can be divided into Expected Behavior (EB) and actual Behavior (actual Behavior, AB).
The integration process of the ontology comprises ontology mapping and ontology fusion, wherein the ontology mapping is to identify a local ontology established or proposed by experts in a certain field and similar knowledge concepts in other fields, and the ontology fusion is to merge concepts with similar relations.
The integration process of the body comprises the following steps:
s211: calculating the similarity of concept names, the similarity of concept attributes, the similarity of concept relationships and the similarity of concept examples, wherein the similarity between the two concepts is calculated through Jaccard factors, and the calculation formula of the similarity of the concept names is as follows:
wherein, C A Ci And C B Cj Sets of synonyms for concepts A and B, respectively, i and j are sets C, respectively A Ci And C B Cj The 'U' operation refers to the calculation of the number of elements of a set formed by the same synonyms owned by the concepts A and B, and the 'U' operation refers to the calculation of the number of elements of a set formed by all the synonyms owned by the concepts A and B;
the similarity between the concept attributes is divided into three aspects of function, constraint and behavior, after the similarity of the three aspects is respectively obtained through the Jaccard factor, the average similarity of the concept attributes, the similarity between the concept relationships and the similarity between the concept instances are respectively calculated by utilizing the Jaccard factor;
s212: on the basis of the four similarities of the name, the attribute, the relationship and the instance calculated in step S211, the relationship between the two concepts is judged by calculating the overall similarity;
s213: and storing the overall similarity in a vector, calculating the similarity between other concepts in the global ontology and the currently calculated concept in the local ontology in the same way as the steps S211 and S212, and finally selecting the global ontology candidate concept corresponding to the maximum value from the vector for storing the similarity as the final result of the ontology mapping.
In the step S2, the process of performing feature recognition on the shape of the cable assembly fixing structure includes the following steps:
s221: by analyzing the adjacency relation of basic geometric elements of a boundary representation model (B-Rep) of a three-dimensional model of the structure and the concave-convex attributes of the basic geometric elements, establishing an attribute adjacency graph of the characteristics and the whole structure, and determining the geometric relation of the basic geometric elements, such as: forming multi-layer attribute shape characteristic models with different thickness and granularity and capable of describing topology, geometry and other information, and establishing a basic shape characteristic library;
B-Rep is a contour envelope wire frame of a structural three-dimensional model, the model is a unified structural three-dimensional model, different key functions are realized only through different explicit expression modes, and the extraction and the recording of boundary information of the structural three-dimensional model are realized;
s222: expressing and storing the three-dimensional model and the extended attribute adjacency graph of the shape characteristic in the form of an extended attribute adjacency matrix, searching and extracting the attribute adjacency matrix of the shape characteristic from the attribute adjacency matrix of the three-dimensional model by means of a multilevel attribute adjacency graph of the shape characteristic and a subgraph search algorithm of the characteristic, and comparing the searched submatrix with a matrix in a shape characteristic library through a subgraph matching algorithm to determine the type of the shape characteristic;
s223: determining the decomposition and repair strategies of the intersecting shape features by analyzing the feature traces, restoring the lost geometric elements and the adjacency relation by using geometric reasoning on the basis to further realize shape feature repair, and finally restoring the basic shape features forming the intersecting shape features.
The process of planning the three-dimensional path of the cable under multiple constraints comprises the following steps:
s231: starting point terminal P of cable through bi-RRT algorithm init And a terminal point terminal P goal Respectively establishing two path node trees T 1 And T 2 ，T 1 Random expansion node P new After, T 2 With P new For expanded target nodes, single step connection, if collision occurs with obstacle areaReturning to the tracked;
s232: exchange two trees, from T 2 Starting to randomly expand node P new ，T 1 To T 2 And (4) connecting in a single step, returning Connected if the two trees are Connected, as shown in FIG. 6 (b), otherwise, returning to Advanced to continue connecting in a single step, and repeating the operation until the two trees are Connected.
The single-step expansion needs to describe the distance between two nodes, and the cable posture is defined as:
p＝(x,y,z,α,β,γ)
p contains position coordinates and orientation coordinates, and the generalized distance function defined is shown as:
in the formula, w t Is a weight coefficient of the position coordinate, w r Is a weight coefficient of a directional coordinate, satisfies a condition w t +w r ＝1，S i And S j Is a component of the position coordinates of two adjacent points, R i And R j Is the directional coordinate component, | S i -S j | | is the Euler distance defined in a three-dimensional coordinate system, | R i -R j | defines the distance of two angles.
In the step S3, the guiding information comprises process animation, wiring harness positioning information display, wiring harness paths and quality detection data, wherein the process animation visualizes a cable assembly model, the wiring paths and an assembling sequence in a three-dimensional animation mode and is accurately matched with the positioning position of the wiring harness tooling plate; the wire harness positioning information is divided into characteristic identification information and process specification information, is obtained by index matching and is visualized based on positioning position association; the wire harness path is a path and indication information which guide an operator in real time through an arrow, a mark and highlight in the wire harness assembling process, and the quality detection data is quality problem data which are fed back to the operator for real-time identification and are used for controlling the assembling quality of the wire harness to meet the standard requirement.
The present embodiment also provides a complex cable assembly assembling human-computer integrated design and guidance control system, including:
the modeling module is used for automatically extracting ontology concepts and relations from empirical domain documents by adopting a machine learning method, combining cable component assembly engineering semantics, completing consistency check and conflict resolution of domain ontologies and data, complementing and enhancing the data around the characteristics of cable data, solving the problems of unbalanced data distribution and overfitting caused by data sparsity, combining logic protocols and state space search, performing consistency detection and conflict resolution on knowledge, and then performing multi-dimensional modeling by adopting an ontology modeling tool Prot g e based on domain context to construct a knowledge ontology model;
the human-computer integrated design module is used for combining the general design frameworks of Pahl and Beitz with the FBS model based on Gero to design an integrated design prototype; then, carrying out feature recognition on the shape of the cable assembly fixing structure; then planning a three-dimensional path of the cable under multiple constraints;
the guiding and error-preventing module is used for extracting corresponding characteristics of a cable assembly object by establishing a characteristic semantic library, identifying in the part geometric characteristic semantic library according to the quantity and the proportion parameters of main characteristics and secondary characteristics, acquiring a confidence sequence of parts of a part to be identified and the library part, indexing a domain knowledge body based on static and dynamic characteristic identification information, accurately registering the guiding information in a visible coordinate position of an operator by taking a matching coordinate system as a reference through a predefined guiding information position calculation method, completing a wiring harness operation guiding task, simultaneously performing real-time analysis and decision on error-preventing information such as a wiring harness turning radius, a diameter and the like, and performing quality control on a wiring harness assembly process;
the central processing module is used for sending instructions to other modules to complete related actions;
the modeling module, the man-machine integrated design module and the guiding and error-proofing module are all electrically connected with the central processing module.
Example two
In order to improve the efficiency of cable assembly process design and the consistency of harness positioning and meet the requirement of the parallel design of a cable assembly of complex electromechanical equipment, the embodiment forms a set of cable assembly human-computer integrated design and positioning guide method by researching three aspects of a cable assembly process knowledge modeling technology, a harness path planning and evaluating technology based on human-computer integration and a harness positioning guide technology based on virtual-real fusion, the overall technical scheme is shown as figure 1, and on the overall technical scheme, a knowledge management system based on a body and a human-computer integrated design prototype based on cognition are established, wherein the knowledge management system is used for modeling the knowledge in the field related to the cable assembly process design and comprises the requirement of cable assembly wiring, the function to be realized, the performance and the standard to be achieved and the like; the latter is used to regulate the direction of information flow during the design process, i.e., how to gradually complete the design of each part of the cable assembly based on the electrical wiring requirements of the cable. The human-computer integrated design prototype is the core of the whole human-computer integrated design architecture and is also a carrier for the specific realization of the cable assembly design body and the cognitive system. In addition, the augmented reality technology is the key for realizing man-machine integrated design, and through the natural interaction technology based on structural features and gesture recognition, the wiring harness flattening diagram, the positioning design, the quality evaluation result and the like can guide assembly operators on line in an intuitive and easily understood mode, so that the method has unique advantages for improving the efficiency and the accuracy of wiring harness assembly.
(1) Ontology-based cable assembly process knowledge modeling and integration method
The cable assembly design is based on a geometric design structure, an electrical design principle, cable wiring specifications and a cable connection list, and the electromagnetic compatibility, the physical property of the cable, the structural rationality and the maintainability of the product are comprehensively considered. These factors are influenced by the correlation, and as shown in fig. 2, the influence factors are designed for the assembly of the cable assembly.
The embodiment provides an information integration model for cable assembly, which not only comprises three-dimensional geometric information, BOM (Bill of Material) structure information and assembly positioning information of a traditional cable assembly model, but also defines wiring harness path information, can integrate physical laws (bending radius, deflection between positioning points and the like) and electromagnetic compatibility (gap and bundling) attributes in the assembly process, and can continuously evolve in the context of the assembly process.
As shown in fig. 3, which is a schematic diagram of a construction process of a knowledge ontology model, the invention adopts a machine learning method to automatically extract ontology concepts and relations from empirical domain documents such as cable path rules, hoop setting rules, design and wiring sequence rules, and the like; based on algorithms such as ontology mapping and logic specification, the consistency check and conflict resolution of the domain ontology and the data are realized by combining with the assembly engineering semantics of the cable assembly. Secondly, irrelevant attributes are filtered around the characteristics of cable data based on domain concept attributes, relations and the like, data are complemented and enhanced, and the problems of unbalanced data distribution and overfitting caused by sparse data are solved; and (4) combining the logic specification with state space search, and carrying out consistency detection and conflict resolution on knowledge. And finally, based on the field context scenario, performing multi-dimensional modeling by adopting an ontology modeling tool Prot g to construct a knowledge ontology model.
And the method for automatically extracting the domain concepts and the relations from the domain unstructured data and the domain structured data is adopted to realize the automatic construction of the domain ontology. The consistency and the integrity of multi-source data and information are improved by methods of consistency detection, conflict resolution and the like of the object data. By using knowledge fusion and enhancement theory and method, the problems of recognition, resolution and knowledge updating of conflicts among knowledge are solved, and the effectiveness and integrity of the acquired knowledge are ensured.
(2) Man-machine integrated design technology of cable assembly based on human factor engineering
(a) Human-computer integrated design architecture
The man-machine integrated design architecture mainly comprises four parts: the system comprises a man-machine integrated design prototype, a knowledge management system based on an ontology, an inference mechanism based on cognition and a man-machine interaction platform based on augmented reality. The invention provides a cable component assembly human-computer integrated design prototype which is suitable for a logic reasoning mode of a computer and accords with human knowledge expression characteristics by combining the general design framework of Pahl and Beitz with a FBS model based on Gero.
FIG. 4 is a schematic view of a human-machine integration design flow based on the FBS model. From the perspective of ontology and cognition, the integrated design prototype can be divided into two core contents, namely modeling and expression of domain knowledge and design reasoning and information flow. The human-machine integrated design includes six design states, which respectively represent six knowledge fields related to the cable assembly design, namely Requirement (R), function (F), configuration (C), structure (S), details (Details, D) and Behavior (Behavior, B). Among them, behaviors can be classified into Expected Behaviors (EB) and Actual Behaviors (AB).
As shown in fig. 5, the ontology integration process is a schematic diagram, and the ontology integration process includes two consecutive steps of ontology mapping and ontology fusion. The ontology mapping identifies local ontologies established or proposed by experts in a certain field and similar knowledge concepts in other fields, and the ontology fusion is a process of merging concepts with similar relations.
The first step is as follows: and calculating the similarity of the concept names, the similarity of the concept attributes, the similarity of the concept relationships and the similarity of the concept examples.
The similarity of the two concepts can be calculated by the Jaccard factor. The calculation formula of the concept name similarity is as follows:
wherein, C A Ci And C B Cj Sets of synonyms for concepts A and B, respectively, i and j are sets C, respectively A Ci And C B Cj The number of words. The operation of "u" refers to calculating the number of elements in a set formed by the same synonyms owned by the concepts a and B, and the operation of "u" refers to calculating the number of elements in a set formed by all the synonyms owned by the concepts a and B.
According to the definition, the similarity between the concept attributes can be decomposed into three aspects of functions, constraints and behaviors, after the similarity of the three aspects is obtained through the Jaccard factor, the average similarity of the concept attributes, the similarity between the concept relationships and the similarity between the concept instances can be calculated through the Jaccard factor, and the average similarity of the concept attributes, the similarity between the concept relationships and the similarity between the concept instances can be calculated respectively;
the second step is that: on the basis of four similarities of the name, the attribute, the relationship and the example calculated in the first step, the relationship between the two concepts is judged by calculating the overall similarity.
The third step: and storing the overall similarity in a vector, and calculating the similarity between other concepts in the global ontology and the concepts in the currently calculated local ontology in the same way as the first step and the second step. And finally, selecting the global ontology candidate concept corresponding to the maximum value from the vector storing the similarity as a final result of ontology mapping.
The ontology fusion process mainly comprises two steps, namely merging of concept names, attributes and instances and rebuilding of semantic relations. Concept merging refers to performing union operation on a concept name, attributes and instances of a concept if the concept is similar to a concept existing in a global ontology. Otherwise, a new independent concept is created in the global ontology, and all the contents of the global ontology in the local ontology are copied and the related semantic relation is added. In the relationship reconstruction, the semantic relationship of the concept is added in a new ontology library, wherein the semantic relationship comprises a hierarchical relationship, a process relationship and the like.
(b) Cable assembly fixing structure shape feature recognition method
Cable assemblies are typically secured to wall purlins, brackets, etc. structures, typically having complex intersecting features of a multi-feature composite. The feature structure is complex, the original geometric elements are seriously lost due to the intersection of the features, and the shape is difficult to identify due to the interference of a curved surface. The implementation steps adopted in the embodiment include:
the first step is as follows: establishing an attribute adjacency graph of the characteristics and the whole structure by analyzing the adjacency relation of basic geometric elements of a boundary representation model (B-Rep) of the three-dimensional model of the structure and concave-convex attributes of the basic geometric elements; determining the geometric relationship of the basic geometric elements such as: angle, size, relative positional relationship, etc. And finally, forming a multi-layer attribute shape characteristic model which can describe information such as topology, geometry and the like and has different thickness and granularity, and establishing a basic shape characteristic library.
The second step is that: expressing and storing the three-dimensional model and the extended attribute adjacency graph of the shape characteristic in the form of the extended attribute adjacency matrix, and searching and extracting the attribute adjacency matrix of the shape characteristic from the attribute adjacency matrix of the three-dimensional model by means of the multi-level attribute adjacency graph of the shape characteristic and a subgraph search algorithm of the characteristic; and comparing the searched submatrix with matrixes in the shape feature library through a subgraph matching algorithm to determine the shape feature type.
The third step: determining the decomposition and repair strategies of the intersecting shape features by analyzing the feature traces, restoring the lost geometric elements and the adjacency relation by using geometric reasoning on the basis to further realize shape feature repair, and finally restoring the basic shape features forming the intersecting shape features.
(c) Cable three-dimensional path planning method under multiple constraints
The method adopts a bi-RRT (bidirectional rapid spanning random tree) algorithm-based sectional connection cable path planning algorithm to automatically generate the initial feasible path of the cable, and performs multi-target path optimization on the obtained path key points. The bi-RRT algorithm is at the beginning terminal P of the cable init And a terminal point terminal P goal Respectively establishing two path node trees T 1 And T 2 ，T 1 Random expansion node P new After, T 2 With P new For the expanded target node, the step length is connected, and if the node collides with the barrier area, the node returns to the tracked state, as shown in FIG. 6 (a); exchange two trees, from T 2 Starting to randomly expand node P new ，T 1 To T 2 And (4) connecting in a single step, and returning to Connected if the two trees are Connected, as shown in FIG. 6 (b), otherwise, returning to Advanced to continue connecting in a single step, and repeating the operation until the two trees are Connected.
In the single-step extension in fig. 6 (a) and 6 (b), the distance between two nodes needs to be described, and the cable attitude is defined as:
p＝(x,y,z,α,β,γ)
p contains position coordinates and orientation coordinates, and the generalized distance function defined is shown as:
in the formula, w t Is the weight coefficient, w, of the position coordinate r Is a weight coefficient of a directional coordinate, satisfies a condition w t +w r ＝1，S i And S j Is a component of the position coordinates of two adjacent points, R i And R j Is the directional coordinate component, | S i -S j | | is the Euler distance defined in a three-dimensional coordinate system, | R i -R j | defines the distance of two angles.
The method comprises the steps of obtaining a space wiring initial path based on a bi-RRT algorithm, performing three-dimensional visualization on the wiring path by adopting an elastic thin rod mechanical model method of a cable, and evaluating and optimizing the initial path by adopting a wire harness path evaluation system and combining identified fixed structure characteristics, electromagnetic compatibility requirements, physical properties such as minimum bending radius, stretching and bending characteristics, gravity received during wiring and the like.
(3) Wire harness positioning guide and error prevention technology based on enhanced projection
Fig. 7 is a schematic diagram of a characteristic identification process of the cable assembly. And establishing a feature semantic library of cable components, cable branches, installation tools and the like. The method comprises the steps of extracting corresponding features of a cable assembly object by using detection algorithms such as Hough and the like, identifying the extracted features in a part geometric feature semantic library by using a radial basis function neural network identification algorithm according to the quantity and proportion parameters of main features and secondary features, acquiring confidence sequences of parts to be identified and library parts, and realizing rapid and accurate identification of cable assemblies (such as terminals, wire bundles, hoops and the like), turning radii of wire harnesses, diameters and the like.
Based on the static and dynamic feature recognition information, indexing a domain knowledge body comprising information such as an object to be assembled, an operation posture, a wiring harness path, an installation tool, quality requirements and the like, accurately registering virtual guide information such as characters, models or images and the like at a visible coordinate position of an operator by using a matching coordinate system as a reference through a predefined guide information position calculation method, and completing a wiring harness operation guide task; meanwhile, the error-proof information such as the turning radius, the diameter and the like of the wire harness is analyzed and decided in real time, and the quality control of the wire harness assembling process is realized.
The specific process of real-time analysis and decision of error-proof information such as turning radius and diameter of the beam is as follows: corresponding characteristics of the cable assembly object are extracted by using a detection algorithm such as Hough, the extracted characteristics are identified in a part geometric characteristic semantic library by using a radial basis function neural network identification algorithm according to the quantity and the proportion parameters of the main characteristics and the secondary characteristics, a confidence sequence of the part to be identified and the library part is obtained, and the cable assembly (such as a terminal, a wire bundle, a hoop and the like), the turning radius of a wire harness, the diameter and the like are quickly and accurately identified. After the identification is completed, the corresponding characteristic information is associated with the augmented reality system, and real-time decision and adjustment of the trend, the layout and the like of the wiring harness can be realized by utilizing the real-time modeling and rendering functions.
The wire harness assembly guiding information comprises process animation, wire harness positioning information display, wire harness paths and quality detection data, the wire harness assembly guiding information is projected onto the wire harness tooling plate through laser, and an operator can carry out man-machine interaction through gestures. The process animation visualizes a cable assembly model, a wiring path and an assembling sequence in a three-dimensional animation form and is accurately matched with the positioning position of the wire harness tooling plate; the wire harness positioning information is divided into characteristic identification information and process specification information, is obtained by index matching and is visualized based on positioning position association; the wire harness path guidance is that an operator guides an operation method, a positioning hoop position and the like which the operator should adopt in real time through methods such as an arrow, an identification, highlight and the like in the wire harness assembly process; the quality error-proofing control is to feed back the quality problems of overlarge bending radius, neglected loading, positioning deviation and the like identified in real time to an operator, and control the assembly quality of the wire harness to meet the standard requirement.
It should be noted that B-Rep refers to an outline enveloping wireframe of a structural three-dimensional model, the model is a unified structural three-dimensional model, and different key functions are realized only through different explicit expression modes, so as to extract and record boundary information of the structural three-dimensional model. The subgraph in the subgraph search algorithm is one of basic concepts of graph theory, and refers to a graph in which a node set and an edge set are respectively a subset of the node set and a subset of the edge set of a certain graph. The subgraph search algorithm refers to a method and a calculation process for finding a complete subgraph in a complex network.
In summary, in the complex cable assembly method and system in the two embodiments, for cable assembly process knowledge, a multi-domain knowledge model based on an ontology is provided, and an ontology concept and a relationship are automatically extracted from process information and data by using a machine learning method; based on algorithms such as ontology mapping, logic specification and the like, the consistency check and conflict resolution of the domain ontology and the data are realized by combining with the cable assembly engineering semantics, and then based on domain concept attributes, relations and the like, irrelevant attributes are filtered, and the data are complemented and enhanced; the logic protocol and state space search are combined, and the knowledge is subjected to consistency detection and conflict resolution; aiming at automatic cable routing planning, a man-machine integrated design prototype for cable assembly is provided, the reasonability of an automatic routing scheme is improved by adopting a method of combining automatic computer search and knowledge decision, and a bi-RRT search method is adopted, and the cable path with multiple constraint conditions is generated by utilizing the automatically identified cable fixed structure characteristics, so that the engineering reasonability of the automatic cable path routing planning scheme is met; the virtual-real superposition enhanced visualization environment in the multi-mode interaction mode is established, namely, the active enhancement superposition of guide information such as pictures, characters, animations and the like in front of an operator in the maintenance process is completed through various interaction modes such as gestures, voice, automatic dismounting process identification and the like and by combining a high-precision virtual-real model registration technology, and the real-time update and accurate positioning of the guide information in the operation process are realized.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description of the specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A method of assembling a complex cable assembly, comprising the steps of:
s1: cable assembly process knowledge modeling
Automatically extracting ontology concepts and relations from experience domain documents by adopting a machine learning method, and carrying out consistency check and conflict resolution on domain ontologies and data by combining cable component assembly engineering semantics; complementing and enhancing the data around the characteristics of the cable data; the logic protocol is combined with state space search, and consistency detection and conflict resolution are carried out on knowledge; then, based on the field context situation, adopting an ontology modeling tool to carry out multi-dimensional modeling to construct a knowledge ontology model;
s2: man-machine integrated design of cable assembly
Combining a general design framework with an FBS model, and designing an integrated design prototype; then, carrying out feature recognition on the shape of the cable assembly fixing structure; then planning the three-dimensional path of the cable under multiple constraints;
s3: harness positioning guide and error proofing
Establishing a feature semantic library of cable assemblies, cable branches and installation tools, extracting corresponding features of cable assembly objects, identifying in a part geometric feature semantic library according to the quantity and proportion parameters of the main features and the secondary features, and acquiring confidence sequences of parts to be identified and library parts; and then, indexing a domain knowledge body based on the static and dynamic characteristic identification information, accurately registering the guide information at the visible coordinate position of an operator by using a matching coordinate system as a reference through a predefined guide information position calculation method, completing a wire harness operation guide task, and simultaneously carrying out real-time analysis and decision on the error-proof information and carrying out quality control on the wire harness assembly process.
2. The method of assembling a complex cable assembly of claim 1, wherein: in the step S2, from the perspective of ontology and cognition, the integrated design prototype includes two core contents, which are modeling and expression of domain knowledge on one hand and design inference and information flow on the other hand.
3. The method of assembling a complex cable assembly of claim 1, wherein: in the step S2, the human-computer integrated design includes six design states, which respectively represent six knowledge fields related to the cable assembly design, namely, requirements, functions, configurations, structures, details, and behaviors, wherein the behaviors are divided into expected behaviors and actual behaviors.
4. The method of assembling a complex cable assembly of claim 2, wherein: the integration process of the ontology comprises ontology mapping and ontology fusion, wherein the ontology mapping is to identify a local ontology established or proposed by experts in a certain field and similar knowledge concepts in other fields, and the ontology fusion is to merge concepts with similar relations.
5. The method of assembling a complex cable assembly of claim 4, wherein the integrating process of the body comprises the steps of:
s211: calculating the similarity of concept names, the similarity of concept attributes, the similarity of concept relationships and the similarity of concept examples, wherein the similarity between the two concepts is calculated through Jaccard factors, and the calculation formula of the similarity of the concept names is as follows:
wherein, C A Ci And C B Cj Sets of synonyms for concepts A and B, respectively, i and j are sets C, respectively A Ci And C B Cj The 'U' operation refers to the calculation of the number of elements of a set formed by the same synonyms owned by the concepts A and B, and the 'U' operation refers to the calculation of the number of elements of a set formed by all the synonyms owned by the concepts A and B;
the similarity between the concept attributes is divided into three aspects of function, constraint and behavior, after the similarity of the three aspects is respectively obtained through the Jaccard factor, the average similarity of the concept attributes, the similarity between the concept relationships and the similarity between the concept instances are respectively calculated by utilizing the Jaccard factor;
s212: on the basis of the four similarities of the name, the attribute, the relationship and the instance calculated in step S211, the relationship between the two concepts is judged by calculating the overall similarity;
s213: and storing the overall similarity in a vector, calculating the similarity between other concepts in the global ontology and the currently calculated concepts in the local ontology in the same way as the steps S211 and S212, and finally selecting the global ontology candidate concept corresponding to the maximum value from the vectors storing the similarity as the final result of the ontology mapping.
6. The method for assembling a complex cable assembly according to claim 1, wherein in the step S2, the process of identifying the characteristic of the shape of the cable assembly fixing structure comprises the following steps:
s221: expressing the adjacency relation of basic geometric elements of the model and the concave-convex attributes of the basic geometric elements by analyzing the boundary of the structural three-dimensional model, establishing an attribute adjacency graph of the characteristics and the whole structure, determining the geometric relation of the basic geometric elements, forming a multi-layer attribute shape characteristic model with different thicknesses and granularities, and establishing a basic shape characteristic library;
s222: expressing and storing the three-dimensional model and the extended attribute adjacency graph of the shape characteristic in the form of an extended attribute adjacency matrix, searching and extracting the attribute adjacency matrix of the shape characteristic from the attribute adjacency matrix of the three-dimensional model, and comparing the searched sub-matrix with a matrix in a shape characteristic library to determine the type of the shape characteristic;
s223: determining the decomposition and repair strategies of the intersecting shape features by analyzing the feature traces, restoring the lost geometric elements and the adjacency relation by using geometric reasoning on the basis to further realize shape feature repair, and finally restoring the basic shape features forming the intersecting shape features.
7. The method of claim 1, wherein the process of performing a three-dimensional path planning of the cable under multiple constraints comprises the steps of:
s231: at the starting point terminal P of the cable init And a terminal P goal Respectively establishing two path node trees T 1 And T 2 ，T 1 Random expansion node P new After, T 2 With P new For an expanded target node, single-step-length connection is carried out, and if the node collides with an obstacle area, the node returns to the tripped;
s232: exchange two trees, from T 2 Starting to randomly expand node P new ，T 1 To T 2 And (4) single-step long connection, if the two trees are Connected, connecting, otherwise, returning to Advanced to continue the single-step long connection, and repeating the operation until the two trees are Connected.
8. The method of assembling a complex cable assembly of claim 7, wherein: the single-step expansion needs to describe the distance between two nodes, and the cable posture is defined as:
p＝(x,y,z,α,β,γ)
p contains position and orientation coordinates, and the defined generalized distance function is given by:
in the formula, w t Is the weight coefficient, w, of the position coordinate r Is a weight coefficient of a directional coordinate, satisfies a condition w t +w r ＝1，S i And S j Is a component of the position coordinates of two adjacent points, R i And R j Is the directional coordinate component, | S i -S j | | is the Euler distance defined in a three-dimensional coordinate system, | R i -R j | defines the distance of two angles.
9. The method of assembling a complex cable assembly of claim 1, wherein: in the step S3, the virtual guide information comprises process animation, wiring harness positioning information display, wiring harness paths and quality detection data, wherein the process animation visualizes a cable assembly model, the wiring paths and an assembling sequence in a three-dimensional animation mode and is accurately matched with the positioning position of the wiring harness tooling plate; the wire harness positioning information is divided into characteristic identification information and process specification information, is obtained by index matching and is visualized based on positioning position association; the wire harness path is a path and indication information for guiding an operator in real time through arrows, marks and highlights in the wire harness assembly process; the quality detection data is quality problem data which is fed back to an operator for real-time identification and is used for controlling the assembly quality of the wire harness to meet the standard requirement.
10. The man-machine integrated design and guidance control system for assembling a complex cable assembly, wherein the man-machine integrated design and guidance control method according to any one of claims 1 to 9 is used for assembling the complex cable, and comprises the following steps:
the modeling module is used for automatically extracting ontology concepts and relations from experience domain documents by adopting a machine learning method, combining cable component assembly engineering semantics, completing consistency check and conflict resolution of domain ontologies and data, complementing and enhancing the data around the characteristics of cable data, solving the problems of unbalanced data distribution and overfitting caused by data sparsity, combining logic protocols and state space search, performing consistency detection and conflict resolution on knowledge, and then performing multi-dimensional modeling by adopting an ontology modeling tool based on domain context and scene to construct a knowledge ontology model;
the human-computer integrated design module is used for combining the general design framework with the FBS model and designing an integrated design prototype; then, carrying out feature recognition on the shape of the cable assembly fixing structure; then planning a three-dimensional path of the cable under multiple constraints;
the guiding and error-preventing module is used for extracting corresponding characteristics of a cable assembly object by establishing a characteristic semantic library, identifying in the part geometric characteristic semantic library according to the quantity and the proportion parameters of main characteristics and secondary characteristics, acquiring a confidence sequence of parts of a part to be identified and the library part, indexing a domain knowledge body based on static and dynamic characteristic identification information, accurately registering the guiding information at a visible coordinate position of an operator by taking a matching coordinate system as a reference through a predefined guiding information position calculation method, completing a wiring harness operation guiding task, simultaneously carrying out real-time analysis and decision on error-preventing information, and carrying out quality control on a wiring harness assembly process;
the central processing module is used for sending instructions to other modules to complete related actions;
the modeling module, the man-machine integrated design module and the guiding and error-proofing module are all electrically connected with the central processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911037668.2A CN110866332B (en) | 2019-10-29 | 2019-10-29 | Complex cable assembly assembling method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911037668.2A CN110866332B (en) | 2019-10-29 | 2019-10-29 | Complex cable assembly assembling method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110866332A CN110866332A (en) | 2020-03-06 |
| CN110866332B true CN110866332B (en) | 2022-12-16 |
Family
ID=69654152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911037668.2A Active CN110866332B (en) | 2019-10-29 | 2019-10-29 | Complex cable assembly assembling method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866332B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111983355B (en) * | 2020-08-21 | 2023-05-26 | 一汽-大众汽车有限公司 | Method for designing low-voltage wire harness product of vehicle |
| CN112215931A (en) * | 2020-10-09 | 2021-01-12 | 南昌航空大学 | Method for generating animation in three-dimensional cable laying process |
| CN112734945B (en) * | 2021-03-30 | 2021-08-17 | 上海交大智邦科技有限公司 | Assembly guiding method, system and application based on augmented reality |
| CN114323000B (en) * | 2021-12-17 | 2023-06-09 | 中国电子科技集团公司第三十八研究所 | Cable AR guide assembly system and method |
| CN114219806B (en) * | 2022-02-22 | 2022-04-22 | 成都数联云算科技有限公司 | Automobile radar detection method, device, equipment, medium and product |
| CN114925495A (en) * | 2022-04-18 | 2022-08-19 | 中国电子科技集团公司第二十九研究所 | Flexible cable assembly design method, device, equipment and medium |
| CN115964959B (en) * | 2023-03-13 | 2023-05-30 | 北京理工大学 | Domain centralized electronic and electric architecture modeling and multi-objective optimization method and system |
| CN116451509B (en) * | 2023-06-15 | 2023-08-22 | 天津有容蒂康通讯技术有限公司 | Method and system for assembling complex cable assembly |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103995858B (en) * | 2014-05-15 | 2017-06-30 | 北京航空航天大学 | The individualized knowledge active push method that task based access control is decomposed |
| CN104182454B (en) * | 2014-07-04 | 2018-03-27 | 重庆科技学院 | The integrated model of multi-source heterogeneous data semantic based on domain body structure and method |
| CN106570566B (en) * | 2016-10-28 | 2019-07-05 | 安徽农业大学 | A kind of tea-plant pests representation of knowledge and sharing method based on ontology |
-
2019
- 2019-10-29 CN CN201911037668.2A patent/CN110866332B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110866332A (en) | 2020-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866332B (en) | Complex cable assembly assembling method and system | |
| US11113431B2 (en) | MBD-based three-dimensional process designing method and platform for typical automobile machined part | |
| Kumar | State of the art-intense review on artificial intelligence systems application in process planning and manufacturing | |
| Ghandi et al. | Review and taxonomies of assembly and disassembly path planning problems and approaches | |
| CN103093023B (en) | Computer aided design model method and system used for managing objects | |
| US20070067146A1 (en) | System and method of interactively optimizing shipping density for a container | |
| Ng et al. | Designing cable harness assemblies in virtual environments | |
| US20170193133A1 (en) | Method and device for automatically routing multi-branch cable | |
| Yin et al. | Virtual prototyping of mold design: geometric mouldability analysis for near-net-shape manufactured parts by feature recognition and geometric reasoning | |
| US7082590B2 (en) | Three-dimensional wire harness assembly models from three-dimensional zone models | |
| Liu et al. | A semantic feature model in concurrent engineering | |
| Bakaev et al. | Application of evolutionary algorithms in interaction design: From requirements and ontology to optimized web interface | |
| Ning et al. | Part machining feature recognition based on a deep learning method | |
| Peng et al. | BOM-based design knowledge representation and reasoning for collaborative product development | |
| Xú et al. | STEP-NC based reverse engineering of in-process model of NC simulation | |
| Xu et al. | Automatic machining feature recognition based on MBD and process semantics | |
| Peddada et al. | Toward holistic design of spatial packaging of interconnected systems with physical interactions (spi2) | |
| US11373022B2 (en) | Designing a structural product | |
| Sheng et al. | A rapid virtual assembly approach for 3D models of production line equipment based on the smart recognition of assembly features | |
| Xiao et al. | Knowledge graph-based manufacturing process planning: A state-of-the-art review | |
| Ng et al. | The design and planning of cable harness assemblies | |
| Yao et al. | A pragmatic system to support interactive assembly planning and training in an immersive virtual environment (I-VAPTS) | |
| Lu et al. | 3D reconstruction of detailed buildings from architectural drawings | |
| Yan et al. | A two-module automated scanning inspection planning methodology for complex surfaces on coordinate measuring machine | |
| Iacob et al. | Generation of disassembly directions based on component mobility |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |