Conformance Checking Research Articles

Training and using neural networks to represent heuristic design knowledge

The detailed stage of structural design has benefited considerably from computer automation of the numerically intensive tasks of structural analysis, optimization and conformance checking using the procedural programming approach. Such an approach, however, does not allow for the representation and utilization of heuristic knowledge implicit in previous design solutions, which is often difficult or impossible to represent algorithmically. This paper describes how artificial neural networks can be trained to learn heuristic knowledge from previous design solutions and how this knowledge can then be applied to produce a solution to a similar design problem.

Addressing Current Issues in Structural Design Software

Software for detailed structural design has advanced considerably in the last 20 years, with progress being primarily related to the numerically intensive tasks of structural analysis, design optimization, and conformance checking. Despite these advances, there remain many areas where improvements can still be realized. Current challenges facing researchers in this area include the additional representation of nonnumerical design knowledge, managing complexity of software development and maintenance, and the production of systems that incorporate reusability. A prototype system for detailed building design is presented that addresses these issues through the generic and object-oriented approach taken in its design and development. To this end, the classes of objects and their relationships involved in structural design are identified, the representation and utilization of different types of structural design knowledge are discussed, and it is shown how the system incorporates reuse as it is easily extended to apply to different building types. A building design example is given to illustrate the system's capabilities.

Role of In-Process Quality Control in Thick Film Hybrids Manufacturing

Traditionally quality control means the checking of conformance of a product's performance with the specifications for which the product is designed. This control method measures the quality of the product and in no way can increase or change the quality. These quality methods are only the certification procedures to state the quality at the time of inspection. Thick film hybrids manufacturing is a sequencial manufacturing activity where the performance of any step is directly dependent on its predecessor activity. If anything wrong has happened in the earlier manufacturing stage, nothing can be done to improve or rectify it. Therefore, the role of in-process quality control in hybrids manufacturing is important and critical for achieving the quality and reliability product. This article tries to highlight the relevance of in-process quality check.

An Object-Logic model for the representation and processing of design standards

There are two distinct categories of knowledge in a design standard: (1) knowledge of the organization of design objects and (2) knowledge of the methods used in reasoning about the design objects. The object-oriented paradigm lends itself naturally to representing the organizational aspect of the design standard. The logic programming paradigm, on the other hand, is well suited to implementing the reasoning mechanisms for design and conformance checking. The object-oriented and logic programming paradigms are combined to provide a unified Object-Logic model for the representation of design codes and the processing of design standards. By storing the design provisions in a knowledge base, the model is capable of performing conformance checking and component design. To evaluate the feasibility and practicality of this model, a prototype system, HyperLRFD++, has been implemented for parts of the American Institute of Steel Construction (AISC) Load and Resistance Factor Design (LRFD) specification and tested on sample problems.

Evaluation of MT systems: A programmatic view

In this paper, I have tried to make several points. First, I have argued that the Human Translator Metaphor does not provide the most fruitful approach to evaluation of MT systems or perhaps even to the design of MT systems in general — one should rather go for specialized systems, whose properties are negotiated between designers and users. Second, I have tried to emphasise the dangers which the gear box evaluation syndrome raises in evaluating MT systems. Third, I have suggested an alternative basis for evaluation: rather than MT systems being seen as simply devices, they should be seen as pairs 〈Specs,Device〉, where the Specs constitute the fixed point for evaluation, and evaluation is seen in terms of both conformity checking between Device and Specs, and usefulness checking via comparison of user requirements and Specs. Though this raises some questions, I have tried to answer the most pressing worries one might have with the proposal, however, it is clear that this approach requires some effort to be put into specification methods and languages for specialized MT systems.

The hierarchical development of a generic type mechanism for functional languages

Adoption of a scientific approach to language design, featuring the identification of language design with programming, leads to the advocacy of an explicitly hierarchical approach to language development. Choice of the lambda-calculus as basis of the linguistic hierarchy is determined when “elegance” is the predominant criterion for assessing the quality of designs. The consequence is that the hierarchy is primarily comprised of a family of untyped functional languages. We embark upon the hierarchical development of a quality data type system for such languages, including a powerful mechanism for generic data abstraction, in five stages. We show that the expressiveness of the system, in comparison with the widespread “polymorphic” typing approach, is well worth the price of the necessarily dynamic checking for type conformance.

Software concept for checking engineering designs for conformance with codes and standards

As we progress toward formalizing models for the knowledge used in the design process, we must also consider the structure of systems that can utilize and operate on the knowledge models. Engineering systems of the future will be comprised of many separate but integrated components. In the systems of the 1970s tightly coupled system integration was achieved through hand coding and through the introduction of data base management. In the next generation of systems it will not be possible to express easily the interaction between systems in the form of handwritten codes. A rule-based approach may be a better way to achieve loose coupling of complex systems. A prototype system for checking designed components for conformance with applicable standards is described in this paper. The integrated system consists of a code conformance checking package, a structural analysis package, an engineering data base management system, a production rule processing system, and an appropriate user interface. The system structure and the representation of the knowledge is emphasized.

Automated Processing of Design Standards

This paper describes the development of software for automated processing of design standards. The language‐compiler system developed is based on the decision table representation, which has been shown previously to be a systematic organizational model for processing design standards. The system provides a complete environment in which the entire process from creating a standard library to performing the design conformance checking is automated. Special features include an effective means of maintaining libraries of standards and an interactive environment for the input and editing of decision tables representing the provisions of a standard. The system can accommodate future changes in design specification, is flexible enough to include different governing codes, and can readily interface with current computer‐aided design programs. Consistency is automatically maintained between the provisions processed and design checking in the computer‐aided design program. The prototype software developed represents a practical and feasible approach to the automation of the design checking process.

Generic Design Standards Processing in an Expert System Environment

Checking design conformance with governing standards, codes, specifications, regulations, and manuals is a mandatory step in designing engineering systems. Automating this design checking process, therefore, is an important goal that has far‐reaching design productivity implications. Current conformance checking automation generally involves the use of application programs into which the standards, or an interpretation of their intent, have been directly coded. This approach is extremely inflexible and often error‐prone. This paper investigates the feasibility of casting design standards in an alternative form, one suitable for flexible processing in a knowledge‐based expert system environment. The proposed form not only enables a designer to readily check the conformance of designs, but it also allows him to evaluate the effects of changing design variables as well as evaluate the impact of down‐stream activities and events, such as change orders, on the initial design. Two prototype standards processing...

Knowledge based standards processing

This paper presents the representational model of a standard, background research in standards processing, and a current research project which uses a knowledge-based system approach to standards processing. The representational model of a standard, based on decision tables, was originally developed in 1966 and has been continually modified and improved since that time. Concurrent with the development of this model was the development of its uses in computer-aided standards processing, such as automated conformance checking and design. As an extension of this standards processing research, a knowledge-based standards processor is being built that will act as an interface between CAD programs and design standards. The knowledge-based standards processor uses a blackboard architecture similar to that of Hearsay-II, a speech understanding program. The processor's knowledge is divided up into about ten knowledge sources, most of which are standard-independent. The knowledge sources are responsible for the development of a design script that can be used to perform the CAD program's member design tasks, while satisfying the governing design standard.

Functional conformance testing of graphics software using a configurable reference system

This paper introduces a scheme for conformance checking of GKS implementations with the given GKS standard specification[1] based on functional black box testing. Specific testing problems caused by the nature of graphics systems and a solution are presented. Thereby emphasis is laid on a software generation technique which allows to configure reference implementations from a suitable specification of GKS. The reference implementation is used to produce correct reference data the contents and formats of which are adjusted for the particular candidate implementation.