Debasish Dutta

An approach to compute similarity between engineering changes

Detailed evaluation of a proposed Engineering Change (EC) or its effects is a time-consuming process requiring considerable user expertise. Therefore, enterprises plan detailed evaluation of only those EC effects that might have a significant impact. Since similar ECs are likely to have similar effects and impacts, past EC knowledge can be utilized for determining whether the proposed EC effect has significant impact. Utilizing past ECs to predict the impact of proposed EC effect requires an approach for computing similarity between ECs. This paper presents an approach to compute similarity between ECs that are defined by a set of disparate attributes. Since the available information is probabilistic, the fundamental measures of information are utilized for defining measures to compute similarity between two attribute values or ECs. The semantics associated with attribute values are identified and utilized to compute similarity between attribute values. The similarities between attribute values are aggregated to compute the similarity between ECs in the context of overall goal. A case-study is presented to demonstrate the applicability of the proposed approach.

Similarity Computation for Knowledge-Based Sustainability Evaluation of Engineering Changes

Systematic sustainability assessment of a proposed Engineering Change (EC) is, typically, a time-consuming process due to the complexity of typical products and the lifecycle-wide impact of a change. One approach to enable faster evaluation is the use of the knowledge from similar past ECs. In this paper, we present an approach based on research in psychology to calculate the similarity of Engineering Changes such that the retrieved ECs can be used to predict only the carbon footprint of the proposed EC. Product knowledge is structured, and there is no acceptable standard for representation. Therefore, we propose a measure that focuses on identifying and aligning corresponding components of the query and target representations. We apply the measure to a case of 14 Engineering Changes (91 matching problems) and compare the matches for relevance to evaluation of carbon footprint. The precision and recall are evaluated by comparing against carbon footprints obtained using commercial LCA tool.Copyright

Requirements for the development of a decision-support solution for sustainability target cascading

Corporations view sustainable manufacturing as a mandate for competitiveness to put them at an advantage with consumers all over the world. This paper focuses on the need for a decision support solution that transforms the current time-consuming and reactive (post-design) sustainability assessment into a proactive approach available in the early phases of product design. Such a solution should focus primarily on the key area of target cascading, evaluation, and management, which does not exist for sustainability metrics, such as carbon footprint. It is important that the handling of sustainability be compatible with handling of these traditional attributes. The emphasis on traditional attributes, such as weight, is necessary, because it is one of the most important and cost-effective ways to improve fuel efficiency and reduce greenhouse gases. In this paper, we discuss several challenges in addressing this problem and propose the major components of an approach to enable target cascading of sustainability attributes. We describe the the multiple requirements on the development of the approach and raise important research questions that need to be addressed.

An Information-Based Approach to Compute Similarity Between Engineering Changes

Utilizing past Engineering Change (EC) knowledge to predict the impact of a proposed EC effect requires an approach for computing similarity between ECs. This paper presents an approach for computing the similarity between ECs each defined by a set of disparate attributes. Since the available information is probabilistic, measures of information are used for defining measures to compute similarity between two attribute values or ECs. The semantics associated with attribute values are used to compute similarity between them. The similarities between attribute values are aggregated to compute the similarity between ECs in the context of overall goal. An example EC knowledge-base is used for evaluating our approach against a statistical approach and two state-of-the-art approaches, namely, metric space and probability-based. The evaluation is done from two perspectives: precision in retrieving similar ECs and success in predicting the impact. The results show that there is a statistically significant improvement in precision and success rate using our approach as compared to those using other approaches. In addition, based on the results, it can be inferred with 90% confidence that for a large number of changes (N >; 100) the success in predicting impact using our approach shall be greater than that obtained using the two state-of-the-art approaches.

Feedback Matching Framework for Semantic Interoperability of Product Data

There is a need to promote drastically increased levels of interoperability of product data across a broad spectrum of stakeholders, while ensuring that the semantics of product knowledge are preserved, and when necessary, translated. In order to achieve this, multiple methods have been proposed to determine semantic maps across concepts from different representations. Previous research has focused on developing different individual matching methods, i.e., ones that compute mapping based on a single matching measure. These efforts assume that some weighted combination can be used to obtain the overall maps. We analyze the problem of combination of multiple individual methods to determine requirements specific to product development and propose a solution approach called FEedback Matching Framework with Implicit Training (FEMFIT). FEMFIT provides the ability to combine the different matching approaches using ranking Support Vector Machine (ranking SVM). The method accounts for nonlinear relations between the individual matchers. It overcomes the need to explicitly train the algorithm before it is used, and further reduces the decision-making load on the domain expert by implicitly capturing the experts decisions without requiring him to input real numbers on similarity. We apply FEMFIT to a subset of product constraints across a commercial system and the ISO standard. We observe that FEMIT demonstrates better accuracy (average correctness of the results) and stability (deviation from the average) in comparison with other existing combination methods commonly assumed to be valid in this domain.

A Graph Search Approach to Automate Product Concept Translation

Product data translation is essential for the seamless integration of various product-centric activities. Yet, the process to build translators among different software has been left mostly to individual expertise rather than a formal procedure. In this paper, we propose a framework to automatically determine translation rules to enable translation of instances from one system to another. We use a graph search method to obtain the overall translation rule as a combination of multiple basic functions. We apply this method to a subset of non-geometric product knowledge, such as date of creation, color and name of feature used in two commercial systems. We detect the rules using a manually created training data set and evaluate their correctness manually.Copyright

A Search-Based Approach for Prediction of Flexible Hose Shapes

Flexible hoses and cables are vital components used in a variety of artifacts, including complex products such as automobiles. When designing a vehicle, it is important to know the shape that a flexible component will take between its two endpoints. Incorrect information regarding hose shapes can lead to shortened component lifespans and even costly recalls. Several efforts have attempted to predict the shape of flexible components. In the past, Computer Aided Engineering (CAE) simulations using mathematical models have been used to predict hose and cable shapes, providing fairly accurate results. However, CAE simulations of hoses and cables are extremely time-consuming, often taking several hours to weeks for completion. In this paper, we propose an approach to dramatically reduce this time burden. We propose the idea of “looking up” a solution. Rather than mathematically calculating a hose shape, our approach called Search-based Real-time Prediction of CAE Solutions (SRPCS) relies on a large database of intelligently represented problems and solutions. The query problem is then intelligently decomposed into problems with known solutions and the individual solutions are then recombined to obtain the overall shape, i.e., solution to the problem. We generated real hose shapes in a test rig and stored in a database. Analysis of the results shows that the SRPCS provides an accurate and rapid solution to obtain the shape of flexible components.Copyright