Discovering a Hierarchical Design Process Model Using Text Mining

Author(s):  
Lijun Lan ◽  
Ying Liu ◽  
Wen Feng Lu

The increasing design documents created in the design process provide a useful source of process-oriented design information. Hence, the need for automated design information extraction using advanced text mining techniques is increasing. However, most of the existing text mining approaches have problems in mining design information in depth, which results in low efficiency in applying the discovered information to improve the design project. With the aim of extracting process-oriented design information from design documents in depth, this paper proposes a layered text mining approach that produces a hierarchical process model which captures the process behavior at the different level of details. Our approach consists of several interrelated algorithms, namely, a content-based document clustering algorithm, a hybrid named entity recognition (NER) algorithm and a frequency-based entity relationship detection method, which have been integrated into a system architecture for extracting design information from coarse-grained views to fine-grained specifications. To evaluate the performance of the proposed algorithms, experiments were conducted on an email archive that was collected from a real-life design project. The results showed an increase in the detection accuracy for the process-oriented information detection.

2018 ◽  
Vol 140 (4) ◽  
Author(s):  
Lijun Lan ◽  
Ying Liu ◽  
Wen Feng Lu

Design documents and design project footprints accumulated by corporate information technology systems have increasingly become valuable sources of evidence for design information and knowledge management. Identification and extraction of such embedded information and knowledge into a clear and usable format will greatly accelerate continuous learning from past design efforts for competitive product innovation and efficient design process management in future design projects. Most of the existing design information extraction systems focus on either organizing design documents for efficient retrieval or extracting relevant product information for product optimization. Different from traditional systems, this paper proposes a methodology of learning and extracting useful knowledge using past design project documents from design process perspective based on process mining techniques. Particularly different from conventional techniques that deal with timestamps or event logs only, a new process mining approach that is able to directly process textual data is proposed at the first stage of the proposed methodology. The outcome is a hierarchical process model that reveals the actual design process hidden behind a large amount of design documents and enables the connection of various design information from different perspectives. At the second stage, the discovered process model is analyzed to extract multifaceted knowledge patterns by applying a number of statistical analysis methods. The outcomes range from task dependency study from workflow analysis, identification of irregular task execution from performance analysis, cooperation pattern discovery from social net analysis to evaluation of personal contribution based on role analysis. Relying on the knowledge patterns extracted, lessons and best practices can be uncovered which offer great support to decision makers in managing any future design initiatives. The proposed methodology was tested using an email dataset from a university-hosted multiyear multidisciplinary design project.


2009 ◽  
Vol 131 (2) ◽  
Author(s):  
Changmuk Kang ◽  
Yoo S. Hong

The design process is difficult to accelerate due to its iterative nature, which increases project cost and delays completion time of a design project. Many previous studies tried to find the optimal structure and sequence of a design process minimizing iteration. In a multiproject environment, however, waiting time caused by resource shortage is a more critical reason for a lengthy project than iteration time. In this paper, we propose a novel sequencing method that reduces waiting time in a multiproject environment by dynamically changing the sequence of design tasks, according to availability of resources. It is called a dynamic sequencing method, as opposed to the traditional static sequencing method by which every design project follows a predefined optimal sequence. In order to evaluate the effect of this method, we developed a design-process model for simulating iteration and waiting in a multiproject environment. The simulation results show that dynamic sequencing is significantly better than traditional static sequencing with respect to average duration of projects. It is noted that more significant improvements can be obtained for the bottlenecked and unbalanced processes, both of which conditions would otherwise have negative effects on process performance.


2020 ◽  
Vol 15 ◽  
Author(s):  
Jin Li ◽  
Xingsheng Jiang ◽  
Jingye Li ◽  
Yadong Zhao ◽  
Xuexing Li

Background: In the whole design process of modular fuel tank, there are some unreasonable phenomena. As a result, there are some defects in the design of modular fuel tank, and the function does not meet the requirements in advance. This paper studies this problem. Objective: Through on-the-spot investigation of the factory, a mechanical design process model is designed. The model can provide reference for product design participants on product design time and design quality, and can effectively solve the problem of low product design quality caused by unreasonable product design time arrangement. Methods: After sorting out the data from the factory investigation, computer software is used to program, simulate the information input of mechanical design process, and the final reference value is got. Results: This mechanical design process model is used to guide the design and production of a new project, nearly 3 months ahead of the original project completion time. Conclusion: This mechanical design process model can effectively guide the product design process, which is of great significance to the whole mechanical design field.


Author(s):  
Marierose Van Dooren ◽  
Valentijn Visch ◽  
Renske Spijkerman ◽  
Richard Goossens ◽  
Vincent Hendriks

Personalization, the involvement of stakeholders in the design process, is often applied in serious game design for health. It is expected to enhance the alignment of a game to the preferences and capacities of the end-user, thereby increasing the end-user’s motivation to interact with the game, which finally might enhance the aimed-for health effects of the game. However, the nature and effect of personalization have never been systematically studied, making assumptions regarding personalization ungrounded. In this literature review, we firstly provide a proposal of our Personalized Design Process-model, where personalization is defined as stakeholder involvement in the Problem Definition-, Product Design- and/or Tailoring Phase. Secondly, we conducted a systematic literature review on this model, focusing on health and its effects. In this review, 62 of the 2579 found studies were included. Analysis showed that a minority of the studies were of methodologically higher quality and some of these tested the health effect by contrasting tailored versus non-tailored games. Most studies involved stakeholders in the Tailoring Design Phase. Therefore, we conclude that involving stakeholders in the Tailoring Phase is valuable. However, to know if personalization is effective in the Product Design- and the Problem Definition Phase, more studies are needed.


Author(s):  
Tetsuo Tomiyama

Abstract This paper proposes a new design process model that unifies theoretical results of General Design Theory (GDT) and empirical findings obtained from design experiments. It first reviews the design process models that were developed within theoretical work on GDT. Then, we describe experimental work on design based on protocol analysis, which resulted in a cognitive design process model from which further a computable design process model was derived. While these experimental results are supposed to support the theoretical conclusions obtained from GDT, we could also find out incompatibilities. We then propose a new design process model, called the refinement design process model, that can unify both theoretical results of GDT and experimental finding obtained from design experiments. The refinement model has better agreements with experimental findings and suggests various issues as a guiding principle to develop a future, advanced CAD system that helps a designer to focus on functional information. We propose and illustrate the concepts of such an advanced CAD system equipped with intensive design knowledge, called a computational framework for knowledge intensive engineering.


Author(s):  
Kim A. Hosler

The purpose of this chapter is to present and discuss the instructional design process model -- ADDIE, and nine flipped course design principles, which when used in parallel, offer a means to support the development and implementation of a hybrid or flipped classroom. Discussion of the pedagogical terms hybrid, blended, flipped classrooms, and active learning, are followed by an overview of the instructional design process model ADDIE, along with evidenced-based flipped classroom design principles. A partial example of how these two frameworks may be applied to the re-design of a fully online course into a flipped or hybrid course is demonstrated, and emergent design-consideration questions are offered.


Sign in / Sign up

Export Citation Format

Share Document