Engineering Change Requests Research Articles

An interpretable machine learning approach for engineering change management decision support in automotive industry

As an essential part of the Product Life Cycle (PLC), the time-to-market of products is influenced by Engineering Change Management (ECM) processes. An Engineering Change (EC) is part of a formal process in industry to describe, rationalize, determine, release components for final production or make changes to already released design. It includes information about shape, functionality, production location, cost, and other relevant data entries. The duration from creation to the approval of a change request can take weeks or even months, without apparent reasons for the bottleneck. In addition, changes to one component can lead to unexpected chain reactions to other components. Therefore, identifying impacts of changes is challenging for all Original Equipment Manufacturers (OEMs). To address the above challenges, the authors have developed and built a machine learning-based decision support solution in this article. Community detection and stacking algorithms were applied to build more robust models. Impacts and lead time of Engineering Change Requests (ECRs) are predicted and explained by Local Interpretable Model-agnostic Explanations (LIME). A case study was conducted on real-world data from an automotive company. After evaluation with industry experts, the solution approach was proved to have positive contributions to increasing the quality, efficiency, and transparency of the existing ECM processes.

Feasibility study for an automated engineering change process

Engineering change is a significant cost for projects. While avoiding and mitigating the risk of change is ideal, mistakes and improvements are recognised as more is learned about the decisions made in a design. This paper presents a feasibility and performance analysis of automating engineering change requests to demonstrate the promise for increasing speed, efficiency, and effectiveness of product-lifecycle-wide engineering-change-requests. A comparatively simple case is examined to mimic the reduced set of alterable aspects of a typical change request and to highlight the need of appropriate search algorithms as brute force methods are prohibitively resource intensive. Although such cases may seem trivial for human agents, with the volume of expected change requests in a typical facility, the potential opportunity gain by eliminating or reducing the amount of human effort in low-level changes accumulate into significant returns for the industry on time and money. Herein, the genetic algorithm is selected to demonstrate feasibility with its broad scope of applicability and low barriers to deployment. Future refinement of this or other sophisticated algorithms leveraging the nature of the standard representations and qualities of alterable design features could produce tools with strong implications for process efficiency and industry competitiveness in its projects execution.

Natural language processing methods for knowledge management—Applying document clustering for fast search and grouping of engineering documents

Product development companies collect data in form of Engineering Change Requests for logged design issues, tests, and product iterations. These documents are rich in unstructured data (e.g. free text). Previous research affirms that product developers find that current IT systems lack capabilities to accurately retrieve relevant documents with unstructured data. In this research, we demonstrate a method using Natural Language Processing and document clustering algorithms to find structurally or contextually related documents from databases containing Engineering Change Request documents. The aim is to radically decrease the time needed to effectively search for related engineering documents, organize search results, and create labeled clusters from these documents by utilizing Natural Language Processing algorithms. A domain knowledge expert at the case company evaluated the results and confirmed that the algorithms we applied managed to find relevant document clusters given the queries tested.

Effects of Digital Twin Simulation Modelling on a Flexible and Fixtureless Production Concept in Automotive Body Shops

Product variants and engineering change requests challenge the automotive body shop and make flexible production systems necessary to sustain competitively. Component-integrated fixture feature (CFF) can enable flexible production by reducing specific jig and fixture technology and integrating their functions in components to be joined. This research paper presents digital twin simulation modelling of a flexible and fixtureless production concept by coupling a physical production cell in a virtual production environment. The effect of CFF on the welding process, production equipment, integration planning, and engineering changes can be forecasted for better decision-making and production planning.

DERIVATION OF DESCRIPTION FEATURES FOR ENGINEERING CHANGE REQUEST BY AID OF LATENT DIRICHLET ALLOCATION

AbstractComplex products and shorter development cycles lead to an increasing number of engineering changes. In order to be able to process these changes more effectively and efficiently, this paper develops a description model as a first step towards a data driven approach of processing engineering change requests. The description model is systematically derived from literature using text mining and natural language processing techniques. An example of the application is given by an automated classification based on similarity calculations between new and historic engineering change requests.

Modeling industrial engineering change processes using the design structure matrix for sequence analysis: a comparison of multiple projects

The problem at hand is that vast amount of data on industrial changes is captured and stored; yet the present challenge is to systematically retrieve and use them in a purposeful way. This paper presents an industrial case study where complex product development processes are modeled using the design structure matrix (DSM) to analyze engineering change requests sequences. Engineering change requests are documents used to initiate a change process to enhance a product. Due to the amount of changes made in different projects, engineers want to be able to analyze these change processes to identify patterns and propose the best practices. The previous work has not specifically explored modeling engineering change requests in a DSM to holistically analyze sequences. This case study analyzes engineering change request sequences from four recent industrial product development projects and compares patterns among them. In the end, this research can help to identify and guide process improvement work within projects.

Supporting Knowledge Re-Use with Effective Searches of Related Engineering Documents - A Comparison of Search Engine and Natural Language Processing-Based Algorithms

AbstractProduct development companies are collecting data in form of Engineering Change Requests for logged design issues and Design Guidelines to accumulate best practices. These documents are rich in unstructured data (e.g., free text) and previous research has pointed out that product developers find current it systems lacking capabilities to accurately retrieve relevant documents with unstructured data. In this research we compare the performance of Search Engine & Natural Language Processing algorithms in order to find fast related documents from two databases with Engineering Change Request and Design Guideline documents. The aim is to turn hours of manual documents searching into seconds by utilizing such algorithms to effectively search for related engineering documents and rank them in order of significance. Domain knowledge experts evaluated the results and it shows that the models applied managed to find relevant documents with up to 90% accuracy of the cases tested. But accuracy varies based on selected algorithm and length of query.

Opportunity discovery in initiated and emergent change requests

When a change request is raised in an engineering project anad hocteam often forms to manage the request. Prior research shows that practitioners often view engineering changes in a risk-averse manner. As a project progresses the cost of changes increases. Therefore, avoiding changes is reasonable. However, a risk-averse perspective fails to recognize that changes might harbor discoverable and exploitable opportunities. In this research, we investigated how practitioners ofad hocteams used practices and praxes aimed at discovering and exploiting opportunities in engineering change requests. A single case study design was employed using change request records and practitioner interviews from an engineering project. 87 engineering change requests were analyzed with regards to change triggers, time-to-decision and rejection rate. In total, 25 opportunities were discovered and then 17 exploited. Three practices and six praxes were identified, used by practitioners to discover and exploit opportunities. Our findings emphasize the importance of the informal structure ofad hocteams, to aid in opportunity discovery. The informal structure enables cross-hierarchal discussions and draws on the proven experience of the team members. Thus, this research guides project managers and presumptivead hocteams in turning engineering changes into successful opportunities.

A framework for capturing and applying design knowledge in new product development

The large amount of information that permeates the various activities of the new product development process (NDP) has become increasingly common in many organisations. Under these conditions, there are difficulties in sharing and reusing design knowledge, especially by the fact that this knowledge is available within the company in different formats and locations. Due to this, design engineers often fail to use such information. To ensure a better use, it is important to organise and integrate the available knowledge in a collaborative manner. Through KBE concepts, the current study aims to develop a set of tools for assisting decision making, by storing and providing useful information in a timely manner. Such solution should meet the needs of its users (i.e., designers), as well as improve the quality of design activities along the NDP. The application of the present proposal, still under development, is expected to facilitate the access to information, significantly reduce the number of engineering change requests, as well as allow acquired knowledge to be used in subsequent projects.

A framework for capturing and applying design knowledge in new product development

The large amount of information that permeates the various activities of the new product development process (NDP) has become increasingly common in many organisations. Under these conditions, there are difficulties in sharing and reusing design knowledge, especially by the fact that this knowledge is available within the company in different formats and locations. Due to this, design engineers often fail to use such information. To ensure a better use, it is important to organise and integrate the available knowledge in a collaborative manner. Through KBE concepts, the current study aims to develop a set of tools for assisting decision making, by storing and providing useful information in a timely manner. Such solution should meet the needs of its users (i.e., designers), as well as improve the quality of design activities along the NDP. The application of the present proposal, still under development, is expected to facilitate the access to information, significantly reduce the number of engineering change requests, as well as allow acquired knowledge to be used in subsequent projects.

On the Application of Text Clustering in Engineering Change Process

In modern industry, the development of complex products involves engineering changes that frequently require redesigning or altering the products or their components. In an Engineering Change process, Engineering Change Requests (ECRs) are natural language written texts exchanged among process operators. ECRs describe the required change on a product or a component and the solution. After the change implementation, ECRs are stored but never consulted, missing opportunities to learn from previous projects. This paper explores the application of text clustering to natural language texts written during the Engineering Change process in industry. In detail, the use of Self Organizing Map (SOM) to the problem of unsupervised clustering of ECR texts is explored. A case study is presented in which ECRs collected during the Engineering Change process of a railways industry are analysed. The results show that SOM text clustering has a good potential to improve overall knowledge reuse and exploitation.

Engineering Change Management Data Analysis from the Perspective of Information Quality

An efficient change management process is vital to companies in order to continuously improve their products. The processing times for Engineering Change Requests (ECR) vary from hours to years. The long processing times lead to unnecessary delays to requested fixes and improvements. This paper is based on analysis of Engineering Change Objects and semi-structured interviews in a case company, where the number of ECRs has been increasing significantly. The goal of the research was to find out reasons for varying ECR processing times. However, analyzing the data afterwards is difficult because part of the modification history disappears during the process.

On the Use of Self-Organizing Map for Text Clustering in Engineering Change Process Analysis: A Case Study.

In modern industry, the development of complex products involves engineering changes that frequently require redesigning or altering the products or their components. In an engineering change process, engineering change requests (ECRs) are documents (forms) with parts written in natural language describing a suggested enhancement or a problem with a product or a component. ECRs initiate the change process and promote discussions within an organization to help to determine the impact of a change and the best possible solution. Although ECRs can contain important details, that is, recurring problems or examples of good practice repeated across a number of projects, they are often stored but not consulted, missing important opportunities to learn from previous projects. This paper explores the use of Self-Organizing Map (SOM) to the problem of unsupervised clustering of ECR texts. A case study is presented in which ECRs collected during the engineering change process of a railways industry are analyzed. The results show that SOM text clustering has a good potential to improve overall knowledge reuse and exploitation.

Multi‐Level Product Platform Strategy for a Multi‐Level Corporation

AbstractReuse strategies based on product platform thinking can provide important advantages over single‐product development, especially for achieving economy‐of‐scale and cost‐efficient product variety. This paper presents the case of a multi‐national corporation that has many opportunities for identifying commonalities across and within its subsidiaries from which product platforms can be defined. The study focuses on the opportunities of one of these subsidiaries to transfer to platform‐based development for some of their components. A framework is presented that defines different levels in the organization where product platforms can be used, as well as different types of reuse strategies that may be adequate for the studied components. These levels are: (A) within each subsidiary, (B) between subsidiaries, and (C) common throughout the umbrella corporation. The types of reuse are categorized as (1) local component sharing, (2) arms‐length buy‐in of components within the corporation, and (3) platform‐based development. It is argued that a platform strategy for the corporation can include various combinations of reuse types and organizational levels, depending on where reuse potential is identified. The main considerations for making this effective is where ownership lies for the shared assets and how to balance multiple stakeholder requirements from different applications, e.g. during engineering change requests.

ADVICE: A virtual environment for Engineering Change Management

In this paper, we analyze Engineering Changes (EC), which are modifications in forms, fits, functions, materials, or dimensions in components constituting the design. We propose a new approach for processing these changes within a Virtual Collaborative Design Environment. This environment, named Active Distributed Virtual Change Environment (ADVICE) offers an Engineering Change Management solution by merging graphical and parametric data involved in the process into a virtual platform, which improves the comprehension of users and hence decreases the time required for review. ADVICE provides smart user support for predicting Engineering Changes to be triggered due to a specific change and for offering priorities to Engineering Change Requests. This is managed by employing Sequential Pattern Mining techniques to process captured Engineering Change history with Prioritization and Change Propagation mechanisms. For verifying these mechanisms, experiments involving synthetic data are conducted. The experiments present the capability of ADVICE to facilitate Engineering Change Management.

Bringing together knowledge about the product life cycle to improve inter-firm collaboration capabilities

The emerging division of labour regarding new product development tasks creates new challenges for Tier 1 Suppliers. They face the need to enable and control increasingly outsourced and geographically dispersed product development activities. Analysis of the way suppliers' teams handle the impacts of Engineering Change Requests shows that their capacity to successfully manage the extended enterprise depends on suppliers' capabilities to collectively represent their functional interdependences while preserving their own requirements for each phase of the product life cycle. Challenges posed by the acceleration of the pace of innovation demonstrate that current product life cycle definition devices are not adapted to managing stretched – and potentially conflicting – situated judgements concerning the conformity of complex product requirements. There are still limiting obstacles in bringing together knowledge about the product definition, tasks dependencies and load and lead time estimates – and, ultimately, consistently describing a manufacturable product life cycle.

Relating company performance to staff perceptions: The impact of concurrent engineering on time to market

A study of 103 electronics manufacturers in the United States has demonstrated a relationship between staff perceptions and actual performance for concurrent engineering. Information was gathered in each company from the manager of the concurrent engineering effort, the team leader and a design, manufacturing and marketing team member. The use of concurrent engineering reduced, on average, the time to market. Companies were grouped into the 'upper third' and 'lower third' with respect to overall effectiveness, based on the mean rating or perception of the respondents. Companies in the 'upper third' and 'lower third' of effectiveness in implementing and using concurrent engineering were found to have engineering change requests occur 45% and 27% earlier, respectively, in the product development process through their concurrent engineering effort. Companies in the 'upper third' in overall concurrent engineering effectiveness reduced time to market by 40% , while the 'lower third' reduced time to market by only 16% . The top one-third of companies in concurrent engineering reduce, on average, the time to market of products by 4.8 months in relation to companies in the bottom one-third. The implications of the findings are discussed for researchers and practitioners in the light of difficulties experienced by reengineering efforts in the 1990s.