A human in the loop corrective maintenance methodology using cross domain engineering data of mechatronic systems

Vathoopan, Milan; Brandenbourger, Benjamin; Zoitl, Alois

doi:10.1109/etfa.2016.7733603

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ging (Vathoopan, Brandenbourger, and Zoitl 2016) or independent workers on crowd-sourcing platforms (Li 2017). By taking advantage of end-users' periodical feedback upon noticing errors, these models can stay updated in the presence of shifting data or changing goals.…”

Section: Introductionmentioning

confidence: 99%

Soliciting Human-in-the-Loop User Feedback for Interactive Machine Learning Reduces User Trust and Impressions of Model Accuracy

Honeycutt

Nourani

Ragan

2020

HCOMP

View full text Add to dashboard Cite

Mixed-initiative systems allow users to interactively provide feedback to potentially improve system performance. Human feedback can correct model errors and update model parameters to dynamically adapt to changing data. Additionally, many users desire the ability to have a greater level of control and fix perceived flaws in systems they rely on. However, how the ability to provide feedback to autonomous systems influences user trust is a largely unexplored area of research. Our research investigates how the act of providing feedback can affect user understanding of an intelligent system and its accuracy. We present a controlled experiment using a simulated object detection system with image data to study the effects of interactive feedback collection on user impressions. The results show that providing human-in-the-loop feedback lowered both participants’ trust in the system and their perception of system accuracy, regardless of whether the system accuracy improved in response to their feedback. These results highlight the importance of considering the effects of allowing end-user feedback on user trust when designing intelligent systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Soliciting Human-in-the-Loop User Feedback for Interactive Machine Learning Reduces User Trust and Impressions of Model Accuracy

Honeycutt

Nourani

Ragan

2020

HCOMP

View full text Add to dashboard Cite

show abstract

“…The envisioned aspects are elaborated by using the characteristics of AML in an abstract way. Extending this approach a functionally integrated mechatronic component model and corresponding implementation in AML is presented in [12], [13]. Here a behavior model is used for functionally integrating multidisciplinary aspects of a component.…”

Section: Related Workmentioning

confidence: 99%

Towards an integrated plant engineering process using a data conversion tool for AutomationML

Vathoopan

Brandenbourger

George

et al. 2017

2017 IEEE International Conference on Industrial Technology (ICIT)

Self Cite

View full text Add to dashboard Cite

Abstract-The development process of modern automated manufacturing plants requires a concurrent engineering process that integrates different engineering disciplines. Envisioning a concurrent development process, we propose an engineering process based on an AutomationML metamodel. The proposed metamodel contains standardized mechatronic component models, which acts as the base engineering data for the disciplines and the tools involved in the process. Since the tools operate on disciplinespecific data structures, a data conversion tool is introduced which parses AutomationML mechatronic model and produces specific data interpretable by the tool employed. The benefits of this approach are evaluated by generating an automation project in CODESYS Application Composer, employing the metamodel and data conversion tool with the proposed engineering process.

show abstract

“…Engineering steps using the object-oriented approach presented in [7] each discipline involved in the engineering process, since the behavior model represents the functionality of the component in an abstract way. Vathoopan et al [14] propose that this aggregated engineering data could be also applicable in the operation stage of the component, such as for raising error during operation and for creating simulation. The proposed metamodel including component models requires multidisciplinary data such as control code, 3D data model, simulation data etc.…”

Section: Related Workmentioning

confidence: 99%

Generating metamodel-based descriptions of automation components in AutomationML

Brandenbourger

Vathoopan

Zoitl

2017

2017 IEEE International Conference on Industrial Technology (ICIT)

Self Cite

View full text Add to dashboard Cite

Abstract-The variability of modern automation systems is getting the key factor in determining the efficiency in manufacturing. The modularity of the employed automation components contributes significantly to the level of variability by enabling multiple compositions of automation components. In order to enable a high modularity, each automation component should be modeled as an integrated mechatronic model containing information from different disciplines. This paper describes a recursive concept allowing the structured generation of manufacturerspecific models of automation components. The concept is based on a metamodel in AutomationML and implemented in a prototypical tool for evaluation purposes.

show abstract

A human in the loop corrective maintenance methodology using cross domain engineering data of mechatronic systems

Cited by 7 publications

References 16 publications

Soliciting Human-in-the-Loop User Feedback for Interactive Machine Learning Reduces User Trust and Impressions of Model Accuracy

Soliciting Human-in-the-Loop User Feedback for Interactive Machine Learning Reduces User Trust and Impressions of Model Accuracy

Towards an integrated plant engineering process using a data conversion tool for AutomationML

Generating metamodel-based descriptions of automation components in AutomationML

Contact Info

Product

Resources

About