Operator Knowledge Inclusion in Data-Mining Approaches for Product Quality Assurance using Cause-Effect Graphs

Vogel‐Heuser, Birgit; Karaseva, Victoria; Folmer, Jens; Kirchen, Iris

doi:10.1016/j.ifacol.2017.08.233

Cited by 16 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A small number of works propose the usage of ML techniques on CEGs. Vogel-Hauser et al [8] used a dataset of expert knowledge provided by an industrial partner and trained logistic regression and decision tree models for predicting product quality based on CEG elements specified in the dataset. Unfortunately, this dataset is not publicly available.…”

Section: Related Workmentioning

confidence: 99%

Usage of Machine Learning Methods for Cause-Effect Graph Feasibility Prediction

Krupalija,

Cogo,

Pozderac

et al. 2023

Machine Learning and Artificial Intelligence

View full text Add to dashboard Cite

Cause-effect graphs (CEGs) are usually applied for black-box testing of complex industrial systems. The specification process is time-consuming and can result in many errors. In this work, machine learning methods were applied for predicting the feasibility of CEG elements. All information was extracted from graphs contained in CEGSet, a dataset of CEGs. The data was converted to two different formats. The Boolean features format represents relations as separate data rows, whereas the Term-Frequency times Inverse-Document-Frequency (TF-IDF) format represents graphs as data rows. Eight machine learning models were trained on this data. The results of testing by using the 80–20 holdout method indicate that important information is lost when converting the graphs to the TF-IDF format, whereas the Boolean feature format enables 100%-accurate predictions of ensemble methods. The achieved results indicate that pre-trained models can be used as help for domain experts during the CEG specification process.

show abstract

Section: Related Workmentioning

confidence: 99%

Usage of Machine Learning Methods for Cause-Effect Graph Feasibility Prediction

Krupalija,

Cogo,

Pozderac

et al. 2023

Machine Learning and Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Recently, algorithms such as Ant-colony-based Generation of Test cases (AGenT) [29] have been developed for the purpose of automatic functional test generation from formal system requirements. Environment modeling was proposed in [30] for black-box testing automation of real-time embedded systems which have safety and time constraints without any knowledge of the system design, whereas data mining techniques have successfully been applied in [31] for converting system requirements to cause-effect graph specifications.…”

Section: Figure 1 Diagram That Describes the Process Of Choosing The ...mentioning

confidence: 99%

Forward-Propagation Approach for Generating Feasible and Minimum Test Case Suites From Cause-Effect Graph Specifications

et al. 2022

View full text Add to dashboard Cite

Cause-effect graphs are a popular black-box testing technique. The most commonly used approach for generating test cases from cause-effect graph specifications uses backward propagation of forced effect activations through the graph in order to get the values of causes for the desired test case. Many drawbacks have been identified when using this approach for different testing requirements. Several algorithms for automatically generating test case suites from cause-effect graph specifications have been proposed. However, many of these algorithms do not solve the main drawbacks of the initial backpropagation approach and offer only minor improvements for specific purposes. This work proposes two new algorithms for deriving test cases from cause-effect representationsan algorithm that uses forwardpropagation of all possible cause values in order to get all feasible test cases and an algorithm that minimizes the feasible test case suite while taking multiple effect activations into account. Cause-effect graphs previously used for testing algorithms based on the backward-propagation approach were used for evaluation and comparison, as well as the newly introduced test effect coverage metric and fault detection rate effectiveness. The evaluation shows that the proposed algorithms work in real time even for a very large number of cause nodes. The results also indicate that the first newly proposed algorithm generates a larger test case suite, whereas the second newly proposed algorithm generates a smaller test case subset than the originally proposed approaches while ensuring the maximum effect coverage, fault detection rate effectiveness and a better test effect coverage ratio.INDEX TERMS Black-box testing, cause-effect graph, forward-propagation algorithm, software quality, test suite generation.

show abstract

“…So-called Cause-Effect Graphs are an appropriate representation of expert knowledge. [54,55] Operation: alarm systems of aPSs are designed to inform operators of abnormal situations and faults of the system. Since these alarms often propagate through the interdependent equipment, alarmfloods are observed regularly, e.g.…”

Section: (A) Applicationsmentioning

confidence: 99%

Potential for combining semantics and data analysis in the context of digital twins

Vogel‐Heuser

Ocker

Weiss

et al. 2021

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Modern production systems can benefit greatly from integrated and up-to-date digital representations. Their applications range from consistency checks during the design phase to smart manufacturing to maintenance support. Such digital twins not only require data, information and knowledge as inputs but can also be considered integrated models themselves. This paper provides an overview of data, information and knowledge typically available throughout the lifecycle of production systems and the variety of applications driven by data analysis, expert knowledge and knowledge-based systems. On this basis, we describe the potential for combining data analysis and knowledge-based systems in the context of production systems and describe two feasibility studies that demonstrate how knowledge-based systems can be created using data analysis. This article is part of the theme issue ‘Towards symbiotic autonomous systems’.

show abstract

Operator Knowledge Inclusion in Data-Mining Approaches for Product Quality Assurance using Cause-Effect Graphs

Cited by 16 publications

References 9 publications

Usage of Machine Learning Methods for Cause-Effect Graph Feasibility Prediction

Usage of Machine Learning Methods for Cause-Effect Graph Feasibility Prediction

Forward-Propagation Approach for Generating Feasible and Minimum Test Case Suites From Cause-Effect Graph Specifications

Potential for combining semantics and data analysis in the context of digital twins

Contact Info

Product

Resources

About