Causal interaction modeling on ultra-processed food manufacturing

Menegozzo, Giovanni; Dall’Alba, Diego; Fiorini, Paolo

doi:10.1109/case48305.2020.9216973

Cited by 8 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We focus our comparison on graph-based CD methods, as they allow a graphical interpretation of the results, suitable for application in analytical and decision-making industrial processes. The following assumptions relate causal relations to probability densities and enable CD from observational data [3]:…”

Section: A Assumptionsmentioning

confidence: 99%

“…The advent of Industry 4.0 has made it possible to acquire an increasing number of process parameters thanks to the extended sensorization of the process supported by an advanced communication, acquisition and data management infrastructure. Thanks to this information, it is possible to introduce data-driven approaches capable of identifying the relationships between the variables of the entire plant [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CIPCaD-Bench: Continuous Industrial Process datasets for benchmarking Causal Discovery methods

Menegozzo¹,

Dall’Alba²,

Fiorini³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Causal relationships are commonly examined in manufacturing processes to support faults investigations, perform interventions, and make strategic decisions. Industry 4.0 has made available an increasing amount of data that enable data-driven Causal Discovery (CD). Considering the growing number of recently proposed CD methods, it is necessary to introduce strict benchmarking procedures on publicly available datasets since they represent the foundation for a fair comparison and validation of different methods. This work introduces two novel public datasets for CD in continuous manufacturing processes. The first dataset employs the well-known Tennessee Eastman simulator for fault detection and process control. The second dataset is extracted from an ultra-processed food manufacturing plant, and it includes a description of the plant, as well as multiple ground truths. These datasets are used to propose a benchmarking procedure based on different metrics and evaluated on a wide selection of CD algorithms. This work allows testing CD methods in realistic conditions enabling the selection of the most suitable method for specific target applications. The datasets are available at the following link: [https://github.com/giovanniMen]

show abstract

Section: A Assumptionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%