Improving production process performance thanks to neuronal analysis

Noyel, Mélanie; Thomas, Philippe; Charpentier, Patrick; Thomas, André; Beaupretre, Bruno

doi:10.3182/20130522-3-br-4036.00055

Cited by 5 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The third classification problem considered is a real quality classification problem from a robotic lacquering process [88]. In this dataset, one defect (stains on back)…”

Section: Quality Datasetmentioning

confidence: 99%

A New Multilayer Perceptron Pruning Algorithm for Classification and Regression Applications

Thomas

Suhner

2014

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

Optimizing the structure of neural networks remains a hard task. If too small, the architecture does not allow for proper learning from the data, whereas if the structure is too large, learning leads to the well-known overfitting problem. This paper considers this issue, and proposes a new pruning approach to determine the optimal structure. Our algorithm is based on variance sensitivity analysis, and prunes the different types of unit (hidden neurons, inputs, and weights) sequentially. The stop criterion is based on a performance evaluation of the network results from both the learning and validation datasets. Four variants of this algorithm are proposed. These variants use two different estimators of the variance. They are tested and compared with four classical algorithms on three classification and three regression problems. The results show that the proposed algorithms outperform the classical approaches in terms of both computational time and accuracy.

show abstract

“…The third classification problem considered is a real quality classification problem from a robotic lacquering process [88]. In this dataset, one defect (stains on back)…”

Section: Quality Datasetmentioning

confidence: 99%

A New Multilayer Perceptron Pruning Algorithm for Classification and Regression Applications

Thomas

Suhner

2014

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

show abstract

“…A qualidade é um atributo essencial que pode ser obtida por meio de práticas, uma delas a aplicação de ferramentas tradicionais da qualidade em processos ou produtos (NOYEL et al, 2013;TOLEDO et al, 2013). Para Carpinetti (2012), essas ferramentas facilitam a coleta, organização, análise e apresentação de dados para identificação de disfunções e tomada de decisões nas empresas.…”

Section: Introductionunclassified

Identificação de fatores causadores de hematomas e fraturas em frangos de corte: estudo de caso

Martim¹,

Castro²,

Silva³

et al. 2019

GEPROS

View full text Add to dashboard Cite

Identificação de fatores causadores de hematomas e fraturas em frangos de corte: estudo de casoEm decorrência da competitividade entre as empresas e a maior exigência dos consumidores quanto aos produtos fornecidos, a qualidade se faz primordial. O presente estudo teve por objetivo identificar os fatores que favorecem as ocorrências de hematomas e fraturas em frangos de corte, com o auxílio de ferramentas da qualidade. O estudo foi realizado nos dois turnos de trabalho de uma indústria situada na região Centro Oeste do Paraná. Para tal, foram realizadas observações intensivas e coleta de dados no setor de recepção de frangos. As ferramentas da qualidade utilizadas no estudo foram o fluxograma, folha de verificação, diagrama de Pareto, diagrama de Ishikawa e 5W1H. As principais causas identificadas foram classificadas com relação à Medida (densidade de carga de frangos), ao Meio ambiente (distância do transporte), ao Método (processo de apanha dos frangos) e à Mão de obra (falta de treinamento). Palavras-chave: Ferramentas da qualidade. Gestão da qualidade. Planejamento da qualidade.Due to the competitiveness between companies and greater demands from the consumers regarding the products supplied, quality becomes paramount. This article aimed identify the factors that cause bruising and fractures in broilers, using quality tools. The study was carried out over two work shifts at a company located in the Midwest region of Paraná. For this, intensive observations and data collection were performed in the chicken reception sector. The quality tools used were flowchart, check sheet, Pareto diagram, Ishikawa diagram and 5W1H. The main causes identified were classified in relation to the Measure (density of broilers), Environment (transport distance), Method (broilers picking) and Labor (lack of training).

show abstract