Online fault diagnosis for smart machines embedded in Industry 4.0 manufacturing systems: A labeled Petri net-based approach

Paiva, Pedro R. R.; Freitas, Braian Igreja de; Carvalho, Lilian K.; Basilio, João Carlos

doi:10.1016/j.ifacsc.2021.100146

Cited by 10 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, during sample training, to maintain the processing efficiency of the network for dynamic data, the input data needs to be transformed from the concurrent vector to the sequential vector. Meanwhile, the batch processing method is adopted for training, to adjust the time delay caused by the data entering the undertaking layer (Paiva et al, 2021).…”

Section: Research Model and The Methodologymentioning

confidence: 99%

The evaluation of enterprise supply chain intelligent manufacturing system for agricultural interconnection data based on machine learning

Yu¹,

Li²,

Li³

et al. 2023

Expert Systems

View full text Add to dashboard Cite

The present work aims to promote the modernization of the real economy and facilitate the manufacturing industry to construct an intelligent manufacturing system. Analysis and evaluation are performed on the intelligent manufacturing system (IMS) of enterprises under the Internet of Things (IoT). First, the connotation and characteristics of machine learning (ML) in the era of IoT are explained, followed by the introduction to neural networks. Second, the optimization process of the neural network is described. Since it has no memory, the traditional deep neural network (DNN) needs to be improved. Then, the Generative Adversarial Network (GAN) is utilized to expand the sample data. Moreover, the confusion matrix is used in the indicator evaluation. The backpropagation neural network (BPNN) is optimized by the genetic algorithm (GA) to improve the network configuration and model performance. In addition, the connotation and development status of IMS are analysed, and the feasibility of applying deep learning to the evaluation of IMS is discussed. Finally, the evaluation model of IMS is designed and built via a neural network, which is ultimately verified in the simulation experiment. The experimental results indicate that the BPNN‐GA algorithm has advantages in predicting fitting accuracy, taking up less memory, and shortening training time; it can achieve generalization and accuracy in the forefront of optimal Pareto value, and the fitting accuracy attains 95.3%. The horizontal evaluation of IMS proves the effectiveness and feasibility of the evaluation model. This shows that the BPNN‐GA algorithm has an excellent evaluation effect on IMS. And the IMS evaluation model is applied to assess the IMS of sample enterprises. The evaluation results demonstrate that there are problems in the current manufacturing industry. For example, the transactions are challenging to be completed smoothly, information technology is updated slowly, and IMS is dependent on collecting resources.

show abstract

Section: Research Model and The Methodologymentioning

confidence: 99%

The evaluation of enterprise supply chain intelligent manufacturing system for agricultural interconnection data based on machine learning

Yu¹,

Li²,

Li³

et al. 2023

Expert Systems

View full text Add to dashboard Cite

show abstract

“…Ref. [7] developed online diagnostics embedded in Industry 4.0 manufacturing systems applied to DES modelled by acyclic or reversible labelled Petri nets, which identify normal and faulty behavior of the system through verification based on a set of inequalities in the variables. Based on a new construction pattern recognition technique for health indicators, Ref.…”

Section: Introductionmentioning

confidence: 99%

Multi-Sensor Fault Diagnosis Based on Time Series in an Intelligent Mechanical System

Qian

et al. 2022

Sensors

View full text Add to dashboard Cite

Intelligent mechanical systems are a focused area nowadays. One of the requirements of intelligent mechanical systems is to achieve intelligent fault diagnosis through the real-time acquisition and analysis of data from various sensors installed on mechanical components. In this paper, a new fault diagnosis method is proposed to solve the problems of difficulty in integrating the fault diagnosis algorithm and locating fault parts due to the complexity of modern mechanical systems. The complexity of modern industrial intelligent systems is due to the fact that the systems are composed of multiple components and there are various connections between them. Common fault diagnosis is to design specialized fault identification algorithms for the physical characteristics of each component, and the integration of different algorithms is a major challenge for system performance. Therefore, this paper investigates a general algorithm for the fault diagnosis of complex systems using the timing characteristics of sensors and transfer entropy. The fault diagnosis algorithm is based on the prediction of multi-dimensional long time series using Autoformer, and fault identification is performed based on the deviation of the predicted value from the actual value. After fault identification, a root cause analysis method of faults based on transfer entropy is proposed. The method can locate the component where the fault occurs more accurately based on the analysis of the cause–effect relationship of each component and help maintenance personnel to troubleshoot the fault.

show abstract

“…A diagnose em tempo real está relacionada à construção de um sistema de diagnose online capaz de determinar a ocorrência de falhas concomitantemente com a operação da planta cuja falha se deseja diagnosticar. Nesse contexto, diversos trabalhos que abordam tanto o problema de diagnose online quanto a diagnosticabilidade podem ser encontrados na literatura: Debouk et al (2000); Contant et al (2006); Qiu and Kumar (2006); Moreira et al (2011); Carvalho et al (2013); Cabral et al (2014); Nunes et al (2018); Santoro et al (2017), que utilizam autômatos, e Genc and Lafortune (2003); Lefebvre and Delherm (2007); Ramírez-Treviño et al (2007); Dotoli et al (2009); Basile et al (2009); Cabasino et al (2011); Liu et al (2017); Al-Ajeli and Bordbar (2016); Paiva et al (2021), que usam redes de Petri como formalismo.…”

Section: Introdu ç ãOunclassified

“…Este artigo considera o problema da diagnose em tempo real de SEDs modelados por redes de Petri e propõe uma abordagem mais geral que aquelas propostas por Genc and Lafortune (2003); Lefebvre and Delherm (2007); Ramírez-Treviño et al (2007); Dotoli et al (2009); Basile et al (2009); Cabasino et al (2011); Liu et al (2017); Al-Ajeli and Bordbar (2016); Paiva et al (2021) uma vez que amplia a classe de redes de Petri rotuladas cujos eventos de falha podem ser diagnosticados. Nesse sentido será proposta neste artigo a criação de uma rede de Petri rotulada com prioridade sem transições não-observáveis (livre de λ) capaz de replicar o comportamento da rede de Petri original do sistema.…”

Section: Introdu ç ãOunclassified

Diagnose de falhas em tempo real de sistemas a eventos discretos modelados por redes de Petri rotuladas utilizando redes de Petri rotuladas com prioridades

Freitas

Basilio

2021

Procedings Do XV Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

The problem of fault diagnosis of discrete event systems concerns the capacity to detect and isolate the occurrence of fault events. In this work, we propose a labeled priority diagnoser Petri net that is obtained from the Petri net of the system to be diagnosed. The diagnoser Petri net transitions are labeled only by observable events and its reachable states have enough information to allow the diagnoser to be sure about the fault occurrence. As in previous works, we assume that the Petri net of the system to be diagnosed does not possess cycles involving places and unobservable transitions. In addition, for a class of Petri nets, the diagnoser will have a structure that does not grow indefinitely due to event observations, making the diagnoser proposed here able to execute the online diagnosis of a class of Petri nets that previous works were only able to diagnose with structures that are likely to grow indefinitely for specific sequences of event observations. Resumo: O problema da diagnose de falha em sistemas a eventos discretos está associado com a capacidade de se detectar e isolar a ocorrência de eventos de falha. Neste artigo, será proposto um algoritmo para construir uma rede de Petri diagnosticadora rotulada com prioridades a partir da rede de Petri do sistema a ser diagnosticado, cujas transições são rotuladas apenas por eventos observáveis e cujos estados alcançáveis possuem informações necessárias para que o diagnosticador possa ter certeza da ocorrência de falha. Assim como em trabalhos anteriores, supõe-se que a rede de Petri do sistema a ser diagnosticado não possui ciclos envolvendo lugares e transições não observáveis. Além disso, para uma classe de redes de Petri, o diagnosticador proposto terá uma estrutura que não crescerá indefinidamente em decorrência das observações de eventos, fazendo com que o diagnosticador aqui proposto seja capaz de executar o diagnóstico online de classes de redes de Petri que trabalhos anteriores somente são capazes de diagnosticar com estruturas passíveis de crescimento indefinido para determinadas sequências de observações de eventos.

show abstract

Online fault diagnosis for smart machines embedded in Industry 4.0 manufacturing systems: A labeled Petri net-based approach

Cited by 10 publications

References 28 publications

The evaluation of enterprise supply chain intelligent manufacturing system for agricultural interconnection data based on machine learning

The evaluation of enterprise supply chain intelligent manufacturing system for agricultural interconnection data based on machine learning

Multi-Sensor Fault Diagnosis Based on Time Series in an Intelligent Mechanical System

Diagnose de falhas em tempo real de sistemas a eventos discretos modelados por redes de Petri rotuladas utilizando redes de Petri rotuladas com prioridades

Contact Info

Product

Resources

About