A Novel Intuitionistic Fuzzy Inhibitor Arc Petri Net With Error Back Propagation Algorithm and Application in Fault Diagnosis

Tan, Mingyue; Li, Jiming; Xu, Guangyuan

doi:10.1109/access.2019.2936212

Cited by 14 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The property prediction and optimization of SMEPs were realized using artificial neural network, 40–45 which has strong self‐learning ability and the ability to find the optimal solution at a high speed, and the major advantages of artificial neural networks are the ability to model multiple outputs simultaneously. Back propagation (BP) neural network is the more outstanding representative among the artificial neural networks, which minimizes the amount of the original data with the same accuracy 46,47 …”

Section: Machine Learning Techniquesmentioning

confidence: 99%

Performance optimization of shape memory epoxy polymers based on machine learning

Liu

Jin

Tao

et al. 2021

Polymers for Advanced Techs

View full text Add to dashboard Cite

In this study, we proposed a machine learning (ML) method to optimize the comprehensive performance of shape memory epoxy polymers (SMEPs) based on experimental data as samples. Firstly, a series of SMEPs specimens were prepared, and their properties were evaluated respectively by testing four indexes including the glass transition temperature (Tg), bending strength, strain fixation rate (Rf), and strain recovery rate (Rr). Subsequently, ML used these experimental data as samples for feature learning to investigate the influence of each component on these properties. The results indicated that methyltetrahydrophthalic anhydride was more favorable to Tg and bending strength than methylhexahydrophthalic anhydride (MHHPA) as a curing agent. However, a certain amount of MHHPA must be included in the system to guarantee a higher Rf and Rr. Moreover, the right amount of bisphenol A cyanate ester in the system improved the comprehensive properties of SMEPs, especially the shape memory effect. Finally, a SMEPs system with superior properties was acquired through the optimization of four indexes of Tg, bending strength, Rf and Rr. Therefore, this study shows that ML methods can also be used to investigate SMEPs that require more specific excellent performance.

show abstract

Section: Machine Learning Techniquesmentioning

confidence: 99%

Performance optimization of shape memory epoxy polymers based on machine learning

Liu

Jin

Tao

et al. 2021

Polymers for Advanced Techs

View full text Add to dashboard Cite

show abstract

“…The training process of the dualtransition influence factors a and b is shown in Equations (18) and (19). The reconstruction gradient of the dual-transition influence factors is described by Equations (20) and (21).…”

Section: ) Improved Fast Gibbs Sampling (Fgs) Algorithmmentioning

confidence: 99%

“…Li et al [19] focused on the use of neural fuzzy Petri nets (NFPN) combined with an error backpropagation (BP) algorithm for fault diagnosis of corresponding variant sensors, providing confidence-level fuzzy inference formulas and accurately assessing the state of sensors. Tan et al [20] studied a method of power grid fault diagnosis based on intuitionistic fuzzy inhibitor arc Petri net (IFINPN), which aims to simplify the logical relationship of complex networks. Cheng et al [21] considered the learning problem of transition influence factor in FPN, and used the comprehensive learning particle swarm optimization (CLPSO) algorithm to realize fault diagnosis for complex motors.…”

Section: Introductionmentioning

confidence: 99%

“…Previous research has used many approaches to combine the FPN with learning algorithms such as the BP algorithm in parameter optimization [18], [20], [22], [23], with a few studies adopting the Elman, genetic, artificial immune, chaotic bat [24], particle swarm optimization (PSO) [25], and CLPSO algorithms, which mainly solved the problem of fault diagnosis in shallow networks. However, for these methods, the weight and the transition influence factor are singular, the network's mapping ability is limited, the weight convergence speed is slower, it is easy to fall into a local optimum, and the transition threshold generally depends on highly subjective expert experience, which is prone to give low accuracy and poor adaptability of fault diagnosis when faced with a complex fault network [21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sensor Fault Diagnosis Based on Adaptive Arc Fuzzy DBN-Petri Net

Zhao

Cheng

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

The adjustable parameters of the traditional fuzzy Petri net (FPN) are single and mostly depend on expert experience. This approach lacks the adaptability to the complex network of sensors, which will result in insufficient accuracy of fault diagnosis. We propose a method combining the FPN with an adaptive arc and deep belief network (DBN) and improved a fast Gibbs sampling (FGS) algorithm to realize sensor fault diagnosis. First, we present the concept of adaptive arcs with label-weights based on the confidence-weights of directed arcs, which is an important component of the sensor fault model. Then, the improved FGS algorithm optimizes the model layer-by-layer, and the adjustment of the transition threshold relies on the marginal distribution of a restricted Boltzmann machine (RBM). Finally, the optimized dualweights and dual-transition influence factors are applied to the forward and backward fuzzy reasoning of the model to achieve network adaptability. Our studies showed that this method has obvious advantages in terms of the accuracy and adaptability of complex networks compared to other FPN fault diagnosis methods. The fault reasoning confidence can provide an effective reference for maintenance personnel and improve maintenance efficiency, ensuring the reliable operation of sensors and related systems. INDEX TERMS Adaptive arc, fuzzy Petri net, deep belief network, fast Gibbs sampling, sensor fault diagnosis.

show abstract

“…FPNs are often used for fault detection and diagnosis of power systems and smart distribution systems, etc. [23]- [25]. A comprehensive risk assessment framework based on FPNs in combination with the analytic hierarchy process (AHP), entropy method (EM), and cloud model has been proposed by Guo et al for long-distance oil and gas transportation pipelines [26].…”

Section: Introductionmentioning

confidence: 99%

Disaster Chain Scenarios Evolutionary Analysis and Simulation Based on Fuzzy Petri Net: A Case Study on Marine Oil Spill Disaster

Zhao

Wang

2019

IEEE Access

View full text Add to dashboard Cite

In a complex environment, a single disaster will generate a series of secondary disasters to form disaster chains. The simulation and prediction of the evolutionary direction of the disaster chain is a key aspect as well as a challenging problem during the emergency management of a disaster chain, accordingly there are two technical problems, the first one is how to describe the form of the disaster chains and the other one is how to model the evolution of the disaster chains. In order to solve these problems, this paper leverage Fuzzy Petri net as a powerful mathematical modelling tool, which can be used for the analysis of process evolution. Based on the traditional fuzzy Petri nets, a Disaster-Chain Fuzzy Petri net (DCFPN) method is proposed for describing the form of disaster chains and analyzing the evolutionary direction with the dynamic observed data. Based on the DCFPN method, this study constructs a general oil spill DCFPN model and takes the petrochemical spill incident in Fujian Province of China as a study case. The DCFPN model is used to dynamically deduce the evolutionary process of the case of oil spill disaster chain, reconstruct the evolutionary direction of the disaster chain, and analyze the riskiest path. The study found that the disaster chain scenarios deduced from the DCFPN model were consistent with the real situation, and this result would be useful for providing a scientific basis for the 'chain-cutting disaster mitigation' strategy for emergency management of disaster chains.INDEX TERMS Fuzzy Petri net, disaster chain evolution analysis, dynamic deduction, chain-cutting disaster mitigation, oil spill disaster chain.

show abstract

A Novel Intuitionistic Fuzzy Inhibitor Arc Petri Net With Error Back Propagation Algorithm and Application in Fault Diagnosis

Cited by 14 publications

References 17 publications

Performance optimization of shape memory epoxy polymers based on machine learning

Performance optimization of shape memory epoxy polymers based on machine learning

Sensor Fault Diagnosis Based on Adaptive Arc Fuzzy DBN-Petri Net

Disaster Chain Scenarios Evolutionary Analysis and Simulation Based on Fuzzy Petri Net: A Case Study on Marine Oil Spill Disaster

Contact Info

Product

Resources

About