A Modular Single-Hidden-Layer Perceptron for Letter Recognition

Gao, Daqi; Zhu, Shangming; Gu, Wenbing

doi:10.1007/11550822_72

Cited by 2 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BP Neural Network is widespread applied to fault diagnosis, and it is composed of three layers: input layerimplicit layeroutput layer. The node of implicit layer could be setting by demand, in these conditions, using three layer Neural Network could approach any continuous function by any accuracy [5] .…”

Section: Advanced Materials Research Vols 383-390mentioning

confidence: 99%

“…According to testing certain armored vehicles' gear-box, simulating three kinds of fault state, therefore the number of output layer node is 3. To choice the number of implicit layer node is a complicated problem, at present, there is not theoretical guide, most method is according to experience [5] .This article adopts the number of the implicit layer node is 12, the conformation of network is…”

Section: Advanced Materials Research Vols 383-390mentioning

confidence: 99%

See 1 more Smart Citation

Research on Fault Diagnosis of Certain Armored Vehicle’ Gear-Box with IMF’s Energy Moment

Wang

Yang³

2011

AMR

View full text Add to dashboard Cite

Aim at the non-stationary and time-variation characteristic of the gear-box fault signal, proposing a condition identify method for gear-box based on EMD and NN. Take the vibrating signal of case as the analysis object, firstly, deal the signal with EMD, extract the IMFs’ energy moment as eigenvector, through neural network based on L-M optimization algorithm to identify gear-box fault. The result of testing certain armored vehicle reveals that method can identify a variety of conditions of gear-box effectively, and provides a availability intelligence fault diagnosis method for gear-box.

show abstract

Section: Advanced Materials Research Vols 383-390mentioning

confidence: 99%

Section: Advanced Materials Research Vols 383-390mentioning

confidence: 99%

Research on Fault Diagnosis of Certain Armored Vehicle’ Gear-Box with IMF’s Energy Moment

Wang

Yang³

2011

AMR

View full text Add to dashboard Cite

show abstract

“…3) Mapping from A to Ap: We use the address function to generate orderly storage space by a certain rules. It's a simple way to avoid the data collision problem [3] . The address function is as:…”

Section: Cmac Network Structurementioning

confidence: 99%

“…It's named Global Dynamical Information Fusion CMAC, called GDIF-CMAC for short. The GDIF-CMAC makes use of historical weight error, combined with the balance parameter in reference [3], and the time window function, to effectively determine the direction and size of weight correction.…”

Section: Introductionmentioning

confidence: 99%

A Fusion CMAC Neural Network Based on Global Dynamic Information

Luo

2011

AMR

View full text Add to dashboard Cite

CMAC neural network has two advantages: the local generalization and no local maximum value. Currently, ICA-CMAC and FCMAC models are used extensively. However, the two models cannot reasonably characterize the direction and magnitude of network weight in the weight correction algorithm. To solve the problem, an improved CMAC learning algorithm is proposed. It takes iterative errors, iteration number and a window function as the performance. Based on information fusion strategy, it introduces global information into the calculation to optimize the network weight. Through a simulation test, it can be found that the model has significant improvement in terms of convergence speed and prediction control.

show abstract

A Modular Single-Hidden-Layer Perceptron for Letter Recognition

Cited by 2 publications

References 8 publications

Research on Fault Diagnosis of Certain Armored Vehicle’ Gear-Box with IMF’s Energy Moment

Research on Fault Diagnosis of Certain Armored Vehicle’ Gear-Box with IMF’s Energy Moment

A Fusion CMAC Neural Network Based on Global Dynamic Information

Contact Info

Product

Resources

About