Fuzzy Neural Model for Flatness Pattern Recognition

Chun-yu, Jia; Shan, Xiu-ying; Liu, Hong‐Min; Niu, Zhao-ping

doi:10.1016/s1006-706x(08)60262-9

Cited by 22 publications

(9 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compare to the other methods such as [1,2,4,5] that inspect outer surface for blob, weld and spot, our method is only able to detect blobs and welds approximately as large as 0.3 mm. Moreover, methods in [3,5–7] are specified to find flatness and waviness defect of outer surface, our method is accurate to find flatness with 0.33 mm −1 deviation. The difference between the proposed method and related work is that our method can find blob, weld, flatness and waviness defects simultaneously which is not seen in related work.…”

Section: Comparison and Discussionmentioning

confidence: 99%

“…Jai et al introduced a model by utilizing a fuzzy neural model for flatness pattern recognition with Legendre orthodoxy polynomial as a basic pattern. The result was practical effective to find flatness pattern defects, with strong self-adaptability and anti-interference ability to dispose data while recognizing flatness [7]. Usamentiaga et al presented a simple and maintainable method to investigate steel manufactures.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Curvature Defect Detection on Outer Surfaces Using Best-Fit Polynomial Interpolation

Golkar

Prabuwono

Patel

2012

Sensors

View full text Add to dashboard Cite

This paper presents a novel, real-time defect detection system, based on a best-fit polynomial interpolation, that inspects the conditions of outer surfaces. The defect detection system is an enhanced feature extraction method that employs this technique to inspect the flatness, waviness, blob, and curvature faults of these surfaces. The proposed method has been performed, tested, and validated on numerous pipes and ceramic tiles. The results illustrate that the physical defects such as abnormal, popped-up blobs are recognized completely, and that flames, waviness, and curvature faults are detected simultaneously.

show abstract

Section: Comparison and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Real-Time Curvature Defect Detection on Outer Surfaces Using Best-Fit Polynomial Interpolation

Golkar

Prabuwono

Patel

2012

Sensors

View full text Add to dashboard Cite

show abstract

“…Legendre polynomials are orthogonal and satisfy self-equilibrium qualification, so they are accurate to express flatness basic patterns [22]. Traditionally, there are eight basic patterns of flatness signal: left waves, right waves, center waves, double-edge waves, right-one-third waves, left-onethird waves, quarter waves and edge-center waves [23]. The normalized equations of basic patterns are:…”

Section: Basic Flatness Patternsmentioning

confidence: 99%

The new method of flatness pattern recognition based on GA–RBF–ARX and comparative research

et al. 2015

View full text Add to dashboard Cite

Radial basis function (RBF) network combines with AutoRegressive eXogenous (ARX) model to create RBF-ARX model. RBF-ARX model can describe the global nonlinear dynamic process of the object, and its function coefficients are approximated by data-driven method. Structured nonlinear parameters optimization method is generally used to optimize model parameters, but this method is very complicated and hard to be mastered by engineers. However, genetic algorithm (GA) is relatively simple and widely used. So thought of GA optimizing RBF-ARX is generated, called GA-ARX-RBF, and applied to nonlinear dynamic flatness recognition model. Flatness pattern recognition is the basis and core of flatness control. Considering disadvantages of traditional pattern recognition method, such as limitation of recognition accuracy and poor fault tolerance, a new intelligent method of flatness pattern recognition based on the GA-RBF-ARX model is proposed. Meanwhile, in order to examine the effectiveness of RBF-ARX, another intelligent flatness recognition model based on dynamic feedback Hopfield NN is set up. Simulation proves that RBF-ARX is more suitable for flatness pattern recognition than Hopfield NN. And optimization effect by GA can achieve the desired requirements and is more precise than structured nonlinear parameters optimization method, when RBF-ARX is applied to rolling mill. GA-RBF-ARX can be a new modeling method for complex nonlinear dynamic system.

show abstract

“…So, there are eight common flatness recognition signal basic patterns: left waves, right waves, center waves, double-edge waves, right-one-third waves, left-one-third waves, quarter waves and edge-center waves. [24][25][26] The flatness rolled can be formulated as linear combination of basic patterns: 27) ... (14) Where: .... (15) According to the requirements of rolling mill implementing agency, left waves and right waves, center waves and double-edge waves, right-one-third waves and left-one-third waves, quarter waves and edge-center waves cannot exist at the same time in the flatness basic pattern identified. 28) Dk is processed as follows: …”

Section: Flatness Pattern Recognition Modelmentioning

confidence: 99%

Flatness Intelligent Control Based on T-S Cloud Inference Neural Network

et al. 2014

View full text Add to dashboard Cite

The accuracy of traditional flatness control methods are limited and it is difficult to establish a precise mathematical model of the rolling mill. In addition, the flatness control system is complex and multivariate. General model approaches can not satisfy the high precision demand of rolling process. In this paper, T-S cloud inference neural network and its stability are proposed. It is constructed by cloud model and T-S fuzzy neural network. The stability of T-S cloud inference neural network is analyzed by Lyapunov method in details. Based on the new network, flatness recognition model and flatness predictive model are established. And they are applied for 900HC reversible cold rolling mill. The flatness control system is designed and a simple controller is developed. Initial parameters of the controller are firstly determined through offline training based on measured data, and then they are optimized online automatically. Genetic Algorithm (GA) is used as the optimizing method which is compared with particle swarm optimization (PSO). The simulation results demonstrate that the flatness control system is effective and has a better precision and robustness.

show abstract

Fuzzy Neural Model for Flatness Pattern Recognition

Cited by 22 publications

References 1 publication

Real-Time Curvature Defect Detection on Outer Surfaces Using Best-Fit Polynomial Interpolation

Real-Time Curvature Defect Detection on Outer Surfaces Using Best-Fit Polynomial Interpolation

The new method of flatness pattern recognition based on GA–RBF–ARX and comparative research

Flatness Intelligent Control Based on T-S Cloud Inference Neural Network

Contact Info

Product

Resources

About