Ladle furnace optimization method
An optimization method, ladle furnace technology, applied in neural learning methods, biological neural network models, heating through discharge, etc., can solve problems such as rising instead of falling, slow convergence speed, dependence of convergence parameters, sudden rise and fall of energy function, etc.
Inactive Publication Date: 2010-09-29
上海华铂智能装备有限公司
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Generally speaking, the larger the learning rate, the more intense the change of the weight value. In the early stage of training, a larger learning rate is beneficial to the rapid decrease of the error, but at a certain stage, a large learning rate may lead to oscillation, that is, the energy function suddenly appears. Up and down or not down but up
Therefore, slow convergence speed and dependence on algorithm convergence parameters are obvious shortcomings of BP algorithm
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a ladle furnace optimization method, relating to an intelligent control method, in particular to an improved neural network control method. The ladle furnace optimization method is provided aiming at the nonlinear and coupling characteristics of a controlled object in theladle furnace optimization method by using a mode combining an improved neural network learning method and a diagonal matrix decoupling method, wherein the improved neural network adopts an improved weight modification method.
Description
Technical field The patent of the present invention relates to an intelligent control method, especially an improved neural network control method, which is applied to a ladle furnace optimization method. Background technique Ladle Furnace (Ladle Furnace referred to as LF furnace) is a secondary refining electric arc furnace heated by electric arc and stirred by argon. The electrode lifting system is a key part of the entire LF furnace. The electrode adjustment system quickly adjusts the position of the electrode in real time to maintain a constant The arc length is used to reduce the fluctuation of arc current, maintain the constant ratio of arc voltage and current, and stabilize the input power. At the same time, by selecting and optimizing the power supply curve, the input power can be maximized. The electrode adjustment system of the LF furnace is a very complex Three-phase nonlinear, time-varying, multi-variable system with mutual coupling of input and output, the hydra...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G05B13/02G06N3/08H05B7/148H05B7/156
CPCY02P10/25
Inventor 程明
Owner 上海华铂智能装备有限公司