Sharp Kabushiki Kaisha Corporation

Arcelor France

Nippon Steel Corporation

Tsuyoshi Inoue

Teruhiko Matsuoka

Guy Hauret

Takashi Aramaki

The invention relates to a method for feeding lubricant during hot rolling, in which the surfaces of the rolling rolls are fed with a lubricating emulsion, characterized in that said lubricating emulsion, consisting of a lubricating oil having a viscosity between 10 cSt and 400 cSt at 40&#xb0; C., mixed with water, is directed onto the surfaces of the rolling rolls via at least one lubricant feed nozzle, at a temperature above 0&#xb0; C. but below 25&#xb0; C.

Method for feeding lubricant during a hot rolling process

An exemplary lubricated hot rolling method is provided which can use a lubricating oil containing, e.g., one or more kinds among an high-basic alkaline-earth metal phenate, high-basic alkaline-earth metal carboxylate, high-basic alkaline-earth salicylate, or high-basic alkaline-earth metal sulfonate having a basicity of 40 mgKOH/g or higher, and has a viscosity at 40&#xb0; C. of 800 cSt or less. The rolling can be performed by granulating or atomizing the lubricating oil into particulates whose average size is less than 1 mm, supplying the lubricating oil to rolls by using a noncombustible gas whose flow rate is 2000 cmor more per minute per lubricating nozzle. The velocity of the oil may be 1 m or more per second. The amount supplied of the lubricating oil can be controlled to 0.01 cmor more and 20 cmor less per 1 mof a surface area of the rolls.

Lubricated hot rolling method

A fuzzy neural network system which is provided with an input layer, a membership layer front half section, a membership layer back half section, a rule layer, and an output layer; and constructs a network from a plurality of input/output items. The input layer and the membership layers are structured so as to divide each input value into three regions of fuzzy sets, respectively. The rule layer selects one each respectively from the above mentioned items divided into three regions, and is structured so as to make these the AND rules for the two input items.

Fuzzy neural network system

A fuzzy neural network system includes a learning function. The learning is performed by determining degrees of coincidence of rules from combinations of membership functions for realizing fuzzy rules, constructing a network based on the number of input and output items, in such a manner as to produce output in conformity with the degrees of coincidence, to thereby properly simulate relations between input and output as to sample data represented by a subject input pattern and an output pattern corresponding thereto. The system further includes a fuzzy rule setup portion for programming fuzzy rules created by engineers into the fuzzy neural network, a fuzzy rule extracting portion for extracting each fuzzy rule from the network after a learning period, and a degree-of-importance extracting portion which extracts, for each input, a respective contribution ratio of each input on each output in the network, after a learning period. In a preferred embodiment, the network structure includes an input layer, a membership layer having front and rear halves, a rule layer, and an output layer.

Growing community of inventors

Chiba, Japan

Tsuyoshi Inoue