Slab number online identification method based on autonomous evolutionary neural network

Abstract

The invention provides a slab number online identification method based on an autonomous evolution neural network, and relates to the technical field of automatic control of a hot rolling production process of a steel enterprise. The method comprises the following steps: firstly, extracting video data of a plate blank advancing process, and carrying out data processing to obtain a plate blank image data set with a plate blank number; based on the thought of transfer learning, the specific position of the slab number on the slab image is positioned, and a data set required for slab number recognition is made; an autonomous evolution neural network algorithm is designed based on the idea of multi-target genetic programming, a slab number recognition integrated model is constructed, and online recognition of slab numbers is achieved; and finally, the identified single slab number character is recombined to obtain a predicted slab number. According to the method, end-to-end online identification of the plate blank number can be realized, the labor cost can be effectively reduced, and the intelligent manufacturing level of a hot rolling production line is improved.

Description

technical field [0001] The invention relates to the technical field of automatic control of the hot rolling production process of iron and steel enterprises, in particular to an online recognition method for slab numbers based on an autonomous evolutionary neural network. Background technique [0002] Hot rolling production is an important production line in iron and steel enterprises. The hot rolling workshop and the continuous casting workshop are arranged adjacent to each other. The qualified continuous casting slabs after cooling, flame treatment and marking in the continuous casting workshop and the hot continuous casting with qualified surface and internal quality The slab will be sent to the hot rolling workshop by the roller table, and then the operator will identify the billet number of the slab and check it with the data in the slab warehouse. The designated stacks in the slab warehouse, waiting to complete the established rolling plan. With the continuous deepeni...

AI Technical Summary

Problems solved by technology

Because the design of the slab number recognition algorithm in the above methods relies on manual experience to build, the performance is greatly affected by human factors, and the algorithm is less robust, so it can only be used in a specific environment, and there are also large recognition errors, etc. Phenomenon, it is difficult to meet the needs of modern intelligent manufacturing

Images