Method and device for identifying and displaying coking of flame-permeable high-temperature filter of thermal power boiler

Abstract

The invention discloses a method and a device for identifying and displaying coking of a flame-permeable high-temperature filter of a thermal power boiler. The method comprises the following steps: preprocessing a collected coking image of the flame-permeable high-temperature filter of the thermal power boiler; performing coking identification based on a neural network prediction algorithm; carrying out quantitative analysis on the identified coking, and calculating the score of the coking; when the coking fraction is greater than a first preset threshold value, performing early warning, and when the coking fraction is greater than a second preset threshold value, taking intervention measures; and displaying the coking condition. According to the method, quantitative analysis of thermal power boiler flame-permeable high-temperature filter coking can be realized, coking classification and display are realized by using deep learning-based coking image recognition, and the detection precision and efficiency are improved. The thermal power boiler flame-permeable high-temperature filter coking identification and display device disclosed by the invention has the same advantages as the method.

Description

technical field [0001] The invention belongs to the technical field of boiler coking monitoring in thermal power plants, and in particular relates to a coking recognition and display method and device for a thermal power boiler through a flame high-temperature filter. Background technique [0002] Boiler coking is a common problem in coal-fired power plants. It will destroy normal combustion conditions, reduce boiler efficiency, disrupt normal water circulation, and even cause tube burst accidents. In severe cases, the furnace outlet will be blocked and the furnace will be shut down, affecting The economy and safety of boiler operation. At present, when decoking the boiler furnace of a thermal power plant, it is necessary to send professional technicians to observe and predict the coking state through the fire viewing port, and then use experience to decoke, because the coking situation cannot be accurately judged under hot conditions, so there is no suitable solution, it i...

AI Technical Summary

Problems solved by technology

[0002] Boiler coking is a common problem in coal-fired power plants. It will destroy normal combustion conditions, reduce boiler efficiency, disrupt normal water circulation, and even cause tube burst accidents. In severe cases, the furnace outlet will be blocked and the furnace will be shut down, affecting Economy and Safety of Boiler Operation

At present, when decoking the boiler furnace of a thermal power plant, it is necessary to send professional technicians to observe and predict the coking state through the fire viewing port, and then use experience to decoke, because the coking situation cannot be accurately judged under hot conditions, so there is no suitable solution, it is impossible to make accurate quantitative judgments on the location and degree of coking

[0003] Now there is a "boiler coking early warning method based on convolutional neural network", which collects temperature data of multiple measuring points at the same time period, and obtains the image characteristics of the temperature data of the measuring points through the neural network to judge whether it is coking, but it cannot judge The type of coking, and the coking state cannot be directly observed. This indirect measurement method belongs to the prediction of small sample data. The prediction of the coking state and degree is not accurate enough, and it cannot be displayed intuitively.

Images