Unset cement damage detection system based on a block chain and a BIM

Abstract

The invention discloses an unset cement damage detection system based on a block chain and a BIM. The system comprises a first encoder unit, a weight addition unit, a second encoder unit, a first fullconnection network unit and a visualization unit. For each unset cement damage detection deep neural network reasoning request, a plurality of available nodes are selected from the server cluster, parameters required by a first encoder unit, a weight addition unit, a second encoder unit and a first full-connection network unit which are respectively distributed at different available nodes are used as block data, and an unset cement damage detection deep neural network reasoning block chain private chain is generated, and the unset cement damage detection deep neural network reasoning is executed, thereby realizing unset cement damage detection. By utilizing the unset cement damage detection system, in the process of detecting the unset cement on the construction site, the result feedbackis diversified, and the detection precision and the confidentiality and the safety in the data processing and transmission process are improved.

Description

technical field [0001] The invention belongs to the technical fields of blockchain and BIM, and in particular relates to a damage detection system for unset cement based on blockchain and BIM. Background technique [0002] In recent years, the construction and real estate industries have developed rapidly. At present, the number of construction sites is constantly increasing, and with it, the internal management problems of the construction sites are also becoming more and more prominent. Especially when the cement is poured on the building or on the ground, before the cement solidifies, the complex site environment of the construction site is easily damaged. Once it is broken and solidified, the entire pouring surface will be judged as unqualified, resulting in huge loss. However, the current method of preventing damage mainly relies on manual inspection, face-to-face notification, and immediate resolution. [0003] The construction site is basically equipped with survei...

AI Technical Summary

Problems solved by technology

However, due to the small size of the stamped target of the uncured cement on the ground plane, and the characteristics of the background, that is, the normal cement plane are not much different, the difference is not obvious, so it is difficult for the network without modification to truly learn its Accurate feature distribution

Therefore, it is difficult to achieve the desired effect by using traditional detection or segmentation methods.

[0006] Therefore, there are problems such as single result feedback, low detection accuracy, low security performance and low confidentiality performance during data processing and transmission in the field of unset cement damage detection on the existing construction site.

Images