PID drawing analysis method based on deep learning, computer system and medium

Abstract

The invention provides a PID drawing analysis method based on deep learning, a computer system and a storage medium. The method comprises the following steps: establishing a recognition model set; traversing the PID drawing image with a first identification frame to obtain a pipeline identification data set; traversing the PID drawing image by using a second identification frame to obtain a device identification data set; performing data fusion in the pipeline identification data set and the device identification data set by applying a non-maximum suppression algorithm to obtain pipeline data and device data; and traversing each pipeline by using a clustering association Attract algorithm, identifying a device associated with the pipeline, and forming a corresponding relationship between the pipeline and the device in the PID drawing. The method has the beneficial effects that the pipelines and the devices on the PID drawing image are identified through the deep learning algorithm, and the pipelines and the correspondingly associated devices are summarized, so that the pipelines and the devices in the PID drawing can be rapidly and intelligently identified and analyzed, a large amount of manual identification, the statistics and arrangement time is shortened, and datamation of the PID drawing is realized.

Description

technical field [0001] The present disclosure relates to the technical field of deep learning algorithms, in particular to a method for analyzing PID drawings based on deep learning, a computer system and media. Background technique [0002] PID diagram is the abbreviation of Process&Instrumentation Drawing, which refers to the use of uniformly specified graphic symbols and text codes to show in detail all the equipment, instruments, pipes, valves and other related public engineering systems of the system, such as: sewage Drawings of conventional treatment, power generation system, heating condensate scheme, central air conditioning system. [0003] In the petroleum engineering design industry, professional engineers are required to manually identify and count the number and model of various instruments, valves, and pipelines according to the PID diagram of the process, and manually organize them into a list before proceeding to the next step. [0004] This work can be solv...

AI Technical Summary

Problems solved by technology

[0004] This work can be solved through the structuring of upstream data. At present, the common practice is that upstream professionals use structured PID drawing software to directly provide structured data for downstream professionals. However, due to various reasons, structured PID drawing software uses The rate is not high, and the workload of manual finishing is still huge

[0005] Some existing software for identifying PID drawings still only stays in the identification of instruments and meters, and in the end it is still necessary to manually organize and associate the identified instruments and meters according to the drawings

Images