Composite material damage intelligent detection method based on infrared thermal waves and convolutional neural network

Abstract

The invention discloses a composite material damage intelligent detection method based on infrared thermal waves and a convolutional neural network. The method specifically comprises the following steps: 1, training a damage position identification model and a damage category classification model; 2, collecting infrared thermal wave data of a to-be-detected composite material, obtaining a plurality of infrared thermal wave images, respectively inputting the infrared thermal wave images into the damage position identification model, detecting whether damage exists in the images, and if yes, outputting a predicted damage area; 3, extracting an infrared thermal wave signal of the damaged area; 4, inputting the infrared thermal wave signals into the damage category classification model to obtain the type of each damage; the position and type information of the damage area in the composite material can be obtained, the damage detection result is accurate, and the efficiency is high.

Description

technical field [0001] The invention belongs to the technical field of composite material damage detection, in particular to an intelligent detection method for composite material damage based on infrared thermal wave and convolutional neural network. Background technique [0002] Composite material refers to a new type of material combined by several types of different materials through a composite process. Because composite materials have excellent properties such as good insulation, strong heat resistance, and good corrosion resistance, they are widely used in aircraft fuselages, machines, etc. Wings, interior parts, radomes and other structures, such as the European A400M military logistics aircraft used composite wing covers, F-22 fighter jets accounted for more than 35% composite materials, Boeing 787 aircraft accounted for 50% composite materials, Airbus Composite materials account for as much as 52% of the A350 airliner. [0003] During the preparation and applicati...

AI Technical Summary

Problems solved by technology

[0003] During the preparation and application of composite materials, various damages such as internal delamination and debonding will inevitably occur, and most of the damages are difficult to observe, and it is difficult to determine the location and degree of damage, which brings serious safety hazards to the aircraft. With the extensive application of composite materials in aircraft, the detection of aircraft composite materials has become a key technology to ensure flight safety

[0004] At present, the commonly used nondestructive testing methods for composite materials include X-rays, ultrasonic waves, acoustic emission, etc. These conventional methods generally have the disadvantages of small single detection area and slow detection speed, and are generally not suitable for damage to large-area components. Rapid detection; active pulse thermal imaging technology in infrared non-destructive testing has many advantages such as large single detection area, fast detection speed, non-contact, simple detection system construction, and is suitable for on-site detection. It has a wide range of research applications. However, infrared Thermal wave imaging requires manual identification. Operators use these images to analyze whether there are defects in the parts, determine the type and location of defects, and largely rely on prior knowledge. The operation process is time-consuming and depends on empiricism

[0005] In the process of realizing the present invention, the inventor found that the existing technology focused on infrared image detection when identifying defects, and did not use infrared signals, and the infrared image only reflected the temperature field distribution of all points in the plane at the same time, so it can be judged The position and size of the defect, but the type of the defect cannot be judged; the infrared signal reflects the temperature change of the fixed point over time. When the internal conditions of the material are different, the change of the infrared signal is also different. The position can be effectively identified by studying this change relationship Types of defects, which help to fully reflect the internal conditions of composite materials

Images