A thermal wave detection method for internal hole defects in plates in complex environments

Abstract

The application is a kind of thermal wave detection method for internal hole defects of plate in complex environment, relates to a kind of section detection method, the method is edge detection algorithm and heat transfer, depth learning is fused to reach detection method;Heat transfer model is interacted by Python programming language through PyAnsys library and Ansys simulation software, material attribute data is established;Deep learning model is composed of yolov5 visual recognition algorithm, and the edge detection algorithm is Canny edge detection algorithm;First, the initial model of heat transfer is established, then the detection results of deep learning and edge detection algorithm are used to correct the simulation model reversely, finally the edge of internal hole defect of the plate is detected;The application detects the plate defect by the fusion of edge detection algorithm and finite element heat transfer model deep learning, avoids the inaccuracy of hole edge detection caused by low contrast, unclear boundary and noise area interference of thermal image in complex environment.

Description

Technical Field

[0001] The present invention relates to a method for detecting the interior of a profile, and in particular to a thermal wave detection method for hole defects inside a plate in a complex environment. Background Art

[0002] Currently, methods for detecting hole defects within plates typically focus on holes visible on one side, but are less effective at detecting blind holes within plates. Due to the irregular internal structure of plates, which leads to uneven surface temperature distribution, traditional edge detection algorithms are typically used to detect the edges of hole defects in images under normal lighting. Current Canny, Sobel, and watershed algorithms can only detect the approximate edges of infrared images, resulting in insufficient detection accuracy and large errors. Especially for complex environments with low contrast, unclear boundaries, and interference from noise areas, which can cause inaccurate hole edge detection, there is an urgent need for a method that combines multiple models to improve edge detection accuracy. Summary of the Invention

[0003] The purpose of the present invention is to provide a thermal wave detection method for internal hole defects in plates in complex environments. The method integrates the edge detection algorithm with heat transfer and deep learning models to identify the edges of hole defects in plates, thereby realizing a non-destructive material detection method that combines thermal wave edge detection algorithm with heat transfer and computers.

[0004] The method proposed in the present invention is achieved through the following technical solutions:

[0005] A thermal wave detection method for internal hole defects in plate materials in complex environments is developed by integrating edge detection algorithms, heat transfer theory, and deep learning. The heat transfer model uses the Python programming language to interact with Ansys simulation software via the PyAnsys library, and material property data is established. The deep learning model is constructed using the Yolov5 visual recognition algorithm and the Canny edge detection algorithm. An initial heat transfer model is first established, and then the simulation model is inversely corrected using the detection results of the deep learning and edge detection algorithms to ultimately detect the edges of hole defects in the plate materials.

[0006] The specific process is as follows:

[0007] (1) Using Python programming language to interact with Ansys simulation software through the PyAnsys library and the field environment, the finite element heat transfer model is established based on the material property data, and the infrared image data is extracted; then the convolutional neural network is used to detect and identify the hole defects inside the plate, and the center point position P of the hole defect and the equivalent radius R of the hole defect in the infrared image are obtained; the center point position error of the hole defect is compared between the two. If it is less than the set threshold e1, the experiment can continue; otherwise, the center point position P of the hole defect and the hole defect radius R will be updated with reverse correction to re-establish the heat transfer model, and then the experiment will be carried out in sequence;

[0008] (2) The Canny operator is used to simultaneously detect the hole edges of the infrared image data collected by the thermal imaging field instrument, and the area T with a large boundary temperature gradient is identified. If the error of the hole edge area T is greater than the set threshold e2, the simulation model is re-established based on the extracted hole edge conditions and features inside the plate, and the experiment is carried out in sequence; if the features of the two are consistent, no update correction is performed, thus avoiding the inaccurate hole edge detection caused by the low brightness contrast of the thermal image in a complex environment and the unclear hole boundary features;

[0009] (3) By reverse updating the heat transfer simulation model, the center point position of the hole, the hole radius, and the temperature distribution at the hole edge are corrected, and finally the hole defect detection results inside the plate are accurately obtained.

[0010] The advantages and effects of the present invention are:

[0011] 1. The present invention is a thermal wave detection method for internal hole defects in complex environment plates that combines edge detection algorithm with heat transfer and deep learning. A thermal imager is used to capture infrared images of the scene and transmit the data through the network. An initial heat transfer model is first established, and then the simulation model is reversely corrected through the detection results of deep learning and edge detection algorithm to achieve the purpose of detecting internal hole defects in the plate.

[0012] 2. This invention uses the Python programming language, via the PyAnsys library, to interact with Ansys simulation software and establish a finite element heat transfer model based on the field environment and material property data, and extracts infrared image data. A convolutional neural network is then used to detect and identify internal hole defects in the plate, obtaining the hole defect's center point position P and equivalent radius R in the infrared image. The error in the hole defect's center point position P is compared between the two. If the error is within a set threshold e1, the experiment continues; otherwise, the heat transfer model is corrected.

[0013] 3. Using a traditional edge detection algorithm to examine the infrared thermal image, the region T with a large boundary temperature gradient is identified. If the error in the hole edge region T exceeds the set threshold e2, the simulation model is rebuilt based on the extracted hole edge conditions and characteristics within the plate, and the experiment is repeated. This method, by integrating traditional edge detection algorithms with heat transfer and deep learning, avoids inaccurate hole edge detection caused by the low brightness contrast of thermal images in complex environments, unclear hole defect boundaries within the plate, and interference from noise areas in complex environments.

[0014] 4. This method can avoid interference from noise areas in complex environments, is suitable for edge detection of infrared defects of different shapes, and improves detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of the thermal wave edge detection method for internal hole defects in complex environment plates based on the fusion of heat transfer and deep learning. DETAILED DESCRIPTION

[0016] The present invention will be described in detail below with reference to the embodiments shown in the accompanying drawings.

[0017] The present invention provides a thermal wave detection method for hole defects inside plates in complex environments, and the process is as follows:

[0018] (1) This detection method and device integrates edge detection algorithms, heat transfer, and deep learning to achieve the purpose of defect detection. The heat transfer model uses the Python programming language and interacts with Ansys simulation software through the PyAnsys library to establish field environment and material property data. The deep learning model is composed of the Yolov5 visual recognition algorithm, and the edge detection algorithm uses the Canny edge detection algorithm.

[0019] (2) First, an initial heat transfer model is established. Then, the simulation model is reversely corrected through the detection results of deep learning and edge detection algorithms. The model and detection results are iteratively optimized to achieve the purpose of accurately detecting hole defects inside the plate.

[0020] (3) For the heat transfer model, the initial Python programming language interacts with the Ansys simulation software and the field environment through the PyAnsys library, the plate material property data is established, and then the heat transfer image data is extracted.

[0021] (4) For data transmission to the deep learning algorithm, a data set is first established based on the infrared thermal wave images collected on site. Then, the holes are detected and identified through a convolutional neural network to obtain the center point position P of the hole in the infrared image and the equivalent radius R of the hole.

[0022] (5) The heat transfer image data extracted from the finite element heat transfer model is compared with the results of the convolutional neural network detection and identification of the internal holes of the plate. If the error of the center point position P of the hole in the two is less than the threshold e1, the Canny operator detection and identification can be performed; otherwise, the hole center point position P and the hole radius R will be updated in reverse, and the heat transfer model will be re-established, and then repeated iterations will be performed for simulation optimization modeling.

[0023] (6) The Canny operator is then used to detect the original infrared thermal wave image and identify the area T with a large boundary temperature gradient. If the error of the hole edge area T is greater than the set threshold e2, the simulation model is re-established based on the extracted hole edge conditions and features inside the plate, and finally the edge detection result of the hole defect inside the plate is accurately obtained. Example

[0024] like Figure 1 As shown in the figure, it is a flow chart of the method and device for detecting internal hole defects in complex thermal wave plates based on the fusion of heat transfer and deep learning of the present invention. The implementation method includes the following steps:

[0025] (1) First, the thermal imaging field instrument collects data, transmits the field environment data and the plate material property parameter data through the Internet, establishes a finite element heat transfer simulation model, and extracts the simulation model image; at the same time, the collected infrared image data is transmitted to the convolutional neural network through the Internet. The convolutional neural network detects the holes inside the plate, identifies the hole area, and obtains its center point position P and equivalent radius R, avoiding the inaccurate hole edge detection caused by the interference of the noise area in a complex environment.

[0026] (2) Then compare the position error of the hole defect center point between the two. If it is less than the set threshold e1, the experiment can continue. Otherwise, the hole defect center point position P and the hole radius R will be corrected and updated in the reverse direction to re-establish the heat transfer model, and then the experiment will be carried out in sequence.

[0027] (3) The Canny operator is then used to simultaneously detect the hole edges in the infrared image data collected by the thermal imaging field instrument, identifying the area T with a large boundary temperature gradient. If the error in the hole edge area T is greater than the set threshold e2, the simulation model is rebuilt based on the extracted hole edge conditions and features inside the board, and the experiment is repeated. If the two features are consistent, the correction is not updated, avoiding the inaccurate hole edge detection caused by the low brightness contrast of the thermal image in a complex environment and the unclear hole boundary features. Finally, the edge detection results of the hole defects inside the wood board are obtained.

[0028] (4) This method can avoid the inaccurate edge detection of hole defects caused by low brightness contrast of thermal images, unclear hole boundaries, and interference from noise areas in complex environments through reverse correction and update design.

Claims

1. A thermal wave detection method for hole defects inside plates in complex environments, characterized by: The method integrates edge detection algorithms with heat transfer and deep learning to achieve detection. The heat transfer model is implemented using the Python programming language and interacts with Ansys simulation software via the PyAnsys library to establish material property data. The deep learning model is constructed using the Yolov5 visual recognition algorithm, and the Canny edge detection algorithm is used for edge detection. An initial heat transfer model is first established, and then the simulation model is reversely corrected using the detection results of the deep learning and edge detection algorithms to ultimately detect the edges of internal hole defects in the plate. The specific process is as follows: (1) Using Python programming language to interact with Ansys simulation software through the PyAnsys library and the field environment, the finite element heat transfer model is established based on the material property data, and the infrared image data is extracted; then the convolutional neural network is used to detect and identify the hole defects inside the plate, and the center point position P of the hole defect and the equivalent radius R of the hole defect in the infrared image are obtained; the center point position error of the hole defect is compared between the two. If it is less than the set threshold e1, the experiment can continue; otherwise, the center point position P of the hole defect and the hole defect radius R will be updated with reverse correction to re-establish the heat transfer model, and then the experiment will be carried out in sequence; (2) The Canny operator is used to simultaneously detect the hole edges of the infrared image data collected by the thermal imaging field instrument, and the area T with a large boundary temperature gradient is identified. If the error of the hole edge area T is greater than the set threshold e2, the simulation model is re-established based on the extracted hole edge conditions and features inside the plate, and the experiment is carried out in sequence; if the features of the two are consistent, no update correction is performed, thus avoiding the inaccurate hole edge detection caused by the low brightness contrast of the thermal image in a complex environment and the unclear hole boundary features; (3) By reverse updating the heat transfer simulation model, the center point position of the hole, the hole radius, and the temperature distribution at the hole edge are corrected, and finally the hole defect detection results inside the plate are accurately obtained.

Images