CN119086721B - Plastic product strength detection method and device based on non-contact measurement - Google Patents
Plastic product strength detection method and device based on non-contact measurement Download PDFInfo
- Publication number
- CN119086721B CN119086721B CN202411587742.9A CN202411587742A CN119086721B CN 119086721 B CN119086721 B CN 119086721B CN 202411587742 A CN202411587742 A CN 202411587742A CN 119086721 B CN119086721 B CN 119086721B
- Authority
- CN
- China
- Prior art keywords
- detection
- target
- area
- segmentation
- ultrasonic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 254
- 238000005259 measurement Methods 0.000 title claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims description 42
- 230000008859 change Effects 0.000 claims description 40
- 239000000463 material Substances 0.000 claims description 24
- 230000003213 activating effect Effects 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 230000007547 defect Effects 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000007847 structural defect Effects 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 238000012360 testing method Methods 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000000877 morphologic effect Effects 0.000 abstract 1
- 238000013461 design Methods 0.000 description 5
- 230000004913 activation Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000009864 tensile test Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
- F03D17/001—Inspection
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
- F03D17/005—Monitoring or testing of wind motors, e.g. diagnostics using computation methods, e.g. neural networks
- F03D17/006—Estimation methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
- G01N29/07—Analysing solids by measuring propagation velocity or propagation time of acoustic waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4409—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by comparison
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/01—Indexing codes associated with the measuring variable
- G01N2291/011—Velocity or travel time
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/028—Material parameters
- G01N2291/02827—Elastic parameters, strength or force
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
- G06T2207/10136—3D ultrasound image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Sustainable Energy (AREA)
- Sustainable Development (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
本发明公开了基于非接触式测量的塑料制品强度检测方法及装置，涉及风电机组监测技术领域，所述方法包括：扫描目标检测物并构建其三维模型，然后按照厚度和形状变化进行目标分割。分析分割结果的面积占比和形态连续关系，确定检测方向和顺序。激活检测模块进行超声波检测，收集并分析检测超声波的波形和传播速度，建立波形和传播速度与分割区域的映射关系。根据数据列表进行波形对齐比对，获得拟合偏差信息。根据拟合偏差信息确定目标检测物的硬度检测结果，并基于三维模型对偏差位置进行定位反馈。解决了检测效率低，检测成本高的技术问题，实现降低检测成本、提高检测效率的技术效果。
The present invention discloses a plastic product strength detection method and device based on non-contact measurement, which relates to the technical field of wind turbine monitoring. The method comprises: scanning a target detection object and constructing a three-dimensional model thereof, and then segmenting the target according to thickness and shape changes. The area proportion and morphological continuity relationship of the segmentation result are analyzed to determine the detection direction and sequence. The detection module is activated to perform ultrasonic detection, and the waveform and propagation speed of the detection ultrasonic wave are collected and analyzed to establish a mapping relationship between the waveform and the propagation speed and the segmented area. Waveform alignment and comparison are performed according to a data list to obtain fitting deviation information. The hardness test result of the target detection object is determined according to the fitting deviation information, and the deviation position is positioned and fed back based on the three-dimensional model. The technical problems of low detection efficiency and high detection cost are solved, and the technical effect of reducing detection cost and improving detection efficiency is achieved.
Description
Technical Field
The invention relates to the technical field of wind turbine generator monitoring, in particular to a plastic product strength detection method and device based on non-contact measurement.
Background
Non-contact measurement techniques are widely used in many fields, and optical, electromagnetic or acoustic techniques are commonly used to remotely measure physical or chemical properties of objects.
Conventional methods for strength testing of plastic articles mainly include tensile testing, bending testing, compression testing, and the like. The existing contact method may cause damage to the sample, and the operation process is complex, and needs to be operated by a professional. The method has the technical problems of low detection efficiency and high detection cost.
Disclosure of Invention
The invention provides a method and a device for detecting the strength of a plastic product based on non-contact measurement, which are used for solving the technical problems of low detection efficiency and high detection cost in the prior art and realizing the technical effects of reducing the detection cost and improving the detection efficiency.
In a first aspect, the present invention provides a method for detecting strength of a plastic article based on non-contact measurement, wherein the method comprises:
scanning a target detection object, constructing a three-dimensional model of the target detection object, and performing target segmentation according to thickness distribution and shape change based on the three-dimensional model;
Analyzing the area occupation ratio and the form continuous relation according to the target segmentation result, and configuring the detection direction and the detection sequence of the segmentation areas;
Activating a detection module based on the detection direction and the detection sequence of the divided areas, performing ultrasonic detection on the divided areas, and collecting detection ultrasonic waves;
analyzing the waveform and the propagation speed of the detected ultrasonic wave to obtain waveform change characteristics and the propagation speed of the ultrasonic wave;
Establishing a mapping relation between the segmentation areas and the waveform change characteristics and the ultrasonic wave propagation speed, constructing a data list, performing waveform alignment comparison according to the data list, and performing differential matching fitting to obtain fitting deviation information;
And determining a hardness detection result of the target detection object based on the fitting deviation information, and carrying out positioning feedback on the deviation position based on the three-dimensional model.
In the method, the non-contact hardness detection of the target detection object is realized by combining the three-dimensional model construction and the ultrasonic detection technology. The accurate acquisition and reliability assessment of the hardness detection result are realized by utilizing waveform alignment comparison and differential matching fitting. Based on the positioning feedback of the three-dimensional model, the position of the abnormal hardness can be accurately positioned, and an important reference is provided for subsequent processing. And the precision and reliability of hardness detection are improved by comprehensively utilizing various technologies such as three-dimensional model construction, ultrasonic detection, waveform analysis and the like.
In a second aspect, the present invention also provides a plastic product strength detection device based on non-contact measurement, wherein the device comprises:
the model segmentation module is used for scanning a target detection object, constructing a three-dimensional model of the target detection object, and carrying out target segmentation according to thickness distribution and shape change based on the three-dimensional model;
The detection configuration module is used for analyzing the area occupation ratio and the form continuous relation according to the target segmentation result and configuring the detection direction and the detection sequence of the segmentation areas;
the detection acquisition module is used for activating the detection module based on the detection direction and the detection sequence of the divided areas, performing ultrasonic detection on the divided areas and collecting detection ultrasonic waves;
the autonomous analysis module is used for analyzing the waveform and the propagation speed of the detected ultrasonic wave to obtain waveform change characteristics and the propagation speed of the ultrasonic wave;
the deviation matching module is used for establishing a mapping relation between the segmentation area and the waveform change characteristics and the ultrasonic wave propagation speed, constructing a data list, carrying out waveform alignment comparison according to the data list, and carrying out differential matching fitting to obtain fitting deviation information;
And the deviation feedback module is used for determining the hardness detection result of the target detection object based on the fitting deviation information and carrying out positioning feedback on the deviation position based on the three-dimensional model.
The invention discloses a method and a device for detecting the strength of a plastic product based on non-contact measurement. And analyzing the area occupation ratio and the form continuous relation of the segmentation result, and determining the detection direction and sequence. And activating the detection module to detect ultrasonic waves, collecting and analyzing the waveform and the propagation speed of the detected ultrasonic waves, and establishing a mapping relation between the waveform and the propagation speed and the segmentation areas. And carrying out waveform alignment comparison according to the data list to obtain fitting deviation information. And determining the hardness detection result of the target detection object according to the fitting deviation information, and carrying out positioning feedback on the deviation position based on the three-dimensional model. The method and the device for detecting the strength of the plastic product based on non-contact measurement solve the technical problems of low detection efficiency and high detection cost, and realize the technical effects of reducing the detection cost and improving the detection efficiency.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting strength of a plastic product based on non-contact measurement;
Fig. 2 is a schematic structural diagram of a plastic product strength detection device based on non-contact measurement.
Reference numerals illustrate a model segmentation module 11, a detection configuration module 12, a detection acquisition module 13, an autonomous analysis module 14, a deviation matching module 15 and a deviation feedback module 16.
Detailed Description
The technical scheme provided by the embodiment of the invention aims to solve the technical problems of low detection efficiency and high detection cost in the prior art, and adopts the following overall thought:
First, a target detection object is scanned, a three-dimensional model of the target detection object is constructed, and target segmentation is performed according to thickness distribution and shape change. Then, the area ratio and the morphology are analyzed in a continuous relation based on the division result, and the detection direction and the sequence of the division regions are arranged. Then, based on the configured detection direction and sequence, the detection module is activated to perform ultrasonic detection on the divided regions, and the detection ultrasonic waves are collected. Next, the detected ultrasonic wave is subjected to waveform and propagation velocity analysis, and waveform change characteristics and ultrasonic wave propagation velocity are obtained. And then, establishing a mapping relation between the segmentation area and the waveform change characteristics and the ultrasonic propagation speed, constructing a data list, carrying out waveform alignment comparison according to the data list, and carrying out differential matching fitting to obtain fitting deviation information. And finally, determining the hardness detection result of the target detection object based on fitting deviation information, and carrying out positioning feedback on the deviation position according to the three-dimensional model.
The foregoing aspects will be better understood by reference to the following detailed description of the invention taken in conjunction with the accompanying drawings and detailed description. It should be apparent that the described embodiments are only some embodiments of the present invention and not all embodiments of the present invention, and it should be understood that the present invention is not limited by the exemplary embodiments used only to explain the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention. It should be noted that, for convenience of description, only some, but not all of the drawings related to the present invention are shown.
Example 1
Fig. 1 is a schematic flow chart of a method for detecting strength of a plastic product based on non-contact measurement, which comprises the following steps:
scanning a target detection object, constructing a three-dimensional model of the target detection object, and performing target segmentation according to thickness distribution and shape change based on the three-dimensional model;
The target detection object refers to a target plastic product to be subjected to intensity detection. Alternatively, a three-dimensional model of the target detection object is scanned and constructed, and first, design data of the target detection object, including a design drawing, a CAD model, and the like, is obtained through interaction with a designer or a related department. And then analyzing the acquired design data to extract key geometric information and parameters. And then, scanning the target detection object by using a three-dimensional scanning device (such as a laser scanner) according to the analyzed geometric information and parameters to generate three-dimensional point cloud data. And finally, combining design data of the target detection object with three-dimensional point cloud data, and generating a three-dimensional model of the target detection object through three-dimensional modeling software or algorithm.
Through the steps, the generation process from design data to three-dimensional point cloud data can be realized, and basic data is provided for the subsequent three-dimensional model construction.
In some embodiments, object segmentation in terms of thickness distribution, shape variation based on the three-dimensional model includes:
carrying out plane image recognition according to the three-dimensional model, and determining a shape change node;
determining graph nodes based on the plane images, layering and superposing the plane images, and determining thickness difference nodes;
And dividing the target object according to the shape change node and the thickness difference node to obtain a target division result, wherein the target division result comprises a plurality of division areas, and the shape and the orientation of each division area are the same and the thickness is consistent.
Specifically, before performing planar image recognition according to the three-dimensional model, first, a projection or rendering technique projects three-dimensional information onto a two-dimensional plane, and then converts the three-dimensional model into a planar image.
Alternatively, the generated planar image is processed using image recognition or computer vision techniques to determine shape change nodes. Illustratively, edges in a planar image are identified by an edge detection algorithm, shapes in the image are described and matched using shape descriptors, features in the image are automatically extracted and identified using a deep learning model such as a Convolutional Neural Network (CNN), and shape change nodes are determined based on the features or abrupt points of the edges.
Optionally, the graph nodes are key points in the image, such as corner points, edge intersection points, and the like. The graph nodes are determined by a feature detection algorithm (such as Harris corner detection, SIFT, SURF and the like). And after determining the graph nodes, layering and superposing the plurality of plane images. Specifically, based on image registration and image fusion techniques, first, the graph nodes of two or more images are aligned so that planar images can be compared or combined under the same coordinate system. And then, accumulating and combining the registered images, thereby acquiring a fused image with thickness characteristics, and determining a thickness difference node.
The method comprises the steps of dividing a target object according to a shape change node and a thickness difference node, pre-dividing the target object by taking the shape change node and the thickness difference node as initial dividing points, and further refining the pre-dividing result based on the technologies of shape matching, shape alignment, shape regularization and the like, so that the shape and the thickness of each dividing region are identical in azimuth and consistent, the consistency of each dividing region in shape and azimuth is ensured, and a target dividing result is obtained. The target segmentation result comprises a plurality of segmentation areas, and the shape and the orientation of each segmentation area are the same and the thickness is consistent.
Analyzing the area occupation ratio and the form continuous relation according to the target segmentation result, and configuring the detection direction and the detection sequence of the segmentation areas;
in some embodiments, according to the target segmentation result, calculating the area occupation ratio of each segmentation area, and performing positive sequence arrangement according to the area occupation ratio;
extracting a segmentation area with the largest area occupation ratio as a starting area, and extending adjacent segmentation areas by taking the starting area as the center to determine continuous segmentation areas;
Determining the detection direction according to the size distribution and the extension scheme of the initial region, analyzing the spatial dimension position relation of the continuous segmented regions based on the detection direction, and screening segmented regions with the same spatial dimension for azimuth marking;
And based on the azimuth labeling, carrying out area proportion arrangement priority analysis on the labeled continuous segmented regions, determining the first priority of the area proportion of each continuous segmented region, taking the segmented region with the largest first priority as a second segmented region, carrying out continuous segmented region identification and determination of a third segmented region by taking the second segmented region as the center, and so on to obtain the detection directions and the detection sequences of all the segmented regions.
Alternatively, first, the number of pixels of each divided region is calculated to the areas of a plurality of divided regions, and then the area ratio thereof in the entire image is calculated. Then, a segmented region with the largest area occupation ratio is selected as a starting region, and then adjacent segmented regions are determined based on a spatial position relationship with the starting region as a center, so that continuous segmented regions are formed.
Optionally, the detection direction is determined according to the size distribution and extension scheme of the starting area. Includes calculating a centroid of the starting region and then determining an extension direction based on a location of the centroid and a shape of the region. The extending direction refers to the direction in which the shape of the initial region changes at the highest speed.
Further, based on the determined detection direction, the space dimension position relation analysis is carried out on the continuous divided areas, the areas with the same detection direction are determined, the azimuth marking is carried out on the divided areas with the same detection direction, and then the control track distance of detection discussion is reduced.
Optionally, based on the azimuth annotation, the area occupation ratio of the annotated continuous segmented regions is subjected to priority analysis, and the first priority of the area occupation ratio of each continuous segmented region is determined. Then taking the segmented area with the largest area occupation ratio and the first priority as a second segmented area, and taking the second segmented area as a center, iteratively identifying and determining the continuous segmented areas, and repeating the steps until all the segmented areas are determined in the detection direction and the detection sequence.
In some implementations, the obtaining the detection direction and the detection order of all the divided areas includes:
Based on the three-dimensional model and the target segmentation result, constructing a segmentation topological structure by taking the segmentation area as a node, and setting a topological connection direction according to the detection direction of the segmentation area;
adding the area ratio of each divided area to the node, and setting the area ratio as a node coefficient;
Taking the initial area as a center, taking the minimum node distance as a first classification characteristic, taking the detection direction consistency as a second classification characteristic, and constructing a classification decision tree to obtain a plurality of association chains;
and superposing the node coefficients in the plurality of association chains, determining the chain coefficient of each association chain, and determining the detection direction and the detection sequence of the segmented region by obtaining the node relationship with the maximum chain coefficient, wherein the node sequence is the detection sequence, and the topological connection direction is the detection direction.
Illustratively, the detection directions and the detection order of all the divided regions are obtained, first, each divided region is regarded as one node based on the three-dimensional model and the target division result, and the topological connection direction is set according to the spatial position relationship and the detection directions of the divided regions. Then, node energization is performed, and the area ratio of each divided region is added to the node, and is set as a node coefficient defining the area weight of the node based on the divided region. Then, the distance from each node to the initial region is calculated by using Euclidean distance or other distance measurement methods with the initial region as a central point, the distance is used as a first classification characteristic, then the consistency of the detection directions is used as a second classification characteristic, if the movement directions of the nodes on different layers are consistent, the nodes can be regarded as a group, then a classification decision tree is constructed by using the two characteristics, and the decision tree classifies the nodes into different categories according to the first classification characteristic and the second classification characteristic, so that the target segmentation is realized. The classification decision tree comprises a plurality of association chains, and nodes in each association chain have consistent feature categories.
Through the steps, the target segmentation based on the consistency of the starting area, the distance from the node to the starting area and the detection direction can be realized, and the nodes are classified into different categories by the classification decision tree, so that the effective target segmentation is realized.
Activating a detection module based on the detection direction and the detection sequence of the divided areas, performing ultrasonic detection on the divided areas, and collecting detection ultrasonic waves;
Specifically, after determining the detection direction and the detection sequence of the divided regions, firstly, an activation signal is sent or an activation function is called to start the ultrasonic detection module. Wherein the ultrasonic detection module comprises one or more groups of ultrasonic sensors for performing non-contact measurement.
Optionally, activating the detection module includes configuring or moving the ultrasonic sensor at a corresponding position based on the detection direction and the detection order of the divided regions, and defining a movement order and an activation order of the ultrasonic sensor in the ultrasonic detection module.
Further, after the detection module is activated, the detection module is activated to perform ultrasonic detection on the divided areas according to the detection direction and the detection sequence of the divided areas. The method comprises the steps of transmitting ultrasonic waves by using an ultrasonic detection module according to a certain path and speed and following a detection direction and a detection sequence, and receiving the reflected ultrasonic waves.
Alternatively, the detected ultrasonic waves are collected and converted into electrical signals, which are then collected using a data acquisition device and converted into a data format that can be further analyzed and processed. These signals contain information about the internal structure, density, shape, etc. of the target object.
Analyzing the waveform and the propagation speed of the detected ultrasonic wave to obtain waveform change characteristics and the propagation speed of the ultrasonic wave;
alternatively, the waveform and propagation velocity of the ultrasonic wave reflect the internal characteristics of the target object, and the waveform analysis is performed on the received ultrasonic signal. Including analyzing characteristics such as amplitude, frequency, waveform shape, etc. of the signal. And further acquires information about the internal structure of the target object, such as the presence of defects or foreign matter.
For example, the frequency component and time-frequency characteristic of the ultrasonic wave are analyzed by fourier transform (Fourier Transform) or wavelet transform (Wavelet Transform), and the waveform and propagation velocity analysis of the detected ultrasonic wave are performed. Meanwhile, the waveform change characteristics are obtained by comparing parameters such as peak value, valley value, period, amplitude and the like of the ultrasonic wave.
Illustratively, the propagation time and path length of the ultrasonic signal are obtained, and the propagation speed of the ultrasonic wave in the target object is calculated. Wherein the propagation velocity is influenced by the target object material and structure and can thus be used to identify regions of different materials or structures. In particular, in materials with higher density and modulus of elasticity, the propagation velocity is faster.
By acquiring the waveform change characteristics and the ultrasonic wave propagation speed, more detailed information about the internal structure and properties of the target detection object is obtained, and the state and characteristics of the target object can be known more accurately.
Establishing a mapping relation between the segmentation areas and the waveform change characteristics and the ultrasonic wave propagation speed, constructing a data list, performing waveform alignment comparison according to the data list, and performing differential matching fitting to obtain fitting deviation information;
Optionally, based on the corresponding relation between the detection direction and the detection sequence and the detected ultrasonic wave, and the corresponding relation between the detected ultrasonic wave and the waveform change characteristic and the ultrasonic wave propagation speed, the waveform change characteristic and the propagation speed data of each divided area are associated with the corresponding divided area, and then the position information, the waveform change characteristic and the ultrasonic wave propagation speed of each area are recorded in a data list to construct the data list. Wherein the data list is a structured data set. For subsequent analysis and prediction.
In some embodiments, performing waveform alignment according to the data list, performing differential matching fitting, and obtaining fitting deviation information, including:
Acquiring waveforms and propagation speeds of all the divided areas based on the divided areas;
Carrying out alignment comparison on the waveforms and the propagation speeds of the divided areas to determine the comparison difference value of the divided areas;
extracting the thickness and the shape of each divided area, and determining a target difference value;
And fitting by utilizing the comparison difference value and the target difference value to obtain fitting deviation information.
Optionally, firstly, the interactive data list is used for calling the corresponding waveforms and propagation speeds according to the divided areas, and then, the waveforms and the propagation speeds of the divided areas are aligned and compared by calculating the similarity or the difference of the waveforms and the propagation speeds. Illustratively, the correlation coefficient, euclidean distance, manhattan distance and other measurement methods are used to calculate the difference degree of the waveform and the propagation speed, and the comparison difference value of each divided area is determined.
Optionally, extracting the thickness and shape of each divided region, and determining a target difference value, where the target difference value is a maximum difference value allowed under the quality control requirement of the divided region, and if the difference value of the target detection object is greater than the target difference value, indicating that the deviation of the target detection object is too large.
Optionally, the comparison difference value and the target difference value are used for fitting. The fitting is performed by means of linear regression, nonlinear regression, machine learning algorithms, etc., so that fitting deviation information is obtained. The fitting deviation information is the integral of the target difference values of a plurality of divided areas of the target detection object to the detection path.
In some implementations, extracting the thickness and shape of each of the segmented regions, and determining the target difference value includes:
Constructing a plurality of experimental samples according to the thickness and the shape of the detected object material, and performing ultrasonic detection experiments to obtain an experimental record data set, wherein the experimental record data set comprises the thickness, the shape information, the size information and corresponding ultrasonic signals of the material;
performing routine, reflection and diffraction waveform analysis and propagation velocity analysis on the ultrasonic signals to obtain ultrasonic characteristics, and adding the ultrasonic characteristics into the experimental record data set;
Training a neural network model based on the experimental record data set, performing ultrasonic signal difference relation recognition learning, and obtaining a difference analysis model, wherein the difference analysis model is used for recognizing the difference relation between the thickness and the shape of a material and ultrasonic signal parameters and outputting an ultrasonic difference value;
And inputting the difference values of the thickness and the shape of each divided region into the difference analysis model to obtain the target difference value.
Specifically, first, a plurality of experimental samples are constructed according to the thickness and shape of different materials, experimental measurement is performed, ultrasonic detection is performed on sample materials with known material thickness, shape information and size information, so that corresponding ultrasonic signals are obtained, and the association relation between the material thickness, the shape information and the size information and the corresponding ultrasonic signals is established and stored as an experimental record data set. The experimentally recorded dataset reflects the correspondence of various thicknesses and shapes of material that may occur to the ultrasonic signal. And then, constructing and training a neural network model based on the experimental record data set to learn the complex mapping relation between the acoustic wave signals and the thickness and shape of the materials, and obtaining a difference analysis model, wherein the difference analysis model takes the ultrasonic signals as input, and outputs ultrasonic difference values through end-to-end processing analysis.
By training the neural network model, complex difference relations can be automatically learned, so that the accuracy and the efficiency of detection are improved.
Optionally, the differential analysis model is automatically updated and optimized based on a preset update period to adapt to new data and conditions, ensuring long-term accuracy of the differential analysis.
In some implementations, fitting with the aligned difference value and the target difference value to obtain the fitting deviation information includes:
acquiring a detection direction difference distance of the divided areas based on the size and the detection direction of the divided areas;
acquiring an ultrasonic loss coefficient of the detection object material;
Determining an ultrasonic wave loss amount according to the detection direction difference distance and the ultrasonic wave loss coefficient;
and correcting the target difference value according to the ultrasonic wave loss.
Optionally, the comparison difference value and the target difference value are used for fitting to evaluate the accuracy and deviation of the model. First, based on the size and detection direction of the divided regions, the detection direction difference distance of the divided regions is acquired. The difference distance reflects the propagation difference of the ultrasonic wave in the detection direction. Then, based on the detection object material, an ultrasonic loss coefficient is extracted. The ultrasonic wave encounters resistance when passing through the material, resulting in energy loss, and the ultrasonic wave loss coefficient reflects the energy loss of the ultrasonic wave in the propagation process, and different materials have different ultrasonic wave loss coefficients. Further, an ultrasonic wave loss amount is determined based on the detection direction difference distance and the ultrasonic wave loss coefficient, and the ultrasonic wave loss amount is a product of the detection direction difference distance and the ultrasonic wave loss coefficient. The ultrasonic wave loss is used for correcting the target difference value so as to reduce the influence of propagation difference and improve the detection accuracy.
Optionally, correcting the target differential value based on the amount of ultrasonic loss includes adding the amount of ultrasonic loss to the target differential value.
And determining a hardness detection result of the target detection object based on the fitting deviation information, and carrying out positioning feedback on the deviation position based on the three-dimensional model.
Optionally, hardness discrimination of a plurality of positions of the target detection object is performed based on fitting deviation information of a plurality of divided regions, and a hardness detection result is obtained. Specifically, if the fitting deviation information is larger, it is indicated that the position of the target detection object corresponding to the fitting deviation information may have defects such as poor uniformity, structural defects, and unqualified density.
Alternatively, the location of the deviation based on the three-dimensional model may help the relevant technician understand the specific location where the deviation occurs. Specifically, fitting deviation information is mapped onto the three-dimensional model, and this region is marked on the three-dimensional model for corresponding feedback and adjustment.
In summary, the method for detecting the strength of the plastic product based on non-contact measurement provided by the invention has the following technical effects:
The method comprises the steps of scanning a target detection object, constructing a three-dimensional model of the target detection object, carrying out target segmentation according to thickness distribution and shape change based on the three-dimensional model, carrying out area ratio and form continuous relation analysis according to a target segmentation result, configuring detection directions and detection sequences of segmentation areas, carrying out ultrasonic detection on the segmentation areas based on the detection directions and the detection sequences of the segmentation areas, collecting detection ultrasonic waves, carrying out waveform and propagation speed analysis on the detection ultrasonic waves to obtain waveform change characteristics and ultrasonic propagation speeds, establishing a mapping relation between the segmentation areas, the waveform change characteristics and the ultrasonic propagation speeds, constructing a data list, carrying out waveform alignment comparison according to the data list, carrying out differential matching fitting to obtain fitting deviation information, determining a hardness detection result of the target detection object based on the fitting deviation information, and carrying out positioning feedback on a deviation position based on the three-dimensional model. The technical problems of low detection efficiency and high detection cost are solved, and the technical effects of reducing the detection cost and improving the detection efficiency are realized.
Example two
Fig. 2 is a schematic structural view of the plastic product strength detecting device based on non-contact measurement. For example, the flow chart of the method for detecting the strength of the plastic product based on non-contact measurement in fig. 1 can be realized by the structure shown in fig. 2.
Based on the same conception as the plastic product strength detection method based on the non-contact measurement in the embodiment, the plastic product strength detection device based on the non-contact measurement further provided by the invention comprises:
The model segmentation module 11 is used for scanning a target detection object, constructing a three-dimensional model of the target detection object, and carrying out target segmentation according to thickness distribution and shape change based on the three-dimensional model;
the detection configuration module 12 is used for analyzing the area occupation ratio and the form continuous relation according to the target segmentation result and configuring the detection direction and the detection sequence of the segmentation areas;
the detection acquisition module 13 is used for activating the detection module based on the detection direction and the detection sequence of the divided areas, performing ultrasonic detection on the divided areas and collecting detection ultrasonic waves;
The autonomous analysis module 14 is used for analyzing the waveform and the propagation speed of the detected ultrasonic wave to obtain the waveform change characteristics and the ultrasonic wave propagation speed;
The deviation matching module 15 is configured to establish a mapping relationship between the segmentation area and the waveform change feature, and between the segmentation area and the ultrasonic propagation speed, construct a data list, perform waveform alignment comparison according to the data list, and perform differential matching fitting to obtain fitting deviation information;
And the deviation feedback module 16 is used for determining the hardness detection result of the target detection object based on the fitting deviation information and carrying out positioning feedback on the deviation position based on the three-dimensional model.
The model segmentation module 11 includes:
the plane image recognition unit is used for carrying out plane image recognition according to the three-dimensional model and determining a shape change node;
The layering and overlapping unit is used for determining graph nodes based on the plane images, layering and overlapping the plane images and determining thickness difference nodes;
And the target object segmentation unit is used for carrying out target object segmentation according to the shape change node and the thickness difference node to obtain a target segmentation result, wherein the target segmentation result comprises a plurality of segmentation areas, and the shape and the orientation of each segmentation area are the same and the thickness is consistent.
Further, the detection configuration module 12 includes:
the positive ordering and arranging unit is used for calculating the area occupation ratio of each divided area according to the target dividing result and carrying out positive ordering and arranging according to the area occupation ratio;
the region extension unit is used for extracting a segmented region with the largest area occupation ratio, taking the segmented region as a starting region, extending adjacent segmented regions by taking the starting region as a center, and determining continuous segmented regions;
the position relation analysis unit is used for determining the detection direction according to the size distribution and the extension scheme of the initial region, carrying out space dimension position relation analysis on the continuous segmented region based on the detection direction, and screening segmented regions with the same space dimension for azimuth marking;
And the priority analysis unit is used for carrying out area proportion arrangement priority analysis on the marked continuous divided areas based on the azimuth mark, determining the area proportion first priority of each continuous divided area, taking the divided area with the largest first priority as a second divided area, carrying out continuous divided area identification and determination of a third divided area by taking the second divided area as a center, and the like, so as to obtain the detection directions and the detection sequences of all the divided areas.
In some implementations, the detection configuration module 12 includes:
The segmentation topological unit is used for constructing a segmentation topological structure by taking the segmentation area as a node based on the three-dimensional model and the target segmentation result, and setting a topological connection direction according to the detection direction of the segmentation area;
A node coefficient unit configured to add an area ratio of each divided area to the node, and set the node coefficient;
the classification decision unit is used for constructing a classification decision tree by taking the initial region as a center, taking the minimum node distance as a first classification characteristic and the consistency of the detection direction as a second classification characteristic, and obtaining a plurality of association chains;
and the coefficient superposition unit is used for superposing the node coefficients in the plurality of associated chains to determine the chain coefficients of each relation chain, and obtaining the node relation with the maximum chain coefficient to determine the detection direction and the detection sequence of the segmented region, wherein the node sequence is the detection sequence, and the topological connection direction is the detection direction.
Further, the offset matching module 15 includes:
a data extraction unit, configured to obtain waveforms and propagation speeds of the respective divided regions based on the divided regions;
The alignment comparison unit is used for carrying out alignment comparison on the waveforms and the propagation speeds of the divided areas and determining the comparison difference value of the divided areas;
The difference value unit is used for extracting the thickness and the shape of each divided area and determining a target difference value;
and the deviation fitting unit is used for fitting by utilizing the comparison difference value and the target difference value to obtain fitting deviation information.
In some implementations, the difference value unit in the offset matching module 15 includes:
The sample detection unit is used for constructing a plurality of experimental samples according to the thickness and the shape of the detected object material, carrying out ultrasonic detection experiments and obtaining an experimental record data set, wherein the experimental record data set comprises the thickness, the shape information, the size information and the corresponding ultrasonic signals of the material;
The characteristic analysis unit is used for carrying out routine, reflection and diffraction waveform analysis and propagation speed analysis on the ultrasonic signals to obtain ultrasonic characteristics, and adding the ultrasonic characteristics into the experimental record data set;
The relation recognition learning unit is used for training the neural network model based on the experimental record data set, carrying out ultrasonic signal difference relation recognition learning, and obtaining a difference analysis model, wherein the difference analysis model is used for recognizing the difference relation between the thickness and the shape of the material and ultrasonic signal parameters and outputting an ultrasonic difference value;
and the difference analysis unit is used for inputting the difference value of the thickness and the shape of each divided area into the difference analysis model to obtain the target difference value.
In some implementations, the bias fitting unit in bias matching module 15 includes:
the difference distance unit is used for acquiring the difference distance of the detection direction of the divided areas based on the size and the detection direction of the divided areas;
the loss coefficient unit is used for acquiring an ultrasonic loss coefficient of the detection object material;
A loss amount calculation unit for determining an ultrasonic loss amount according to the detection direction difference distance and the ultrasonic loss coefficient;
and the difference value correction unit is used for correcting the target difference value according to the ultrasonic loss.
It should be understood that the embodiments mentioned in this specification focus on the differences from other embodiments, and the specific embodiment in the first embodiment is equally applicable to the plastic product strength detection device based on non-contact measurement described in the second embodiment, and is not further developed herein for brevity of description.
It is to be understood that both the foregoing description and the embodiments of the present invention enable one skilled in the art to utilize the present invention. Meanwhile, the invention is not limited to the above-mentioned embodiments, and it should be understood that those skilled in the art may still modify the technical solutions described in the above-mentioned embodiments or substitute some technical features thereof, and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the invention, and all the modifications or substitutions should be included in the protection scope of the invention.
Claims (7)
1. A method for detecting strength of a plastic product based on non-contact measurement, the method comprising:
scanning a target detection object, constructing a three-dimensional model of the target detection object, and performing target segmentation according to thickness distribution and shape change based on the three-dimensional model;
Analyzing the area occupation ratio and the form continuous relation according to the target segmentation result, and configuring the detection direction and the detection sequence of the segmentation areas;
Activating a detection module based on the detection direction and the detection sequence of the divided areas, performing ultrasonic detection on the divided areas, and collecting detection ultrasonic waves;
analyzing the waveform and the propagation speed of the detected ultrasonic wave to obtain waveform change characteristics and the propagation speed of the ultrasonic wave;
Establishing a mapping relation between the segmentation areas and the waveform change characteristics and the ultrasonic wave propagation speed, constructing a data list, performing waveform alignment comparison according to the data list, and performing differential matching fitting to obtain fitting deviation information;
Judging the intensities of a plurality of positions of the target detection object based on the fitting deviation information, determining the intensity detection result of the target detection object, if the fitting deviation information is large, indicating that the positions of the target detection object corresponding to the fitting deviation information have defects of poor uniformity, structural defects and unqualified density, and carrying out positioning feedback on the deviation positions based on the three-dimensional model;
Performing waveform alignment comparison according to the data list, performing differential matching fitting, and obtaining fitting deviation information, wherein the method comprises the following steps:
Acquiring waveforms and propagation speeds of all the divided areas based on the divided areas;
Carrying out alignment comparison on the waveforms and the propagation speeds of the divided areas to determine the comparison difference value of the divided areas;
extracting the thickness and the shape of each divided area, and determining a target difference value;
And fitting by utilizing the comparison difference value and the target difference value to obtain fitting deviation information.
2. The method of claim 1, wherein performing object segmentation in terms of thickness distribution, shape change based on the three-dimensional model, comprises:
carrying out plane image recognition according to the three-dimensional model, and determining a shape change node;
determining graph nodes based on the plane images, layering and superposing the plane images, and determining thickness difference nodes;
And dividing the target object according to the shape change node and the thickness difference node to obtain a target division result, wherein the target division result comprises a plurality of division areas, and the shape and the orientation of each division area are the same and the thickness is consistent.
3. The method of claim 2, wherein the area ratio and morphology continuous relation analysis is performed based on the target division result, and the configuration of the detection direction and the detection order of the divided regions includes:
Calculating the area occupation ratio of each divided area according to the target dividing result, and carrying out positive sequence arrangement according to the area occupation ratio;
extracting a segmentation area with the largest area occupation ratio as a starting area, and extending adjacent segmentation areas by taking the starting area as the center to determine continuous segmentation areas;
Determining the detection direction according to the size distribution and the extension scheme of the initial region, analyzing the spatial dimension position relation of the continuous segmented regions based on the detection direction, and screening segmented regions with the same spatial dimension for azimuth marking;
And based on the azimuth labeling, carrying out area proportion arrangement priority analysis on the labeled continuous segmented regions, determining the first priority of the area proportion of each continuous segmented region, taking the segmented region with the largest first priority as a second segmented region, carrying out continuous segmented region identification and determination of a third segmented region by taking the second segmented region as the center, and so on to obtain the detection directions and the detection sequences of all the segmented regions.
4. A method according to claim 3, wherein the obtaining the detection direction and the detection order of all the divided regions comprises:
Based on the three-dimensional model and the target segmentation result, constructing a segmentation topological structure by taking the segmentation area as a node, and setting a topological connection direction according to the detection direction of the segmentation area;
adding the area ratio of each divided area to the node, and setting the area ratio as a node coefficient;
Taking the initial area as a center, taking the minimum node distance as a first classification characteristic, taking the detection direction consistency as a second classification characteristic, and constructing a classification decision tree to obtain a plurality of association chains;
and superposing the node coefficients in the plurality of association chains, determining the chain coefficient of each association chain, and determining the detection direction and the detection sequence of the segmented region by obtaining the node relationship with the maximum chain coefficient, wherein the node sequence is the detection sequence, and the topological connection direction is the detection direction.
5. The method of claim 1, wherein extracting the thickness, shape of each segmented region, determining a target variance value, comprises:
Constructing a plurality of experimental samples according to the thickness and the shape of the detected object material, and performing ultrasonic detection experiments to obtain an experimental record data set, wherein the experimental record data set comprises the thickness, the shape information, the size information and corresponding ultrasonic signals of the material;
performing routine, reflection and diffraction waveform analysis and propagation velocity analysis on the ultrasonic signals to obtain ultrasonic characteristics, and adding the ultrasonic characteristics into the experimental record data set;
Training a neural network model based on the experimental record data set, performing ultrasonic signal difference relation recognition learning, and obtaining a difference analysis model, wherein the difference analysis model is used for recognizing the difference relation between the thickness and the shape of a material and ultrasonic signal parameters and outputting an ultrasonic difference value;
And inputting the difference values of the thickness and the shape of each divided region into the difference analysis model to obtain the target difference value.
6. The method of claim 5, wherein fitting the target variance value with the aligned variance value to obtain the fitting variance information comprises:
acquiring a detection direction difference distance of the divided areas based on the size and the detection direction of the divided areas;
acquiring an ultrasonic loss coefficient of the detection object material;
Determining an ultrasonic wave loss amount according to the detection direction difference distance and the ultrasonic wave loss coefficient;
and correcting the target difference value according to the ultrasonic wave loss.
7. Plastic product strength detection device based on non-contact measurement, characterized in that the device comprises:
the model segmentation module is used for scanning a target detection object, constructing a three-dimensional model of the target detection object, and carrying out target segmentation according to thickness distribution and shape change based on the three-dimensional model;
The detection configuration module is used for analyzing the area occupation ratio and the form continuous relation according to the target segmentation result and configuring the detection direction and the detection sequence of the segmentation areas;
the detection acquisition module is used for activating the detection module based on the detection direction and the detection sequence of the divided areas, performing ultrasonic detection on the divided areas and collecting detection ultrasonic waves;
the autonomous analysis module is used for analyzing the waveform and the propagation speed of the detected ultrasonic wave to obtain waveform change characteristics and the propagation speed of the ultrasonic wave;
the deviation matching module is used for establishing a mapping relation between the segmentation area and the waveform change characteristics and the ultrasonic wave propagation speed, constructing a data list, carrying out waveform alignment comparison according to the data list, and carrying out differential matching fitting to obtain fitting deviation information;
The deviation feedback module is used for judging the intensities of a plurality of positions of the target detection object based on the fitting deviation information, determining the intensity detection result of the target detection object, if the fitting deviation information is large, indicating that the positions of the target detection object corresponding to the fitting deviation information have defects of poor uniformity, structural defects and unqualified density, and carrying out positioning feedback on the deviation positions based on the three-dimensional model;
the deviation matching module comprises:
a data extraction unit, configured to obtain waveforms and propagation speeds of the respective divided regions based on the divided regions;
The alignment comparison unit is used for carrying out alignment comparison on the waveforms and the propagation speeds of the divided areas and determining the comparison difference value of the divided areas;
The difference value unit is used for extracting the thickness and the shape of each divided area and determining a target difference value;
and the deviation fitting unit is used for fitting by utilizing the comparison difference value and the target difference value to obtain fitting deviation information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411587742.9A CN119086721B (en) | 2024-11-08 | 2024-11-08 | Plastic product strength detection method and device based on non-contact measurement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411587742.9A CN119086721B (en) | 2024-11-08 | 2024-11-08 | Plastic product strength detection method and device based on non-contact measurement |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119086721A CN119086721A (en) | 2024-12-06 |
| CN119086721B true CN119086721B (en) | 2025-03-14 |
Family
ID=93662506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411587742.9A Active CN119086721B (en) | 2024-11-08 | 2024-11-08 | Plastic product strength detection method and device based on non-contact measurement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119086721B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119310184B (en) * | 2024-12-19 | 2025-03-18 | 吉林省誉能科技有限公司 | Method for testing crack resistance and creep resistance of lightweight foam concrete |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105259252A (en) * | 2015-10-15 | 2016-01-20 | 浙江大学 | Method for automatically identifying defect type of polyethylene electrofusion joint through ultrasonic phased array inspection |
| CN106680375A (en) * | 2016-11-25 | 2017-05-17 | 中国商用飞机有限责任公司 | Air-coupled ultrasonic testing method for determining elastic modulus of material |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9989502B2 (en) * | 2014-10-14 | 2018-06-05 | UT Comp Inc. | System and method for analysis of fibre reinforced composites |
| CN110220917B (en) * | 2019-06-11 | 2021-09-07 | 江苏农林职业技术学院 | Crown cap surface defect online detection method based on image processing |
| CN116030039A (en) * | 2023-02-20 | 2023-04-28 | 安徽工业大学 | A method for detecting internal defects of plastic-encapsulated chips combined with deep learning |
| CN117011829A (en) * | 2023-08-04 | 2023-11-07 | 内蒙古工业大学 | Obstacle detection method based on geometric orbit segmentation fitting algorithm |
| CN116953196B (en) * | 2023-09-20 | 2023-12-05 | 上海飞挺管业制造有限公司 | Defect detection and safety state assessment method for steel tee joint |
| CN117269333A (en) * | 2023-09-26 | 2023-12-22 | 四川畅向乐裕科技有限公司 | OLED device defect prediction method |
| CN118294533A (en) * | 2024-05-07 | 2024-07-05 | 广东珈源检测有限公司 | Quality detection method for concrete member and computer equipment |
-
2024
- 2024-11-08 CN CN202411587742.9A patent/CN119086721B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105259252A (en) * | 2015-10-15 | 2016-01-20 | 浙江大学 | Method for automatically identifying defect type of polyethylene electrofusion joint through ultrasonic phased array inspection |
| CN106680375A (en) * | 2016-11-25 | 2017-05-17 | 中国商用飞机有限责任公司 | Air-coupled ultrasonic testing method for determining elastic modulus of material |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119086721A (en) | 2024-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Automatic pavement crack detection by multi-scale image fusion | |
| CN101980250B (en) | Method for identifying target based on dimension reduction local feature descriptor and hidden conditional random field | |
| KR20200137219A (en) | Method and apparatus for wafer defect pattern detection based on unsupervised learning | |
| CN119086721B (en) | Plastic product strength detection method and device based on non-contact measurement | |
| Dong et al. | A random forest-based automatic inspection system for aerospace welds in X-ray images | |
| Geetha et al. | Fast identification of concrete cracks using 1D deep learning and explainable artificial intelligence-based analysis | |
| D'Angelo et al. | Shape-based defect classification for non destructive testing | |
| CN117541483B (en) | Structural performance evaluation method and system for diffusion plate | |
| CN109270079A (en) | A kind of Surface Flaw accurate detecting method based on point cloud model | |
| CN118334015B (en) | Defect recognition method, system, equipment and medium based on visual image | |
| Dai et al. | Aircraft seam feature extraction from 3D raw point cloud via hierarchical multi-structure fitting | |
| CN111693945A (en) | Method and system for identifying modulation mode between pulses, computer equipment and storage medium | |
| KR101782364B1 (en) | Vision inspection method based on learning data | |
| Xu et al. | Wood broken defect detection with laser profilometer based on Bi-LSTM network | |
| Ghamisi et al. | Anomaly detection in automated fibre placement: Learning with data limitations | |
| Ekambaram et al. | Identification of defects in casting products by using a convolutional neural network | |
| CN116735723A (en) | Rail damage ultrasonic positioning and identifying system | |
| Pozzer et al. | Enhancing concrete defect segmentation using multimodal data and Siamese Neural Networks | |
| Wei et al. | Feature Extraction and Retrieval of Ecommerce Product Images Based on Image Processing. | |
| Guldur et al. | Automated classification of detected surface damage from point clouds with supervised learning | |
| Wang et al. | Similarity evaluation of 3D surface topography measurements | |
| CN116519808A (en) | Rail damage ultrasonic positioning identification method and computer readable storage medium | |
| CN116818891A (en) | Ultrasonic defect detection and classification system using machine learning | |
| Konovalenko et al. | Using fuzzy sets to estimate the geometric parameters of surface damage | |
| Saeed et al. | A novel heuristic approach to detect induced forming defects using point cloud scans |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |