CN117147699A - Medical non-woven fabric detection method and system - Google Patents
Medical non-woven fabric detection method and system Download PDFInfo
- Publication number
- CN117147699A CN117147699A CN202311421350.0A CN202311421350A CN117147699A CN 117147699 A CN117147699 A CN 117147699A CN 202311421350 A CN202311421350 A CN 202311421350A CN 117147699 A CN117147699 A CN 117147699A
- Authority
- CN
- China
- Prior art keywords
- coordinates
- result
- woven fabric
- acquisition
- detection
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 168
- 239000004745 nonwoven fabric Substances 0.000 title claims abstract description 130
- 230000002159 abnormal effect Effects 0.000 claims abstract description 97
- 230000033001 locomotion Effects 0.000 claims abstract description 62
- 238000013507 mapping Methods 0.000 claims abstract description 39
- 230000007547 defect Effects 0.000 claims description 55
- 238000000034 method Methods 0.000 claims description 45
- 230000005856 abnormality Effects 0.000 claims description 33
- 238000012545 processing Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 8
- 230000032669 eclosion Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 13
- 230000008859 change Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000002592 echocardiography Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000002427 irreversible effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000011179 visual inspection 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
- 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
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
- G01N21/898—Irregularities in textured or patterned surfaces, e.g. textiles, wood
- G01N21/8983—Irregularities in textured or patterned surfaces, e.g. textiles, wood for testing textile webs, i.e. woven material
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Chemical & Material Sciences (AREA)
- Textile Engineering (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Wood Science & Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The application provides a detection method and a detection system of medical non-woven fabrics, which relate to the technical field of non-woven fabric detection and comprise the following steps: configuring the curling tension of a non-woven fabric detection rack, executing non-woven fabric motion control, recording the motion speed, sequentially arranging an ultrasonic detection unit and a CCD sensor, recording arrangement position coordinates and acquisition coordinates, establishing node coordinate mapping, executing non-woven fabric detection through the ultrasonic detection unit, recording abnormal coordinates, determining an attention area, performing focusing acquisition through the CCD sensor, executing abnormal detection based on a focusing acquisition result, generating an abnormal detection result, associating the abnormal detection result with the attention area, and outputting the detection result of the non-woven fabric according to the association result. The application solves the technical problems that the traditional non-woven fabric detection method lacks accurate control of movement speed and position coordinates, and cannot efficiently realize comprehensive detection of the non-woven fabric and accurate positioning of abnormal areas.
Description
Technical Field
The application relates to the technical field of non-woven fabric detection, in particular to a detection method and system of medical non-woven fabric.
Background
The detection of medical nonwoven fabrics is one of the important tasks in the medical field, and nonwoven fabrics are widely used in the fields of medical instruments, operating room towels, operating gowns and the like, so that the assurance of the quality and the safety of the nonwoven fabrics is of great importance for medical work. The traditional medical non-woven fabric detection method generally depends on manual visual inspection or simple physical test, on one hand, the traditional method generally can only detect certain specific areas of the non-woven fabric, can not realize comprehensive detection of the whole non-woven fabric surface, and has the risk of missed detection; on the other hand, for the found abnormal region, the conventional method often lacks accurate positioning information, resulting in difficulties in subsequent processing and improvement.
Therefore, a more accurate and comprehensive detection method of the medical non-woven fabric is needed, and reliable detection and evaluation of quality and safety of the medical non-woven fabric are realized.
Disclosure of Invention
The application provides a detection method and a detection system for medical non-woven fabrics, and aims to solve the technical problems that the traditional non-woven fabric detection method lacks accurate control of movement speed and position coordinates, and cannot efficiently realize comprehensive detection of the non-woven fabrics and accurate positioning of abnormal areas.
In view of the above problems, the present application provides a method and a system for detecting a medical nonwoven fabric.
In a first aspect of the present disclosure, a method for detecting a medical nonwoven fabric is provided, the method comprising: configuring the curling tension of the non-woven fabric detection rack, executing non-woven fabric motion control, and recording the motion speed; sequentially arranging an ultrasonic detection unit and a CCD sensor, and recording arrangement position coordinates and acquisition coordinates, wherein the arrangement position coordinates and the acquisition coordinates are generated by constructing the same coordinate system; establishing node coordinate mapping of a detection result of the ultrasonic detection unit and a CCD sensor acquisition result according to the arrangement position coordinates, the acquisition coordinates and the movement speed; performing non-woven fabric detection through an ultrasonic detection unit, recording abnormal coordinates, determining an attention area based on the node coordinate mapping and the abnormal coordinates, and carrying out focusing acquisition on the attention area through the CCD sensor; performing abnormality detection based on a focus acquisition result, generating an abnormality detection result, and associating the abnormality detection result with the attention area; and outputting a detection result of the non-woven fabric according to the association result.
In another aspect of the disclosure, a system for detecting a medical nonwoven fabric is provided, the system being used in the above method, the system comprising: the motion control module is used for configuring the curling tension of the non-woven fabric detection rack, executing non-woven fabric motion control and recording the motion speed; the system comprises a coordinate acquisition module, a CCD sensor, a storage module and a storage module, wherein the coordinate acquisition module is used for sequentially arranging an ultrasonic detection unit and the CCD sensor, recording arrangement position coordinates and acquisition coordinates, and the arrangement position coordinates and the acquisition coordinates are generated by constructing the same coordinate system; the coordinate mapping module is used for establishing node coordinate mapping of the detection result of the ultrasonic detection unit and the acquisition result of the CCD sensor according to the arrangement position coordinates, the acquisition coordinates and the movement speed; the focusing acquisition module is used for executing non-woven fabric detection through the ultrasonic detection unit, recording abnormal coordinates, determining an attention area based on the node coordinate mapping and the abnormal coordinates, and carrying out focusing acquisition on the attention area through the CCD sensor; the association module is used for executing abnormality detection based on a focusing acquisition result, generating an abnormality detection result and associating the abnormality detection result with the attention area; and the result output module is used for outputting a detection result of the non-woven fabric according to the association result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
by configuring the curling tension of the non-woven fabric detection rack and executing non-woven fabric movement control, recording the movement speed, realizing accurate control of the non-woven fabric movement process and accurate recording of the speed, so as to ensure the accuracy and reliability of data acquisition and analysis in the subsequent steps; the ultrasonic detection unit and the CCD sensor are sequentially arranged, the arrangement position coordinates and the acquisition coordinates are recorded, the arrangement position coordinates and the acquisition coordinates are generated by constructing the same coordinate system, the consistency of the space relationship and the coordinates between the ultrasonic detection unit and the CCD sensor can be ensured, and an accurate basis is provided for the subsequent node coordinate mapping; based on the arrangement position coordinates, the acquisition coordinates and the movement speed, node coordinate mapping of the detection result of the ultrasonic detection unit and the acquisition result of the CCD sensor is established, and the corresponding relation between the ultrasonic detection unit and the CCD sensor data can be realized by establishing the node coordinate mapping, so that the subsequent abnormal coordinate determination and focusing acquisition are convenient; the non-woven fabric detection is executed through the ultrasonic detection unit, the abnormal coordinates are recorded, the attention area is determined based on node coordinate mapping, then the CCD sensor is used for focusing and collecting the attention area, and the abnormal detection is executed based on a focusing and collecting result, so that the comprehensive detection of the non-woven fabric material, the accurate positioning of the abnormal area and the generation of an abnormal detection result can be realized; according to the association result, the detection result of the non-woven fabric is output, and by associating the abnormality detection result with the attention area, the accurate non-woven fabric detection result can be provided and associated with the specific position and the area, so that the accurate abnormality detection is realized. In summary, the detection method of the medical non-woven fabric solves the technical problems of position recording, region positioning, abnormality detection accuracy and the like in the traditional method through the technologies of motion control, coordinate mapping, focusing acquisition and the like, realizes comprehensive detection of the non-woven fabric, and generates an accurate abnormality detection result.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
Fig. 1 is a schematic flow chart of a detection method of a medical non-woven fabric according to an embodiment of the application;
fig. 2 is a schematic structural diagram of a detection system for medical non-woven fabrics according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a motion control module 10, a coordinate acquisition module 20, a coordinate mapping module 30, a focusing acquisition module 40, a correlation module 50 and a result output module 60.
Detailed Description
The embodiment of the application solves the technical problems that the traditional non-woven fabric detection method lacks accurate control of movement speed and position coordinates and cannot efficiently realize comprehensive detection of the non-woven fabric and accurate positioning of abnormal areas by providing the detection method of the medical non-woven fabric.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a method for detecting a medical nonwoven fabric, where the method includes:
configuring the curling tension of the non-woven fabric detection rack, executing non-woven fabric motion control, and recording the motion speed;
preparing a rack for detecting the non-woven fabric, loading the non-woven fabric on the rack, using a tensioning device such as a roller or a clamp to enable the non-woven fabric to be kept in a tension state in the detection process, and applying proper curling tension by adjusting the tensioning device to enable the non-woven fabric to be kept in proper tension and compactness in the detection process so as to be capable of detecting existing anomalies. And starting a motion control system of the frame, and enabling the non-woven fabric to move at a constant speed through a driving motor, a conveyor belt and the like so as to comprehensively and accurately detect the non-woven fabric. In the motion control process, the displacement of the non-woven fabric in unit time is determined by a sensor or a detection device, such as a photoelectric sensor, a laser range finder and the like, so that the motion speed is calculated.
Sequentially arranging an ultrasonic detection unit and a CCD sensor, and recording arrangement position coordinates and acquisition coordinates, wherein the arrangement position coordinates and the acquisition coordinates are generated by constructing the same coordinate system;
an ultrasonic detection unit and a CCD sensor are arranged right above the non-woven fabric in front and back along the motion path of the non-woven fabric, and the ultrasonic detection unit is used for sending ultrasonic waves and receiving echoes so as to detect abnormality in the non-woven fabric; the CCD sensor is used for further shooting the image of the non-woven fabric so as to acquire more visual information.
The running line of the non-woven fabric is taken as an x axis, a straight line perpendicular to the x axis on a plane where the non-woven fabric is located is taken as a y axis, a straight line perpendicular to the plane and passing through the ultrasonic detection unit is taken as a z axis, and a point where the x axis, the y axis and the z axis intersect is taken as an origin, so that a space rectangular coordinate system is established. For the arranged ultrasonic detection units and CCD sensors, measuring tools such as a measuring ruler, a laser range finder and the like are used for measuring and recording the arrangement positions of all the devices, and the arrangement positions are filled into a coordinate system to obtain arrangement position coordinates.
In the same coordinate system, the same measuring tool is used for measuring the acquisition positions, the acquisition positions are filled into the coordinate system, acquisition coordinates are obtained, and the acquisition coordinates represent the corresponding relation between the data acquired by the corresponding ultrasonic detection unit and the CCD sensor and the arrangement positions of the data, so that the data of each sensor can be accurately matched.
Establishing node coordinate mapping of a detection result of the ultrasonic detection unit and a CCD sensor acquisition result according to the arrangement position coordinates, the acquisition coordinates and the movement speed;
by matching the order when the arrangement positions are recorded with the order when the acquisition data is recorded, a correspondence relationship between the arrangement position coordinates and the acquisition coordinates is established, for example, if the ultrasonic detection unit and the CCD sensor are arranged and acquired in the order from left to right, the first arrangement position coordinate corresponds to the first acquisition coordinate, and so on.
And (3) using the recorded movement speed and time information to correlate the movement speed and the time information with the acquisition coordinates, and determining the displacement of the non-woven fabric in each time period by calculating the time interval between each acquisition point and combining the movement speed, so as to obtain the position coordinates of each acquisition point.
And matching each arrangement position with the corresponding acquisition point position, and corresponding the arrangement position coordinates with the corresponding acquisition point position coordinates to establish node coordinate mapping of the detection result of the ultrasonic detection unit and the acquisition result of the CCD sensor. The mapping relation is used for corresponding the data between the ultrasonic detection unit and the CCD sensor, so that the abnormal position of the non-woven fabric is positioned.
Performing non-woven fabric detection through an ultrasonic detection unit, recording abnormal coordinates, determining an attention area based on the node coordinate mapping and the abnormal coordinates, and carrying out focusing acquisition on the attention area through the CCD sensor;
the laid ultrasonic detection unit is used for detecting the non-woven fabric, and the ultrasonic detection unit can identify irreversible anomalies such as warp and weft breaking and breakage by sending ultrasonic waves and receiving echoes, so that the irreversible anomalies such as dirt cannot be directly identified. Specifically, for the warp and weft breaking condition, as the continuity of the non-woven fabric material is broken due to the warp and weft breaking condition, the transmission of ultrasonic waves in the area is disturbed, so that the ultrasonic waves can be detected by the ultrasonic detection unit; for the damage condition, when the non-woven fabric is damaged, the ultrasonic waves can generate reflection, diffraction or interference phenomena at the damaged part, so that abnormal signals are generated and captured by the ultrasonic detection unit;
unlike warp and weft breaks and breakage, the dirt is reversible surface contamination, and the ultrasonic waves are not significantly disturbed or reflected during the propagation process, so that the dirt is difficult to be effectively detected by the ultrasonic waves and needs to be further identified by other devices, such as a CCD sensor.
When the ultrasonic detection unit detects the abnormal signal, abnormal coordinates are recorded, the abnormal coordinates correspond to positions of the non-woven fabric, the abnormal coordinates are taken as a center point, and an attention area is determined according to the abnormal size, wherein the attention area represents the position range of the non-woven fabric.
The determined region of interest is focus captured using a CCD sensor, capturing high resolution image data to analyze the region of interest in more detail.
Further, performing nonwoven fabric detection by an ultrasonic detection unit, and recording abnormal coordinates, comprising:
recording an emitting ultrasonic node and a receiving echo node of the ultrasonic detection unit;
echo analysis is carried out on the echo, and the defect size, the defect type and the virtual calibration coordinates are determined;
aligning the transmitting ultrasonic node and the virtual calibration coordinates, and determining drift time based on the time difference between the transmitting ultrasonic node and the receiving echo node;
generating drift compensation coordinates according to the drift time and the movement speed;
and carrying out defect coordinate backtracking through the virtual calibration coordinates and the drift compensation coordinates, and recording abnormal coordinates based on a backtracking result, the defect size and the defect type.
The ultrasonic detection unit consists of a plurality of transmitting ultrasonic modules and a plurality of receiving ultrasonic modules, wherein the transmitting ultrasonic modules transmit ultrasonic signals to the tested object, namely the non-woven fabric, and the receiving ultrasonic modules receive ultrasonic echo signals reflected from the tested object. Monitoring and recording a time node for sending out ultrasonic signals, namely a node for transmitting ultrasonic signals; and a time node for receiving the ultrasonic echo signal, i.e. a receiving echo node. By recording the time node information of the transmitting ultrasonic node and the receiving echo node, the transmission of ultrasonic signals and the accurate time measurement of echoes can be carried out, so that the abnormality detection of the non-woven fabric is realized.
Preprocessing the received echo, including denoising, filtering, enhancing and the like, so as to reduce noise interference, extracting characteristic information related to the defect, such as echo mode and amplitude characteristic of specific frequency, by analyzing time domain characteristics, including amplitude, duration and the like, of the echo signal, and acquiring the size of the defect by using the amplitude of the echo signal;
defining various defect modes in advance, classifying echo signals into different types of defects, including warp breaking, weft breaking, breakage and the like, comparing echo signal characteristics with the defect modes, and obtaining defect types corresponding to the echo signals;
and analyzing the echo signal, and recording the current position as a virtual calibration coordinate when the defect is detected, wherein the actual defect position is moved forwards by a certain distance due to the forward movement of the non-woven fabric. The virtual calibration coordinates are used as reference coordinates for calculating actual coordinates, so that defect position offset caused by forward movement of the non-woven fabric can be corrected, and more accurate actual coordinate information can be obtained.
And aligning the transmitting ultrasonic node with the corresponding virtual calibration coordinates by taking time as a reference. The difference between the time nodes of the transmitting ultrasonic node and the receiving echo node is calculated and half of the difference is taken as a drift time representing the time taken for the ultrasonic wave to reach the nonwoven fabric from the transmission, for correcting the positional shift due to the movement of the nonwoven fabric.
The moving speed of the nonwoven fabric, that is, the distance of the nonwoven fabric moving in the x-axis direction per unit time is obtained. The drift time is multiplied by the movement speed to obtain a drift compensation amount, which represents the distance the nonwoven actually moves in the x-axis direction during the drift time. Substituting the drift compensation amount into coordinates generates drift compensation coordinates for only drift in the x-axis direction and no drift in the y-axis direction.
And according to the drift compensation coordinate, the original virtual calibration coordinate is adjusted to reflect the actual position of the non-woven fabric in the x-axis direction, for example, the x-coordinate value of the virtual calibration coordinate is added with the x-coordinate value of the drift compensation coordinate, and the actual defect coordinate traced back through the defect coordinate is generated. Recording is performed in accordance with the size and type of the defect in combination with the actual coordinates of the defect, for example, the abnormal coordinates are recorded corresponding to the size and type of the defect as one abnormal coordinate for subsequent analysis and processing.
Further, determining an attention area based on the node coordinate map and the abnormal coordinates includes:
positioning the center point coordinates of the defects, taking the center point coordinates as reference points, taking the defect sizes as expansion points, and executing positioning expansion;
generating an expansion constraint of a rule graph, expanding a positioning expansion result specification based on the expansion constraint, and determining the size of an attention area;
and taking the center point coordinates as area coordinates of an attention area, taking the defect type as an identification reference defect of the attention area, and finishing the determination of the attention area.
And (3) analyzing the detected defects, determining the coordinates of the center points of the defects according to the shape, edge characteristics and other information of the defects, and taking the coordinates of the center points of the defects as reference points, wherein the reference points are starting points for subsequent positioning expansion. Depending on the size of the defect, the extent of expansion is determined, for example using the diameter, width or area of the defect to determine the size of expansion. Positioning and expanding operation is performed on the non-woven fabric with the datum point as the center according to the determined expanding range, for example, a circular, rectangular or other shaped area is drawn around the datum point to expand the positioning range of the defect.
The extended constraints of the regular pattern are determined according to the application requirements and target specifications, e.g. according to the resolution of the CCD sensor, including the rules of minimum size, maximum size, aspect ratio limitation of the pattern, etc. Matching the positioning expansion result with the generated expansion constraint, carrying out standardization processing on the positioning expansion result according to the expansion constraint, ensuring to meet the requirement of a rule graph, and determining the size of the attention area according to the standard expansion result.
And taking the center point coordinates as a starting point of the region coordinates of the attention region, determining characteristics for identifying references, such as the shape, the edge, the texture and the like of the defect according to the type of the defect, and determining the boundary of the attention region according to the center point coordinates and the identifying references of the defect type so as to ensure that the whole defect region is covered. This provides a limited area within which further analysis can be performed for more accurate handling of defects.
Further, the method further comprises:
establishing equal-length marks on the non-woven fabric, and carrying out speed steady-state verification of the movement speed according to the equal-length marks;
generating compensation coordinates based on the speed steady-state verification result;
and performing coordinate compensation of the abnormal coordinates through the compensation coordinates.
The non-woven fabric is provided with preset interval distances, and identification points are arranged at intervals of the preset interval distances, and have the same interval so as to ensure equal length. The steady-state verification of the movement speed is carried out by recording the change of the identification points in the movement process, specifically, before starting the movement, the position coordinates of each identification point are recorded, the non-woven fabric is controlled to move so as to pass through the equal-length identification within a certain time, whether the movement speed of the non-woven fabric is stable or not is verified by recording the position change of each identification point in the movement process, for example, the distance change between the identification points is compared, and whether the speed fluctuation exists or not is checked.
And determining the speed change condition of the non-woven fabric in the motion process according to the speed steady-state verification result, wherein the speed change condition comprises speed fluctuation, acceleration or deceleration and the like. When the speed change exceeds a preset threshold, indicating that the speed has obvious fluctuation or instability, compensation is needed to correct the position error. And calculating the deviation distance caused by speed change in the motion process according to the speed fluctuation, the acceleration or the deceleration, and substituting the deviation distance into a coordinate system to obtain the compensation coordinate.
And applying the generated compensation coordinates to the abnormal coordinates, and executing coordinate compensation of the abnormal coordinates by adding the compensation coordinates to the abnormal coordinates or replacing the abnormal coordinates, and updating the original abnormal coordinates by using the compensated coordinate values, so that position errors caused by speed change in the motion process are corrected, and the accuracy and the reliability of data are further improved.
Performing abnormality detection based on a focus acquisition result, generating an abnormality detection result, and associating the abnormality detection result with the attention area;
image processing algorithms such as image filtering, edge detection, texture analysis, color analysis and the like are used for detecting anomalies of image data collected by focusing to detect defects, foreign matters or other anomalies, and anomaly detection results are obtained by comparing image characteristics, threshold setting and the like, wherein the results indicate which areas in an image are anomalies, and the image processing algorithms also comprise information such as anomaly type, anomaly size, anomaly position and the like.
The coordinates of the abnormal region are converted into coordinates of the attention region using the node coordinate map so that the two are associated, so that the abnormal region in the nonwoven fabric can be more accurately determined and detailed information about the regions can be provided.
And outputting a detection result of the non-woven fabric according to the association result.
Marking the detected abnormal areas on the non-woven fabric image to visually show the positions where defects, damages or other anomalies exist, and outputting the types of each abnormal area, such as warp and weft breaking, damages and the like, and the corresponding abnormal numbers to provide statistical information on various abnormal conditions of the non-woven fabric. And simultaneously, more detailed information such as abnormal coordinates, sizes, shapes and the like is provided for each abnormal region, so that a user can intuitively know the detection result and quality condition of the non-woven fabric.
Further, the method further comprises:
configuring a universal CCD sensor, wherein the universal CCD sensor is a sensor for collecting universal traversal images;
synchronously executing data acquisition according to the universal CCD sensor, and performing eclosion removal of an attention area on the data acquisition result;
establishing a reference pixel gray value, and carrying out binary comparison on a data acquisition result after eclosion removal through the reference pixel gray value;
the abnormal region is newly added through the binary comparison result;
and outputting a detection result of the non-woven fabric according to the abnormality identification and association result of the newly added abnormal region.
And selecting a general CCD sensor suitable for application requirements, wherein the general CCD sensor has higher resolution, sensitivity and dynamic range and is used for further image acquisition tasks. Parameters of the universal CCD sensor including exposure time, gain, white balance and the like and acquisition modes such as continuous acquisition or trigger acquisition are configured, and the configured universal CCD sensor is used for executing universal traversal image acquisition, namely, comprehensively scanning the non-woven fabric to acquire complete image data.
And acquiring data by using the universal CCD sensor, acquiring image data of the non-woven fabric, and applying the image data to a data acquisition result according to the determined attention area. The contraction removal is performed for the attention area, and the pixel values of the attention area are set as background values, that is, they are replaced with pixel values similar to the background, by way of example, so that they are eliminated in the data acquisition result.
A reference pixel is selected from the eclosion-removed data, and its gray value is acquired as a reference point, for example, a pixel located at the center of the image or representative is selected, and this reference pixel gray value is used as a reference for subsequent binary comparison.
Comparing the gray value of the data acquisition result after eclosion removal with the gray value of the reference pixel, binarizing the pixel according to the comparison result, and setting the gray value of the pixel to be 1 if the gray value of the pixel is larger than the reference gray value; if the gray value of the pixel is equal to or less than the reference gray value, it is set to 0, and thus a binary image is obtained, wherein 1 represents the abnormal region and 0 represents the background region.
And extracting the abnormal region marked as 1 in the binary comparison result to be used as a newly added abnormal region.
Performing dirt recognition on the newly-increased abnormal region to obtain the reversible surface pollution which is dirt on the non-woven fabric and cannot be detected by ultrasonic waves; the association result shows the abnormality of ultrasonic detection such as warp breaking, weft breaking and breakage, and the two are combined to obtain a more comprehensive and accurate non-woven fabric detection result.
Further, the anomaly identification of the newly added anomaly area includes:
establishing a dirty feature set through big data, and performing dirty adaptation on the dirty feature set and a factory, so as to determine the matching constraint of the features according to dirty probability;
after the newly added abnormal region is determined, carrying out pollution matching on the newly added abnormal region by the pollution characteristic set through the matching constraint;
and finishing the abnormal recognition based on the dirt matching result.
A large amount of image data related to dirt is collected, a dirt area is marked, dirt characteristics are extracted based on the color, texture, shape and the like of the image, a data set containing the dirt related characteristics is established, and the characteristic set comprises a plurality of characteristic vectors, wherein each characteristic vector represents a measurement result of one characteristic.
The method comprises the steps of adapting a dirty feature set to data of a factory, calculating similarity between the feature of the data acquired in the factory and the dirty feature set by comparing the feature of the data with the dirty feature set, and using a similarity calculation result as dirty probability to represent the matching degree of dirty features of the factory and dirty features of big data, wherein a higher dirty probability means that the feature and the dirty have higher correlation. And taking the dirt probability as a matching constraint for judging whether the matching condition of the dirt characteristic is met.
And extracting corresponding dirty features including colors, textures, shapes and the like from the newly added abnormal region to generate feature vectors for representing the dirty features of the newly added abnormal region. And performing similarity calculation on the extracted feature vector of the newly added abnormal region and the features in the dirty feature set, for example, using cosine similarity to compare the similarity between the features. And judging the matching condition of the characteristics of the newly added abnormal region and the dirty characteristic set according to the set matching constraint, and if the similarity is higher than the constraint value, considering that the region is related to the dirty. And marking the newly added abnormal region determined to be related to the dirt according to the matching result as a dirt matching result.
And marking the newly added abnormal region determined to be related to the dirt according to the matching result, wherein the results represent the region related to the dirt as the dirt matching result, and the abnormal recognition of the dirt is completed.
Further, the method further comprises:
carrying out exception statistics based on the detection result, and recording an exception data set;
performing position and feature commonality clustering on the abnormal data set to generate a commonality clustering result;
and judging whether the common clustering result can be subjected to processing parameter mapping, and if so, performing feedback control of processing based on the mapping result.
And carrying out statistical analysis on the detection results, including indexes such as frequency, duration, spatial distribution and the like of each type of abnormality, so as to define the overall trend and characteristics of the abnormal situation, and integrating the abnormal statistical results into an abnormal data set.
The method comprises the steps of extracting position and characteristic information from an abnormal data set as input, applying the position and characteristic information to a K-means clustering algorithm, executing a clustering process, and dividing the anomalies into different groups according to similarity measurement by the clustering algorithm, wherein each group represents common abnormal characteristics including anomalies at the same position and anomalies of the same type. And generating a commonality clustering result, namely the center of each group and the information of the abnormality associated with each group, according to the output of the clustering algorithm, wherein the commonality clustering result reflects the commonality of the abnormality in position and characteristics and is used for revealing the potential abnormality type and mode.
And analyzing the generated commonality clustering result to obtain characteristic differences and commonalities among groups, including the aspects of position, characteristics, size, shape and the like. Judging whether the commonality clustering result has enough distinction and consistency according to the analysis result so that the mapping and adjustment of the processing parameters can be effectively adapted to the characteristics of each group.
If applicable, processing parameter mapping rules based on commonality clustering results are defined, which are set according to the characteristics and requirements of each group, e.g. setting specific processing parameter values for specific types of anomalies. Based on the mapping result, the corresponding processing parameters are adjusted to realize the control of the abnormal region.
And monitoring the effect in the processing process, and carrying out real-time optimization of parameters according to feedback, wherein the real-time optimization comprises monitoring indexes such as processing results of abnormal areas, changes of production quality and the like, so as to continuously improve and optimize mapping of the processing parameters.
In summary, the method and system for detecting the medical non-woven fabric provided by the embodiment of the application have the following technical effects:
1. by configuring the curling tension of the non-woven fabric detection rack and executing non-woven fabric movement control, recording the movement speed, realizing accurate control of the non-woven fabric movement process and accurate recording of the speed, so as to ensure the accuracy and reliability of data acquisition and analysis in the subsequent steps;
2. the ultrasonic detection unit and the CCD sensor are sequentially arranged, the arrangement position coordinates and the acquisition coordinates are recorded, the arrangement position coordinates and the acquisition coordinates are generated by constructing the same coordinate system, the consistency of the space relationship and the coordinates between the ultrasonic detection unit and the CCD sensor can be ensured, and an accurate basis is provided for the subsequent node coordinate mapping;
3. based on the arrangement position coordinates, the acquisition coordinates and the movement speed, node coordinate mapping of the detection result of the ultrasonic detection unit and the acquisition result of the CCD sensor is established, and the corresponding relation between the ultrasonic detection unit and the CCD sensor data can be realized by establishing the node coordinate mapping, so that the subsequent abnormal coordinate determination and focusing acquisition are convenient;
4. the non-woven fabric detection is executed through the ultrasonic detection unit, the abnormal coordinates are recorded, the attention area is determined based on node coordinate mapping, then the CCD sensor is used for focusing and collecting the attention area, and the abnormal detection is executed based on a focusing and collecting result, so that the comprehensive detection of the non-woven fabric material, the accurate positioning of the abnormal area and the generation of an abnormal detection result can be realized;
5. according to the association result, the detection result of the non-woven fabric is output, and by associating the abnormality detection result with the attention area, the accurate non-woven fabric detection result can be provided and associated with the specific position and the area, so that the accurate abnormality detection is realized.
In summary, the detection method of the medical non-woven fabric solves the technical problems of position recording, region positioning, abnormality detection accuracy and the like in the traditional method through the technologies of motion control, coordinate mapping, focusing acquisition and the like, realizes comprehensive detection of the non-woven fabric, and generates an accurate abnormality detection result.
Example two
Based on the same inventive concept as the detection method of a medical nonwoven fabric in the foregoing embodiments, as shown in fig. 2, the present application provides a detection system of a medical nonwoven fabric, the system comprising:
the motion control module 10 is used for configuring the curling tension of the non-woven fabric detection rack, executing non-woven fabric motion control and recording the motion speed;
the coordinate acquisition module 20 is used for sequentially arranging the ultrasonic detection unit and the CCD sensor, and recording arrangement position coordinates and acquisition coordinates, wherein the arrangement position coordinates and the acquisition coordinates are generated by constructing the same coordinate system;
the coordinate mapping module 30 is used for establishing node coordinate mapping of the detection result of the ultrasonic detection unit and the acquisition result of the CCD sensor according to the arrangement position coordinates, the acquisition coordinates and the movement speed;
the focusing acquisition module 40 is used for executing non-woven fabric detection through an ultrasonic detection unit, recording abnormal coordinates, determining an attention area based on the node coordinate mapping and the abnormal coordinates, and carrying out focusing acquisition on the attention area through the CCD sensor;
an association module 50, wherein the association module 50 is configured to perform anomaly detection based on a focus acquisition result, generate an anomaly detection result, and associate the anomaly detection result with the attention area;
and a result output module 60, wherein the result output module 60 is used for outputting the detection result of the non-woven fabric according to the association result.
Further, the system also comprises an abnormal coordinate recording module for executing the following operation steps:
recording an emitting ultrasonic node and a receiving echo node of the ultrasonic detection unit;
echo analysis is carried out on the echo, and the defect size, the defect type and the virtual calibration coordinates are determined;
aligning the transmitting ultrasonic node and the virtual calibration coordinates, and determining drift time based on the time difference between the transmitting ultrasonic node and the receiving echo node;
generating drift compensation coordinates according to the drift time and the movement speed;
and carrying out defect coordinate backtracking through the virtual calibration coordinates and the drift compensation coordinates, and recording abnormal coordinates based on a backtracking result, the defect size and the defect type.
Further, the system also includes an attention area determination module to perform the following operation steps:
positioning the center point coordinates of the defects, taking the center point coordinates as reference points, taking the defect sizes as expansion points, and executing positioning expansion;
generating an expansion constraint of a rule graph, expanding a positioning expansion result specification based on the expansion constraint, and determining the size of an attention area;
and taking the center point coordinates as area coordinates of an attention area, taking the defect type as an identification reference defect of the attention area, and finishing the determination of the attention area.
Further, the system further comprises a detection result output module for executing the following operation steps:
configuring a universal CCD sensor, wherein the universal CCD sensor is a sensor for collecting universal traversal images;
synchronously executing data acquisition according to the universal CCD sensor, and performing eclosion removal of an attention area on the data acquisition result;
establishing a reference pixel gray value, and carrying out binary comparison on a data acquisition result after eclosion removal through the reference pixel gray value;
the abnormal region is newly added through the binary comparison result;
and outputting a detection result of the non-woven fabric according to the abnormality identification and association result of the newly added abnormal region.
Further, the system also comprises an anomaly identification module for executing the following operation steps:
establishing a dirty feature set through big data, and performing dirty adaptation on the dirty feature set and a factory, so as to determine the matching constraint of the features according to dirty probability;
after the newly added abnormal region is determined, carrying out pollution matching on the newly added abnormal region by the pollution characteristic set through the matching constraint;
and finishing the abnormal recognition based on the dirt matching result.
Further, the system also comprises a coordinate compensation module for executing the following operation steps:
establishing equal-length marks on the non-woven fabric, and carrying out speed steady-state verification of the movement speed according to the equal-length marks;
generating compensation coordinates based on the speed steady-state verification result;
and performing coordinate compensation of the abnormal coordinates through the compensation coordinates.
Further, the system also comprises a feedback control module for executing the following operation steps:
carrying out exception statistics based on the detection result, and recording an exception data set;
performing position and feature commonality clustering on the abnormal data set to generate a commonality clustering result;
and judging whether the common clustering result can be subjected to processing parameter mapping, and if so, performing feedback control of processing based on the mapping result.
The foregoing detailed description of a method for detecting a medical nonwoven fabric will clearly be known to those skilled in the art, and the device disclosed in this embodiment is relatively simple to describe, and the relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method for detecting a medical nonwoven fabric, the method comprising:
configuring the curling tension of the non-woven fabric detection rack, executing non-woven fabric motion control, and recording the motion speed;
sequentially arranging an ultrasonic detection unit and a CCD sensor, and recording arrangement position coordinates and acquisition coordinates, wherein the arrangement position coordinates and the acquisition coordinates are generated by constructing the same coordinate system;
establishing node coordinate mapping of a detection result of the ultrasonic detection unit and a CCD sensor acquisition result according to the arrangement position coordinates, the acquisition coordinates and the movement speed;
performing non-woven fabric detection through an ultrasonic detection unit, recording abnormal coordinates, determining an attention area based on the node coordinate mapping and the abnormal coordinates, and carrying out focusing acquisition on the attention area through the CCD sensor;
performing abnormality detection based on a focus acquisition result, generating an abnormality detection result, and associating the abnormality detection result with the attention area;
and outputting a detection result of the non-woven fabric according to the association result.
2. The method of claim 1, wherein the method further comprises:
recording an emitting ultrasonic node and a receiving echo node of the ultrasonic detection unit;
echo analysis is carried out on the echo, and the defect size, the defect type and the virtual calibration coordinates are determined;
aligning the transmitting ultrasonic node and the virtual calibration coordinates, and determining drift time based on the time difference between the transmitting ultrasonic node and the receiving echo node;
generating drift compensation coordinates according to the drift time and the movement speed;
and carrying out defect coordinate backtracking through the virtual calibration coordinates and the drift compensation coordinates, and recording abnormal coordinates based on a backtracking result, the defect size and the defect type.
3. The method of claim 2, wherein the method further comprises:
positioning the center point coordinates of the defects, taking the center point coordinates as reference points, taking the defect sizes as expansion points, and executing positioning expansion;
generating an expansion constraint of a rule graph, expanding a positioning expansion result specification based on the expansion constraint, and determining the size of an attention area;
and taking the center point coordinates as area coordinates of an attention area, taking the defect type as an identification reference defect of the attention area, and finishing the determination of the attention area.
4. The method of claim 1, wherein the method further comprises:
configuring a universal CCD sensor, wherein the universal CCD sensor is a sensor for collecting universal traversal images;
synchronously executing data acquisition according to the universal CCD sensor, and performing eclosion removal of an attention area on the data acquisition result;
establishing a reference pixel gray value, and carrying out binary comparison on a data acquisition result after eclosion removal through the reference pixel gray value;
the abnormal region is newly added through the binary comparison result;
and outputting a detection result of the non-woven fabric according to the abnormality identification and association result of the newly added abnormal region.
5. The method of claim 4, wherein the method further comprises:
establishing a dirty feature set through big data, and performing dirty adaptation on the dirty feature set and a factory, so as to determine the matching constraint of the features according to dirty probability;
after the newly added abnormal region is determined, carrying out pollution matching on the newly added abnormal region by the pollution characteristic set through the matching constraint;
and finishing the abnormal recognition based on the dirt matching result.
6. The method of claim 1, wherein the method further comprises:
establishing equal-length marks on the non-woven fabric, and carrying out speed steady-state verification of the movement speed according to the equal-length marks;
generating compensation coordinates based on the speed steady-state verification result;
and performing coordinate compensation of the abnormal coordinates through the compensation coordinates.
7. The method of claim 1, wherein the method further comprises:
carrying out exception statistics based on the detection result, and recording an exception data set;
performing position and feature commonality clustering on the abnormal data set to generate a commonality clustering result;
and judging whether the common clustering result can be subjected to processing parameter mapping, and if so, performing feedback control of processing based on the mapping result.
8. A system for detecting a medical nonwoven fabric, characterized by being used for carrying out the method for detecting a medical nonwoven fabric according to any one of claims 1 to 7, comprising:
the motion control module is used for configuring the curling tension of the non-woven fabric detection rack, executing non-woven fabric motion control and recording the motion speed;
the system comprises a coordinate acquisition module, a CCD sensor, a storage module and a storage module, wherein the coordinate acquisition module is used for sequentially arranging an ultrasonic detection unit and the CCD sensor, recording arrangement position coordinates and acquisition coordinates, and the arrangement position coordinates and the acquisition coordinates are generated by constructing the same coordinate system;
the coordinate mapping module is used for establishing node coordinate mapping of the detection result of the ultrasonic detection unit and the acquisition result of the CCD sensor according to the arrangement position coordinates, the acquisition coordinates and the movement speed;
the focusing acquisition module is used for executing non-woven fabric detection through the ultrasonic detection unit, recording abnormal coordinates, determining an attention area based on the node coordinate mapping and the abnormal coordinates, and carrying out focusing acquisition on the attention area through the CCD sensor;
the association module is used for executing abnormality detection based on a focusing acquisition result, generating an abnormality detection result and associating the abnormality detection result with the attention area;
and the result output module is used for outputting a detection result of the non-woven fabric according to the association result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311421350.0A CN117147699B (en) | 2023-10-31 | 2023-10-31 | Medical non-woven fabric detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311421350.0A CN117147699B (en) | 2023-10-31 | 2023-10-31 | Medical non-woven fabric detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117147699A true CN117147699A (en) | 2023-12-01 |
| CN117147699B CN117147699B (en) | 2024-01-02 |
Family
ID=88901121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311421350.0A Active CN117147699B (en) | 2023-10-31 | 2023-10-31 | Medical non-woven fabric detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117147699B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117949539A (en) * | 2024-03-26 | 2024-04-30 | 天津风霖物联网科技有限公司 | Engineering building strength detection system and detection method thereof |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108693186A (en) * | 2018-08-28 | 2018-10-23 | 广东省智能制造研究所 | A kind of non-woven fabrics air hole detection device and method |
| CN110501342A (en) * | 2019-08-20 | 2019-11-26 | 北京信息科技大学 | A kind of cheese yarn bar positioning visible detection method |
| CN112330746A (en) * | 2020-11-27 | 2021-02-05 | 苏州感测通信息科技有限公司 | Mobile chassis obstacle detection method based on TX2 |
| CN113768527A (en) * | 2021-08-25 | 2021-12-10 | 中山大学 | Real-time three-dimensional reconstruction method, device and medium based on CT and ultrasonic image fusion |
| CN114113115A (en) * | 2021-11-29 | 2022-03-01 | 哈尔滨工业大学 | High-precision automatic positioning method for micro-defects on surface of large-diameter element |
| CN115201211A (en) * | 2022-09-15 | 2022-10-18 | 江苏牛掌柜科技有限公司 | Quality control method and system for intelligent visual textile product |
| CN115211961A (en) * | 2021-04-17 | 2022-10-21 | 诺创智能医疗科技(杭州)有限公司 | Positioning method, device, system and computer readable storage medium |
| CN115452846A (en) * | 2022-09-14 | 2022-12-09 | 江苏理工学院 | Medical non-woven fabric flaw on-line monitoring system based on machine vision |
| CN115963112A (en) * | 2022-12-29 | 2023-04-14 | 易思维（杭州）科技有限公司 | Visual detection method based on real-time positioning information |
| CN116236222A (en) * | 2023-03-22 | 2023-06-09 | 哈尔滨工业大学（威海） | Ultrasonic probe pose positioning system and method of medical remote ultrasonic scanning robot |
| CN116386028A (en) * | 2023-04-06 | 2023-07-04 | 扬州市管件厂有限公司 | Image layering identification method and device for processing tee pipe fitting |
| CN116593589A (en) * | 2023-07-18 | 2023-08-15 | 中国铁路设计集团有限公司 | Three-dimensional ultrasonic intelligent detection method for large-volume concrete structure |
| CN116794451A (en) * | 2023-06-25 | 2023-09-22 | 国网江苏省电力有限公司泰州供电分公司 | Non-contact live detection device and method for insulation defect of power distribution overhead line |
-
2023
- 2023-10-31 CN CN202311421350.0A patent/CN117147699B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108693186A (en) * | 2018-08-28 | 2018-10-23 | 广东省智能制造研究所 | A kind of non-woven fabrics air hole detection device and method |
| CN110501342A (en) * | 2019-08-20 | 2019-11-26 | 北京信息科技大学 | A kind of cheese yarn bar positioning visible detection method |
| CN112330746A (en) * | 2020-11-27 | 2021-02-05 | 苏州感测通信息科技有限公司 | Mobile chassis obstacle detection method based on TX2 |
| CN115211961A (en) * | 2021-04-17 | 2022-10-21 | 诺创智能医疗科技(杭州)有限公司 | Positioning method, device, system and computer readable storage medium |
| CN113768527A (en) * | 2021-08-25 | 2021-12-10 | 中山大学 | Real-time three-dimensional reconstruction method, device and medium based on CT and ultrasonic image fusion |
| CN114113115A (en) * | 2021-11-29 | 2022-03-01 | 哈尔滨工业大学 | High-precision automatic positioning method for micro-defects on surface of large-diameter element |
| CN115452846A (en) * | 2022-09-14 | 2022-12-09 | 江苏理工学院 | Medical non-woven fabric flaw on-line monitoring system based on machine vision |
| CN115201211A (en) * | 2022-09-15 | 2022-10-18 | 江苏牛掌柜科技有限公司 | Quality control method and system for intelligent visual textile product |
| CN115963112A (en) * | 2022-12-29 | 2023-04-14 | 易思维（杭州）科技有限公司 | Visual detection method based on real-time positioning information |
| CN116236222A (en) * | 2023-03-22 | 2023-06-09 | 哈尔滨工业大学（威海） | Ultrasonic probe pose positioning system and method of medical remote ultrasonic scanning robot |
| CN116386028A (en) * | 2023-04-06 | 2023-07-04 | 扬州市管件厂有限公司 | Image layering identification method and device for processing tee pipe fitting |
| CN116794451A (en) * | 2023-06-25 | 2023-09-22 | 国网江苏省电力有限公司泰州供电分公司 | Non-contact live detection device and method for insulation defect of power distribution overhead line |
| CN116593589A (en) * | 2023-07-18 | 2023-08-15 | 中国铁路设计集团有限公司 | Three-dimensional ultrasonic intelligent detection method for large-volume concrete structure |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117949539A (en) * | 2024-03-26 | 2024-04-30 | 天津风霖物联网科技有限公司 | Engineering building strength detection system and detection method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117147699B (en) | 2024-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Usamentiaga et al. | Multi-camera calibration for accurate geometric measurements in industrial environments | |
| CN117147699B (en) | Medical non-woven fabric detection method and system | |
| CN110084854B (en) | System and method for runtime determination of camera calibration errors | |
| US8220335B2 (en) | Accurate image acquisition for structured-light system for optical shape and positional measurements | |
| CN109099860A (en) | 3 dimensional coil geometry measuring device and 3 dimensional coil geometry measurement method | |
| CN108492327B (en) | AOI image matching method, system, readable storage medium and intelligent device | |
| CN100372089C (en) | Pattern evaluating apparatus, pattern evaluating method and program | |
| CN111369484B (en) | Rail profile detection method and device | |
| JP2013213733A (en) | Apparatus and method for inspecting object to be inspected | |
| CN115375610A (en) | Detection method and device, detection equipment and storage medium | |
| CN108844469B (en) | Method and system for testing workpiece step height based on laser | |
| CN118115372A (en) | Workpiece defect detection system and method | |
| CN115575407B (en) | Detection method applied to track and tunnel | |
| CN111369533A (en) | Steel rail profile detection method and device based on polarization image fusion | |
| CN114111576B (en) | Aircraft skin gap surface difference detection method | |
| Lilienblum et al. | A coded 3D calibration method for line-scan cameras | |
| CN108534707A (en) | Industry manufacture component scale scanning detection method | |
| JP2015503110A (en) | Sensor for measuring surface non-uniformity | |
| JP2021174216A (en) | Facility inspection system, facility inspection method | |
| JP5929518B2 (en) | Surface shape measuring method and surface shape measuring apparatus | |
| Usamentiaga et al. | Rail flatness measurement based on dual laser triangulation | |
| CN108020557A (en) | A kind of vehicle body coating quality adaptation detection method based on laser scanning | |
| EP3467431A1 (en) | Device and method for in-line quality control of components obtained by flat sheets forming | |
| CN116576806B (en) | Precision control system for thickness detection equipment based on visual analysis | |
| Vacho et al. | Selected method of image analysis used in quality control of manufactured components |
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 |