CN117911402A - Water pump impeller appearance defect detection method and system - Google Patents
Water pump impeller appearance defect detection method and system Download PDFInfo
- Publication number
- CN117911402A CN117911402A CN202410295080.1A CN202410295080A CN117911402A CN 117911402 A CN117911402 A CN 117911402A CN 202410295080 A CN202410295080 A CN 202410295080A CN 117911402 A CN117911402 A CN 117911402A
- Authority
- CN
- China
- Prior art keywords
- impeller
- degree
- data
- image
- point
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 77
- 238000001514 detection method Methods 0.000 title claims abstract description 67
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000001427 coherent effect Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims 2
- 238000003860 storage Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000002950 deficient Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000005266 casting Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000003801 milling Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003110 molding sand Substances 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a method and a system for detecting appearance defects of a water pump impeller, comprising the following steps: acquiring continuous frame images of a water pump impeller during working, and preprocessing the continuous frame images to obtain gray images of the impeller; and (3) carrying out scribing processing on the gray level image by adopting an 8-chain code, wherein the pixel points through which scribing passes are recorded as detection bits of 1 to n layers from a starting point to an end point, and the gray level value of the pixel point of each frame image at the position corresponding to the detection bit is recorded, so that a circulation curve corresponding to each detection bit is obtained. According to the invention, the gray value of each pixel point in the gray image of the impeller is multiplied by the corresponding appearance defect degree, so that all the pixel points in the gray image of the impeller are enhanced, and then the defect positions of the impeller are obtained by dividing by an Ojin threshold method. The method can accurately detect the defects on the surface of the impeller, and improves the detection result of the defects of the impeller.
Description
Technical Field
The invention relates to the technical field of image processing. More particularly, the invention relates to a method and a system for detecting appearance defects of a water pump impeller.
Background
The water pump utilizes centrifugal force generated by rotation of a closed metal impeller to convey fluid, and the manufacturing process of the closed metal impeller adopts the following method: copper, aluminum or stainless steel is made into a compact by a casting red punching method, and the surface is milled by a milling machine, so that a single impeller formed by integrating a disc-shaped body and a plurality of blades is formed. In each manufacturing procedure link, the closed water pump impeller is easy to cause different types of surface defects such as unsmooth, sand holes, cracks, air holes, edge notches, scratches and the like during production due to process medium pollution, unstable temperature, improper casting of molding sand, improper milling process and other equipment fault factors, so that the impeller has faults such as cavitation, fracture, mechanical abrasion, vibration noise, water delivery function reduction and the like during operation.
However, the leaf surface appearance of the impeller of the water pump is curved, and the gray level of the defect on the slope surface is different, so that the defect detection method of the impeller at present cannot accurately detect the leaf surface defect of the impeller, and the final detection result is inaccurate.
Disclosure of Invention
The invention provides a method and a system for detecting appearance defects of a water pump impeller, and aims to solve the problem that the existing method for detecting the defects of the impeller cannot accurately detect the defects of the blade surfaces because the appearance of the blade surfaces of the water pump impeller is curved and the defects are different in gray scale on the slope in the related art.
In a first aspect, the present invention provides a method for detecting an appearance defect of a water pump impeller, comprising: acquiring continuous frame images of a water pump impeller during working, and preprocessing the continuous frame images to obtain gray images of the impeller; marking the gray level image by adopting an 8-chain code, wherein the pixel points where marking passes are marked as detection bits of 1 to n layers from a starting point to an end point, and the gray level value of the pixel point of each frame image at the position corresponding to the detection bit is recorded, so that a circulation curve corresponding to each detection bit is obtained, wherein the circulation curve is drawn by the gray level value of the detection bit along with the time change curve of the corresponding image frame; the circulation curves are subjected to sectional processing to obtain circulation sections of the circulation curves, the coherent anomaly degree of the circulation sections is calculated, and a calculation formula is as follows:
wherein, For/>First/>, of the cycle curveThe coherent anomalies of the cyclic segments, expressed as/>The coherence degree of the circulation section; /(I)Represents the/>The average value of the approximation degree of each cycle segment of the cycle segment and each other cycle segment of the corresponding cycle curve; /(I)Expressed as/>The number of data points of the circulation segment; /(I)Represents the/>The data point number average value of other circulating segments except the circulating segment; /(I)Represents the/>The ratio of the slope of the circulating section to the average value of the slopes of all other circulating sections, wherein the smaller value is used as a denominator; weighting and adjusting the pixel points of each circulation segment to obtain the corresponding feature degree of each pixel point, and obtaining the appearance defect degree of the pixel point according to the coherent anomaly degree and the feature degree; adjusting each pixel point in the gray level image of the impeller through the appearance defect degree to obtain an adjusted image; and dividing the adjusted image to obtain the impeller defect position.
In an embodiment, the feature degree corresponding to each pixel point is obtained, and the calculation formula is as follows:
wherein, Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionThe degree of characteristic to which the data points correspond,Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionThe coherence degree of the data points; /(I)Represents the/>The mean value of the absolute value of the numerical difference between a data point and a data point adjacent to the same cycle segment; /(I)The gray value corresponding to the pixel is represented.
In an embodiment, the appearance defect degree of the pixel point is obtained according to the coherent anomaly degree and the feature degree, and the calculation formula is as follows:
wherein, Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionAppearance defect degree of pixel corresponding to data point/I-And/>Corresponding difference values of data respectively representing corresponding positions of left and right adjacent cyclic segments,/>And/>Respectively represent the/>Data points associated detection area/>Regional relevance of individual data to adjacent cyclic segments of the corresponding cyclic curve,/>Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionCharacteristic degree corresponding to data point,/>Representing the total number of data associated with the detection region,/>Representing a standard normalization function.
In one embodiment, the method comprises the steps of,And/>Respectively represent the corresponding difference of the left and right positions,/>The calculation formula of (2) is as follows:
wherein, Represents the/>Data points associated detection area/>The pixel characteristic degree corresponding to the data,Represents the/>Data points associated detection area/>Pixel point characteristic degree corresponding to data of corresponding position of left adjacent cyclic segment of cyclic curve corresponding to each data,/>Represents the/>Data points associated detection area/>And the difference value of the pixel point characteristic degree corresponding to the data of the corresponding position of the left adjacent cycle segment of the corresponding cycle curve.
In an embodiment, the adjusting each pixel point in the gray image of any impeller by using the appearance defect degree to obtain an adjusted image includes: and multiplying the gray value of the pixel point in the gray image of any impeller by the corresponding appearance defect degree to obtain an enhanced image.
In one embodiment, an enhanced image is obtained comprising: the contrast ratio of the image defect pixel point and the normal pixel point is enhanced.
In one embodiment, the coherent anomaly corresponding to the kth data point comprises: the coherence anomalies of each data point in a cycle segment are the coherence anomalies of the corresponding cycle segment.
In an embodiment, segmenting the adjusted image to obtain the impeller defect position includes: and (5) segmenting the adjusted image by adopting an Ojin threshold method to obtain the impeller defect position.
In one embodiment, the scribing the gray scale image using an 8-chain code includes: calculating to obtain the center point of the impeller by a circle center algorithm, and marking the center point of the impeller as a starting point in the direction of 0 of 8-chain codes.
The invention also provides a water pump impeller appearance defect detection system, which comprises a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to realize the water pump impeller appearance defect detection method according to any one of the above methods.
The beneficial effects are that: the gray value of each pixel point in the gray image of the impeller is multiplied by the corresponding appearance defect degree, so that all the pixel points in the gray image of the impeller are enhanced, and then the defect positions of the impeller are obtained by dividing by the Ojin threshold method. The method can accurately detect the defects on the surface of the impeller, and improves the detection result of the defects of the impeller.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a flow chart schematically illustrating detection of impeller defects according to an embodiment of the present invention;
Fig. 2 is a schematic diagram schematically illustrating a system configuration according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the 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 be within the scope of the invention.
The following describes in detail the embodiments of the present invention with reference to the accompanying drawings, as shown in fig. 1:
Step S101: and acquiring continuous frame images of the water pump impeller during working, and preprocessing the continuous frame images to obtain gray images of the impeller.
In one embodiment, a water pump impeller is placed on a quality inspection table rotating at a slow speed and a uniform speed to rotate for one circle, a high-definition industrial camera is used for overlooking the water pump impeller in the rotating process to obtain continuous frame images of the water pump impeller, and then semantic segmentation is used for separating impeller parts from the background on the continuous frame images of the water pump impeller to obtain impeller images. And then graying the impeller image by using a graying algorithm to obtain a gray image of the impeller.
Step S102: and (3) carrying out scribing processing on the gray level image of the impeller, wherein the pixel points through which scribing passes are recorded as detection bits of 1 to n layers from the starting point to the end point, and a circulation curve corresponding to each detection bit is obtained.
In one embodiment, the gray scale cycle is not uniform at each location because the impeller has a fan-shaped blade face that is narrower in width and narrower closer to the center. Therefore, the center point of the impeller is obtained through calculation by a circle center algorithm in the prior art, then the center point of the impeller is taken as a starting point to score in the direction of 0 in the 8-chain code direction, and the pixel point through which the score passes is recorded as a detection position of 1 to n layers from the starting point to the end point for later image processing. And recording the gray value of the pixel point of each frame image at the position corresponding to the detection bit, so as to obtain a circulation curve corresponding to each detection bit, and using the circulation curve to subsequently detect the pixel point of the full image (impeller gray image), wherein the circulation curve is drawn by the gray value of the detection bit along with the time change curve of the corresponding image frame.
Illustratively, taking the r-th detection bit as an example, a loop curve of the r-th detection bit is obtained. The method comprises the steps of firstly determining the position of an r-th detection position, then enabling a leaf surface to rotate, enabling the position of the r-th detection position to be unchanged in the process of rotating the leaf surface, and drawing a curve of the gray value of the r-th detection position along with the time change of a corresponding image frame to obtain a circulation curve in the process of rotating the leaf surface because the leaf surface is inclined.
Step S103: and carrying out sectional processing on each circulation curve to obtain each circulation section of the circulation curve, and calculating the coherence degree of each circulation section.
In one embodiment, the horizontal axis defining the loop curve is the time of the corresponding image frame and the vertical axis is the detected bit gray level in the corresponding time image frame. Since each blade surface is inclined from low to high, when the blade surface of the impeller rotates along the direction from low to high, the gray value of the detection position gradually increases, so that the circulation curve of each blade surface is circulated from low to high in order under the normal state, and the maximum value point on each circulation curve is selected for segmentation, thus obtaining each circulation section of each circulation curve, for example, the third circulation section is usedLayer detection bits are exemplified, item/>The cycle curve obtained by the detection bit is recorded as the/>Cycle curve, th/>First/>, of the cycle curveThe cycle segment is denoted as/>And (5) a circulation section. And because each leaf surface corresponds to one circulation section under the condition of normal appearance, and because the circulation section of each leaf surface has unified characteristics and appearance defects have randomness, the coherence degree can be obtained according to the regularity of the circulation sections of the circulation curve.
The coherence degree reflects the possibility of abnormality of the circulation section, and the larger the value of the coherence degree is, the larger the possibility of defects of the pixel point corresponding to the data point of the circulation section is. The smaller the value of the coherence anomaly, the less likely the pixel point corresponding to the segment of data point is defective.
Step S104: and carrying out weighted adjustment on the pixel points of each circulation segment to obtain the corresponding feature degree of each pixel point, and obtaining the appearance defect degree of the pixel point according to the coherent anomaly degree and the feature degree.
In one embodiment, the coherence degree of each cycle segment is obtained through the steps above, and then the weighting is performed according to the situation of each pixel point data point, so as to represent the data characteristic corresponding to each pixel point. The weighting adjustment of each pixel point is used for distinguishing each pixel point data characteristic of the same section. Then in order to make the data have more integrity, the data are further refined through other circulation sections of the same circulation curve, and for the integrity, specifically, in a normal state, the pixel point characteristics of the corresponding positions of all the leaf surfaces are the same, and in the case of defects, the defects have randomness, so the characteristics of the data of the corresponding positions of all the circulation sections are the same, and the judgment is carried out through the associated data of the corresponding positions of all the circulation sections, so that the defective pixel point is accurately determined.
Specifically, the corresponding position data and adjacent data of the cycle curve are obtained for the adjacent time of the data point (the horizontal axis of the cycle curve is the time of the corresponding image frame) and the detection position of the corresponding adjacent layer, and the region corresponding to these data is referred to as the firstAnd (3) detecting the area associated with the data points, and then calculating the appearance defect degree of the pixel point corresponding to the data point, wherein each pixel point corresponds to one data point.
Exemplary, in the firstLayer detection bits are exemplified by, and/>The adjacent detection bits of the layer detection bits are P detection bits and L detection bits, respectively. Select the first/>First/>, of the cycle curveFirst/>, of the circulation sectionData points, first get the/>Data points of adjacent time of data points, wherein the data points of adjacent time are respectively/>Data points/>Data points. Then according to/>On layer detection bitsData points,/>Data points/>Data points matching P detection bits, L detection bits/>Layer detection is performed on data points corresponding to three data points, and the area corresponding to the data points is recorded as the/>The correlation of data points detects the area.
Step S105: and adjusting each pixel point in the gray level image of any impeller through the appearance defect degree to obtain an adjusted image.
In one embodiment, a gray image of one impeller is selected from impeller images of continuous frames, gray values of all pixels in the gray images of the impeller are multiplied by corresponding appearance defect degrees, and all pixels in the gray images of the impeller are updated to obtain an adjusted image, wherein the adjusted image is an image obtained by enhancing contrast between defective pixels and normal pixels.
Step S106: and dividing the adjusted image to obtain the impeller defect position.
In one embodiment, the adjusted image is segmented using an oxford thresholding method to obtain the defective portion of the impeller.
In one embodiment, regarding step S103, the formula for calculating the coherent anomaly degree of each of the cyclic segments is:
represents the/> First/>, of the cycle curveThe coherence degree of the cyclic segment is simply called/>A circulation section; /(I)Represents the/>The average value of the approximation degree of each cycle segment of the cycle segment and each other cycle segment of the corresponding cycle curve; /(I)Expressed as/>The number of data points of the circulation segment; /(I)Represents the/>The data point number average value of other circulating segments except the circulating segment; /(I)Represents the/>The ratio of the slope of the circulation segment to the average value of all other slope of the circulation segment, wherein the smaller value is used as denominator.
In one embodiment, the first is calculated by the DTW algorithmThe approximation of the loop segment to each of the other loop segments of the corresponding loop curve is then calculated as the average of all approximations of the corresponding loop curve, the average being noted/>。
Wherein by means ofEmbody the/>The similarity of the data volume of the circulation segment and the whole data volume so as to embody the unified characteristics of the data volume of the circulation segment and other segments, and the larger the value is, the greater the possibility that the circulation has an abnormal state is; and/>Represents the/>The ratio of the slope of the circulation segment to the average value of the slopes of other circulation segments, wherein the smaller value is taken as a denominator, thereby embodying the/>The greater the value of the synchronicity of the loop segment with the overall trend, the greater the likelihood that the loop will have an abnormal condition.
In one embodiment, the coherence degree of each data point in the cyclic segment is the coherence degree of the corresponding cyclic segment, and the calculation formula of the feature degree corresponding to each pixel point is as follows:
wherein, Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionThe degree of characteristic to which the data points correspond,Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionThe coherence degree of the data points; /(I)Represents the/>The mean value of the absolute value of the numerical difference between a data point and a data point adjacent to the same cycle segment; /(I)The gray value corresponding to the pixel is represented.
The larger the value of the feature degree of the pixel point is, the greater the possibility that the pixel point corresponding to the data has defects is; and pass throughThe special characteristics of the pixel point are embodied, so that the weighting adjustment is carried out on the data of each pixel point, and the characteristics of each pixel point in the same section are distinguished.
In one embodiment, regarding step S104, the calculation formula of the appearance defect degree is:
wherein, Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionAppearance defect degree of pixel corresponding to data point/I-And/>Corresponding difference values of data respectively representing corresponding positions of left and right adjacent cyclic segments,/>And/>Respectively represent the/>Data points associated detection area/>Region correlation of each data with adjacent cyclic segments of the corresponding cyclic curve, m represents the total number of data associated with the detection region,/>Representing a standard normalization function.
In the above-mentioned description of the invention,The calculation formula of (2) is as follows:
wherein, Represents the/>Data points associated detection area/>The pixel characteristic degree corresponding to the data,Represents the/>Data points associated detection area/>Pixel point characteristic degree corresponding to data of corresponding position of left adjacent cyclic segment of cyclic curve corresponding to each data,/>Represents the/>Data points associated detection area/>And the difference value of the pixel point characteristic degree corresponding to the data of the corresponding position of the left adjacent cycle segment of the corresponding cycle curve.
In one embodiment of the present invention, in one embodiment,The calculation formula of (2) is as follows:
wherein, Represents the/>Data points associated detection area/>Pixel point characteristic degree corresponding to data of corresponding position of right adjacent cycle segment of cycle curve corresponding to each data,/>Represents the/>Data points associated detection area/>And the difference value of the pixel point characteristic degree corresponding to the data of the corresponding position of the right adjacent cycle segment of the corresponding cycle curve. Embodying the/>Data points associated detection area/>The smaller the difference value is, the higher the correlation degree is, the smaller the possibility of abnormality exists in the pixel point of the corresponding position of the data, otherwise, the greater the possibility of abnormality exists.
By the way, byAnd/>Respectively embody the/>Data points associated detection area/>The smaller the value of the region correlation between the data and the adjacent cyclic segment of the corresponding cyclic curve is, the higher the correlation degree is, and the lower the possibility that the pixel point at the corresponding position of the data is abnormal is. By passing throughEmbody the/>The larger the value of the defect weight of the corresponding pixel point, the more likely the corresponding pixel point is defective. /(I)Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionThe larger the value of the appearance defect degree of the corresponding pixel point is, the greater the probability that the corresponding pixel point has defects is.
Through the steps, the appearance defect degree of the pixel point corresponding to the detection position of each frame image is obtained, a gray image of one impeller is selected, the gray value of each pixel point in the gray image of the impeller is multiplied by the corresponding appearance defect degree, all the pixel points in the gray image of the impeller are updated, the contrast ratio of the image defect pixel point and the normal pixel point is enhanced, and then the defect position of the impeller is obtained through segmentation by an Ojin threshold method. The method can accurately detect the defects on the surface of the impeller, and improves the detection result of the defects of the impeller.
The invention also provides a system for detecting the appearance defects of the water pump impeller. As shown in fig. 2, the system comprises a processor and a memory storing computer program instructions which, when executed by the processor, implement a method for detecting an appearance defect of a water pump impeller according to the first aspect of the present invention.
In one embodiment, the present invention provides a computer device whose internal structure may be as shown in FIG. 2. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. The processor of the computer equipment is used for providing calculation and control capability, and various varieties such as CPU, singlechip, DSP or FPGA can be selected. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The steps described in the above method embodiments, e.g. S101-S106, may be completed when the computer program is executed. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program, when executed by the processor, implements a method for detecting an appearance defect of a water pump impeller. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 2 is a block diagram of only some of the structures associated with the aspects of the present invention and is not limiting of the computer device of the present invention, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
The system further comprises other components known to those skilled in the art, such as a communication bus and a communication interface, the arrangement and function of which are known in the art and are therefore not described in detail herein.
In the context of this patent, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change memory RRAM (Resistive Random Access Memory), dynamic random access memory DRAM (Dynamic Random Access Memory), static random access memory SRAM (static random-access memory), enhanced dynamic random access memory EDRAM (ENHANCED DYNAMIC Random Access Memory), high-bandwidth memory HBM (high-bandwidth memory), hybrid storage cube HMC (Hybrid Memory Cube), or the like, or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device. Any of the applications or modules described herein may be implemented using computer-readable/executable instructions that may be stored or otherwise maintained by such computer-readable media.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention.
Claims (10)
1. The method for detecting the appearance defect of the water pump impeller is characterized by comprising the following steps of:
acquiring continuous frame images of a water pump impeller during working, and preprocessing the continuous frame images to obtain gray images of the impeller;
Marking the gray level image by adopting an 8-chain code, wherein the pixel points where marking passes are marked as detection bits of 1 to n layers from a starting point to an end point, and the gray level value of the pixel point of each frame image at the position corresponding to the detection bit is recorded, so that a circulation curve corresponding to each detection bit is obtained, wherein the circulation curve is drawn by the gray level value of the detection bit along with the time change curve of the corresponding image frame;
the circulation curves are subjected to sectional processing to obtain circulation sections of the circulation curves, the coherent anomaly degree of the circulation sections is calculated, and a calculation formula is as follows:
wherein, For/>First/>, of the cycle curveThe coherent anomalies of the cyclic segments, expressed as/>The coherence degree of the circulation section; /(I)Represents the/>The average value of the approximation degree of each cycle segment of the cycle segment and each other cycle segment of the corresponding cycle curve; /(I)Expressed as/>The number of data points of the circulation segment; /(I)Represents the/>The data point number average value of other circulating segments except the circulating segment; represents the/> The ratio of the slope of the circulating section to the average value of the slopes of all other circulating sections, wherein the smaller value is used as a denominator;
Weighting and adjusting the pixel points of each circulation segment to obtain the corresponding feature degree of each pixel point, and obtaining the appearance defect degree of the pixel point according to the coherent anomaly degree and the feature degree;
adjusting each pixel point in the gray level image of the impeller through the appearance defect degree to obtain an adjusted image;
And dividing the adjusted image to obtain the impeller defect position.
2. The method for detecting the appearance defect of the water pump impeller according to claim 1, wherein the feature degree corresponding to each pixel point is obtained, and the calculation formula is as follows:
wherein, Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionCharacteristic degree corresponding to data point,/>Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionThe coherence degree of the data points; /(I)Represents the/>The mean value of the absolute value of the numerical difference between a data point and a data point adjacent to the same cycle segment; /(I)The gray value corresponding to the pixel is represented.
3. The method for detecting the appearance defect of the water pump impeller according to claim 2, wherein the appearance defect degree of the pixel point is obtained according to the coherent anomaly degree and the feature degree, and the calculation formula is as follows:
wherein, Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionAppearance defect degree of pixel corresponding to data point/I-And/>Corresponding difference values of data respectively representing corresponding positions of left and right adjacent cyclic segments,/>AndRespectively represent the/>Data points associated detection area/>Regional relevance of individual data to adjacent cyclic segments of the corresponding cyclic curve,/>Represents the/>First/>, of the cycle curveFirst/>, of the circulation sectionCharacteristic degree corresponding to data point,/>Representing the total number of data associated with the detection region,/>Representing a standard normalization function.
4. The method for detecting an appearance defect of a water pump impeller according to claim 3, comprising,And/>Respectively represent the corresponding difference of the left and right positions,/>The calculation formula of (2) is as follows:
wherein, Represents the/>Data points associated detection area/>The pixel characteristic degree corresponding to the data,Represents the/>Data points associated detection area/>Pixel point characteristic degree corresponding to data of corresponding position of left adjacent cyclic segment of cyclic curve corresponding to each data,/>Represents the/>Data points associated detection area/>And the difference value of the pixel point characteristic degree corresponding to the data of the corresponding position of the left adjacent cycle segment of the corresponding cycle curve.
5. The method for detecting the appearance defect of the impeller of the water pump according to claim 1, wherein each pixel point in the gray level image of any impeller is adjusted by the appearance defect degree to obtain an adjusted image, comprising:
And multiplying the gray value of the pixel point in the gray image of any impeller by the corresponding appearance defect degree to obtain an enhanced image.
6. The method of claim 5, wherein obtaining an enhanced image comprises:
The contrast ratio of the image defect pixel point and the normal pixel point is enhanced.
7. The method of detecting an appearance defect of a water pump impeller according to claim 2, wherein the degree of coherence anomaly corresponding to the kth data point includes:
The coherence anomalies of each data point in a cycle segment are the coherence anomalies of the corresponding cycle segment.
8. The method of claim 1, wherein segmenting the adjusted image to obtain impeller defect positions comprises:
and (5) segmenting the adjusted image by adopting an Ojin threshold method to obtain the impeller defect position.
9. The method for detecting the appearance defect of the water pump impeller according to claim 1, wherein the scribing process is performed on the gray scale image by using an 8-chain code, comprising:
Calculating to obtain the center point of the impeller by a circle center algorithm, and marking the center point of the impeller as a starting point in the direction of 0 of 8-chain codes.
10. A water pump impeller visual defect detection system comprising a processor and a memory, said memory storing a computer program, wherein said processor executes said computer program to implement a water pump impeller visual defect detection method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410295080.1A CN117911402B (en) | 2024-03-15 | Water pump impeller appearance defect detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410295080.1A CN117911402B (en) | 2024-03-15 | Water pump impeller appearance defect detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117911402A true CN117911402A (en) | 2024-04-19 |
| CN117911402B CN117911402B (en) | 2024-05-31 |
Family
ID=
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080240300A1 (en) * | 2007-03-29 | 2008-10-02 | Samsung Electronics Co., Ltd. | Method of processing abnormal modulation signal, and receiver having abnormal modulation signal compensation function |
| CN103744850A (en) * | 2013-10-14 | 2014-04-23 | 国家电网公司 | Power grid disaster real-time regulating and control device and method based on intuition fuzzy rough set |
| CN104373820A (en) * | 2014-09-19 | 2015-02-25 | 北京化工大学 | Method for lowering false alarm rate of pipeline leakage monitoring |
| CN108014117A (en) * | 2017-05-19 | 2018-05-11 | 南开大学 | The small molecular antagonists of glucocorticoid receptor |
| US20180140829A1 (en) * | 2016-04-21 | 2018-05-24 | Ángel Ramos de Miguel, Sr. | Advanced electrode array insertion with conditioning |
| CN109356585A (en) * | 2018-11-16 | 2019-02-19 | 青海省第三地质矿产勘查院 | A method of judging metal sulfide ore body occurrence |
| CN112014689A (en) * | 2020-10-19 | 2020-12-01 | 国网江西省电力有限公司电力科学研究院 | Method and device for diagnosing abnormity of current sampling loop |
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080240300A1 (en) * | 2007-03-29 | 2008-10-02 | Samsung Electronics Co., Ltd. | Method of processing abnormal modulation signal, and receiver having abnormal modulation signal compensation function |
| CN103744850A (en) * | 2013-10-14 | 2014-04-23 | 国家电网公司 | Power grid disaster real-time regulating and control device and method based on intuition fuzzy rough set |
| CN104373820A (en) * | 2014-09-19 | 2015-02-25 | 北京化工大学 | Method for lowering false alarm rate of pipeline leakage monitoring |
| US20180140829A1 (en) * | 2016-04-21 | 2018-05-24 | Ángel Ramos de Miguel, Sr. | Advanced electrode array insertion with conditioning |
| CN108014117A (en) * | 2017-05-19 | 2018-05-11 | 南开大学 | The small molecular antagonists of glucocorticoid receptor |
| CN109356585A (en) * | 2018-11-16 | 2019-02-19 | 青海省第三地质矿产勘查院 | A method of judging metal sulfide ore body occurrence |
| CN112014689A (en) * | 2020-10-19 | 2020-12-01 | 国网江西省电力有限公司电力科学研究院 | Method and device for diagnosing abnormity of current sampling loop |
Non-Patent Citations (1)
| Title |
|---|
| 徐世军;李磊;张文生;王永炎;: "基于"方证相关"理论的治"痹"经方调控TLR/TRAF信号通路的比较研究", 中国中药杂志, no. 08, 15 April 2010 (2010-04-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112446327B (en) | Remote sensing image target detection method based on non-anchor frame | |
| CN110598851A (en) | Time series data abnormity detection method fusing LSTM and GAN | |
| CN116342610B (en) | Steel structure assembly type building welding abnormality detection method | |
| CN112580668B (en) | Background fraud detection method and device and electronic equipment | |
| CN113807396B (en) | Internet of things high-dimensional data anomaly detection method, system, device and medium | |
| CN117911402B (en) | Water pump impeller appearance defect detection method and system | |
| CN102855642B (en) | The extracting method of image processing apparatus and its contour of object | |
| CN114387332B (en) | Pipeline thickness measuring method and device | |
| CN117911402A (en) | Water pump impeller appearance defect detection method and system | |
| CN112419243B (en) | Power distribution room equipment fault identification method based on infrared image analysis | |
| WO2021217854A1 (en) | False positive filtering method, device, equipment, and storage medium | |
| CN114046993A (en) | Slewing bearing state evaluation method based on multi-feature parameter fusion and FCM-HMM | |
| US11328402B2 (en) | Method and system of image based anomaly localization for vehicles through generative contextualized adversarial network | |
| CN111623905B (en) | Wind turbine generator bearing temperature early warning method and device | |
| CN112597539A (en) | Unsupervised learning-based time series anomaly detection method and system | |
| CN110086860A (en) | A kind of data exception detection method and device under Internet of Things big data environment | |
| CN116309517A (en) | Wire rod roller flaw detection method and system for enameled wire | |
| Yuan et al. | Retracted: Manifold learning‐based fuzzy k‐principal curve similarity evaluation for wind turbine condition monitoring | |
| He et al. | A simple method to train the AI diagnosis model of pulmonary nodules | |
| CN111354019B (en) | Visual tracking failure detection system based on neural network and training method thereof | |
| CN113852629A (en) | Network connection abnormity identification method based on natural neighbor self-adaptive weighted kernel density and computer storage medium | |
| CN117909692B (en) | Intelligent analysis method for operation data of double-disc motor bearing | |
| CN118014996B (en) | Electric energy meter circuit board defect detection method and system based on image recognition | |
| CN115683631B (en) | Bearing fault detection method and device | |
| CN116929753B (en) | Transmission gear state detection method, device, computer equipment and storage medium |
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 |