CN115082486B - Method for detecting surface quality of piston rod of hydraulic cylinder - Google Patents
Method for detecting surface quality of piston rod of hydraulic cylinder Download PDFInfo
- Publication number
- CN115082486B CN115082486B CN202211009524.8A CN202211009524A CN115082486B CN 115082486 B CN115082486 B CN 115082486B CN 202211009524 A CN202211009524 A CN 202211009524A CN 115082486 B CN115082486 B CN 115082486B
- Authority
- CN
- China
- Prior art keywords
- degree
- piston rod
- column
- pixel points
- scratch
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims abstract description 67
- 230000007547 defect Effects 0.000 claims abstract description 30
- 239000006185 dispersion Substances 0.000 claims abstract description 12
- 238000003708 edge detection Methods 0.000 claims abstract description 8
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000002547 anomalous effect Effects 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 5
- 239000002184 metal Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005253 cladding Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/70—
-
- G06T5/90—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Abstract
The invention relates to a method for detecting the surface quality of a piston rod of a hydraulic cylinder, which comprises the following steps: performing edge detection on the unfolded gray level image of the surface of the piston rod to be detected to obtain a scratch area of the surface of the piston rod; obtaining the transverse damage degree of the piston rod according to the length in the scratch area and the gray value of the abnormal pixel point; obtaining the damage degree of each column according to the gray value of the abnormal pixel point in each column; obtaining the damage degree of each column according to the distance between adjacent abnormal pixel points in each column and the dispersion degree of the abnormal pixel points; the comprehensive defect degree of the surface of the piston rod to be detected is obtained according to the transverse damage degree, the maximum longitudinal damage degree and the maximum scratch damage degree of the piston rod to be detected, and the quality of the piston rod to be detected is judged according to the comprehensive defect degree.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method for detecting the surface quality of a piston rod of a hydraulic cylinder.
Background
Pneumatic cylinder simple structure, operate steadily, easily speed governing, can realize linear motion etc., by the hoisting mechanism of wide application in hoist, luffing mechanism and bearing structure etc., the piston rod is the key part of pneumatic cylinder, the sealing performance of its surface quality direct influence pneumatic cylinder, the piston rod is the cylindrical metal parts of high bright gyration, in the piston rod use, because abrasive particle wearing and tearing, solid pollutant, body of rod surface hardness is low, contact stress is too big, lead to piston rod surface cladding material to have rectangular shape mar along the axial, along with the mar deepening, the leakproofness variation will directly lead to leaking the phenomenon, influence the operation safety.
Therefore, the defects existing on the surface of the piston rod are detected in advance, the piston rod is reprocessed, the leakage problem of the piston rod can be greatly reduced, the quality of the hydraulic cylinder is improved, the defect degree of a defect area is detected by traditional piston rod surface defect detection, and the distribution condition of the defect area is not considered, so that the detection result is not accurate enough, and therefore, a hydraulic cylinder piston rod surface quality detection method is needed.
Disclosure of Invention
The invention provides a method for detecting the surface quality of a piston rod of a hydraulic cylinder, which aims to solve the existing problems.
The invention discloses a method for detecting the surface quality of a piston rod of a hydraulic cylinder, which adopts the following technical scheme that the method comprises the following steps:
acquiring an expansion gray image of the surface of a piston rod to be detected, and carrying out edge detection on the expansion gray image to obtain a scratch area of the surface of the piston rod;
recording the pixels in the scratch area as abnormal pixels, and obtaining the damage degree of the scratch by utilizing the gray value of the abnormal pixels in each scratch area and the length of the scratch area; obtaining the transverse damage degree of the piston rod according to the damage degrees of all the scratches;
obtaining the damage degree of each column according to the gray value of the abnormal pixel point of each column in the expanded gray image;
obtaining the longitudinal damage degree of each column according to the damage degree of each column in the expanded gray image, the distance between adjacent abnormal pixel points of each column and the dispersion degree of the abnormal pixel points in each column;
and obtaining the comprehensive defect degree of the surface of the piston rod to be detected according to the obtained transverse damage degree, the maximum longitudinal damage degree in each row of longitudinal damage degrees and the maximum damage degree of the scratches, and judging the quality of the piston rod to be detected according to the comprehensive defect degree.
Further, the step of obtaining the scratch area on the surface of the piston rod according to the edge pixel points comprises the following steps:
obtaining a plurality of initial scratch areas on the surface of the piston rod according to the gray values of the edge pixel points;
and respectively carrying out closing operation on each initial scratch area to obtain a plurality of scratch areas.
Further, the step of obtaining the damage degree of the scratch by using the gray value of the abnormal pixel point of each scratch area and the length of the scratch area comprises the following steps:
respectively acquiring the gray value and the value of all abnormal pixel points in each scratch area and the maximum gray value;
respectively carrying out thinning operation on each scratch area to obtain the length of the corresponding scratch area;
and obtaining the damage degree of each scratch according to the gray value and the value, the maximum gray value and the length of each scratch area.
Further, the step of obtaining the longitudinal damage degree of each column according to the damage degree of each column in the expanded gray image, the distance between adjacent abnormal pixel points of each column and the dispersion degree of the abnormal pixel points in each column comprises the following steps:
obtaining the distribution range of the abnormal pixel points of each row according to the distance between the adjacent abnormal pixel points in each row;
the degree of longitudinal damage for each column was calculated according to the following formula:
T
wherein T represents the degree of longitudinal damage of each column;
indicating the damage degree of each column;
expressing the discrete degree of the abnormal pixel points in each column;
indicating the range of distribution of the anomalous pixel points in each column.
Further, the step of obtaining the distribution range of the abnormal pixel points in each column according to the distance between the adjacent abnormal pixel points in the column comprises the following steps:
respectively obtaining the distance sum value of each column by summing the distances between two adjacent abnormal pixel points in each column;
and taking the distance and the value of each column as the distribution range of the abnormal pixel points of each column.
Further, the step of obtaining the discrete degree of the abnormal pixel points in each row comprises:
respectively averaging the distances between two adjacent abnormal pixel points in each row to obtain the distance average value of each row;
and obtaining the dispersion degree of the abnormal pixel points of each row according to the distance mean value of each row and the distance between two adjacent abnormal pixel points.
Further, the step of obtaining the comprehensive defect degree of the surface of the piston rod to be detected according to the obtained transverse damage degree, the maximum longitudinal damage degree in each row of longitudinal damage degrees and the maximum damage degree of the scratch comprises the following steps:
calculating the comprehensive defect degree of the surface of the piston rod to be detected according to the following formula:
wherein, the first and the second end of the pipe are connected with each other,
representing the comprehensive defect degree of the surface of the piston rod to be detected;
indicating the degree of lateral damage to the piston rod;
represents the maximum damage degree of the scratch;
represents the maximum longitudinal damage;
weighting corresponding to the transverse damage degree of the piston rod;
the maximum degree of damage and the maximum degree of longitudinal damage of the scratch are weighted accordingly.
The invention has the beneficial effects that: according to the method for detecting the surface quality of the piston rod of the hydraulic cylinder, the scratch area is obtained through edge detection, the transverse damage degree of the piston rod is obtained according to the gray value of the abnormal pixel point of the scratch area, the maximum longitudinal damage degree of the piston rod is obtained through the gray value, the distribution range and the dispersion degree of the abnormal pixel point, the transverse damage degree represents all detected defect areas, the longitudinal damage degree represents the distribution condition of the defect areas, the longitudinal damage degree and the transverse damage degree are combined to determine the comprehensive defect degree, and the accuracy of detecting the surface quality of the piston rod can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart illustrating the general steps of an embodiment of a method for detecting the surface quality of a piston rod of a hydraulic cylinder according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An embodiment of the method for detecting the surface quality of the piston rod of the hydraulic cylinder according to the invention is shown in fig. 1, and the method comprises the following steps:
s1, acquiring an expansion gray image of the surface of a piston rod to be detected, and carrying out edge detection on the expansion gray image to obtain a scratch area of the surface of the piston rod.
The quality detection is carried out on the surface of the piston rod, images which are not affected by illumination on the surface of the piston rod need to be collected, the surface of the piston rod is made of metal, and due to the full-spectrum strong reflection effect of the surface of the metal, light supplement needs to be carried out on the surface of the piston rod, so that the image characteristics of the surface of the piston rod needed by the quality detection are guaranteed.
Specifically, a piston rod is placed on a roller conveyor, so that the piston rotates around an axis at a constant speed, two diffuse reflection LED light sources are placed on two sides of the piston rod to supplement light to the piston rod, a camera is placed above the piston rod to shoot the surface of the piston rod, and an initial unfolded image of the surface of the piston rod with uniform illumination distribution is obtained; inputting the obtained initial expansion image of the surface of the piston rod into a DNN network, enabling the label corresponding to the training set to be a single-channel semantic label, marking the background pixel point to be 0, marking the pixel point on the surface of the piston rod to be 1, and enabling the function used by the DNN network to be a cross entropy function, removing the background image to obtain a final expansion image of the surface of the piston rod; and (3) carrying out graying processing on the final expanded image on the surface of the piston rod to obtain an initial expanded gray image, and denoising the initial gray image by using the median filtering of a 3 x 3 window to obtain the expanded gray image on the surface of the piston rod to be detected because the image can generate photon noise and transmission noise in the generation and transmission processes.
Canny edge detection is carried out on the de-noised unfolded gray image, the brightness change at the scratch is obvious, namely the gray value change of pixel points in the unfolded gray image is obvious, and edge pixel points in the unfolded gray image are obtained through edge detection; segmenting an initial scratch area according to the gray value of the edge pixel point, and performing closed operation on the obtained initial scratch area, namely performing expansion operation firstly and then performing corrosion operation to obtain more accurate scratch area and scratch number; and thinning the scratch area to obtain a thinned image, and obtaining the length of each scratch area according to the thinned image.
S2, recording the pixels in the scratch area as abnormal pixels, and obtaining the damage degree of the scratch by using the gray value of the abnormal pixels in each scratch area and the length of the scratch area; the transverse damage degree of the piston rod is obtained according to the damage degree of all the scratches.
The deeper the depth of the scratch area is, the larger the width of the scratch area is, the larger the area of the scratch area illuminated by the diffuse reflection LED is, the more the reflection light is, therefore, the higher the brightness is, the larger the gray value is, and the damage degree of the scratch area is obtained according to the gray value.
Specifically, the gray values of all abnormal pixel points in each scratch area are respectively obtained to obtain a plurality of gray value sets, the sum of the gray values of all the abnormal pixel points in each set is obtained, and the obtained gray value sum of each set is the total damage of the scratch area; the deepest and widest area of the scratch is a key area which influences whether the hydraulic cylinder leaks or not, so the maximum gray value in each set is selected to represent the maximum damage of the scratch; the damage degree of the scratch was calculated according to the following formula (1):
wherein the content of the first and second substances,
indicating the degree of damage of the scratch;
indicates the length of the scratched area;
represents the total damage of the scratched area;
represents the maximum damage in the scratched area;
representing the weight corresponding to the length of the scratch area;
a weight corresponding to the total damage representing the scratched area;
weight corresponding to the largest damage in the scratch region, wherein the largestWeight corresponding to large damage
Weight corresponding to much greater than scratch length
And total damage correspondence weight
The specific value of the weight is set by the implementer according to the needs.
Extracting the maximum damage degree of the scratches from the obtained damage degree of each scratch, and summing the damage degrees of all the scratches to obtain the longitudinal damage degree of the piston rod to be detected.
And S3, obtaining the damage degree of each column according to the gray value of the abnormal pixel point of each column in the expanded gray image.
The leakproofness of pneumatic cylinder is related to the impaired degree of piston rod circumference, and if the piston rod distributes densely with the round mar in pneumatic cylinder contact chamber, the possibility of weeping is just bigger.
Specifically, the expansion gray image obtained in step S1 is a rectangular image, the direction parallel to the axial direction of the piston rod in the expansion gray image is recorded as a transverse direction, i.e., a row, and the direction perpendicular to the axial direction of the piston rod is recorded as a longitudinal direction, i.e., a column; and respectively acquiring the gray value of each row of abnormal pixel points in the expanded gray image, wherein each row refers to each single pixel row, and the gray value and the value of the abnormal pixel points in each row are the damage degree of the row.
And S4, obtaining the longitudinal damage degree of each column according to the damage degree of each column in the expanded gray image, the distance between adjacent abnormal pixel points of each column and the dispersion degree of the abnormal pixel points.
Specifically, the distance between two adjacent abnormal pixel points in each row is respectively obtained, the distance between the two pixel points is calculated according to the central distance of the pixel points, namely the distance between the two adjacent pixel points is 1, the distances between the two adjacent abnormal pixel points obtained in each row are summed to obtain a distance sum value, and the distance sum value is the distribution range of the abnormal pixel points in the row; averaging the distances between adjacent abnormal pixel points obtained in each row to obtain a distance average value, and calculating the dispersion degree of the abnormal pixel points in each row according to the following formula (2):
V
（2）
wherein, V represents the discrete degree of the abnormal pixel points of each column;
representing the mean of the distances of each column;
is shown as
The distance between every two adjacent abnormal pixel points;
indicates the number of columns; the smaller the discrete degree is, the more concentrated the abnormal pixel points are, and the more serious the circumferential damage of the piston rod is.
The degree of longitudinal damage for each column is calculated according to the following formula:
T
wherein T represents the degree of longitudinal damage of each column;
indicating the damage degree of each column;
expressing the discrete degree of the abnormal pixel points in each column;
indicating the distribution range of abnormal pixel points in each column。
S5, obtaining the comprehensive defect degree of the surface of the piston rod to be detected according to the obtained transverse damage degree, the maximum longitudinal damage degree in each row of longitudinal damage degrees and the maximum damage degree of the scratches, and judging the quality of the piston rod to be detected according to the comprehensive defect degree.
Specifically, the maximum longitudinal damage degree is obtained from the obtained longitudinal damage degrees of the plurality of columns
Whether the hydraulic cylinder leaks or not is affected by the most seriously damaged circumferential surface; calculating the comprehensive defect degree of the surface of the piston rod according to the following formula:
wherein, the first and the second end of the pipe are connected with each other,
representing the comprehensive defect degree of the surface of the piston rod to be detected;
indicating the degree of lateral damage to the piston rod;
represents the maximum damage degree of the scratch;
represents the maximum longitudinal damage;
weighting corresponding to the transverse damage degree of the piston rod;
the maximum degree of damage of the scratch and the maximum degree of longitudinal damage are weighted correspondingly,
、
the value implementer of (2) sets the value according to the requirement.
Setting composite defect threshold
When the obtained comprehensive defect degree
Less than or equal to the threshold value of the comprehensive defect
When the surface quality of the piston rod is qualified, the comprehensive defect degree is obtained
Greater than the threshold of the composite defect
When the piston rod surface quality is unqualified, the sorting device is controlled to sort out the unqualified piston rod for reprocessing, and the comprehensive defect threshold value
The implementer sets the settings according to the requirements.
In summary, according to the method for detecting the surface quality of the piston rod of the hydraulic cylinder, the scratch area is obtained through edge detection, the transverse damage degree of the piston rod is obtained according to the gray value of the abnormal pixel point in the scratch area, the maximum longitudinal damage degree of the piston rod is obtained through the gray value, the distribution range and the dispersion degree of the abnormal pixel point, the transverse damage degree represents all detected defect areas, the longitudinal damage degree represents the distribution condition of the defect areas, the longitudinal damage degree and the transverse damage degree are combined to determine the comprehensive defect degree, and the accuracy of detecting the surface quality of the piston rod can be improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. A method for detecting the surface quality of a piston rod of a hydraulic cylinder is characterized by comprising the following steps:
acquiring an expansion gray image of the surface of a piston rod to be detected, and carrying out edge detection on the expansion gray image to obtain a scratch area of the surface of the piston rod;
recording the pixels in the scratch area as abnormal pixels, and obtaining the damage degree of the scratch by utilizing the gray value of the abnormal pixels in each scratch area and the length of the scratch area; obtaining the transverse damage degree of the piston rod according to the damage degrees of all the scratches;
obtaining the damage degree of each column according to the sum of the gray values of the abnormal pixel points of each column in the expanded gray image;
obtaining the longitudinal damage degree of each column according to the damage degree of each column in the expanded gray image, the distance between adjacent abnormal pixel points of each column and the dispersion degree of the abnormal pixel points in each column;
obtaining the comprehensive defect degree of the surface of the piston rod to be detected according to the obtained transverse damage degree, the maximum longitudinal damage degree in each row of longitudinal damage degrees and the maximum damage degree of the scratch, wherein a formula for calculating the comprehensive defect degree of the surface of the piston rod to be detected is as follows:
wherein the content of the first and second substances,
representing the comprehensive defect degree of the surface of the piston rod to be detected;
indicating the degree of lateral damage to the piston rod;
represents the maximum damage degree of the scratch;
represents the maximum longitudinal damage;
weighting corresponding to the transverse damage degree of the piston rod;
weights corresponding to the maximum damage degree and the maximum longitudinal damage degree of the scratch;
and judging the quality of the piston rod to be detected according to the comprehensive defect degree.
2. The method of claim 1, wherein the step of obtaining the scratch area of the piston rod surface according to the edge pixel points comprises:
obtaining a plurality of initial scratch areas on the surface of the piston rod according to the gray values of the edge pixel points;
and respectively carrying out closing operation on each initial scratch area to obtain a plurality of scratch areas.
3. The method as claimed in claim 1, wherein the step of obtaining the damage degree of the scratch using the gray value of the abnormal pixel point of each scratch region and the length of the scratch region comprises:
respectively acquiring the gray value and the value of all abnormal pixel points in each scratch area and the maximum gray value;
respectively carrying out thinning operation on each scratch area to obtain the length of the corresponding scratch area;
and obtaining the damage degree of each scratch according to the gray value and the value, the maximum gray value and the length of each scratch area.
4. The method for detecting the surface quality of the piston rod of the hydraulic cylinder according to claim 1, wherein the step of obtaining the longitudinal damage degree of each column according to the damage degree of each column in the expanded gray image, the distance between adjacent abnormal pixel points of each column and the dispersion degree of the abnormal pixel points in each column comprises the following steps:
obtaining the distribution range of the abnormal pixel points of each row according to the distance between the adjacent abnormal pixel points in each row;
the degree of longitudinal damage for each column is calculated according to the following formula:
T
wherein T represents the degree of longitudinal damage of each column;
indicating the damage degree of each column;
expressing the discrete degree of the abnormal pixel points in each column;
indicating the range of distribution of the anomalous pixel points in each column.
5. The method of claim 4, wherein the step of obtaining the distribution range of the abnormal pixel points of each column according to the distance between the adjacent abnormal pixel points of the column comprises:
respectively obtaining the distance sum value of each column by the distance sum value between two adjacent abnormal pixel points in each column;
and taking the distance and the value of each column as the distribution range of the abnormal pixel points of each column.
6. The method of claim 1, wherein the step of obtaining the dispersion degree of the abnormal pixel points in each row comprises:
respectively averaging the distances between two adjacent abnormal pixel points in each row to obtain the distance average value of each row;
and obtaining the dispersion degree of the abnormal pixel points of each row according to the distance mean value of each row and the distance between two adjacent abnormal pixel points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211009524.8A CN115082486B (en) | 2022-08-23 | 2022-08-23 | Method for detecting surface quality of piston rod of hydraulic cylinder |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211009524.8A CN115082486B (en) | 2022-08-23 | 2022-08-23 | Method for detecting surface quality of piston rod of hydraulic cylinder |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115082486A CN115082486A (en) | 2022-09-20 |
| CN115082486B true CN115082486B (en) | 2022-11-11 |
Family
ID=83244760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211009524.8A Active CN115082486B (en) | 2022-08-23 | 2022-08-23 | Method for detecting surface quality of piston rod of hydraulic cylinder |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115082486B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206546340U (en) * | 2017-03-01 | 2017-10-10 | 青岛智目科技有限公司 | A kind of piston rod surface defective vision detection device |
| CN111692998B (en) * | 2020-06-11 | 2022-02-11 | 西格迈股份有限公司 | Piston rod surface roughness detecting system |
| CN212988292U (en) * | 2020-06-11 | 2021-04-16 | 西格迈股份有限公司 | Piston rod surface roughness detecting system |
| CN114235047A (en) * | 2021-12-16 | 2022-03-25 | 浙江保康电器有限公司 | Vacuum cup manufacturing process for online detection of production quality |
| CN114359274B (en) * | 2022-03-16 | 2022-05-31 | 布鲁奇维尔通风设备启东有限公司 | Ventilation equipment blade quality detection method, device and system based on image processing |
-
2022
- 2022-08-23 CN CN202211009524.8A patent/CN115082486B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115082486A (en) | 2022-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115239704B (en) | Accurate detection and repair method for wood surface defects | |
| CN115345885B (en) | Appearance quality detection method for metal fitness equipment | |
| CN115147409B (en) | Mobile phone shell production quality detection method based on machine vision | |
| CN114972326A (en) | Defective product identification method for heat-shrinkable tube expanding process | |
| CN116777916B (en) | Defect detection method based on metal shell of pump machine | |
| CN109949209B (en) | Rope detection and removal method based on deep learning | |
| CN101140216A (en) | Gas-liquid two-phase flow type recognition method based on digital graphic processing technique | |
| CN113628189A (en) | Rapid strip steel scratch defect detection method based on image recognition | |
| CN115272303B (en) | Textile fabric defect degree evaluation method, device and system based on Gaussian blur | |
| CN110544261A (en) | Blast furnace tuyere coal injection state detection method based on image processing | |
| CN113989716A (en) | Method, system, equipment and terminal for detecting foreign object of underground coal mine conveyor belt | |
| CN115049657A (en) | Glass defect detection method | |
| CN104834939A (en) | Method for automatically detecting cavity detect of porous metal material online | |
| CN113989257A (en) | Electric power comprehensive pipe gallery settlement crack identification method based on artificial intelligence technology | |
| CN115272347A (en) | Bearing defect identification method | |
| CN115063620A (en) | Bit layering-based Roots blower bearing wear detection method | |
| CN115526889B (en) | Nondestructive testing method of boiler pressure pipeline based on image processing | |
| CN114881960A (en) | Feature enhancement-based cloth linear defect detection method and system | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN115082486B (en) | Method for detecting surface quality of piston rod of hydraulic cylinder | |
| CN115797361B (en) | Aluminum template surface defect detection method | |
| CN110400320A (en) | A kind of dividing method of electrowetting defect pixel | |
| Mansano et al. | Inspection of metallic surfaces using local binary patterns | |
| CN115115624A (en) | Rolling damage detection method for anti-corrosion coating of cable bridge | |
| Lian et al. | Film and television animation sensing and visual image by computer digital image technology |
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 |