CN114627316A - Hydraulic system oil leakage detection method based on artificial intelligence - Google Patents
Hydraulic system oil leakage detection method based on artificial intelligence Download PDFInfo
- Publication number
- CN114627316A CN114627316A CN202210278608.5A CN202210278608A CN114627316A CN 114627316 A CN114627316 A CN 114627316A CN 202210278608 A CN202210278608 A CN 202210278608A CN 114627316 A CN114627316 A CN 114627316A
- Authority
- CN
- China
- Prior art keywords
- oil leakage
- hydraulic oil
- suspected
- hydraulic system
- area
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F15—FLUID-PRESSURE ACTUATORS; HYDRAULICS OR PNEUMATICS IN GENERAL
- F15B—SYSTEMS ACTING BY MEANS OF FLUIDS IN GENERAL; FLUID-PRESSURE ACTUATORS, e.g. SERVOMOTORS; DETAILS OF FLUID-PRESSURE SYSTEMS, NOT OTHERWISE PROVIDED FOR
- F15B19/00—Testing; Calibrating; Fault detection or monitoring; Simulation or modelling of fluid-pressure systems or apparatus not otherwise provided for
- F15B19/005—Fault detection or monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Abstract
The invention relates to an oil leakage detection method of a hydraulic system based on artificial intelligence, and belongs to the field of oil leakage detection of the hydraulic system. The method comprises the following steps: acquiring RGB images of a lower ground area of a hydraulic system, and performing HSV conversion processing on the RGB images of the lower ground area of the hydraulic system to obtain HSV images of the lower ground area of the hydraulic system; judging a suspected hydraulic oil leakage area in an RGB image of the ground area under the hydraulic system according to the lightness and saturation of each pixel point in the HSV image of the ground area under the hydraulic system; calculating the difference value between the texture complexity of the suspected hydraulic oil leakage area and the standard texture complexity of the corresponding area when no leakage occurs, and judging whether the difference value is greater than a set complexity difference value threshold value or not; and if the complexity difference is larger than the set complexity difference threshold, judging that the hydraulic system has a hydraulic oil leakage fault. The invention belongs to an automatic detection method, and solves the problems of human resource consumption, incapability of timely detection and the like existing in dependence on manual detection.
Description
Technical Field
The invention relates to the field of oil leakage detection of hydraulic systems, in particular to an artificial intelligence-based oil leakage detection method of a hydraulic system.
Background
The hydraulic system has high leakage frequency of hydraulic oil, and once the hydraulic oil leaks, the hydraulic oil resource is wasted, the environment is easily polluted, and the hydraulic system cannot work normally. In order to find out the leakage of hydraulic oil in time, the hydraulic system is usually tested by related personnel at intervals, for example, every 1 day.
Whether the method for detecting by means of related personnel can find out in time whether the hydraulic oil leakage condition depends on the frequency of manual time-sharing detection to a greater extent can cause the following problems: if the detection efficiency is high, although the leakage condition of the hydraulic oil can be identified in time, large human resources are consumed; if the detection frequency is lower, although the consumption of manpower resources is reduced, the leakage condition of the hydraulic oil is not easy to find in time, the waste of the hydraulic oil resources and the environmental pollution are caused, and the normal work of a hydraulic system can be influenced when the leakage is serious.
Disclosure of Invention
The invention aims to provide an oil leakage detection method of a hydraulic system based on artificial intelligence, which is used for solving the problems existing in the prior art that whether the hydraulic oil leakage condition of the hydraulic system occurs or not is detected manually.
In order to solve the problems, the technical scheme of the hydraulic system oil leakage detection method based on artificial intelligence comprises the following steps:
acquiring RGB images of a lower ground area of a hydraulic system, and performing HSV conversion processing on the RGB images of the lower ground area of the hydraulic system to obtain HSV images of the lower ground area of the hydraulic system;
judging a suspected hydraulic oil leakage area in an RGB image of the ground area under the hydraulic system according to the lightness and saturation of each pixel point in the HSV image of the ground area under the hydraulic system;
calculating the difference value between the texture complexity of the suspected hydraulic oil leakage area and the standard texture complexity of the corresponding area when no leakage occurs, and judging whether the difference value is greater than a set complexity difference value threshold value or not;
and if the complexity difference is larger than the set complexity difference threshold, judging that the hydraulic system has a hydraulic oil leakage fault.
Has the advantages that: according to the invention, the change of the ground image when the hydraulic oil leakage occurs in the hydraulic oil system is reflected through the pixel point information change and the texture information change of the RGB image in the ground area under the hydraulic system, and whether the hydraulic oil leakage occurs in the hydraulic system is detected according to the change of the ground image when the hydraulic oil leakage occurs in the hydraulic oil system, so that the detection result is objective and accurate; the invention realizes the detection of whether the hydraulic oil leakage occurs in the hydraulic system based on the RGB image of the ground area under the hydraulic system, belongs to an automatic detection method, and solves the problems of human resource consumption, incapability of timely detection and the like existing in the manual detection.
Further, the determining a suspected hydraulic oil leakage area in an RGB image of the ground area under the hydraulic system according to the lightness and saturation of each pixel point in the HSV image of the ground area under the hydraulic system includes:
calculating pixel judgment indexes corresponding to all pixel points in the HSV image of the ground area under the hydraulic system according to the brightness and the saturation of all the pixel points in the HSV image of the ground area under the hydraulic system;
constructing a gray level image according to pixel judgment indexes corresponding to all pixel points in an HSV image of a ground area under a hydraulic system, wherein the gray level value of each pixel point in the gray level image is a value obtained after normalization processing of the corresponding pixel judgment indexes;
judging whether the gray value of each pixel point in the gray image is greater than a set gray threshold value or not, and taking a connected domain formed by the pixel points of which the gray values are greater than the set gray threshold value as a suspected hydraulic oil leakage area in the gray image; and taking an area corresponding to the suspected hydraulic oil leakage area in the gray level image in the RGB image of the ground area under the hydraulic system as the suspected hydraulic oil leakage area.
Further, a pixel judgment index corresponding to each pixel point in the HSV image of the ground area under the hydraulic system is calculated by using the following formula:
wherein, deltakA pixel judgment index S corresponding to the kth pixel point in the HSV image of the ground area under the hydraulic systemkCorresponding saturation degree V to the kth pixel point in the HSV image of the ground area under the hydraulic systemkAnd the lightness corresponding to the kth pixel point in the HSV image of the ground area under the hydraulic system.
Further, the method for calculating the texture complexity of the suspected hydraulic oil leakage area comprises the following steps:
constructing a binary group corresponding to each pixel point in the suspected hydraulic oil leakage area according to the gray value of each pixel point in the suspected hydraulic oil leakage area and the mean value of the gray values of the pixel points in the corresponding 8 neighborhoods;
constructing a binary group corresponding to each pixel point at the edge of the suspected hydraulic oil leakage area according to the gray value of each pixel point at the edge of the suspected hydraulic oil leakage area and the mean value of similar pixel points in the corresponding 8 neighborhoods, wherein the similar pixel points are pixel points of which the pixel gradient values relative to the pixel points at the corresponding edge are smaller than a set gradient threshold;
calculating the gray entropy of the suspected hydraulic oil leakage area according to the binary group corresponding to each pixel point in the suspected hydraulic oil leakage area and the binary group corresponding to each pixel point at the edge of the suspected hydraulic oil leakage area, and taking the gray entropy of the suspected hydraulic oil leakage area as the texture complexity of the suspected hydraulic oil leakage area.
Further, the gray entropy of the suspected hydraulic oil leakage area is calculated by using the following formula:
h is the gray entropy of a suspected hydraulic oil leakage area, and N is1The number of the pixel points in the suspected hydraulic oil leakage area,
is the jth hydraulic oil leakage area1The gray value of each pixel point is calculated,
is the jth hydraulic oil leakage area1The average value of the gray levels of the pixel points in 8 neighborhoods corresponding to each pixel point,
is composed of
Number of occurrences, N2The number of the edge pixel points in the suspected hydraulic oil leakage area,
is the j-th suspected hydraulic oil leakage area2The gray value of the pixel points at each edge,
is the j-th suspected hydraulic oil leakage area2The average value of the gray levels of similar pixel points in 8 neighborhoods corresponding to the edge pixel points,
is composed of
The number of occurrences.
Further, if the complexity difference is not greater than the set complexity difference threshold, it is determined that the hydraulic oil leakage fault does not occur in the hydraulic oil system.
Drawings
FIG. 1 is a flow chart of an oil leakage detection method of a hydraulic system based on artificial intelligence.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
The embodiment aims to solve the problems of manpower consumption and incapability of timely detection when the hydraulic oil leakage condition of the hydraulic system is detected manually or not in the prior art, and as shown in fig. 1, the method for detecting the oil leakage of the hydraulic system based on artificial intelligence comprises the following steps:
(1) acquiring RGB images of a lower ground area of a hydraulic system, and performing HSV conversion processing on the RGB images of the lower ground area of the hydraulic system to obtain HSV images of the lower ground area of the hydraulic system;
when the hydraulic system has a hydraulic oil leakage fault, hydraulic oil can flow to the ground below the hydraulic system, and the ground area below the hydraulic system can be polluted by the hydraulic oil; because hydraulic system generally sets up in mechanical factory building, mechanical factory building internal environment is relatively poor, and ground is mostly materials such as cement, if a certain region on ground is covered by hydraulic oil, some changes can take place for the colour in this region to compare in the colour before not being covered by hydraulic oil, mainly reflects in the colour deepening.
In consideration of some changes of the ground when hydraulic oil leaks in the hydraulic system, in order to determine whether the hydraulic system leaks hydraulic oil, image acquisition equipment is arranged around the hydraulic system and used for acquiring RGB images of the ground area under the hydraulic system. In the embodiment, in order to find the hydraulic oil leakage condition in time when the hydraulic oil leakage occurs in the hydraulic system, the image of the ground area under the hydraulic system is acquired in real time; as another embodiment, the collection may be performed once every set time interval.
And after the RGB image of the lower ground area of the hydraulic system is obtained, performing HSV conversion processing on the RGB image to obtain a corresponding HSV image of the lower ground area of the hydraulic system. For any pixel point in the RGB image, the lightness V of the corresponding pixel point after conversion is as follows:
the saturation S of the converted corresponding pixel point is:
wherein the content of the first and second substances,
the conversion of RGB images into corresponding HSV images is prior art and will not be described herein too much.
(2) Judging a suspected hydraulic oil leakage area in an RGB image of the ground area under the hydraulic system according to the lightness and saturation of each pixel point in the HSV image of the ground area under the hydraulic system;
when the ground area below the hydraulic system is covered by hydraulic oil, the color of the covered area becomes dark, and compared with the pixel points of the uncovered area, the brightness and the saturation of the pixel points in the covered area are lower and higher in the corresponding HSV image. Therefore, the suspected hydraulic oil leakage area in the RGB image of the ground area under the hydraulic system is determined by the following process:
calculating a pixel judgment index corresponding to each pixel point in the HSV image of the ground area under the hydraulic system according to the lightness and the saturation of each pixel point in the HSV image of the ground area under the hydraulic system, wherein the calculation formula of the pixel judgment index is as follows:
wherein, deltakA pixel judgment index S corresponding to the kth pixel point in the HSV image of the ground area under the hydraulic systemkCorresponding to the kth pixel point in HSV image of ground area under hydraulic systemDegree of saturation, VkAnd the lightness corresponding to the kth pixel point in the HSV image of the ground area under the hydraulic system.
Constructing a gray level image according to pixel judgment indexes corresponding to all pixel points in an HSV image of the ground area under the hydraulic system, wherein the gray level value of each pixel point in the gray level image is a value obtained after normalization processing of the corresponding pixel judgment indexes; namely: the method comprises the steps of normalizing pixel judgment indexes corresponding to all pixel points in an HSV image of a ground area under a hydraulic system, constructing a gray image according to the normalized values corresponding to all the pixel points, wherein the gray value of each pixel point in the gray image is the normalized value of the pixel judgment index corresponding to the pixel point.
Judging whether the gray value of each pixel point in the gray image is larger than a set gray threshold value or not, and taking a connected domain formed by each pixel point of which the gray value is larger than the set gray threshold value as a suspected hydraulic oil leakage area in the gray image; and taking an area corresponding to the suspected hydraulic oil leakage area in the gray level image in the RGB image of the ground area under the hydraulic system as the suspected hydraulic oil leakage area. The specific process is as follows:
based on the gray level threshold deltaTAnd (4) segmenting the gray level image to extract a suspected hydraulic oil leakage area. In order to avoid the problem that the suspected hydraulic oil leakage area is extracted inaccurately due to artificially setting the gray threshold, the embodiment is provided with: by a grey scale threshold deltaTDividing the gray level image into two categories, and then respectively calculating probability indexes of the two categories of pixels:
in the formula, Pi is the probability of the occurrence of the pixel point with the gray value i,
nithe number of pixels with gray value i, N is the total number of pixels in the gray image, C1(U1) is the proportion of the number of pixels in the first type region U1 to the total number of pixels in the gray level image, C2(U2) is the ratio of the number of pixels in the second category region U2 to the total number of pixels in the gray scale image, C1(U1)+C2(U2)＝1，δChinese angelica root-barkThe processed values are normalized by δ.
Then, the mean of the grays of the two classes is calculated:
in the formula, g1Is the mean value of the gray levels, g, corresponding to the first category region U12The gray level average value corresponding to the second category area U2.
Calculating the gray threshold value based on the average gray value of the two categories, specifically calculating the delta corresponding to the maximum difference between the two categoriesChinese angelica root-barkAs a gray level threshold value deltaTI.e. the gray level threshold δTIt can be guaranteed that the difference between the pixels in the two classes is maximal. Namely:
Q(δchinese angelica root-bark)＝|g1-g2|，δChinese angelica root-bark∈[0,1]
δT＝argmax{Q(δChinese angelica root-bark),δChinese angelica root-bark∈[0,1]}
The gray threshold value delta is obtainedTThen, based on the gray threshold, extracting a suspected leakage area: value delta after normalization of pixel determination index value corresponding to certain pixel pointChinese angelica root-bark>δTThen, the pixel point is taken as the pixel point of the suspected leakage area; value delta after normalization of pixel determination index value corresponding to certain pixel pointChinese angelica root-bark≤δTAnd judging that the pixel point is not the pixel point of the suspected leakage area.
Therefore, a set of pixel points of a suspected leakage area can be obtained, and a connected domain corresponding to the set is the suspected hydraulic oil leakage area in the gray level image; and according to the position information in the suspected hydraulic oil leakage area in the gray level image, taking the area, corresponding to the suspected hydraulic oil leakage area in the gray level image, in the RGB image of the ground area under the hydraulic system as the suspected hydraulic oil leakage area.
It should be noted that: in this embodiment, each connected domain corresponding to the set of the pixel points of the suspected leakage area is used as a leakage area, and if the number of the connected domains corresponding to the set of the pixel points of the suspected leakage area is multiple, the corresponding gray-scale image includes multiple suspected hydraulic oil leakage areas, and the corresponding RGB image also includes multiple suspected hydraulic oil leakage areas. When the RGB image comprises a plurality of suspected hydraulic oil leakage areas, each suspected hydraulic oil leakage area is analyzed independently.
(3) Calculating the difference value between the texture complexity of the suspected hydraulic oil leakage area and the standard texture complexity of the corresponding area when no leakage occurs, and judging whether the difference value is greater than a set complexity difference value threshold value or not;
in a mechanical production plant, shadows generated by various hydraulic equipment or other facilities due to illumination factors may also have reduced lightness and increased saturation in the RGB image, which may interfere with the determination process of the suspected hydraulic oil leakage area; in consideration of this situation, the embodiment further determines whether the suspected hydraulic oil leakage area is a shadow area by combining the texture complexity of the suspected hydraulic oil leakage area, so as to avoid taking the shadow area on the ground as the hydraulic oil leakage coverage area on the ground.
The gray level entropy index can reflect the texture complexity, and for a suspected hydraulic oil leakage area, the gray level entropy index corresponding to the suspected hydraulic oil leakage area is calculated, wherein the process is as follows:
firstly, constructing a binary group corresponding to each pixel point in the suspected hydraulic oil leakage area according to the gray value of each pixel point in the suspected hydraulic oil leakage area and the mean value of the gray values of the pixel points in the corresponding 8 neighborhoods
Is the c-th in 8 neighborhoods1The gray values of adjacent pixel points;
secondly, constructing a binary group corresponding to each pixel point at the edge of the suspected hydraulic oil leakage area according to the gray value of each pixel point at the edge of the suspected hydraulic oil leakage area and the average value of the similar pixel points in the corresponding 8 neighborhoods
n is the number of similar pixel points in the 8 neighborhoods,
is the c-th in 8 neighborhoods2The gray values of the similar pixel points;
in this embodiment, the similar pixel points are pixel points whose gradient values of pixels relative to corresponding edge pixel points are smaller than a set gradient threshold, and for each pixel point at the edge of the suspected hydraulic oil leakage area, only the similar pixel points in the 8 neighborhoods of the edge pixel points are used as a basis for calculating a binary group corresponding to the edge pixel point, so that the influence of large pixel difference of the pixel points in the non-suspected hydraulic oil leakage area adjacent to the edge pixel points on the subsequent calculation of the gray entropy of the suspected hydraulic oil leakage area can be avoided, and the accuracy of the calculation of the gray entropy of the suspected hydraulic oil leakage area is improved. The pixel gradient value of a pixel point can reflect the pixel difference between the pixel point and a certain adjacent pixel point, and the calculation of the pixel gradient value of the pixel point is the prior art and is not repeated here.
And thirdly, calculating the gray entropy of the suspected hydraulic oil leakage area according to the binary group corresponding to each pixel point in the suspected hydraulic oil leakage area and the binary group corresponding to each pixel point at the edge of the suspected hydraulic oil leakage area, and taking the gray entropy of the suspected hydraulic oil leakage area as the texture complexity of the suspected hydraulic oil leakage area.
The formula for calculating the gray entropy of the suspected hydraulic oil leakage area in the embodiment is as follows:
h is the gray entropy of a suspected hydraulic oil leakage area, and N is1The number of the pixel points in the suspected hydraulic oil leakage area,
is the jth hydraulic oil leakage area1The gray value of each pixel point is calculated,
is the jth in the suspected hydraulic oil leakage area1The average value of the gray levels of the pixel points in the 8 neighborhoods corresponding to each pixel point,
is composed of
Number of occurrences, N2The number of the edge pixel points in the suspected hydraulic oil leakage area,
is the j-th suspected hydraulic oil leakage area2The gray value of the pixel points at each edge,
is the j th suspected hydraulic oil leakage area2The average value of the gray levels of similar pixel points in 8 neighborhoods corresponding to the edge pixel points,
is composed of
The number of occurrences.
If the ground is covered with hydraulic oil, a layer of oil film is added on the ground relative to the situation that the ground is not covered with the hydraulic oil, on one hand, the oil film can change the imaging effect in the image of the ground area under the hydraulic system by combining the light reflection and light refraction phenomena, so that the texture information of the ground area under the hydraulic system in the image is changed compared with the corresponding texture information when the ground area under the hydraulic system is not covered with the hydraulic oil, wherein the change of the texture complexity is included; on the other hand, oil stains and other impurities may exist in the hydraulic oil, and the imaging effect in the ground area image under the hydraulic system can be changed after the hydraulic oil covers the ground, so that the texture complexity is changed.
In consideration of the above change of the ground area under the hydraulic system in the image after the ground is covered with the hydraulic oil, but the texture complexity of the shadow area does not change when the camera view angle and the light source are not changed, in this embodiment, after the gray entropy of the suspected hydraulic oil leakage area is obtained, the difference between the gray entropy of the suspected hydraulic oil leakage area and the standard texture complexity of the corresponding area when the leakage does not occur is calculated, and whether the area is the shadow area can be judged according to the difference and the set complexity difference threshold. The standard texture complexity of the corresponding region when no leakage occurs can be solved by the same method for solving the texture complexity of the suspected hydraulic oil leakage region as the method for solving the texture complexity of the suspected hydraulic oil leakage region, except that the image based on the texture is the image acquired when no hydraulic oil leakage occurs.
If the difference is smaller than the set complexity difference threshold, the corresponding suspected hydraulic oil leakage area can be judged to be a shadow area, the set complexity difference threshold can be determined according to an empirical value, but in order to avoid the misjudgment of the hydraulic oil coverage area caused by the influence of the shadow area when the hydraulic oil coverage area and the shadow area are overlapped, the set complexity difference threshold is set to be relatively smaller, so that the area corresponding to the difference smaller than the set complexity difference threshold can be ensured to only include the shadow area and not the hydraulic oil leakage area basically.
It should be noted that: when the number of the suspected hydraulic oil leakage areas determined in the step (2) is more than 2, calculating and determining each suspected leakage area respectively; and if all the suspected hydraulic oil leakage areas are judged to be shadow areas, it is indicated that hydraulic oil of the hydraulic system does not leak.
(4) And if the complexity difference is larger than the set complexity difference threshold, judging that the hydraulic system has a hydraulic oil leakage fault.
When the difference value between the texture complexity of the suspected hydraulic oil leakage area and the standard texture complexity of the corresponding area when no leakage occurs is larger than the set complexity difference value threshold value, the hydraulic oil leakage condition of the hydraulic system is indicated, and related personnel can be reminded to confirm in an alarm mode.
In the embodiment, the change of the ground image when the hydraulic oil leakage occurs in the hydraulic oil system is reflected through the change of pixel point information and the change of texture information of the RGB image in the ground area under the hydraulic system, and whether the hydraulic oil leakage occurs in the hydraulic system is detected according to the change of the ground image when the hydraulic oil leakage occurs in the hydraulic oil system, so that the detection result is objective and accurate; the embodiment realizes the detection of the hydraulic system whether hydraulic oil leakage occurs or not based on the RGB image of the ground area under the hydraulic system, belongs to an automatic detection method, and solves the problems of human resource consumption, incapability of timely detection and the like existing in the manual detection.
It should be noted that while the preferred embodiments of the present invention have been described, additional variations and modifications to these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
Claims (6)
1. An oil leakage detection method of a hydraulic system based on artificial intelligence is characterized by comprising the following steps:
acquiring RGB images of a lower ground area of a hydraulic system, and performing HSV conversion processing on the RGB images of the lower ground area of the hydraulic system to obtain HSV images of the lower ground area of the hydraulic system;
judging a suspected hydraulic oil leakage area in an RGB image of the ground area under the hydraulic system according to the lightness and saturation of each pixel point in the HSV image of the ground area under the hydraulic system;
calculating the difference value between the texture complexity of the suspected hydraulic oil leakage area and the standard texture complexity of the corresponding area when no leakage occurs, and judging whether the difference value is greater than a set complexity difference value threshold value or not;
and if the complexity difference is larger than the set complexity difference threshold, judging that the hydraulic system has a hydraulic oil leakage fault.
2. The method for detecting the oil leakage of the hydraulic system based on the artificial intelligence as claimed in claim 1, wherein the step of determining the suspected hydraulic oil leakage area in the RGB image of the ground area under the hydraulic system according to the lightness and saturation of each pixel point in the HSV image of the ground area under the hydraulic system comprises the steps of:
calculating pixel judgment indexes corresponding to all pixel points in the HSV image of the ground area under the hydraulic system according to the brightness and the saturation of all the pixel points in the HSV image of the ground area under the hydraulic system;
constructing a gray level image according to pixel judgment indexes corresponding to all pixel points in an HSV image of a ground area under a hydraulic system, wherein the gray level value of each pixel point in the gray level image is a value obtained after normalization processing of the corresponding pixel judgment indexes;
judging whether the gray value of each pixel point in the gray image is larger than a set gray threshold value or not, and taking a connected domain formed by the pixel points of which the gray values are larger than the set gray threshold value as a suspected hydraulic oil leakage area in the gray image; and taking an area corresponding to the suspected hydraulic oil leakage area in the gray level image in the RGB image of the ground area under the hydraulic system as the suspected hydraulic oil leakage area.
3. The hydraulic system oil leakage detection method based on artificial intelligence of claim 2, wherein the pixel judgment index corresponding to each pixel point in the HSV image of the ground area under the hydraulic system is calculated by using the following formula:
wherein, deltakA pixel judgment index S corresponding to the kth pixel point in the HSV image of the ground area under the hydraulic systemkCorresponding saturation degree V to the kth pixel point in the HSV image of the ground area under the hydraulic systemkAnd the lightness corresponding to the kth pixel point in the HSV image of the ground area under the hydraulic system.
4. The artificial intelligence based oil leakage detection method for the hydraulic system according to claim 1, wherein the calculation method for the texture complexity of the suspected hydraulic oil leakage area comprises:
constructing a binary group corresponding to each pixel point in the suspected hydraulic oil leakage area according to the gray value of each pixel point in the suspected hydraulic oil leakage area and the mean value of the gray values of the pixel points in the corresponding 8 neighborhoods;
constructing a binary group corresponding to each pixel point at the edge of the suspected hydraulic oil leakage area according to the gray value of each pixel point at the edge of the suspected hydraulic oil leakage area and the mean value of similar pixel points in the corresponding 8 neighborhoods, wherein the similar pixel points are pixel points of which the pixel gradient value relative to the pixel point at the corresponding edge is smaller than a set gradient threshold;
calculating the gray entropy of the suspected hydraulic oil leakage area according to the binary group corresponding to each pixel point in the suspected hydraulic oil leakage area and the binary group corresponding to each pixel point at the edge of the suspected hydraulic oil leakage area, and taking the gray entropy of the suspected hydraulic oil leakage area as the texture complexity of the suspected hydraulic oil leakage area.
5. The hydraulic system oil leakage detection method based on artificial intelligence of claim 4, wherein the gray entropy of the suspected hydraulic oil leakage area is calculated by using the following formula:
h is the gray entropy of a suspected hydraulic oil leakage area, and N is1The number of pixel points in a suspected hydraulic oil leakage area, gj1Is the jth hydraulic oil leakage area1The gray value of each pixel point is calculated,
is the jth hydraulic oil leakage area1The average value of the gray levels of the pixel points in 8 neighborhoods corresponding to each pixel point,
is composed of
Number of occurrences, N2The number of edge pixel points g of suspected hydraulic oil leakage areaj2Is the j-th suspected hydraulic oil leakage area2The gray value of the pixel points at each edge,
is the j-th suspected hydraulic oil leakage area2The average value of the gray levels of similar pixel points in 8 neighborhoods corresponding to the edge pixel points,
is composed of
The number of occurrences.
6. The hydraulic system oil leakage detection method based on artificial intelligence of claim 1, wherein if the complexity difference is not greater than a set complexity difference threshold, it is determined that no hydraulic oil leakage fault occurs in the hydraulic oil system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210278608.5A CN114627316B (en) | 2022-03-21 | 2022-03-21 | Hydraulic system oil leakage detection method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210278608.5A CN114627316B (en) | 2022-03-21 | 2022-03-21 | Hydraulic system oil leakage detection method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114627316A true CN114627316A (en) | 2022-06-14 |
| CN114627316B CN114627316B (en) | 2022-11-25 |
Family
ID=81903612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210278608.5A Active CN114627316B (en) | 2022-03-21 | 2022-03-21 | Hydraulic system oil leakage detection method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114627316B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115311285A (en) * | 2022-10-12 | 2022-11-08 | 南通普盛动力有限公司 | Oil leakage identification method for diesel engine |
| CN115326297A (en) * | 2022-10-11 | 2022-11-11 | 江苏明锋食品有限公司 | Water injection glove air tightness detection method |
| CN116309599A (en) * | 2023-05-24 | 2023-06-23 | 青岛国源中创电气自动化工程有限公司 | Water quality visual monitoring method based on sewage pretreatment |
| CN117788464A (en) * | 2024-02-26 | 2024-03-29 | 卡松科技股份有限公司 | Industrial gear oil impurity visual detection method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102797727A (en) * | 2012-08-17 | 2012-11-28 | 国电联合动力技术有限公司 | Method and device for detecting oil leakage of hydraulic system of wind turbine based on CCD (Charge Coupled Device) |
| CN109241851A (en) * | 2018-08-07 | 2019-01-18 | 电子科技大学 | A kind of the Oil Leakage Detecting method and its system of view-based access control model image |
| CN110363109A (en) * | 2019-06-26 | 2019-10-22 | 成都新舟锐视科技有限公司 | A kind of cover type Oil Leakage Detecting system and method based on computer vision |
| WO2020073686A1 (en) * | 2018-10-08 | 2020-04-16 | 上海建工集团股份有限公司 | Foundation pit automatic monitoring data screening method and system based on image identification |
| CN111209876A (en) * | 2020-01-10 | 2020-05-29 | 汕头大学 | Oil leakage defect detection method and system |
| CN112053322A (en) * | 2020-07-31 | 2020-12-08 | 上海电机学院 | Method for segmenting and detecting surface shielding of photovoltaic cell panel |
| CN113724216A (en) * | 2021-08-24 | 2021-11-30 | 广东工业大学 | Method and system for detecting wave crest welding spot defects |
| CN114152678A (en) * | 2021-12-01 | 2022-03-08 | 郑州大学 | Bridge safety detection method and system based on artificial intelligence |
-
2022
- 2022-03-21 CN CN202210278608.5A patent/CN114627316B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102797727A (en) * | 2012-08-17 | 2012-11-28 | 国电联合动力技术有限公司 | Method and device for detecting oil leakage of hydraulic system of wind turbine based on CCD (Charge Coupled Device) |
| CN109241851A (en) * | 2018-08-07 | 2019-01-18 | 电子科技大学 | A kind of the Oil Leakage Detecting method and its system of view-based access control model image |
| WO2020073686A1 (en) * | 2018-10-08 | 2020-04-16 | 上海建工集团股份有限公司 | Foundation pit automatic monitoring data screening method and system based on image identification |
| CN110363109A (en) * | 2019-06-26 | 2019-10-22 | 成都新舟锐视科技有限公司 | A kind of cover type Oil Leakage Detecting system and method based on computer vision |
| CN111209876A (en) * | 2020-01-10 | 2020-05-29 | 汕头大学 | Oil leakage defect detection method and system |
| CN112053322A (en) * | 2020-07-31 | 2020-12-08 | 上海电机学院 | Method for segmenting and detecting surface shielding of photovoltaic cell panel |
| CN113724216A (en) * | 2021-08-24 | 2021-11-30 | 广东工业大学 | Method and system for detecting wave crest welding spot defects |
| CN114152678A (en) * | 2021-12-01 | 2022-03-08 | 郑州大学 | Bridge safety detection method and system based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 邓永川: "基于图像处理的油田漏油检测方法设计与研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115326297A (en) * | 2022-10-11 | 2022-11-11 | 江苏明锋食品有限公司 | Water injection glove air tightness detection method |
| CN115311285A (en) * | 2022-10-12 | 2022-11-08 | 南通普盛动力有限公司 | Oil leakage identification method for diesel engine |
| CN116309599A (en) * | 2023-05-24 | 2023-06-23 | 青岛国源中创电气自动化工程有限公司 | Water quality visual monitoring method based on sewage pretreatment |
| CN116309599B (en) * | 2023-05-24 | 2023-08-15 | 青岛国源中创电气自动化工程有限公司 | Water quality visual monitoring method based on sewage pretreatment |
| CN117788464A (en) * | 2024-02-26 | 2024-03-29 | 卡松科技股份有限公司 | Industrial gear oil impurity visual detection method |
| CN117788464B (en) * | 2024-02-26 | 2024-04-30 | 卡松科技股份有限公司 | Industrial gear oil impurity visual detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114627316B (en) | 2022-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114627316B (en) | Hydraulic system oil leakage detection method based on artificial intelligence | |
| CN107506798B (en) | Water level monitoring method based on image recognition | |
| US20190331301A1 (en) | Method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing | |
| CN106650812B (en) | A kind of urban water-body extracting method of satellite remote-sensing image | |
| CN101799921B (en) | Cloud detection method of optic remote sensing image | |
| CN111027446B (en) | Coastline automatic extraction method of high-resolution image | |
| CN112149543B (en) | Building dust recognition system and method based on computer vision | |
| CN116309600B (en) | Environment-friendly textile quality detection method based on image processing | |
| CN115115638B (en) | Oil leakage detection and judgment method for hydraulic system | |
| CN104851086A (en) | Image detection method for cable rope surface defect | |
| CN115082744B (en) | Artificial intelligence-based solar heat collection efficiency analysis method and system | |
| CN103489187A (en) | Quality test based segmenting method of cell nucleuses in cervical LCT image | |
| Jing et al. | Pavement crack distress detection based on image analysis | |
| CN109064479A (en) | A kind of sea horizon detection method based on neighbouring video frame gray scale behavioral characteristics | |
| CN116485785A (en) | Surface defect detection method for solar cell | |
| CN110211128B (en) | Loess plateau terrace extraction method based on remote sensing image and DEM | |
| Yu | YOLO V5s-based deep learning approach for concrete cracks detection | |
| CN114723691B (en) | Method for detecting oil leakage fault degree of hydraulic system based on artificial intelligence | |
| CN112037244B (en) | Landsat-8 image culture pond extraction method combining index and contour indicator SLIC | |
| CN114049320A (en) | Device missing AI quality inspection method and device based on picture similarity | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN116993745A (en) | Method for detecting surface leakage of water supply pipe based on image processing | |
| CN113177473B (en) | Automatic water body extraction method and device for remote sensing image | |
| CN108830834A (en) | A kind of cable-climbing robot video artefacts information automation extraction method | |
| CN114937004A (en) | Method for detecting surface pore defects of mechanical parts based on computer vision |
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 |