A complex working condition engine state infrared image interpretation method

Abstract

The present application relates to a kind of complex working condition engine state infrared image interpretation method, it is related to engine testing field, first by calculation to obtain the projection position of engine afterflame and envelope shape based on projection position information and envelope shape information, set target frame frame each engine afterflame of selected;According to the relationship between the centroid position of each engine afterflame envelope shape, select background frame;The average value, median and standard deviation of the average value of all pixel gray values in target frame are calculated, the average value of all pixel gray values in background frame and the average value of all pixel gray values in whole image are calculated, the minimum value in the average value of all pixel gray values in all target frames is selected, the maximum value in the average value of all pixel gray values in all background frames and the average value of all pixel gray values in whole image is selected, the difference between minimum value and maximum value is calculated;By comparing the size of difference value and set threshold value, the opening or closing state of engine can be judged, and the present application has the advantage of automatically judging the opening or closing state of engine.

Description

Technical Field

[0001] This invention relates to the field of engine testing technology, and in particular to a method for interpreting infrared images of engine status under complex operating conditions. Background Technology

[0002] Engine exhaust plume measurement is a common scenario in infrared testing, and determining the engine's operating status (such as on or off) is a crucial step closely related to the infrared characteristics of the engine exhaust plume and engine performance analysis. For efficiency and cost considerations, and provided the spatial arrangement is reasonable and safe, infrared testing often includes multiple engines under test within the same measurement field of view, conducting simultaneous measurements of their exhaust plumes. After the test, the acquired infrared images are interpreted, and the engine's on / off status is determined based on changes in grayscale values.

[0003] However, due to the combined and varied operating states of multiple engines simultaneously, multiple measured states can arise. Furthermore, the activation of certain high-power engines can affect the determination of the on / off states of other engines. Therefore, for interpreting the on / off states of engines under such complex operating conditions, manual judgment is currently the most common method. While manual judgment boasts high accuracy, its efficiency is extremely low due to the limitations of human visual perception, making it difficult to meet the demands of today's high-frame-rate, ultra-large-volume infrared measurement data processing. In addition, subjective judgment criteria, operator fatigue, and training costs are also disadvantages of manual judgment methods.

[0004] Therefore, to address the above shortcomings, a method for interpreting the status of engines under complex operating conditions using infrared images is needed. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] The technical problem this invention aims to solve is the lack of an effective automatic method for determining the engine on / off status in the context of engine exhaust flame measurement, where interference from multiple engines in the same field of view prevents accurate determination.

[0007] (II) Technical Solution

[0008] To address the aforementioned technical problems, this invention provides a method for interpreting infrared images of engine status under complex operating conditions, comprising the following steps:

[0009] I. Based on the distribution location of each engine and the basic shape characteristics of its exhaust flame, calculate the projection position and envelope shape of the engine exhaust flame on the measurement receiving plane.

[0010] II. Based on the projection position information and envelope shape information, set a target box to select the exhaust flames of each engine;

[0011] III. Select a background frame based on the relationship between the centroid positions of the exhaust plume envelope shapes of each engine, with the background frame having the same size as the target frame;

[0012] IV. Calculate the mean, median, and standard deviation of all pixel gray values ​​within the target bounding box; calculate the mean of all pixel gray values ​​within the background bounding box; calculate the mean of all pixel gray values ​​for the entire image.

[0013] V. Select the minimum value among the average values ​​of all pixels within all target boxes, select the maximum value among the average values ​​of all pixels within all background boxes and the average values ​​of all pixels in the entire image, and calculate the difference between the minimum and maximum values;

[0014] VI. The engine's on or off status can be determined by comparing the difference with a set threshold.

[0015] As a further explanation of the present invention, preferably, the relative positional relationship between the engine to be analyzed and the high-power engine is determined by obtaining engine deployment location information.

[0016] As a further explanation of the present invention, preferably, both the target frame and the background frame are selected as rectangles.

[0017] As a further explanation of the invention, preferably, the centroid of one of the background frames of the small engine is located at a point one-half to one-quarter of the distance from the centroid of the exhaust envelope shape of the large engine to the centroid of the exhaust envelope shape of the small engine.

[0018] As a further illustration of the invention, preferably, the centroid of another background frame of the small engine is located at a point one-half to one-quarter of the outer extension line of the centroid of the exhaust envelope shape of the large engine and the centroid of the exhaust envelope shape of the other small engine.

[0019] As a further explanation of the present invention, preferably, the background frame does not overlap with the target frame.

[0020] As a further explanation of the present invention, preferably, the threshold is x times the standard deviation of all pixel grayscale values ​​within the target box of the desired engine state.

[0021] As a further explanation of the present invention, preferably, the initial value of x is 1.

[0022] As a further explanation of the present invention, preferably, when the difference between the minimum value and the maximum value is greater than the threshold, the measured engine is in the on state; if it is less than the threshold, the measured engine is in the off state.

[0023] (III) Beneficial Effects

[0024] The above-described technical solution of the present invention has the following advantages:

[0025] This invention starts with information about the engine's deployment location, combines it with the geometric characteristics of the engine's exhaust plume, and utilizes infrared image processing differential technology. By selecting the exhaust plume region and optimizing the background region separately, statistical data is calculated. Through iterative detection with a set threshold, the automatic judgment and output of the engine's on / off state is achieved, significantly improving the efficiency of infrared image interpretation of engine status under complex operating conditions and avoiding misjudgments caused by human-specific data processing, personnel fatigue, and training deficiencies. Attached Figure Description

[0026] Figure 1 This is a diagram showing the working state of engine A and engine B, and the non-working state of engine C in this invention.

[0027] Figure 2 This is a diagram showing the working state of engine A and the non-working states of engines B and C in this invention.

[0028] Figure 3 This is a diagram showing the working state of engine B and the non-working states of engines A and C in this invention.

[0029] Figure 4 This is a diagram showing the state where engines A, B, and C of the present invention are all not working;

[0030] Figure 5 This is a diagram showing the operating states of engines A, B, and C of the present invention;

[0031] Figure 6 This is a diagram showing the working state of engine A and engine C, and the non-working state of engine B in this invention.

[0032] Figure 7 This is a diagram showing the state where engines B and C are working, and engine A is not working, according to the present invention.

[0033] Figure 8 This invention relates to a diagram showing the working state of engine A when neither engine A nor engine B is in operation.

[0034] Figure 9 This is a diagram showing the exhaust flame state of engine A and B in this invention;

[0035] Figure 10 This is a diagram showing the normal exhaust flame state of engine A and engine C of the present invention;

[0036] Figure 11 This is a diagram showing the weak exhaust plume of the engine armor in this invention;

[0037] Figure 12 This is a state diagram of the background frame area affected by the exhaust plume of engine C of the present invention;

[0038] Figure 13 This is a state diagram of the target area affected by the exhaust plume of engine C according to the present invention.

[0039] In the image: 1. Engine A; 2. Engine B; 3. Exhaust Flame A; 4. Exhaust Flame B; 5. Engine C; 6. Exhaust Flame C; 7. Second Background Frame A; 8. Target Frame A; 9. First Background Frame A; 10. First Background Frame B; 11. Target Frame B; 12. Second Background Frame B. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] A method for interpreting the status of an engine under complex operating conditions using infrared images includes the following steps:

[0042] I. By communicating with on-site testing personnel and reviewing test reports, we obtained the deployment location information of multiple engines. By obtaining the engine deployment location information, we determined the relative positional relationship between the engine to be analyzed and the high-power engine.

[0043] II. Based on the projection position information and envelope shape information, set a target box to select the exhaust flame of each engine.

[0044] III. Select a background frame based on the relationship between the centroid positions of the exhaust plume envelope shapes of each engine. The background frame should be the same size as the target frame.

[0045] IV. Calculate the mean, median, and standard deviation of all pixel gray values ​​within the target bounding box; calculate the mean of all pixel gray values ​​within the background bounding box; and calculate the mean of all pixel gray values ​​for the entire image.

[0046] V. Select the minimum value among the average gray values ​​of all pixels within all target boxes, select the maximum value among the average gray values ​​of all pixels within all background boxes and the average gray values ​​of all pixels in the entire image, and calculate the difference between the minimum and maximum values.

[0047] VI. The engine's on or off status can be determined by comparing the difference with a set threshold.

[0048] Combination Figures 1-8This invention uses three engines as an example, where engine A1 and engine B2 are lower-powered engines, and engine C is a high-powered engine. According to the requirements of the engine testing client, engines A, B, and C are located at the same testing site. Engines A and B are the engines whose exhaust infrared radiation characteristics need to be analyzed; their exhaust ejection directions are opposite and both parallel to the observation plane. Engine C is a high-powered engine that will cause interference, and its exhaust ejection direction is perpendicular to the observation plane.

[0049] Through communication with personnel from the engine manufacturing unit and on-site testing personnel, it was learned that the exhaust plume shapes of engines A, B, and C are all approximately ellipsoidal, and different operating conditions will affect the length of the ellipsoid's major axis. Therefore, a rectangular frame can be used to select the target. Given the field of view of the measuring equipment, the distance between the measuring equipment and the engine, and the length of the exhaust plume of the rated-power engine, combined with the number of pixels, pixel size, and focal length of the measuring equipment, the center pixel position and the number of pixels on the side of the rectangular frame of the engine exhaust plume were initially estimated, thus obtaining the projection position information and envelope shape information.

[0050] The measurement data of the engine exhaust flame is analyzed to obtain the image frame number and time axis information. The image frame number is used as a unique ID for the data processing result. Analysis reveals that the infrared image contains... Figures 1 to 8 The eight measurement conditions can be categorized into two main types based on whether they are affected by the high-power engine (not under test, type C):

[0051] 1. For example Figures 1-4 It is unaffected by engine C.

[0052] 2. For example Figures 5-8 It is affected by engine C.

[0053] like Figures 9-13 Using the calculated projection position and envelope shape information, a rectangular frame is used as the target selection shape. In the infrared measurement image, the four endpoints of the rectangular frames of target frame A8 and target frame B11 are selected respectively to form target frames A8 and B11 for selecting tail flame A3 and tail flame B4 respectively.

[0054] Based on the relative positions of engines A1, B2, and C3, and according to the centroid positions of the exhaust flame envelope shapes, two background frames are selected for engines A1 and B2 respectively. These background frames are the same size as the target frames. Specifically, the centroid of the first background frame A9 is located at a position between one-half and one-quarter of the distance from exhaust flame A3 along the line connecting the centroids of exhaust flame C6 and A3. The centroid of the second background frame A7 is located at a position between one-half and one-quarter of the distance from exhaust flame C6 along the outer extension line connecting the centroids of exhaust flame B4 and C6. The centroid of the first background frame B10 is located at a position between one-half and one-quarter of the distance from exhaust flame B4 along the line connecting the centroids of exhaust flame C6 and B4. The centroid of the second background frame B12 is located at a position between one-half and one-quarter of the distance from exhaust flame C6 along the outer extension line connecting the centroids of exhaust flame A3 and C6. In addition, the target bounding boxes do not overlap with any of the background bounding boxes.

[0055] Calculate the average (DN1), median (DN2), and standard deviation (std) of all pixel grayscale values ​​within target box A (8) or target box B (11). Calculate the average (DN3) of all pixel grayscale values ​​within the first background box A (9) or the first background box B (10). Calculate the average (DN4) of all pixel grayscale values ​​within the second background box A (7) or the second background box B (12). Calculate the average (DN5) of all pixel grayscale values ​​in the entire image. Select the minimum value (DNt) between DN1 and DN2, and the maximum value (DNb) among DN3, DN4, and DN5. Calculate the difference (dDN) between DNt and DNb. Set a threshold of x times std, where x is initially 1 and can be adjusted through small sample testing.

[0056] When dDN is greater than x times std, engine A1 or engine B2 is in the on state; otherwise, it is in the off state. The output method of the state determination results for engine A1 and engine B2 is not limited.

[0057] In summary, the above method, by determining the state of engine A1 or engine B2 under test, achieves automatic judgment and output of engine on / off status, significantly improving the efficiency of infrared image interpretation of engine status under complex operating conditions. It avoids misjudgments caused by human-dependent data processing, personnel fatigue, and training deficiencies. Furthermore, the confidence level only weakens when engine C5 is activated, affecting the background area, and when the exhaust plume A3 or B4 is weak. Therefore, it has a wider range of applications while maintaining high accuracy.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for interpreting the status of an engine under complex operating conditions using infrared images, characterized in that: Includes the following steps, I. Based on the distribution location of each engine and the basic shape characteristics of its exhaust flame, calculate the projection position and envelope shape of the engine exhaust flame on the measurement receiving plane. II. Based on the projection position information and envelope shape information, set a target box to select the exhaust flames of each engine; III. Select a background frame based on the relationship between the centroid positions of the exhaust plume envelope shapes of each engine, with the background frame having the same size as the target frame; IV. Calculate the mean, median, and standard deviation of all pixel gray values ​​within the target bounding box; calculate the mean of all pixel gray values ​​within the background bounding box; calculate the mean of all pixel gray values ​​for the entire image. V. Select the minimum value among the average values ​​of all pixels within all target boxes, select the maximum value among the average values ​​of all pixels within all background boxes and the average values ​​of all pixels in the entire image, and calculate the difference between the minimum and maximum values; VI. The engine's on or off status can be determined by comparing the difference with a set threshold.

2. The method for interpreting the infrared image of an engine under complex operating conditions according to claim 1, characterized in that: By acquiring engine deployment location information, the relative positional relationship between the engine to be analyzed and the high-power engine can be determined.

3. The method for interpreting the infrared image of an engine under complex operating conditions according to claim 2, characterized in that: Both the target bounding box and the background bounding box are selected as rectangles.

4. The method for interpreting the infrared image of an engine under complex operating conditions according to claim 3, characterized in that: The centroid of one of the background frames of the small engine is located at approximately one-half to one-quarter of the distance between the centroid of the large engine's exhaust envelope shape and the centroid of the engine's exhaust envelope shape.

5. The method for interpreting the infrared image of an engine under complex operating conditions according to claim 4, characterized in that: The centroid of the other background frame of the small engine is located at approximately one-half to one-quarter of the outer extension of the centroid of the large engine's exhaust envelope shape and the centroid of the centroid of the other small engine's exhaust envelope shape.

6. The method for interpreting the infrared image of an engine under complex operating conditions according to claim 5, characterized in that: The background frame does not overlap with the target frame.

7. The method for interpreting the infrared image of an engine under complex operating conditions according to claim 1, characterized in that: The standard deviation of all pixel grayscale values ​​within the target bounding box of the desired engine state, with a threshold of x times.

8. The method for interpreting the infrared image of an engine under complex operating conditions according to claim 7, characterized in that: The initial value of x is 1.

9. The method for interpreting the infrared image of an engine under complex operating conditions according to claim 8, characterized in that: When the difference between the minimum and maximum values ​​is greater than the threshold, the engine being measured is in the on state; if it is less than the threshold, the engine being measured is in the off state.

Images