System and method for accurately judging fault of hydraulic generator based on image recognition

Abstract

The invention discloses a hydraulic generator fault accurate discrimination system and method based on image recognition, a first image recognition assembly of the discrimination system is installed on the upper surface of an inner top cover of a hydraulic generator set, and a shear pin signal device is installed on the back of a guide vane crank arm. The second image recognition assembly is installed on an upper rack of the water-turbine generator set, the air brake sensors are installed above and below the movement direction of an air brake flashboard, the image processing assembly carries out image processing, and the display screen displays a judgment result; the judging system obtains image information of an included angle between a guide vane crank arm and a connecting rod of a water-turbine generator set and distance information between an air brake flashboard and the lower surface of a brake ring, and compared with manual field judgment, the efficiency can be greatly improved, real-time monitoring is achieved, and the working efficiency is improved. According to the judgment method, the actual operation condition of the hydro-generator is judged by combining the states of the shear pin signal device and the air brake sensor with the result of the image processing assembly, accurate judgment is achieved, and the fault processing efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower production operation and maintenance, and in particular to a precise fault discrimination system and method for hydro-generators based on image recognition. Background Art

[0002] The shear pin of a large hydropower station is the most common guide vane drive protection device for the guide vane mechanism of a hydro-generator unit, and plays a crucial role in the safe operation of the water turbine. When foreign objects are stuck between the guide vanes of the water turbine, it will cause the guide vanes to be blocked during the opening and closing processes. At this time, the operating torque is transmitted to the guide vanes through the shear pin. When the torque exceeds the shear force set by the shear pin, the shear pin of the guide vane is cut off and separated from the control of the control ring, thereby protecting the guide vane from damage. The other guide vanes can still be normally linked with the control ring, avoiding the unit from getting out of control. The air brake (usually referring to the air braking system) in a large hydropower station is an important auxiliary device for the hydro-generator unit, mainly used for the safe shutdown and operation protection of the unit.

[0003] In the existing operation and maintenance practice of hydropower stations, the status monitoring of shear pins and air brakes both uses sensors to monitor for faults. After the sensor signal is lost, that is, after the fault signal is sent, the staff needs to conduct on-site inspections and confirmations before processing. However, in the actual operation and maintenance process of hydropower stations, both shear pins and air brakes have a certain false alarm rate of sensor signals. When dealing with faults, it is necessary to first rule out the possibility of false alarms of sensor signals, and then judge the fault type. At the same time, there are dozens of shear pins and air brakes for each hydro-generator unit. The shear pins are located in the turbine pit, and the air brakes are located in the air brake chamber. The spaces of the turbine pit and the air brake chamber are very narrow, and the distances between the turbine pit and the air brake chamber and the central control room are relatively far. It takes a lot of time for the staff to conduct on-site confirmations, resulting in delays in accident handling, affecting the fault handling efficiency, further affecting the unit startup success rate, and moreover, inaccurate confirmations may occur due to insufficient staff experience.

[0004] Machine vision inspection is a technology for inspecting product quality by simulating human vision, thinking, and operations. It uses a high-precision optical imaging system, a powerful computer processing ability, and an automated actuator to automatically detect various problems such as the appearance, dimensions, and defects of products, comprehensively improving the efficiency and accuracy of inspection. In the actual operation and maintenance process of hydropower stations, in the fault discrimination of hydro-generator units, the status of the shear pin can be determined by observing the included angle between the guide vane crank arm and the connecting rod on-site, and the lifting position of the air brake gate plate can be determined by observing the distance between the upper surface of the air brake gate plate and the lower surface of the braking ring of the hydro-generator. Applying machine vision monitoring to the fault judgment of hydro-generator units can obtain accurate fault judgment results. Summary of the Invention

[0005] To overcome the above problems, the object of the present invention is to provide a precise fault discrimination system and method for water turbine generators based on image recognition. The discrimination system obtains the image information of the included angle between the guide vane crank arm and the connecting rod of the water turbine generator set through the first image recognition component, obtains the distance information between the brake shoe and the lower surface of the brake ring through the second image recognition component, and obtains specific parameter values through the image processing component. Compared with manual on-site judgment, it can greatly improve the efficiency and achieve real-time monitoring, so as to detect and handle faults in a timely manner. The discrimination method combines the states of the shear pin signal device and the brake sensor with the results of the image processing component to judge the actual operating conditions of the water turbine generator, and outputs the judgment results on the display screen for easy observation and improvement of the fault handling efficiency.

[0006] The technical solution adopted by the present invention is as follows:

[0007] A precise fault discrimination system for water turbine generators based on image recognition includes a first image recognition component, a shear pin signal device, a second image recognition component, a brake sensor, an image processing component, and a display screen. The first image recognition component is installed on the upper surface of the inner top cover of the water turbine generator set. The shear pin signal device is installed on the back of the guide vane crank arm of the water turbine generator. The second image recognition component is installed on the upper frame of the water turbine generator set. The brake sensor includes an upper sensor and a lower sensor, which are respectively installed above and below the movement of the brake shoe. The image processing component receives the image information of the first image recognition component and the second image recognition component and performs image processing. The display screen displays the final discrimination result;

[0008] The first image recognition component includes an annular track, a moving bracket, a first industrial camera, and a first industrial lens. The annular track is fixedly installed on the upper surface of the inner top cover. The moving bracket is slidably connected to the annular track. The first industrial camera is fixedly installed on the moving bracket. The first industrial lens is connected to the first industrial camera;

[0009] There are multiple groups of the second image recognition components, including a base, a bracket, a second industrial camera, and a second industrial lens. The base is fixedly installed on the edge of the upper surface of the upper frame near the brake shoe. The bracket is located on the upper surface of the base. The second industrial camera is fixedly connected to the bracket. The second industrial lens is connected to the second industrial camera.

[0010] As a further description of the present invention, the outer side of the annular track is designed in a groove shape, and gear columns are evenly distributed in the groove on the outer side of the annular track. The moving bracket includes a sliding plate, a motor, a gear, a camera mounting bracket, and pulleys. The sliding plate is slidably connected to the upper surface of the annular track. A groove is provided on one side above the sliding plate. The motor is installed in the groove. The output shaft of the motor passes through the sliding plate and is connected to the gear. The gear is adapted to the gear columns. The camera mounting bracket is fixedly connected to the upper surface of the sliding plate and is located on the right side of the motor. There are four pulleys, which are respectively fixedly connected to the front and rear sides of the sliding plate. The two pulleys on the side of the sliding plate located in the groove of the annular track are respectively located on the left and right sides of the gear, and the other two pulleys are respectively tangent to the inner side surface of the annular track.

[0011] As a further description of the present invention, the second image recognition component further includes a vision light source and a light source controller. The bracket is of an S-shaped structure. The second industrial camera is fixedly installed on the upper surface of the bracket. The vision light source is installed below the second industrial camera. The light source controller is connected to the vision light source and is located on the right side of the vision light source;

[0012] The vision light source adopts a strip light source.

[0013] As a further description of the present invention, the air brake sensor adopts a pressure sensor.

[0014] As a further description of the present invention, the first image recognition component further includes telescopic support columns. There are multiple telescopic support columns, which are installed at the position between the lower surface of the annular track and the inner top cover;

[0015] The base of the second image recognition component is a telescopic base.

[0016] As a further description of the present invention, the number of the second image recognition components is the same as the number of the air brake gates of the hydrogenerator. A second image recognition component is installed at the position where each group of air brake gates is located.

[0017] The discrimination method using the above-mentioned accurate discrimination system for hydrogenerator faults based on image recognition includes the following steps:

[0018] S01: Data acquisition, obtaining the shear pin state, the air brake sensor state, the images of the first image recognition component, and the images of the second image recognition component;

[0019] S02: Data processing,

[0020] Calculating the included angle between the guide vane crank and the connecting rod in the image processing component through the image taken by the first image recognition component ,

[0021] The distance between the upper surface of the brake gate and the lower surface of the braking ring of the hydrogenerator is calculated in the image processing component from the image captured by the second image recognition component. ;

[0022] S03: Fault judgment;

[0023] S04: Output the result on the display screen.

[0024] As a further description of the present invention, the judgment process of the S03 is as follows:

[0025] When it is detected that in the image features is less than or equal to the preset angle threshold, it is determined that the comparison with the features in the preset image feature library of the normal position state of the shear pin is consistent;

[0026] When it is detected that in the image features is greater than the preset angle threshold, it is determined that the comparison with the features in the preset image feature library of the normal position state of the shear pin is inconsistent;

[0027] When it is detected that in the image features is less than or equal to the preset jacking distance threshold, it is determined that the comparison with the features in the preset image feature library of the jacking position state of the brake gate is consistent;

[0028] When it is detected that in the image features is greater than the preset jacking distance threshold, it is determined that the comparison with the features in the preset image feature library of the jacking position state of the brake gate is inconsistent;

[0029] When it is detected that in the image features is less than or equal to the preset falling distance threshold, it is determined that the comparison with the features in the preset image feature library of the falling position state of the brake gate is consistent;

[0030] When it is detected that in the image features is greater than the preset falling distance threshold, it is determined that the comparison with the features in the preset image feature library of the falling position state of the brake gate is inconsistent.

[0031] As a further description of the present invention, the angle threshold is 17°, the jacking distance threshold is 35 mm, and the falling distance threshold is 5 mm.

[0032] As a further description of the present invention, the output process of the S04 is as follows:

[0033] If the state of the shear pin sensor is sheared and in the image features is inconsistent with the features in the preset image feature library, output: Shear pin No. X is sheared;

[0034] If the shear pin status is not sheared, when the in the image features is inconsistent with the features in the preset image feature library, output: The shear pin No. X may be sheared, and the signal is not reported at this time;

[0035] If the shear pin status is sheared, when the in the image features is consistent with the features in the preset image feature library, output: False alarm of the shear signal of shear pin No. X;

[0036] If the shear pin status is not sheared, when the in the image features is consistent with the features in the preset image feature library, output: The status of shear pin No. X is normal;

[0037] If the status of the brake sensor is lifted, that is, the upper sensor detects a pressure signal, and when the position of the brake plate is consistent with the position status image feature library of the preset lifted position of the brake plate, output: The lifting status of brake No. X is normal;

[0038] If the status of the brake sensor is lifted, that is, the upper sensor detects a pressure signal, and when the position of the brake plate is inconsistent with the position status image feature library of the preset lifted position of the brake plate, output: The status of brake No. X is abnormal;

[0039] If the status of the brake sensor is falling, that is, the lower sensor detects a pressure signal, and when the position of the brake plate is consistent with the position status image feature library of the preset falling position of the brake plate, output: The falling status of brake No. X is normal;

[0040] If the status of the brake sensor is falling, that is, the lower sensor detects a pressure signal, and when the position of the brake plate is inconsistent with the position status image feature library of the preset falling position of the brake plate, output: The status of brake No. X is abnormal;

[0041] If the status of the brake sensor is neither lifted nor falling, that is, neither the upper sensor nor the lower sensor detects a pressure signal, and when the position of the brake plate is inconsistent with the position status image feature library of the preset lifted position or falling position of the brake plate, output: The position of brake No. X is abnormal;

[0042] If the status of the brake sensor is neither lifted nor falling, that is, neither the upper sensor nor the lower sensor detects a pressure signal, and when the position of the brake plate is inconsistent with the position status image feature library of the preset middle position of the brake plate, output: The status of brake No. X is abnormal.

[0043] Advantages of the present invention:

[0044] The accurate fault discrimination system for hydro-generators based on image recognition of the present invention includes a first image recognition component, a shear pin signal device, a second image recognition component, a brake sensor, an image processing component, and a display screen. The discrimination system obtains the image information of the included angle between the guide vane crank arm and the connecting rod of the hydro-generator set through the first image recognition component, obtains the distance information between the brake plate and the lower surface of the brake ring through the second image recognition component, and obtains specific parameter values through the image processing component. Compared with manual on-site judgment, it can greatly improve the efficiency, achieve real-time monitoring, thus timely discover faults and process them, and improve the one-time starting success rate of the hydro-generator set.

[0045] The accurate fault discrimination system for hydro-generators based on image recognition of the present invention, the first image recognition component includes an annular track, a moving bracket, a first industrial camera, and a first industrial lens. There are multiple groups of the second image recognition components, including a base, a bracket, a second industrial camera, and a second industrial lens. This system combines the actual fault conditions of the hydro-generator set, adopts the moving first image recognition component for shear pin monitoring, and adopts multiple static second image recognition components for brake plate monitoring. Since the failure rate of shear pins is low and the failure rate of brake plates is high, such a system design can ensure the lowest system cost while achieving real-time monitoring and accurate discrimination, and realize the optimal configuration of the system.

[0046] The accurate fault discrimination system for hydro-generators based on image recognition of the present invention, the second image recognition component further includes a vision light source and a light source controller. Since the brightness in the wind tunnel is low and the monitoring of the lifting position of the brake plate requires high precision, with an accuracy requirement of up to 1 mm, a vision light source is set in the second image recognition component. At the same time, the vision light source adopts a strip light source, which has high brightness and uniform illumination, can provide a high-brightness and uniform illumination effect, making every detail at the image recognition site clearly visible, helping to improve the detection accuracy and production efficiency, further ensuring the accuracy of the obtained image information of the brake plate, improving the discrimination accuracy rate of the system, and achieving accurate judgment.

[0047] The present invention uses a discrimination method for the accurate fault discrimination system of hydro-generators based on image recognition. The discrimination method combines the states of the shear pin signal device and the brake sensor with the results of the image processing component to make a judgment on the actual operation condition of the hydro-generator, and outputs the judgment result on the display screen for easy observation, improving the fault handling efficiency. Description of the Drawings

[0048] Figure 1 It is the overall structural block diagram of the accurate fault discrimination system for hydro-generators based on image recognition proposed by the present invention;

[0049] Figure 2Three-dimensional structure diagram of the first image recognition component of the accurate fault discrimination system for hydro-generators based on image recognition proposed by the present invention;

[0050] Figure 3 Structure diagram of the moving bracket of the accurate fault discrimination system for hydro-generators based on image recognition proposed by the present invention;

[0051] Figure 4 Structure diagram of the telescopic support column of the accurate fault discrimination system for hydro-generators based on image recognition proposed by the present invention;

[0052] Figure 5 Three-dimensional structure diagram of the second image recognition component of the accurate fault discrimination system for hydro-generators based on image recognition proposed by the present invention;

[0053] Figure 6 Structure diagram of the vision light source and light source controller of the accurate fault discrimination system for hydro-generators based on image recognition proposed by the present invention;

[0054] Figure 7 Flowchart of the discrimination method using the accurate fault discrimination system for hydro-generators based on image recognition proposed by the present invention.

[0055] Explanation of reference numerals

[0056] 1 - First image recognition component,

[0057] 11 - Ring track, 111 - Gear column,

[0058] 12 - Moving bracket, 121 - Sliding plate, 122 - Motor, 123 - Gear, 124 - Camera mounting bracket, 125 - Pulley,

[0059] 13 - First industrial camera,

[0060] 14 - First industrial lens,

[0061] 15 - Telescopic support column,

[0062] 2 - Shear pin signal device,

[0063] 3 - Second image recognition component,

[0064] 31 - Base, 32 - Bracket, 33 - Second industrial camera, 34 - Second industrial lens, 35 - Vision light source, 36 - Light source controller,

[0065] 4 - Brake sensor,

[0066] 41 - Upper sensor, 42 - Lower sensor,

[0067] 5 - Image processing component,

[0068] 6 - Display screen. Detailed implementation manners

[0069] The following describes the detailed implementation manners of the present invention in conjunction with the accompanying drawings and embodiments:

[0070] It should be noted that the structures, ratios, sizes, etc. illustrated in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those skilled in this technology to understand and read, and are not used to limit the implementation conditions of the present invention. Any modification of the structure, change of the proportional relationship or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0071] At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" cited in this specification are only for the convenience of clear narration, and are not used to limit the implementation scope of the present invention. The change or adjustment of their relative relationships, without substantial change in the technical content, should also be regarded as the implementation scope of the present invention.

[0072] As Figures 1 to 7 shown, it shows the detailed implementation manners of the present invention:

[0073] Embodiment 1

[0074] A precise discrimination system for water turbine generator faults based on image recognition includes a first image recognition component 1, a shear pin signal device 2, a second image recognition component 3, a brake sensor 4, an image processing component 5, and a display screen 6. The first image recognition component 1 is installed on the upper surface of the inner top cover of the water turbine generator set. The shear pin signal device 2 is installed on the back of the guide vane crank of the water turbine generator. The second image recognition component 3 is installed on the upper frame of the water turbine generator set. The brake sensor 4 includes an upper sensor 41 and a lower sensor 42, which are respectively installed above and below the movement of the brake plate. The image processing component 5 receives the image information of the first image recognition component 1 and the second image recognition component 3 and performs image processing. The display screen 6 displays the final discrimination result.

[0075] In this embodiment, as Figure 1 shown, this discrimination system obtains the image information of the included angle between the guide vane crank and the connecting rod of the water turbine generator set through the first image recognition component 1, obtains the distance information between the brake plate and the lower surface of the brake ring through the second image recognition component 3, and processes the image information of the first image recognition component 1 and the second image recognition component 3 through the image processing component 5 to obtain specific parameter values. Compared with manual on-site judgment, this discrimination system can greatly improve the efficiency, achieve real-time monitoring, so as to timely detect faults and process them, and improve the one-time starting success rate of the water turbine generator set.

[0076] The first image recognition component 1 includes an annular track 11, a moving bracket 12, a first industrial camera 13, and a first industrial lens 14. The annular track 11 is fixedly installed on the upper surface of the inner top cover. The moving bracket 12 is slidably connected to the annular track 11. The first industrial camera 13 is fixedly installed on the moving bracket 12. The first industrial lens 14 is connected to the first industrial camera 13.

[0077] In this embodiment, as Figure 2 shown, the moving bracket 12 can run on the annular track 11. By the movement of the moving bracket 12, the position of the first industrial camera 13 on the moving bracket 12 is moved, so as to obtain the image information of the included angle between the guide vane crank and the connecting rod above the guide vanes at different positions. In the actual use process, the position of the guide vane is confirmed according to the positioning point of the moving bracket 12, so as to clarify which guide vane the image information collected at this position is the image information above. It is also possible to use the first industrial camera 13 to shoot a video, extract the image information through the video, and then obtain the feature information.

[0078] There are multiple groups of the second image recognition components 3, which include a base 31, a bracket 32, a second industrial camera 33, and a second industrial lens 34. The base 31 is fixedly installed at the edge of the upper surface of the upper frame near the air brake gate plate position. The bracket 32 is located on the upper surface of the base 31. The second industrial camera 33 is fixedly connected to the bracket 32. The second industrial lens 34 is connected to the second industrial camera 33.

[0079] Specifically, the number of the second image recognition components 3 is the same as the number of the air brake gate plates of the hydrogenerator. Each group of second image recognition components 3 is installed at the position where the air brake gate plate is located.

[0080] In this embodiment, as Figure 5 shown, the second image recognition component 3 is used to obtain the image of the air brake gate plate, which is realized by using the stationary bracket 32.

[0081] In this embodiment, the system combines the actual fault conditions of the hydrogenerator set. The moving first image recognition component 1 is used for shear pin monitoring, and multiple stationary second image recognition components 3 are used for air brake gate plate monitoring. Since the failure rate of the shear pin is low and the failure rate of the air brake gate plate is high, such a system design can ensure the lowest cost of the system while realizing real-time monitoring and accurate discrimination, achieve the optimal configuration of the system, and maximize the energy efficiency.

[0082] Specifically, the outer side of the annular track 11 is designed in a groove shape. Gear columns 111 are evenly distributed in the groove on the outer side of the annular track 11. The moving support 12 includes a sliding plate 121, a motor 122, a gear 123, a camera mounting bracket 124, and pulleys 125. The sliding plate 121 is slidably connected to the upper surface of the annular track 11. A groove is formed on one side above the sliding plate 121. The motor 122 is installed in the groove. The output shaft of the motor 122 passes through the sliding plate 121 and is connected to the gear 123. The gear 123 is adapted to the gear columns 111. The camera mounting bracket 124 is fixedly connected to the upper surface of the sliding plate 121, on the right side of the motor 122. There are four pulleys 125, which are respectively fixedly connected to the front and rear sides of the sliding plate 121. The two pulleys 125 on the groove side of the sliding plate 121 located on the annular track 11 are respectively located on the left and right sides of the gear 123. The other two pulleys 125 are respectively tangent to the inner side surface of the annular track 11.

[0083] In this embodiment, as Figure 3 shown, the movement process of the moving support 12 on the annular track 11 is as follows: The motor 122 rotates under the action of electric energy. At this time, the gear 123 connected to the output shaft of the motor 122 rotates. Since the gear 123 is adapted to the gear columns 111 in the groove of the annular track 11, under the rotation of the gear 123, it moves among the gear columns 11, causing the sliding plate 121 to start sliding on the upper surface of the annular track 11 and realizing circular motion around the annular track 11. The camera mounting bracket 124 is used to mount the first industrial camera 13 to obtain image information at different positions. The pulleys 125 are located at the front and rear sides of the sliding plate 121 to ensure the movement of the sliding plate 121 between the annular tracks 11 and realize the reliable movement of the moving support 12.

[0084] Embodiment Two

[0085] On the basis of the above embodiment, in order to accurately judge the fault state of the hydro-generator set, accurate data information is required. Therefore, this Embodiment Two is proposed.

[0086] Specifically, the second image recognition component 3 further includes a vision light source 35 and a light source controller 36. The bracket 32 is of an S-shaped structure. The second industrial camera 33 is fixedly installed on the upper surface of the bracket 32. The vision light source 35 is installed below the second industrial camera 33. The light source controller 36 is connected to the vision light source 35 and is located on the right side of the vision light source 35;

[0087] The vision light source 35 uses a strip light source.

[0088] Specifically, the brake sensor 4 uses a pressure sensor.

[0089] In this embodiment, asFigure 6 As shown in Figure 6 , the second image recognition component 3 further includes a vision light source 35 and a light source controller 36. Since the brake flap is installed in the wind tunnel where the brightness is low, and the monitoring of the lifting position of the brake flap requires high precision, with an accuracy of up to 1 mm, a vision light source 35 is provided in the second image recognition component 3. At the same time, the vision light source 35 adopts a strip light source, which has high brightness and uniform illumination, can provide a high-brightness and uniform illumination effect, making every detail at the image recognition site clearly visible, helping to improve the detection accuracy and production efficiency, further ensuring the accuracy of the obtained image information of the brake flap, improving the discrimination accuracy of the system, and achieving accurate judgment.

[0090] Embodiment Three

[0091] Based on the above embodiment, since the included angle height positions of the guide vane crank arms and connecting rods of different specifications of hydro-generator units are different, and the height positions of the brake flaps are different, in order to make the system more applicable, this embodiment is specifically proposed.

[0092] Specifically, the first image recognition component 1 further includes telescopic support columns 15. There are multiple telescopic support columns 15, which are installed at the position between the lower surface of the annular track 11 and the inner top cover;

[0093] The base 31 of the second image recognition component 3 is a telescopic base.

[0094] In this embodiment, as Figure 4 shown, telescopic support columns 15 are provided below the annular track 11 of the first image recognition component 1, and the base 31 of the second image recognition component 3 is designed as a telescopic base, which is convenient for operators to adjust the height according to actual usage needs to adapt to different height requirements. The telescopic design can choose the existing hydraulic telescopic or the existing snap-type telescopic, and the height adjustment accuracy is selected to be 2 mm.

[0095] Embodiment Four

[0096] The method of using the above-mentioned accurate discrimination system for hydro-generator faults based on image recognition includes the following steps:

[0097] S01: Data acquisition, obtaining the shear pin state in the shear pin signal device 2, the state of the brake sensor 4, the image of the first image recognition component 1, and the image of the second image recognition component 3;

[0098] S02: Data processing,

[0099] Calculating the included angle between the guide vane crank arm and the connecting rod in the image processing component 5 through the image taken by the first image recognition component 1 ,

[0100] The distance between the upper surface of the brake flap of the air brake and the lower surface of the brake ring of the hydrogenerator is calculated in the image processing component 5 from the image captured by the second image recognition component 3. ;

[0101] S03: Fault judgment;

[0102] S04: Output the result on the display screen 6.

[0103] In this embodiment, as Figure 7 shown, this discrimination method combines the states of the shear pin signal device 2 and the air brake sensor 4 with the result of the image processing component 5 to make a judgment on the actual operation of the hydrogenerator, and outputs the judgment result on the display 6 for easy observation and improving the fault handling efficiency.

[0104] Specifically, the judgment process of the S03 is as follows:

[0105] When it is detected that the in the image features is less than or equal to the preset angle threshold, it is determined that the comparison with the features in the preset image feature library of the normal position state of the shear pin is consistent;

[0106] When it is detected that the in the image features is greater than the preset angle threshold, it is determined that the comparison with the features in the preset image feature library of the normal position state of the shear pin is inconsistent;

[0107] When it is detected that the in the image features is less than or equal to the preset jacking distance threshold, it is determined that the comparison with the features in the preset image feature library of the jacking position state of the air brake flap is consistent;

[0108] When it is detected that the in the image features is greater than the preset jacking distance threshold, it is determined that the comparison with the features in the preset image feature library of the jacking position state of the air brake flap is inconsistent;

[0109] When it is detected that the in the image features is less than or equal to the preset falling distance threshold, it is determined that the comparison with the features in the preset image feature library of the falling position state of the air brake flap is consistent;

[0110] When it is detected that the in the image features is greater than the preset falling distance threshold, it is determined that the comparison with the features in the preset image feature library of the falling position state of the air brake flap is inconsistent.

[0111] In this embodiment, the judgment process is divided into two aspects. On the one hand, the included angle between the guide vane crank and the connecting rod Compare with the actual preset angle threshold. When the included angle value is not within the threshold range, it is determined that the comparison with the features in the feature library is inconsistent. On the other hand, the distance between the upper surface of the brake gate and the lower surface of the brake ring of the water turbine generator Compare with the preset jacking distance threshold and falling distance threshold to obtain a conclusion that the comparison result is consistent or inconsistent.

[0112] Specifically, the output process of S04 is as follows:

[0113] If the shear pin status is sheared, and the in the image features is inconsistent with the features in the preset image feature library, output: The Xth shear pin is sheared;

[0114] If the shear pin status is not sheared, and the in the image features is inconsistent with the features in the preset image feature library, output: The Xth shear pin may be sheared, and the signal is not reported at this time;

[0115] If the shear pin status is sheared, and the in the image features is consistent with the features in the preset image feature library, output: False alarm of the sheared signal of the Xth shear pin;

[0116] If the shear pin status is not sheared, and the in the image features is consistent with the features in the preset image feature library, output: The status of the Xth shear pin is normal;

[0117] If the status of the brake gate sensor 4 is jacked up, that is, the upper sensor 41 detects a pressure signal, and the position of the brake gate is consistent with the comparison in the preset image feature library of the jacked-up position status of the brake gate, output: The jacked-up status of the Xth brake gate is normal;

[0118] If the status of the brake gate sensor 4 is jacked up, that is, the upper sensor 41 detects a pressure signal, and the position of the brake gate is inconsistent with the comparison in the preset image feature library of the jacked-up position status of the brake gate, output: The status of the Xth brake gate is abnormal;

[0119] If the status of the brake gate sensor 4 is falling, that is, the lower sensor 42 detects a pressure signal, and the position of the brake gate is consistent with the comparison in the preset image feature library of the falling position status of the brake gate, output: The falling status of the Xth brake gate is normal;

[0120] If the status of the brake gate sensor 4 is falling, that is, the lower sensor 42 detects a pressure signal, and the position of the brake gate is inconsistent with the comparison in the preset image feature library of the falling position status of the brake gate, output: The status of the Xth brake gate is abnormal;

[0121] If the status of the air brake sensor 4 is neither lifted nor lowered, that is, neither the upper sensor 41 nor the lower sensor 42 detects a pressure signal, and the position of the air brake flap is inconsistent with the preset state image feature library of the lifted position or the lowered position of the air brake flap, the output is: The position of air brake No. X is abnormal;

[0122] If the status of the air brake sensor 4 is neither lifted nor lowered, that is, neither the upper sensor 41 nor the lower sensor 42 detects a pressure signal, and the position of the air brake flap is inconsistent with the preset state image feature library of the middle position of the air brake flap, the output is: The status of air brake No. X is abnormal.

[0123] In this embodiment, the output result is combined with the status of the shear pin and the status of the air brake sensor for output, ensuring the accuracy of the fault judgment of the guide vane of the hydrogenerator, so as to take corresponding measures in time, improve the efficiency of fault handling, and directly output the result on the display screen 6 for easy observation.

[0124] Embodiment Five

[0125] Specifically, the angle threshold is 17°, the lifted distance threshold is 35 mm, and the lowered distance threshold is 5 mm.

[0126] In this embodiment, according to the actual experience and test results of the hydropower plant, this threshold range is obtained, which can realize the accurate judgment of the faults of the hydrogenerator set.

[0127] The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the knowledge scope of those of ordinary skill in the art, various changes can be made without departing from the purpose of the present invention.

[0128] Many other changes and modifications can be made without departing from the concept and scope of the present invention. It should be understood that the present invention is not limited to the specific embodiments, and the scope of the present invention is defined by the appended claims.

Claims

1. A precise discrimination system for water turbine generator faults based on image recognition, characterized in that, It includes a first image recognition component (1), a shear pin signal device (2), a second image recognition component (3), a wind brake sensor (4), an image processing component (5), and a display screen (6). The first image recognition component (1) is installed on the upper surface of the inner top cover of the hydro-generating unit. The shear pin signal device (2) is installed on the back of the guide vane toggle arm of the hydro-generator. The second image recognition component (3) is installed on the upper frame of the hydro-generating unit. The wind brake sensor (4) includes an upper sensor (41) and a lower sensor (42), which are respectively installed above and below the movement of the wind brake gate plate. The image processing component (5) receives the image information of the first image recognition component (1) and the second image recognition component (3) and performs image processing. The display screen (6) displays the final discrimination result; The first image recognition component (1) includes an annular track (11), a moving bracket (12), a first industrial camera (13), and a first industrial lens (14). The annular track (11) is fixedly installed on the upper surface of the inner top cover. The moving bracket (12) is slidably connected to the annular track (11). The first industrial camera (13) is fixedly installed on the moving bracket (12). The first industrial lens (14) is connected to the first industrial camera (13); There are multiple groups of the second image recognition components (3), which include a base (31), a bracket (32), a second industrial camera (33), and a second industrial lens (34). The base (31) is fixedly installed at the edge of the upper surface of the upper frame near the wind brake gate plate. The bracket (32) is located on the upper surface of the base (31). The second industrial camera (33) is fixedly connected to the bracket (32). The second industrial lens (34) is connected to the second industrial camera (33).

2. The image recognition-based accurate fault discrimination system for hydro-generators according to claim 1, characterized in that, The outer side of the annular track (11) is designed in a groove type. Gear columns (111) are evenly distributed in the outer groove of the annular track (11). The moving bracket (12) includes a sliding plate (121), a motor (122), a gear (123), a camera mounting bracket (124), and pulleys (125). The sliding plate (121) is slidably connected to the upper surface of the annular track (11). A groove is opened on one side above the sliding plate (121). The motor (122) is installed in the groove. The output shaft of the motor (122) passes through the sliding plate (121) and is connected to the gear (123). The gear (123) is adapted to the gear columns (111). The camera mounting bracket (124) is fixedly connected to the upper surface of the sliding plate (121) and is located on the right side of the motor (122). There are four pulleys (125), which are respectively fixedly connected to the front and rear sides of the sliding plate (121). The two pulleys (125) on the side of the sliding plate (121) located in the groove of the annular track (11) are respectively located on the left and right sides of the gear (123). The other two pulleys (125) are respectively tangent to the inner side surface of the annular track (11).

3. The image recognition-based accurate fault discrimination system for hydro-generators according to claim 1, wherein The second image recognition component (3) further includes a vision light source (35) and a light source controller (36). The bracket (32) has an S-shaped structure. The second industrial camera (33) is fixedly installed on the upper surface of the bracket (32). The vision light source (35) is installed below the second industrial camera (33). The light source controller (36) is connected to the vision light source (35) and is located on the right side of the vision light source (35). The vision light source (35) uses a strip light source.

4. The image recognition-based precise fault discrimination system for hydro-generators according to claim 1, wherein The air brake sensor (4) uses a pressure sensor.

5. The image recognition-based precise fault discrimination system for hydro-generators according to claim 1, characterized in that The first image recognition component (1) further includes telescopic support columns (15). There are multiple telescopic support columns (15), which are installed at the position between the lower surface of the annular track (11) and the inner top cover. The base (31) of the second image recognition component (3) is a telescopic base.

6. The image recognition-based accurate fault discrimination system for hydro-generators according to claim 1, wherein, The number of the second image recognition components (3) is the same as the number of the air brake gates of the hydro-generator. A second image recognition component (3) is installed at the position of each group of air brake gates.

7. The discrimination method of the water turbine generator fault precise discrimination system based on image recognition according to any one of claims 1-6 above, characterized in that, It includes the following steps: S01: Data acquisition, obtaining the shear pin status in the shear pin signal device (2), the status of the air brake sensor (4), the images of the first image recognition component (1), and the images of the second image recognition component (3). S02: Data processing The angle between the guide vane crank arm and the connecting rod is calculated in the image processing component (5) for the image captured by the first image recognition component (1). , The distance between the upper surface of the wind brake shutter and the lower surface of the brake ring of the hydrogenerator is calculated in the image processing component (5) for the image captured by the second image recognition component (3). ; S03: Fault judgment; S04: Output the result on the display screen (6).

8. The discrimination method of the water turbine generator fault precise discrimination system based on image recognition according to claim 7, characterized in that, The judgment process of S03 is as follows: When it is detected that among the said image features is less than or equal to a preset angular threshold value, it is determined that the comparison with the features in the image feature library of the normal position state of the preset shear pin is consistent; When it is detected that among the is greater than a preset angular threshold, it is determined that there is a mismatch in the comparison with the features in the image feature library of the normal position state of the preset shear pin; When it is detected that among the image features is less than or equal to a preset jacking distance threshold, it is determined that the comparison with the features in the preset image feature library of the jacking position state of the air brake flap is consistent; When it is detected that among the is greater than a preset jacking distance threshold, it is determined that there is a mismatch in the comparison with the feature in the preset image feature library of the jacking position state of the air brake flap; When it is detected that among the said image features is less than or equal to a preset falling distance threshold value, it is determined that the comparison with the features in the preset image feature library of the falling position state of the air brake flap is consistent; When it is detected that among the said image features is greater than a preset falling distance threshold value, it is determined that there is a mismatch in the comparison with the features in the preset image feature library of the falling position state of the air brake flap.

9. The discrimination method of the water turbine generator fault precise discrimination system based on image recognition according to claim 8, characterized in that, The angle threshold is 17°, the jacking distance threshold is 35 mm, and the falling distance threshold is 5 mm.

10. The discrimination method of the water turbine generator fault precise discrimination system based on image recognition according to claim 7, characterized in that, The output process of S04 is as follows: If the shear pin status is sheared and the feature in the image feature does not match the feature in the preset image feature library, output: Shear pin No. X is sheared; If the shear pin status is not sheared, when the in the image features does not match the features in the preset image feature library, output: The shear pin No. X may be sheared, and the signal is not reported at this time; If the shear pin is in a sheared state, when the in the image features matches the features in the preset image feature library, output: False alarm of the shear signal of shear pin No. X; If the shear pin status is not sheared, when the in the image features is consistent with the features in the preset image feature library, output: The status of shear pin No. X is normal; If the status of the air brake sensor (4) is jacking, that is, the upper sensor (41) detects a pressure signal, and when the position of the air brake gate is consistent with the image feature library of the preset jacking position state of the air brake gate, output: The jacking state of the No. X air brake is normal; If the status of the air brake sensor (4) is jacking, that is, the upper sensor (41) detects a pressure signal, and when the position of the air brake gate is inconsistent with the image feature library of the preset jacking position state of the air brake gate, output: The state of the No. X air brake is abnormal; If the status of the air brake sensor (4) is falling, that is, the lower sensor (42) detects a pressure signal, and when the position of the air brake gate is consistent with the image feature library of the preset falling position state of the air brake gate, output: The falling state of the No. X air brake is normal; If the status of the air brake sensor (4) is falling, that is, the lower sensor (42) detects a pressure signal, and when the position of the air brake gate is inconsistent with the image feature library of the preset falling position state of the air brake gate, output: The state of the No. X air brake is abnormal; If the status of the air brake sensor (4) is not jacking or falling, that is, neither the upper sensor (41) nor the lower sensor (42) detects a pressure signal, and when the position of the air brake gate is inconsistent with the image feature library of the preset jacking position or falling position state of the air brake gate, output: The position of the No. X air brake is abnormal; If the status of the air brake sensor (4) is not jacking or falling, that is, neither the upper sensor (41) nor the lower sensor (42) detects a pressure signal, and when the position of the air brake gate is inconsistent with the image feature library of the preset intermediate position state of the air brake gate, output: The state of the No. X air brake is abnormal.

Images