Intelligent monitoring and alarming system for falling off of electric bucket teeth, processor and memory

Abstract

The invention discloses an intelligent monitoring and alarming system for falling off of bucket teeth of an electric shovel, a processor and a memory. The intelligent monitoring and alarming system for falling off of the bucket teeth of the electric shovel comprises the steps that bucket teeth on two continuous frames of bucket images of the electric shovel are recognized; when the position of the bucket tooth on the latter frame of the electric shovel bucket image is lower than the position of the bucket tooth on the former frame of the electric shovel bucket image, it is judged that the electric shovel is in a shovel-down state at the moment; the number of the bucket tooth target monitoring frames on the multiple images is recorded in sequence; when the maximum value of the number of the bucket tooth target monitoring frames is smaller than the number of the complete bucket teeth on the bucket, it is judged that the electric bucket teeth fall off; when the electric bucket tooth falls off, the image marking the falling bucket tooth is displayed on the display screen, and the alarm is started, so that the accuracy and reliability of monitoring whether the electric bucket tooth falls off or not can be improved, misjudgment can be prevented, an alarm can be given in time, the alarm can be controlled to stop alarming in time according to needs, and operation of operators is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of bucket tooth shedding monitoring, and in particular to an electric shovel bucket tooth shedding intelligent monitoring and alarm system, a processor and a memory based on visual triggering. Background Art

[0002] Electric shovels are often used in mining operations such as ore extraction and loading. The teeth on the bucket come into direct contact with the ore, subjecting them to complex forces and making them susceptible to detachment. Because the teeth are made of a strong alloy, if they become detached and enter the subsequent crushing process along with the ore-laden truck, they can cause crusher failure, production line shutdown, and even personnel accidents. Therefore, tooth detachment alarms are essential to enable operators to promptly locate the tooth and avoid unforeseen production line downtime.

[0003] Currently, there are two main approaches to monitoring and alarming for tooth loss. One involves placing sensors inside the tooth cavity. When a tooth falls off, the sensor generates a signal that triggers an alarm system. However, the tooth is in direct contact with the ore, subject to intense friction and impact, which can easily damage the sensor and cause it to fail. The other approach involves using surveillance cameras to capture images of the tooth and identifying it through a target monitoring network to determine if the tooth has fallen off. However, this approach is limited by ore obstruction and model accuracy, resulting in frequent false alarm triggering. There is also no clearing mechanism for the alarm, significantly impacting the work of on-site operators. Summary of the Invention

[0004] The present invention aims to address at least one of the technical problems existing in the prior art. To this end, one objective of the present invention is to provide a visually triggered intelligent monitoring and alarm method for bucket tooth detachment in electric shovels. This monitoring and alarm method overcomes the shortcomings of existing camera-based bucket tooth detachment monitoring and alarm methods, which frequently generate false alarms when ore is obscured or model accuracy is limited. This method significantly improves the accuracy of bucket tooth detachment detection and includes an alarm cancellation mechanism to minimize the impact on on-site operators.

[0005] The present invention further proposes an intelligent monitoring and alarm system for bucket tooth shedding of an electric shovel.

[0006] The present invention further provides a memory.

[0007] The present invention further provides a processor.

[0008] According to an embodiment of the present invention, a visually triggered intelligent monitoring and alarm method for electric shovel bucket tooth detachment includes the following steps: continuously acquiring bucket images of the electric shovel while it is in operation; identifying bucket teeth on two consecutive frames of the electric shovel bucket images; determining that the electric shovel is in a shoveling down state when bucket teeth are present in both consecutive frames of the electric shovel bucket images, and the position of the bucket teeth in the latter frame of the electric shovel bucket image is lower than the position of the bucket teeth in the previous frame of the electric shovel bucket image; when the electric shovel is in the shoveling down state, saving the continuously acquired electric shovel bucket images and sequentially recording the number of bucket tooth target monitoring frames on multiple images; when the bucket tooth target monitoring frame is zero, comparing the maximum number of bucket tooth target monitoring frames on the recorded multiple images with the number of complete bucket teeth on the bucket; determining that the electric shovel bucket teeth are detached when the maximum number of bucket tooth target monitoring frames is less than the number of complete bucket teeth on the bucket; when it is determined that the electric shovel bucket teeth are detached, displaying an image marked with the detached bucket teeth on a display screen and activating an alarm. The alarm is selectively controlled to stop the alarm based on the image on the display screen.

[0009] Therefore, the number of bucket teeth target monitoring frames is obtained during the shovel's shoveling process, and compared with the number of complete bucket teeth of the electric shovel. When the number of bucket teeth target monitoring frames obtained during the shovel's shoveling process is less than the number of complete bucket teeth of the electric shovel, it is determined that the bucket teeth of the electric shovel are off. Since the bucket teeth of the electric shovel will not be blocked by ore during the shovel's shoveling process, the number of bucket teeth obtained through infrared video images is more accurate. Only monitoring whether the bucket teeth are off during the shovel's shovel is performed to improve the accuracy and reliability of the intelligent monitoring and alarm method for bucket teeth off of the electric shovel based on visual triggering, which can reduce the probability of misjudgment, improve the stability and reliability of the electric shovel device, and can also alarm in time, and control the alarm to stop in time as needed, which is convenient for the operator's operation.

[0010] In some examples of the present invention, the step of identifying bucket teeth in two consecutive frames of electric shovel bucket images further includes: In some examples of the present invention, a target detection algorithm is used to obtain bucket teeth on two consecutive frames of images of the electric shovel when it is working based on the two consecutive frames of images of the electric shovel when it is working.

[0011] In some examples of the present invention, when it is determined that the bucket teeth of the electric shovel have fallen off, an image marked with the fallen bucket teeth is displayed on the display screen, and the step of starting the alarm also includes: when the operator presses the pause reset button, the alarm is controlled to stop the alarm, and the display screen is controlled to display multiple images of the electric shovel bucket during the shoveling process.

[0012] In some examples of the present invention, the step of controlling the alarm to stop sounding and controlling the display screen to display multiple images of the electric shovel bucket during the shoveling process when the operator presses the pause reset button also includes: when the operator presses the pause reset button again, controlling the alarm to be silent and controlling the display screen to display a real-time image of the electric shovel bucket.

[0013] In some examples of the present invention, when it is determined that the bucket teeth of the electric shovel have fallen off, an image marked with the fallen bucket teeth is displayed on the display screen, and the step of activating the alarm also includes: controlling the electric shovel to stop working and the bucket of the electric shovel to return to the initial position to facilitate the maintenance or replacement of the electric shovel.

[0014] The intelligent monitoring and alarm system for bucket tooth shedding of an electric shovel based on visual triggering according to an embodiment of the present invention is applicable to the above-mentioned intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering, and is characterized in that it includes: a video image acquisition device; a monitoring and alarm host, the monitoring and alarm host is electrically connected to the video image acquisition device, and the monitoring and alarm host is integrated with a display screen, an alarm, a start / stop button, a pause / reset button, a back button, and a fast-forward button.

[0015] The memory according to the embodiment of the present invention stores a computer program thereon, and when the computer program is executed, the above-mentioned intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering is implemented.

[0016] According to the processor of the embodiment of the present invention, the processor is communicatively connected to the memory, and the computer program in the memory can be executed on the processor.

[0017] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments with reference to the accompanying drawings, in which: Figure 1 This is a flow chart of an intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering according to an embodiment of the present invention; Figure 2 This is a flow chart of the alarm and release mechanism of the intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering according to an embodiment of the present invention; Figure 3 2 is a schematic structural diagram of an electric shovel device according to an embodiment of the present invention.

[0019] Reference numerals: 100. Electric shovel device; 10. Bucket; 11. Bucket teeth; 20. Sky wheel; 21. Infrared video image acquisition device; 30. Intelligent monitoring and alarm system for bucket tooth shedding of electric shovel based on visual triggering; 31. Display screen; 32. Alarm; 33. Host; 34. Pause and resume button; 35. Start and stop button; 36. Fast forward button; 37. Backward button. DETAILED DESCRIPTION

[0020] The embodiments of the present invention will be described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. The embodiments of the present invention will be described in detail below.

[0021] Reference below Figure 1-Figure 3 The present invention describes an intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering according to an embodiment of the present invention.

[0022] Combine Figure 1-Figure 3 As shown, the intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering according to the present invention may include the following steps: S1, continuously acquiring images of the bucket of the electric shovel when it is working; S2, identifying bucket teeth on two consecutive frames of electric shovel bucket images; S3. When bucket teeth are present in two consecutive frames of the electric shovel bucket image, and the position of the bucket teeth in the latter frame of the electric shovel bucket image is lower than the position of the bucket teeth in the former frame of the electric shovel bucket image, it is determined that the electric shovel is in the shoveling down state at this time; S4. When the electric shovel is in the shoveling state, saving continuously acquired electric shovel bucket images and sequentially recording the number of bucket tooth target monitoring frames on the multiple images; S5. When the bucket tooth target monitoring frame is zero, compare the maximum number of bucket tooth target monitoring frames on the multiple recorded images with the number of complete bucket teeth on the bucket; S6. When the maximum number of bucket teeth target monitoring frames is less than the number of complete bucket teeth on the bucket, it is determined that the bucket teeth of the electric shovel are off; S7. When it is determined that the bucket teeth of the electric shovel are detached, an image indicating the detached bucket teeth is displayed on the display screen and an alarm is activated; S8. Selectively controlling the alarm to stop sounding according to the image on the display screen.

[0023] Specifically, an electric shovel controls the movement of the bucket 10 to load ore into the bucket and then transfer the ore to a haul truck. The operation of the bucket 10 is a cyclical motion consisting primarily of lowering the bucket, scooping ore, lifting the bucket, and discharging the ore. Ore or dust may obstruct the bucket teeth 11 of the electric shovel during these stages. Therefore, monitoring whether the bucket teeth 11 are dislodged during these stages, where the teeth 11 may be obstructed by ore or dust, is highly likely to result in misjudgment, reducing the accuracy and reliability of the electric shovel's bucket tooth dislodgment monitoring method.

[0024] Therefore, in some embodiments of the present invention, infrared video images of the electric shovel are obtained frame by frame during the shovel's shoveling process, and the number of bucket teeth 11 during the shovel's shoveling process is obtained through multiple frames of infrared video images obtained during the shovel's shoveling process. Since there is no obstruction from ore and dust, the obtained number of bucket teeth 11 is more accurate. The obtained number of bucket teeth 11 of the electric shovel is compared with the number of complete bucket teeth 11 of the electric shovel. If the number of bucket teeth 11 during the shovel's shoveling process is less than the number of complete bucket teeth 11 of the electric shovel, it is determined that the bucket teeth 11 of the electric shovel have fallen off, and the alarm 32 is controlled to sound an alarm. After hearing the alarm 32, the operator can take relevant measures to prevent the bucket teeth 11 from falling off, causing failures in subsequent operations, thereby improving the structural reliability of the electric shovel device 100.

[0025] Therefore, the number of bucket teeth 11 is obtained during the shovel's lowering process and compared with the number of complete bucket teeth 11 of the electric shovel. When the number of bucket teeth 11 obtained during the shovel's lowering process is less than the number of complete bucket teeth 11 of the electric shovel, it is determined that the bucket teeth 11 of the electric shovel have fallen off. Since the bucket teeth 11 of the electric shovel will not be blocked by ore during the shovel's lowering process, the number of bucket teeth 11 obtained through infrared video images is more accurate. Monitoring whether the bucket teeth 11 have fallen off is only performed during the shovel's lowering process to improve the accuracy of the electric shovel bucket teeth 11 falling-off monitoring method, which can reduce the probability of misjudgment and improve the stability and reliability of the electric shovel device 100.

[0026] In some embodiments of the present invention, due to the limited accuracy of the target monitoring algorithm, it may be impossible to accurately identify the bucket teeth 11 using a single frame of infrared video. Furthermore, because the bucket 10 of an electric shovel needs to move downward when mining ore, two consecutive frames of infrared video images of the electric shovel are acquired, and the bucket teeth 11 in the infrared video images are obtained based on the acquired two consecutive frames of infrared video images of the electric shovel. When the bucket teeth 11 are present in both consecutive frames of infrared video images of the electric shovel, it indicates that the bucket teeth 11 region in the two consecutive frames of infrared video images of the electric shovel is clear and unobstructed. Furthermore, under this premise, the positional relationship of the bucket teeth 11 in the two consecutive frames of infrared video images is determined. When the position of the bucket teeth 11 in the subsequent frame of infrared video image is lower in the vertical direction than in the previous frame of infrared video image of the electric shovel, it indicates that the bucket 10 of the electric shovel is moving downward. Although the bucket 10 is also operated from top to bottom in the shoveling stage, because of the above judgment that there is no ore obstruction at this time, and the bucket teeth 11 in the shoveling stage will definitely be obstructed by the ore, the situation that the electric shovel is in the shoveling stage can be ruled out. In summary, it can be determined that the electric shovel is in the down-shoveling state at this time. This not only makes it more accurate to judge whether the electric shovel is in the down-shoveling state, but also makes the judgment simpler, which can further improve the reliability of judging whether the electric shovel is in the down-shoveling state.

[0027] In some embodiments of the present invention, the target monitoring algorithm belongs to the field of computer vision and is mainly used to identify and locate multiple objects in an image or video. The target monitoring algorithm can not only identify what objects are in the image, but also determine where these objects are. The position of each object is usually given in the form of a target monitoring frame. The bucket tooth 11 on the infrared video image is acquired by the target monitoring algorithm, which not only improves the accuracy and reliability of the acquisition of the bucket tooth 11, but also improves the efficiency of the acquisition.

[0028] In some embodiments of the present invention, target monitoring algorithms can be roughly divided into two categories: traditional target monitoring algorithms and deep learning-based target monitoring algorithms. Traditional target monitoring algorithms generally include the following steps: Methods such as selective search generate candidate regions.

[0029] Extract features, such as using feature descriptors such as SIFT and HOG, classify the extracted features using a classifier (such as SVM), and remove redundant overlapping boxes using non-maximum suppression (NMS). Representative algorithms include Deformable Parts Model (DPM).

[0030] The target monitoring algorithm based on deep learning is mainly divided into two-stage monitoring and single-stage monitoring.

[0031] Two-stage detection algorithms first generate a series of candidate regions that may contain objects, then classify and refine the locations of these candidate regions. Representative algorithms include the R-CNN series (including R-CNN, Fast R-CNN, and Faster R-CNN) and the Region-based Fully Convolutional Network (R-FCN).

[0032] Single-stage detection algorithms can directly predict the object category and location without generating candidate regions, making them faster. Representative algorithms include YOLO (You Only Look Once), SSD (Single Shot MultiBox Detector), and RetinaNet.

[0033] In some specific embodiments of the present invention, the target monitoring algorithm may be a target monitoring algorithm based on deep learning.

[0034] Furthermore, by saving the infrared video image of each frame during the shovel's shoveling process, and recording the number of bucket teeth 11 target monitoring frames on each frame of the infrared video image. When the number of bucket teeth 11 target monitoring frames is zero, it means that the electric shovel has entered the shoveling stage, and the bucket teeth 11 of the electric shovel are completely blocked by the ore. At this time, it can be determined that the electric shovel's shoveling state has ended. The maximum value of the number of bucket teeth 11 target monitoring frames during the entire shovel's shoveling process is selected as the number of bucket teeth 11 during the above-mentioned shovel's shoveling process, that is, the maximum value of the number of bucket teeth 11 target monitoring frames during the entire shovel's shoveling process is compared with the number of complete bucket teeth 11 of the electric shovel. When the maximum value of the number of bucket teeth 11 target monitoring frames during the entire shovel's shoveling process is less than the number of complete bucket teeth 11 of the electric shovel, it is determined that the bucket teeth 11 have fallen off.

[0035] It should be noted that, since the bucket teeth 11 will not rub against the ore during the shoveling process and will not be affected by external forces, the bucket teeth 11 will not detach during this process. If the bucket teeth 11 fall off, it will generally occur during the shoveling, lifting and releasing stages. Therefore, the actual number of bucket teeth 11 should remain unchanged during the entire shoveling process, and the number of bucket teeth 11 will not change from more to less during the shoveling process. However, since the target monitoring algorithm may have inevitable accuracy errors, and objective factors in the external environment may also cause errors in the target monitoring algorithm, the number of target monitoring frames of the bucket teeth 11 in the infrared video images of multiple frames of bucket teeth 11 may be inconsistent. Therefore, the maximum value of the number of target monitoring frames of the bucket teeth 11 during the entire shoveling process of the electric shovel is the actual number of bucket teeth 11 when the electric shovel is shoveling, which is more accurate and can eliminate the accuracy errors of the target monitoring algorithm, thereby improving the accuracy of the target monitoring algorithm.

[0036] Further, combined with Figure 3 As shown, the infrared video images captured during the shovel's digging process are infrared video images of the shovel's bucket 10. To prevent the shovel's boom and other structures from obstructing the field of view, an infrared video image acquisition device 21 for capturing infrared video images of the shovel's bucket 10 during operation is fixedly mounted in the center of the shovel's head wheel 20. This device is used to capture visible light or infrared video images of the shovel's bucket 10 area. The field of view and installation angle of the infrared video image acquisition device 21 are determined based on the motion trajectory of the bucket 10. In some embodiments of the present invention, the video image acquisition area of ​​the infrared video image acquisition device 21 needs to cover the entire bucket 10 area in the horizontal field of view and more than half of the bucket 10's motion area during digging in the vertical field of view.

[0037] It should be noted that the sky wheel 20 is located at the top of the bucket 10, and the infrared video image acquisition device 21 is set in the middle of the sky wheel 20. This not only makes it convenient for the infrared video image acquisition device 21 to collect infrared video images of the bucket teeth 11 of the bucket 10, but also improves the safety, reliability and service life of the infrared video image acquisition device 21.

[0038] Furthermore, after determining that the bucket teeth 11 of the electric shovel have fallen off and controlling the alarm device 32 to sound an alarm, the controller can mark the infrared video image of the electric shovel's bucket teeth 11 falling off and display the infrared video image of the electric shovel's bucket teeth 11 falling off on the display screen 31. With this arrangement, on the one hand, after hearing the alarm, the operator can immediately confirm whether the bucket teeth 11 have actually fallen off by observing the infrared video image of the electric shovel's bucket teeth 11 falling off displayed on the display screen. If the display screen shows that the bucket teeth 11 of the electric shovel have fallen off, the operator can perform relevant operations. If the display screen shows that the bucket teeth 11 of the electric shovel have not fallen off, it can be determined that the monitored bucket teeth 11 have fallen off due to algorithm errors. This can further eliminate the possibility that the monitored bucket teeth 11 have fallen off due to algorithm errors, prevent the operator from discovering that the bucket teeth 11 have not fallen off when inspecting the bucket teeth 11, further improve the accuracy and reliability of the electric shovel bucket teeth 11 falling off monitoring method, and thus improve the stability and reliability of the electric shovel operation.

[0039] Combine Figure 1As shown, when the number of bucket teeth 11 during the shovel's shoveling process is less than the number of complete bucket teeth 11 of the shovel, it is determined that the shovel's bucket teeth 11 have fallen off, and the step of controlling the alarm 32 to alarm also includes: when the operator presses the pause reset button, controlling the alarm 32 to stop the alarm, and controlling the display screen to display the infrared video image of the shovel during the shovel's shovel-down process. Specifically, after the alarm 32 sounds an alarm and the display screen displays the infrared video image of the shovel's bucket teeth 11 falling off, the operator can control the alarm 32 to stop the alarm by pressing the pause reset button, thereby preventing the alarm 32 from continuously alarming and affecting the operator, thereby improving the operator's operating comfort. Furthermore, after the operator presses the pause reset button, the display screen can display the infrared video image of the shovel's entire shovel-down process, allowing the operator to conduct a more detailed and accurate check, thereby further improving the reliability of the shovel's bucket teeth 11-down monitoring method.

[0040] It should be noted that in some specific embodiments of the present invention, the alarm 32 is an audible and visual alarm, which emits a buzzer and is accompanied by a flash, thereby improving the alarm effect of the alarm 32 in different application scenarios, thereby allowing the operator to respond in time.

[0041] In some examples of the present invention, when the operator presses the pause reset button 34, the step of controlling the alarm 32 to stop the alarm and controlling the display screen to display the infrared video image of the electric shovel during the shoveling process also includes: when the operator presses the pause reset button again, controlling the alarm 32 to be silent and controlling the display screen to display the real-time infrared video image of the electric shovel.

[0042] Specifically, when the operator presses the pause reset button again, the alarm 32 is silenced, i.e., the alarm 32 returns to its initial state, and the display shows the real-time infrared video image of the electric shovel. The electric shovel then continues to operate normally. It should be noted that in this case, one possibility is that a misjudgment occurred, and the operator, after confirming that no bucket teeth 11 had fallen off, pressed the pause reset button a second time, allowing the electric shovel device 100 to continue operating normally. Another possibility is that the maintenance personnel have completed repairing or replacing the bucket 10 of the electric shovel device 100, and the electric shovel device 100 is now capable of continuing to operate.

[0043] Such a configuration not only makes it easier and more direct for the operator to operate the electric shovel device 100 , but also further improves the reliability of the electric shovel device 100 .

[0044] Further, combined with Figure 3As shown, the intelligent monitoring and alarm system for bucket tooth shedding of an electric shovel based on visual triggering according to the present invention can mainly include a video image acquisition device and a monitoring and alarm host. The monitoring and alarm host 30 is mainly used for storing relevant data of the entire monitoring system, calculating the monitoring algorithm and alarming the shedding of the bucket teeth 11. It mainly includes components such as a host 33, a display screen, a photoacoustic alarm 32 and buttons: the host 33 is used to store the algorithm and image data and calculate the monitoring algorithm, calculate the result of the bucket tooth 11 shedding and store the image data within a monitoring cycle. The display screen is used to display the monitoring process and the infrared video image of the bucket 10 after the bucket teeth 11 fall off. When the bucket teeth 11 fall off is detected, the display screen will display an image of the bucket 10 with annotations, which is convenient for the operator to verify the bucket teeth 11 shedding. The photoacoustic alarm 32 is used to remind the on-site operator to verify the bucket teeth 11 shedding situation. The multiple buttons have the functions of start and stop, pause reset, fast forward and rewind. The start / stop button 35 is used to start and stop the entire intelligent monitoring and alarm system. After the electric shovel device 100 stops working, the electric shovel bucket tooth detachment intelligent monitoring and alarm system 30 based on visual triggering can also be turned off, which can further improve the reliability of the electric shovel device 100.

[0045] Furthermore, the pause and reset button 34 and the fast forward and rewind buttons 37 on the monitoring and alarm host 30 are used to assist the operator in verifying the tooth 11's detachment. When the light and sound alarm sounds, the operator presses the pause and reset button 34 to stop the alarm. The operator can then use the fast forward and rewind buttons 36 and 37 to view images of the tooth 11 frame by frame on the display screen throughout the entire monitoring cycle, reviewing details of the tooth 11 detachment. If a false alarm occurs, the pause and reset button can be pressed again to resume normal operation of the electric shovel device 100.

[0046] Furthermore, in order to facilitate the operator to verify the status of the bucket teeth 11 falling off, the monitoring and alarm host 30 is installed next to the driving seat in the cab, which does not affect the operator's work and makes it convenient for the operator to watch and operate the electric shovel bucket tooth falling off intelligent monitoring and alarm system 30 based on visual triggering of the embodiment of the present invention.

[0047] Furthermore, this can also keep the electric shovel bucket tooth detachment intelligent monitoring and alarm system 30 based on visual triggering away from the ore, thereby preventing damage to the bucket teeth 11 and the impact damage of the ore, thereby improving the safety and reliability of the electric shovel bucket tooth detachment intelligent monitoring and alarm system 30 based on visual triggering, thereby improving the service life of the electric shovel bucket tooth detachment intelligent monitoring and alarm system 30 based on visual triggering.

[0048] In some embodiments of the present invention, when the number of bucket teeth 11 during the shovel's shoveling process is less than the number of complete bucket teeth 11 of the shovel, it is determined that the bucket teeth 11 of the shovel are detached, and the step of controlling the alarm 32 to alarm also includes: controlling the shovel to stop working, and the bucket 10 of the shovel returns to the initial position to facilitate the maintenance or replacement of the shovel.

[0049] Specifically, when it is determined that the bucket tooth 11 of the electric shovel has fallen off, the electric shovel can be controlled to return to the initial position. It should be noted that the initial position of the bucket 10 of the electric shovel refers to the lowest position of the bucket 10. This can facilitate the maintenance or replacement of the bucket 10 of the electric shovel, reduce the cost of maintenance or replacement of the bucket 10 of the electric shovel, and make the maintenance or replacement of the bucket 10 of the electric shovel safer.

[0050] It should be noted that if the bucket 10 of the electric shovel is obstructed by the ore pile during the process of returning to the initial position, the user needs to move the electric shovel device 100 to a position where the ore pile cannot obstruct the electric shovel from returning to the initial position.

[0051] The memory according to the present invention stores a computer program thereon, which, when executed, implements the above-mentioned method for detecting missing bucket teeth of an electric shovel based on the infrared vision translation-invariant feature.

[0052] According to the processor of the present invention, the processor is communicatively connected to the memory, and the computer program in the memory can be executed on the processor.

[0053] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0054] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "example," "specific example," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example.

[0055] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. An intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering, characterized in that: The following steps are involved: Continuously acquire images of the bucket while the shovel is working; Identify bucket teeth on two consecutive frames of shovel bucket images; When bucket teeth are present in two consecutive frames of shovel bucket images, and the position of the bucket teeth in the latter frame of the shovel bucket image is lower than that in the previous frame of the shovel bucket image, the shovel is determined to be in the shoveling down state. When the electric shovel is in a shoveling state, continuously acquired electric shovel bucket images are saved, and the number of bucket tooth target monitoring frames on the multiple images is recorded in sequence; When the bucket tooth target monitoring frame is zero, comparing the maximum number of bucket tooth target monitoring frames on the multiple recorded images with the number of complete bucket teeth on the bucket; When the maximum number of bucket teeth target monitoring frames is less than the number of complete bucket teeth on the bucket, it is determined that the bucket teeth of the electric shovel are off; When it is determined that the bucket teeth of the electric shovel are falling off, an image with the falling teeth will be displayed on the display screen and the alarm will be activated; According to the image on the display screen, the alarm is selectively controlled to stop the alarm.

2. The intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering according to claim 1 is characterized in that: The step of identifying bucket teeth on two consecutive frames of electric shovel bucket images also includes: A target detection algorithm is used to obtain bucket teeth on two consecutive frames of images of the electric shovel when it is working based on the two consecutive frames of images of the electric shovel when it is working.

3. The intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering according to claim 1 is characterized in that: When it is determined that the bucket teeth of the electric shovel are off, the image marked with the off bucket teeth is displayed on the display screen, and the step of activating the alarm further includes: When the operator presses the pause reset button, the alarm is controlled to stop sounding, and the display screen is controlled to display multiple images of the electric shovel bucket during the shoveling process.

4. The intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering according to claim 3 is characterized in that: The step of controlling the alarm to stop sounding when the operator presses the pause reset button and controlling the display screen to display multiple images of the electric shovel bucket during the shoveling process further includes: When the operator presses the pause reset button again, the alarm is controlled to be silent and the display screen is controlled to display the real-time image of the electric shovel bucket.

5. The method for intelligent monitoring and alarming of bucket tooth shedding of an electric shovel based on visual triggering according to claim 4 is characterized in that: When it is determined that the bucket teeth of the electric shovel are off, the image marked with the off bucket teeth is displayed on the display screen, and the step of activating the alarm further includes: The electric shovel is controlled to stop working and the bucket of the electric shovel returns to the initial position to facilitate the maintenance or replacement of the electric shovel.

6. An intelligent monitoring and alarm system for bucket teeth falling off of an electric shovel based on visual triggering, applicable to the intelligent monitoring and alarm method for bucket teeth falling off of an electric shovel based on visual triggering according to any one of claims 1 to 5, characterized in that: include: Video image acquisition device; A monitoring and alarm host is electrically connected to the video image acquisition device, and the monitoring and alarm host is integrated with a display screen, an alarm, a start / stop button, a pause / reset button, a back button, and a fast-forward button.

7. A memory having a computer program stored thereon, characterized in that: When the computer program is executed, the intelligent monitoring and alarm method for bucket tooth shedding of an electric shovel based on visual triggering according to any one of claims 1 to 5 is implemented.

8. A processor, characterized in that: The processor is communicatively connected to the memory, and the computer program in the memory can be executed on the processor.

Images