Main shaft automatic loading and unloading method, device and system, electronic equipment and storage medium

Abstract

The invention relates to an automatic loading and unloading system, method and device for a main shaft, electronic equipment and a storage medium, and belongs to the technical field of coal loading and unloading. The method comprises the steps that the weight of coal loaded every time, the weight of conveyed materials in a skip, tension of a steel wire rope and skip image information after coal unloading are obtained; a judgment step is executed, and the judgment step comprises the steps of judging whether the weight of conveyed materials is consistent with the weight of loaded coal materials or not after skip bucket feeding; judging whether the conveying weight of the skip bucket after unloading is zero or not; judging whether the steel wire rope tension after skip unloading is consistent with the steel wire rope tension when the skip is unloaded or not; if at least one item is not judged in the judging step, analyzing skip image information by applying a neural network model, and determining the position and residual quantity of a residual coal pile in the skip; determining the impact path and the impact strength of the air cannon according to the position and the residual quantity of the residual coal pile; and the air cannon treats the residual coal pile according to the impact path and the impact strength. According to the invention, the possibility of secondary loading is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of coal loading and unloading, and in particular to a method, device, system, electronic equipment and storage medium for automatic loading and unloading of a main shaft. Background Art

[0002] The main shaft automatic loading and unloading system is responsible for the production and transportation tasks of the entire mine, and its safe and efficient operation is crucial.

[0003] In the current main shaft automatic loading and unloading PLC system, the coal feeder at the loading and unloading station loads coal into the skip of the elevator. Under the lifting of the elevator, the coal is lifted to the unloading station through the skip, thereby realizing the automation of coal loading and unloading.

[0004] However, if the internal lining of the skip is damaged due to friction or impact of coal flow, or the coal quality changes and becomes sticky, or the coal flow is mixed with gangue, ironware, or wood to block the coal unloading port, the coal unloading will not be smooth, resulting in excess coal remaining in the skip, resulting in incomplete coal unloading. If the staff fails to determine whether the skip has been unloaded of coal in time and handle it, the skip may descend to the coal feeder for reloading, resulting in secondary loading, which poses a safety hazard. Summary of the invention

[0005] In order to reduce the possibility of secondary loading and improve transportation safety, the present application provides a main shaft automatic loading and unloading method, device, system, electronic equipment and storage medium.

[0006] In the first aspect, the present application provides a main well automatic loading and unloading method, which is applied to the main well automatic loading and unloading system and is executed by electronic equipment, and adopts the following technical solutions: Obtain the coal weight of each load, real-time bucket weight, wire rope tension and bucket image information after coal unloading; Execute a judgment step, the judgment step comprising: Determining whether the weight of the skip after loading is consistent with the weight of the coal; Judging whether the skip is emptied after discharging materials according to the weight of the skip; Judging whether the bucket is empty after discharging materials according to the tension of the wire rope; If at least one of the judgments in the judging step is negative, a neural network model is used to analyze the skip image information to determine the position and amount of the residual coal pile in the skip; Determine the impact path and impact strength of the air cannon according to the position and residual amount of the residual coal pile; The air cannon is used to process the residual coal pile according to the impact path and impact intensity.

[0007] By adopting the above technical solution, the electronic equipment obtains the weight of the coal loaded each time and compares it with the weight after the skip is loaded. This can accurately verify whether the loading process is accurate and effectively prevent overloading or underloading. In addition, real-time monitoring of the skip weight can dynamically grasp the changes in the coal in the skip, and combine the two parameters of the skip weight and the wire rope tension to determine whether the skip is empty, thereby improving the accuracy and reliability of the judgment. By using a neural network model to analyze the skip image information, the location and amount of the residual coal pile can be accurately determined. By using an air cannon to process the residual coal pile, it can be ensured that the skip is completely emptied after each unloading, thereby avoiding transportation and unloading problems caused by residual coal piles, improving transportation efficiency, reducing manual intervention, and reducing labor costs.

[0008] Further, the applying of the neural network model to analyze the skip image information to determine the position and amount of the residual coal pile in the skip includes: Acquire multiple time-continuous bucket image information; Determine the clarity of each of the bucket image information, and use the bucket image information with the highest clarity as the first image information; Inputting the first image information into a neural network model to determine the contour of the residual coal pile; Establishing a coordinate system on the first image information, determining a set of coordinate points within the outline, and determining the set of coordinate points as the position of the residual coal pile; The point cloud data within the outline is acquired, a virtual model of the skip is established according to the point cloud data, the volume of the residual coal pile is determined in the virtual model, and the residual amount of the residual coal pile is calculated according to the volume.

[0009] By adopting the above technical solution, by acquiring multiple time-continuous skip image information and selecting the image with the highest definition as the first image information, it can be ensured that the image data processed subsequently has high resolution and detail clarity. By processing the first image information using a neural network model, the outline of the residual coal pile can be automatically identified. A coordinate system is established on the first image information, and a set of coordinate points within the outline is determined. The position of the residual coal pile can be accurately located. By acquiring point cloud data within the outline and establishing a virtual model of the skip, three-dimensional modeling of the residual coal pile can be achieved. This helps to more intuitively understand the shape and distribution of the residual coal pile, and then accurately calculate its volume and residual amount.

[0010] Furthermore, the method of determining the impact path and impact strength of the air cannon according to the position and residual amount of the residual coal pile further includes: Determine the residual quantity of each residual coal pile; Determine at least one cylindrical impact range according to the residual amount of each residual coal pile, the axis of the impact range is directly opposite to the air cannon, and adjust the size of the impact range according to a first ratio of a first residual amount of the residual coal pile within the impact range to a total residual amount of all residual coal piles, until the first ratio reaches a first preset value; The impact path and impact intensity of the air cannon are determined according to the location of the air cannon, the location of each impact range and the size of each impact range.

[0011] By adopting the above-mentioned technical scheme, the present application sorts the residual coal pile in descending order according to the residual amount to obtain the first sequence, and then takes the residual coal pile with a large residual amount as the main residual body, and first divides the impact range according to the main residual body for analysis. When the first ratio reaches the first preset value, it is determined that the air cannon can solve most of the residues at one time according to the impact range. When the first ratio does not reach the first preset value, the air cannon is required to expand the impact range or generate another impact range, and determine the next residual coal pile in the first sequence as a new main residual body. When the distance between the main residual body and the original impact range is greater than the preset distance, another impact range is generated, so that the air cannon processes the residual coal in multiple times; when the distance between the main residual body and the original impact range is greater than the preset value, the impact range is expanded, so that the air cannon continuously processes the residual coal, and then the air cannon cleaning plan can be automatically planned according to the actual situation of the residual coal in the bucket.

[0012] Further, the method of determining the impact path and impact strength of the air cannon according to the position of the air cannon, the position of each impact range and the size of each impact range includes: Determine whether each of the impact ranges is greater than a maximum impact range corresponding to the air cannon at a maximum impact intensity; If it is not greater than the maximum impact range, the air cannon is placed directly opposite the impact range in the virtual model to determine the impact path of the air cannon, and the impact strength of the air cannon corresponding to the impact range is searched according to a preset table; If it is greater than the maximum impact range, the axis of the impact range is overlapped with the axis of the maximum impact range, and a second ratio of a first residual amount of the residual coal pile within the impact range to a second residual amount of the residual coal pile within the maximum impact range is calculated; Determining whether the second ratio is greater than a second preset value; If the second ratio is greater than a second preset value, the air cannon is made to face the axis of the impact range in the virtual model to determine the impact path of the air cannon, and the maximum impact intensity is adopted; If the second ratio is not greater than the second preset value, the impact path and impact strength of the air cannon are determined in the virtual model according to the shape of the residual coal pile.

[0013] By adopting the above technical solution, after determining the impact range, the present application further determines the impact path and impact strength according to the position of the air cannon, the location and size of the impact range, wherein the air cannon has the maximum impact strength and also has a corresponding maximum impact range. Therefore, the impact range is first compared with the maximum impact range.

[0014] When it is not greater than the maximum impact range, the direction of the air cannon is simulated and determined in the virtual model, and the impact strength required for the impact range is determined according to the specifications of the air cannon. When it is greater than the maximum impact range, the air cannon is analyzed when using the maximum impact strength, and the second ratio of the second residual amount within the maximum impact range to the first residual amount within the overall impact range is calculated. When the second ratio is greater than the preset value, the maximum impact strength is used, and the air cannon can impact most of the residual coal, and due to the fluidity of the coal, the residual coal nearby will also be cleaned up, so it is sufficient to simulate and determine in the virtual model that the air cannon is cleaned in a fixed direction; when the second ratio is not greater than the second preset value, the air cannon needs to be moved for cleaning, and the method of projecting the circumscribed rectangle is used at this time.

[0015] When the rectangle is close to a square, the air cannon can be moved in a circular manner for cleaning; when the rectangle is not close to a square, that is, it is long and narrow, the air cannon can be moved back and forth for cleaning, and then the routes are planned according to the preset rules, and the moving direction and impact strength of the air cannon are simulated and determined in the virtual model. Then, the air cannon cleaning plan can be automatically planned according to the actual situation of the residual coal in the skip.

[0016] Furthermore, the method further comprises: Get video information of loading station; generating an electronic fence in the video information; The staff in the video information is identified, and when the staff enters the electronic fence, an alarm message is generated.

[0017] In the second aspect, the present application provides a main well automatic loading and unloading device, which adopts the following technical solution: An acquisition module is used to obtain the weight of coal loaded each time, the weight of material transported in the bucket, the tension of the wire rope, and the image information of the bucket after coal unloading; The judging module is used to execute the judging step, wherein the judging step includes: Determining whether the weight of the material delivered after the skip is loaded is consistent with the weight of the loaded coal; Determine whether the feeding weight is zero after the bucket is unloaded; Determine whether the wire rope tension after the bucket is unloaded is consistent with the wire rope tension when the bucket is empty; A residual analysis module, for analyzing the skip image information using a neural network model to determine the position and amount of the residual coal pile in the skip if at least one of the judgment steps performed by the judgment module is judged to be no; An air cannon treatment plan planning module is used to determine the impact path and impact strength of the air cannon according to the position and residual amount of the residual coal pile; An execution module is used to enable the air cannon to process the residual coal pile according to the impact path and impact intensity.

[0018] In the third aspect, the present application provides a main well automatic loading and unloading system, which adopts the following technical solutions: It comprises a PLC controller, a hoist, a loading station and an unloading station, wherein the hoist is located between the loading station and the unloading station, the hoist comprises a winch and a bucket, and the winch drives the bucket to rise and fall between the coal feeder and the unloading station; The loading station includes a loading weighing sensor, the skip is provided with a feeding weighing sensor, the winch is provided with a wire rope tension detection sensor, and the unloading station is provided with an air cannon facing the skip and emptying the skip after coal unloading, a pan / tilt for adjusting the direction of the air cannon, and a laser radar camera for photographing the image information of the skip after coal unloading; The loading weighing sensor, the feeding weighing sensor, the wire rope tension detection sensor and the air cannon are all connected to the PLC controller; It also includes an electronic device, which is connected to the PLC controller and the lidar camera respectively, and executes the method as described in any one of the first aspects.

[0019] By adopting the above technical solution, the PLC controller obtains the data of each sensor, forwards the data calculated by the electronic device, and issues instructions to each execution device to realize comprehensive automated control of the elevator, loading station and unloading station. Furthermore, the loading weighing sensor detects the weight of the loaded coal, and the feeding weighing sensor detects the weight of the coal in the bucket. The electronic device compares the weights of the two to determine whether it is in a normal loading state. After the bucket is unloaded, the weight of the coal in the bucket and the tension of the wire rope can be used to monitor whether there is any coal residue in the bucket. With the auxiliary identification of the laser radar camera, the residual coal can be processed by the air cannon. Therefore, the automation level of the loading and unloading station is further improved, and there is no need to manually handle the residual coal. The bucket can be emptied more accurately, which improves the overall performance and operation efficiency of the main shaft automatic loading and unloading system.

[0020] In a fourth aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program being configured to: execute the method as described in any one of the second aspects.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and executes the method as described in any one of the first aspects.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. Obtain the weight of coal loaded each time and compare it with the weight after the skip is loaded, which can accurately verify whether the loading process is accurate and effectively prevent overloading or underloading. In addition, real-time skip weight monitoring can dynamically grasp the changes in coal in the skip, and combine the two parameters of skip weight and wire rope tension to determine whether the skip is empty, thereby improving the accuracy and reliability of judgment; 2. The use of neural network models to analyze the bucket image information can accurately determine the location and amount of residual coal pile; 3. Using air cannons to treat the residual coal pile can ensure that the bucket can be completely emptied after each unloading, avoiding transportation and unloading problems caused by residual coal piles, improving transportation efficiency, reducing manual intervention, and reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is the electrical control structure diagram of the main well automatic loading and unloading system in the embodiment of the present application.

[0024] Figure 2 It is a flow chart of the main well automatic loading and unloading method in the embodiment of the present application.

[0025] Figure 3 This is a schematic diagram of the running trajectory generated when the aspect ratio of the minimum circumscribed rectangle is close to 1 in the embodiment of the present application.

[0026] Figure 4 It is a schematic diagram of the running trajectory generated when the aspect ratio of the minimum circumscribed rectangle is not close to 1 in the embodiment of the present application.

[0027] Figure 5 It is a structural block diagram of the main well automatic loading and unloading device in an embodiment of the present application.

[0028] Figure 6 It is a structural block diagram of an electronic device in an embodiment of the present application.

[0029] Figure numerals: 1. PLC controller; 2. Loading weighing sensor; 3. Feeding weighing sensor; 4. Wire rope tension detection sensor; 5. Pan / tilt; 6. Air cannon; 7. LiDAR camera; 8. Radar level meter; 9. Display screen. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0032] The present application embodiment provides a main well automatic loading and unloading system, referring to Figure 1 , which is set at the loading station, includes a PLC controller 1, an elevator and a coal feeder. The elevator includes a winch and a bucket. The winch can drive the bucket to rise and fall between the coal feeder and the unloading station. The coal feeder adds coal into the bucket, and then the bucket lifts the coal upward and transports it to the unloading station for unloading.

[0033] Furthermore, a loading weighing sensor 2 is provided on the coal feeder, and a feeding weighing sensor 3 is provided on the skip. Both the loading weighing sensor 2 and the feeding weighing sensor 3 are connected to the PLC controller 1. The PLC controller 1 uses PROFINET data communication and I / O hard line transmission to transmit data to the upper computer in the workshop, which is referred to as an electronic device. Then, the electronic device obtains the weight of the coal loaded on the skip and the weight of the coal actually loaded in the skip, and then, by comparison, it can be judged whether the coal feeding is accurate.

[0034] A wire rope tension detection sensor 4 is provided on the winch, and the wire rope tension detection sensor 4 is also connected to the PLC controller 1, so that the electronic equipment can comprehensively analyze whether the loading process is normal according to the wire rope tension and the coal weight.

[0035] After the skip transports the coal to the unloading station, the coal is unloaded to the unloading station, and then the unloading station receives the coal and carries out the next step of transportation.

[0036] The system also includes a pan / tilt 5, an air cannon 6 and a laser radar camera 7 arranged on the unloading station. The pan / tilt 5 can drive the air cannon 6 to rotate to different directions and angles, such as the pan / tilt 5. The air cannon 6 and the laser radar camera 7 are directly opposite to the position where the bucket is lifted to the highest point. When the bucket is lifted to the highest point and coal is unloaded, the air cannon 6 can clean the coal remaining in the bucket, and the laser radar camera 7 can capture the image information of the bucket after unloading coal.

[0037] Among them, the pan-tilt head 5, air cannon 6 and lidar camera 7 are all connected to the PLC controller 1. Therefore, the electronic equipment can obtain the bucket image information through the PLC controller 1, analyze the remaining coal in the bucket according to the bucket image information, plan the rotation plan of the pan-tilt head 5 and the impact strength of the air cannon 6, and make the air cannon 6 clean the bucket according to the planned direction and impact strength.

[0038] Furthermore, in order to improve the stability of the system, the system adopts a dual redundant system so that the backup system can be started in time when a failure occurs to ensure the stability of the system.

[0039] In order to facilitate the control of starting and stopping the coal feeder, the loading station also includes a coal feeder silo. A radar level meter 8 is arranged in the coal feeder silo. The radar level meter 8 is connected to the PLC controller 1. When the coal in the coal feeder silo is lower than the preset value, the PLC controller 1 gives feedback to stop the coal feeder.

[0040] The PLC controller 1 is also connected to a display screen 9, which may preferably be a touch screen, for viewing system-related data, such as the material level of the coal feeder, the weight of the material transported in the bucket, the operating data of the elevator, the image information of the bucket, etc.

[0041] The present application embodiment discloses a main well automatic loading and unloading method, which is applied to the main well automatic loading and unloading system. Figure 2 , executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto. It includes (steps S101 to S105): Step S101: Obtain the weight of coal loaded each time, the weight of material in the bucket, the tension of the wire rope and the image information of the bucket after unloading coal.

[0042] Specifically, the electronic device communicates with the PLC controller to obtain the weight of the coal loaded each time, the weight of the material in the bucket, the tension of the wire rope and the image information of the bucket after unloading the coal.

[0043] Step S102: Execute the judgment step, which includes (steps S1021 to S1023): Step S1021: Determine whether the weight of the material after the skip is loaded is consistent with the weight of the loaded coal.

[0044] Step S1022: Determine whether the material weight after the bucket is unloaded is zero.

[0045] Step S1023: Determine whether the wire rope tension after the bucket is unloaded is consistent with the wire rope tension when the bucket is empty.

[0046] Specifically, under normal loading conditions, the feeding weight after the skip is loaded should be consistent with the weight of the loaded coal. If not, there may be residual coal piles in the skip, resulting in overweight during loading. Furthermore, under normal unloading and emptying conditions, after the skip is unloaded, the feeding weight should be zero and the wire rope tension should be close to the tension when pulling the empty skip. Therefore, when the feeding weight after the skip is unloaded is not zero or the wire rope tension after the skip is unloaded is inconsistent with the wire rope tension when the skip is empty, there may be residual coal piles in the skip.

[0047] If the judgment steps are all yes, no operation is performed.

[0048] If at least one of the determinations in the determination step is negative, then steps S103 to S105 are executed.

[0049] Step S103: applying a neural network model to analyze the bucket image information to determine the position and amount of the residual coal pile in the bucket, including (steps S1031 to S1035): Step S1031: Obtain bucket image information corresponding to multiple continuous times.

[0050] Specifically, the laser radar camera continuously photographs the bucket in real time, and the electronic device obtains the bucket image information for multiple consecutive times after the moment when the judgment is no.

[0051] Step S1032: Determine the clarity of each bucket image information, and use the bucket image information with the highest clarity as the first image information.

[0052] Step S1033: input the first image information into the coal contour convolutional neural network model to determine the contour of the residual coal pile.

[0053] Specifically, the electronic device selects an image with higher definition for analysis, so as to improve the accuracy of the analysis result.

[0054] The electronic device pre-trains the coal contour convolutional neural network model. During the training, a large amount of sample data containing coal images is collected. These sample images cover different forms, lighting conditions, backgrounds, etc. of coal to ensure the generalization ability of the model. The sample images are annotated to clarify the contour area of ​​the coal. The sample images are pre-processed by normalization, cropping, rotation, scaling, etc. to improve the training efficiency and accuracy of the model.

[0055] Configure training parameters, such as learning rate, batch size, number of iterations, etc., and use the preprocessed sample data to train the model. During the training process, the model will continuously adjust the weight and bias parameters to minimize the loss function. By monitoring indicators such as loss value and accuracy during the training process, the training effect of the model can be evaluated.

[0056] The trained model is evaluated using the test data set. The performance of the model is evaluated by calculating indicators such as accuracy, recall, and F1 score. The model is optimized based on the evaluation results, and the optimized model is retrained and its performance is evaluated again. Through multiple iterative training, the accuracy and generalization ability of the model are continuously improved, and then the coal profile convolutional neural network model is trained.

[0057] After the electronic device inputs the first image information into the coal contour convolutional neural network model, the coal contour in the first image information can be identified.

[0058] Step S1034: establishing a coordinate system on the first image information, determining a set of coordinate points within the coal material contour, and determining the set of coordinate points as the position of the residual coal pile.

[0059] Step S1035: Acquire the point cloud data within the coal material outline, establish a virtual model of the bucket according to the point cloud data within the coal material outline, determine the volume of the residual coal pile in the virtual model, and calculate the residual amount of the residual coal pile according to the volume.

[0060] Specifically, the electronic device can obtain the point cloud data of the bucket image information captured by the laser radar camera, and then overlap the point cloud data with the coordinate system to determine the point cloud data located within the coal material outline. The point cloud data includes the three-dimensional coordinates of each point, and then the volume of the residual coal pile can be determined by the three-dimensional coordinates of each point within the coal material outline, and then the residual amount of the residual coal pile can be calculated by multiplying the weight per unit volume of the coal material by the volume.

[0061] Step S104: Determine the impact path and impact strength of the air cannon according to the position and residual amount of the residual coal pile, including (steps S1041 to S1043): Step S1041: Determine the residual amount of each residual coal pile.

[0062] Specifically, the electronic device determines the residual amount of each residual coal pile through image recognition.

[0063] Step S1042: Determine at least one cylindrical impact range according to the residual amount of each residual coal pile, with the axis of the impact range facing the air cannon, and adjust the size of the impact range according to a first ratio of the first residual amount of the residual coal pile within the impact range to the total residual amount of all residual coal piles, until the first ratio reaches a first preset value.

[0064] Step S1043: determining the impact path and impact intensity of the air cannon according to the location of the air cannon, the location of each impact range, and the size of each impact range.

[0065] Wherein, step S1042 includes (steps S11 to S19): Step S11: Determine the residual coal pile with the largest residual amount as the main residual body, and determine the distance between each residual coal pile and the main residual body in the virtual model.

[0066] Specifically, after the residual coal pile is determined in the virtual model, the distance is determined as the length of the closest line segment between the edges of the two residual coal piles.

[0067] Step S12: Arrange the residual coal piles in descending order according to the distance, and take the main residual body as the head of the queue to obtain the first sequence.

[0068] Step S13: Determine a cylindrical impact range including the main residual body contour in the virtual model, with the axis of the impact range facing the air cannon.

[0069] Specifically, when the air cannon is working, it will quickly release the stored compressed air through a specific nozzle or discharge port. In this process, the compressed air will form a strong airflow, which will maintain a certain shape and speed when it is ejected. Under the premise that the air cannon barrel is circular, the application believes that the generated air column is close to a cylindrical shape.

[0070] Therefore, a cylindrical impact range for simulating the impact airflow is generated in the virtual model, and the axis of the impact range is directly facing the air cannon. In order to completely clean the main residual body, the impact range covers the contour of the main residual body.

[0071] Execute loop steps: Step S14: determining a first ratio of the sum of the residual amount of the main residual body and the first residual amount of the residual coal piles in the first sequence within the impact range to the total residual amount of all residual coal piles.

[0072] Specifically, after the impact range is generated in the virtual model, other residual coal piles in the first sequence may also be covered in the impact range, that is, when the main residual body is impacted, the residual coal piles located in the impact range are impacted. Then, the electronic device determines the first residual amount based on the point cloud data of the residual coal piles located in the impact range.

[0073] The sum of the first residue and the residue of the main residue is the amount of coal that can be impacted in the current impact range, and then the first ratio of the sum to the total residue can be calculated. The first ratio can determine whether the current impact range can impact most of the residual coal piles.

[0074] Step S15: Determine whether the first ratio reaches a first preset value.

[0075] If the first ratio reaches the first preset value, step S1043 is executed: the impact path and impact strength of the air cannon are determined according to the position of the air cannon, the positions of each impact range and the size of each impact range.

[0076] Specifically, the electronic device presets a first preset value, which can be set to a value close to 1, such as 0.97. The closer the first preset value is to 1, the higher the cleanliness required by the air cannon cleaning. When the first ratio is greater than or equal to the first preset value, it can be determined that the current impact range can impact most of the residual coal pile.

[0077] Furthermore, when the first ratio reaches the first preset value, the electronic device can further determine the impact path and impact intensity of the air cannon according to the current location and size of the impact range and the location of the air cannon.

[0078] If the first ratio does not reach the first preset value, step S16 to step S19 are executed.

[0079] Step S16: taking the next residual coal pile in the first sequence as a new main residual body.

[0080] Step S17: determining whether the distances between the new main residual body and each impact range are greater than a preset distance.

[0081] Specifically, the electronic device is preset with a preset distance, and the preset distance is used to determine whether to change the size of the impact range or to reset another impact range.

[0082] If both are greater than the preset distance, step S18 is executed: another impact range including a new main residual body is determined, and the loop steps are repeated until the first ratio reaches a first preset value.

[0083] Specifically, if the distance between the main residual body and each impact range is greater than the preset distance, the distance between the new main residual body and each impact range is too far. When the air cannon is cleaned according to the impact range, it is difficult to impact the new main residual body. Therefore, another impact range including the new main residual body is generated, and the cycle steps are further repeated to determine in turn whether the next residual coal pile in the first sequence can be impacted.

[0084] If there is at least one distance that is not greater than the preset distance, step S19 is executed: the radius of the circle of the impact range closest to the new main residual body is enlarged to obtain a new impact range, so that the updated impact range includes the new main residual body, and the loop steps are repeated until the first ratio reaches the first preset value.

[0085] Specifically, when there is at least one distance that is not greater than the preset distance, the impact range closest to the new main residual body is first determined, and its circle radius is expanded, and the new main residual body is included in the new impact range, and the cycle steps are further repeated to determine in turn whether the next residual coal pile in the first sequence can be impacted.

[0086] Furthermore, when the electronic device executes step S1043, it includes (steps S21 to S26): Step S21: Determine whether each impact range is greater than the maximum impact range corresponding to the air cannon at the maximum impact intensity.

[0087] Specifically, the air cannon has a maximum impact strength. If the impact range is too large, it is difficult to complete the cleaning in one go without changing the direction angle of the air cannon. Therefore, the impact range is compared with the maximum impact range at the maximum impact strength.

[0088] If it is not greater than the maximum impact range, step S22 is executed: in the virtual model, the air cannon is directed to the impact range to determine the impact path of the air cannon, and the impact strength of the air cannon corresponding to the impact range is searched according to a preset table.

[0089] Specifically, when the impact range is not greater than the maximum impact range, it means that the air cannon can operate in a fixed direction. Therefore, the position of the air cannon is simulated in the virtual model according to the actual situation, and the corresponding direction when the air cannon is facing the impact range is determined, such as the horizontal angle and the numerical direction angle.

[0090] Furthermore, since the size of the impact range is proportional to the impact strength of the air cannon, the stronger the impact strength, the larger the generated impact range. Therefore, the electronic device presets a table, which includes the impact strength of the air cannon corresponding to each size of the impact range, and determines the impact strength by looking up the table.

[0091] If there is no impact intensity completely corresponding to the compared impact range in the preset table, the impact intensity corresponding to the impact range in the preset table that is larger than and closest to the compared impact range is selected.

[0092] If it is greater than the maximum impact range, steps S23 to S26 are executed.

[0093] Step S23: Overlap the axis of the impact range with the axis of the maximum impact range, and calculate a second ratio of a first residual amount of the residual coal pile within the impact range to a second residual amount of the residual coal pile within the maximum impact range.

[0094] Specifically, if it is greater than the maximum impact range, it is necessary to plan the operation plan for air cannon cleaning.

[0095] In order to complete the cleaning as quickly as possible, the air cannon adopts the maximum impact intensity, the axis of the impact range is overlapped with the axis of the maximum impact range, and the busbar length of the maximum impact range is the same as the busbar length of the impact range, which makes it easier to determine the second residual amount of the residual coal pile within the maximum impact range based on the point cloud data.

[0096] Step S24: determining whether the second ratio is greater than a second preset value.

[0097] Specifically, the electronic device first calculates a second ratio of the second residual amount to the first residual amount, and a second preset value is preset, and the second preset value is close to 1, such as 0.97, etc. The second preset value is used to measure whether the residual coal pile can be mostly cleaned up when the air cannon impacts with the maximum impact intensity and does not move.

[0098] If the second ratio is greater than the second preset value, step S25 is executed: in the virtual model, the air cannon is made to face the axis of the impact range to determine the impact path of the air cannon, and the maximum impact intensity is adopted.

[0099] Specifically, when the second ratio is greater than the second preset value, the air cannon can clean up most of the residual coal pile within the impact range when it impacts with the maximum impact intensity and does not move in the direction. Even if the first residual amount is not completely equal to the second residual amount, in the actual cleaning process, the aftermath of the air wave emitted by the air cannon or the vibration caused by the coal sliding down can clean up a small amount of residual coal pile together. Therefore, in the virtual model, the air cannon is operated in the axial direction of the impact range.

[0100] In another possible implementation, if the second ratio is not greater than the second preset value, the air cannon cannot achieve the expected effect by cleaning the residual coal pile in one direction, so it is necessary to further plan the operation path of the air cannon.

[0101] If the second ratio is not greater than the second preset value, step S26 is executed: determining the impact path and impact strength of the air cannon in the virtual model according to the shape of the residual coal pile.

[0102] Specifically, step S26 includes (steps S261 to S266): Step S261: Determine the projection of the residual coal pile within the impact range on the circular end surface of the impact range.

[0103] Step S262: Generate a minimum circumscribed rectangle of the projection, and obtain the length and width of the minimum circumscribed rectangle respectively.

[0104] Specifically, since the air cannon is impacting the impact range, the projection of the residual coal pile on the circular end surface of the impact range can reflect the approximate layout of the residual coal pile. The minimum circumscribed rectangle is used to facilitate the layout of the air cannon's operating route, so that the air cannon can complete the cleaning along the path with the least operation, thus shortening the cleaning time.

[0105] Furthermore, if the ratio of the length to the width of the minimum circumscribed rectangle is close to 1, it means that the shape of the minimum circumscribed rectangle is approximately a square, and the air cannon can be cleaned in a circle.

[0106] Step S263: If the ratio of length to width is close to 1, the following steps are performed: Step S264: taking the line connecting the center of the minimum circumscribed rectangle and any corner as the first line segment.

[0107] If the first line segment is larger than the diameter of the maximum impact range, execute step S265: generate multiple concentric circles around the center of the minimum circumscribed rectangle, the radius of the first inner concentric circle is equal to the radius of the maximum impact range, and the distance between two adjacent concentric circles is equal to the diameter of the maximum impact range, select a starting point on the innermost concentric circle, and generate a running trajectory based on the starting point and the concentric circles, so that when the air cannon impacts the running trajectory with the maximum impact intensity, the minimum circumscribed rectangle is covered, and in the virtual model, the air cannon is made to run directly opposite the running trajectory to determine the impact path.

[0108] Specifically, if the first line segment is larger than the diameter of the maximum impact range, the expected cleaning effect may not be achieved when the air cannon cleans around the center of the minimum circumscribed rectangle with the maximum impact intensity.

[0109] Reference Figure 3 a, concentric circles are divided in the minimum circumscribed rectangle. Each concentric circle is the trajectory that the axis of the air cannon is facing. After the concentric circles are divided, a starting point is selected in the inner circle. After going around the inner circle, it moves to the outer circle and reaches point ki (i=1, 2, ...n, n is the number of concentric circles). Then it moves around the second circle, and then walks through each concentric circle from the inside to the outside.

[0110] After determining the running trajectory, the electronic equipment moves the air cannon according to the running trajectory in the virtual model to determine the actual impact path of the air cannon.

[0111] If the first line segment is not larger than the diameter of the maximum impact range, execute step S183: generate a circular motion trajectory with the center of the minimum circumscribed rectangle as the center of the circle and half the length of the first line segment as the radius, and in the virtual model, make the air cannon run directly opposite the motion trajectory to obtain the impact path, use the first line segment as the impact diameter of the air cannon, and look up the impact strength of the air cannon corresponding to the impact diameter according to the preset table.

[0112] Specifically, refer to Figure 3 In b, if the first line segment is not larger than the diameter of the maximum impact range, the air cannon moves in a circle, with any point on the circular trajectory as the starting point, and one circle around the circle is the circular trajectory.

[0113] In the virtual model, the axis of the maximum impact range generated by the air cannon is moved along a circular trajectory to obtain the air cannon's running path. In order to enable the air cannon to completely clean the residual coal pile, the length of the first line segment is used as the impact diameter of the air cannon. The impact range of the air cannon is larger than the minimum circumscribed rectangle, and can affect all the residual coal piles, achieving a better cleaning effect.

[0114] Furthermore, the electronic device determines the impact strength of the air cannon corresponding to the impact diameter by looking up a table.

[0115] In another implementation, if the ratio of the length to the width of the minimum circumscribed rectangle is not close to 1, the air cannon can be cleaned in a reciprocating manner.

[0116] Step S266: If the ratio of length to width is not close to 1, the following steps are performed: If the width is greater than the diameter of the maximum impact range, execute step S267: confirm the starting point on any width, the distance between the starting point and the nearest corner is equal to the radius of the maximum impact range, and generate a running trajectory that moves back and forth within the minimum circumscribed rectangle from the starting point, so that when the axis of the air cannon is facing the running trajectory and impacts with the maximum impact intensity, the minimum circumscribed rectangle is covered, and in the virtual model, the air cannon is facing the running trajectory to determine the impact path.

[0117] Specifically, if the width is greater than the diameter of the maximum impact range, the air cannon needs to be moved back and forth at least once with the maximum impact intensity to complete the cleaning. Therefore, a reciprocating translation trajectory is generated within the minimum circumscribed rectangle, and then the actual impact path of the air cannon is determined through the virtual model.

[0118] Reference Figure 4a in the figure is one of the possibilities. The starting point is determined on the width, and the first trajectory parallel to the long side is generated. Then, it moves downward along the width, and the second trajectory parallel to the long side is generated. The distance between two adjacent trajectories parallel to the long side is equal to the diameter corresponding to the maximum impact range, and the running trajectory is generated.

[0119] If the width is not greater than the diameter of the maximum impact range, execute step S268: take the midpoint of any width as the starting point, generate a running trajectory parallel to the length, make the air cannon face the running trajectory in the virtual model to determine the impact path, determine the width as the impact diameter, and find the impact strength of the air cannon corresponding to the impact diameter according to the preset table.

[0120] Specifically, refer to Figure 4 If the width of b is not greater than the diameter of the maximum impact range, the air cannon can move in a straight line to complete the cleaning. Therefore, a running trajectory is generated in the minimum circumscribed rectangle. Then, the impact path is simulated and determined in the virtual model.

[0121] Step S105: Use the air cannon to process the residual coal pile according to the impact path and impact intensity.

[0122] Specifically, after the electronic equipment determines the impact path and impact intensity, it determines the driving scheme of the pan-tilt head according to the impact path, and sends instructions to the PLC controller to make the pan-tilt head move according to the driving scheme, make the air cannon operate according to the impact path, and work at the impact intensity to complete the processing of the residual coal pile.

[0123] In another possible implementation, the method further includes: Obtain video information of the loading station; generate an electronic fence in the video information; identify the staff in the video information, and generate an alarm message when the staff enters the electronic fence.

[0124] Specifically, a camera is installed at the loading station to capture dangerous work areas, such as the location of the elevator, coal feeder or unloader. The camera is connected to the PLC controller. After the electronic device obtains the video information through the PLC controller, it generates an electronic fence in the video information. Then, the staff in the video information is identified. When the staff enters the electronic fence, an alarm is issued to remind the staff to pay attention to work safety.

[0125] In order to better implement the above method, the present application also provides a main well automatic loading and unloading device, referring to Figure 5 The main well automatic loading and unloading device 200 comprises: The acquisition module 201 is used to acquire the weight of coal loaded each time, the weight of material transported in the bucket, the tension of the wire rope and the image information of the bucket after coal unloading; The judgment module 202 is used to perform a judgment step, which includes: Determine whether the weight of the material after the skip is loaded is consistent with the weight of the loaded coal; Determine whether the feeding weight is zero after the bucket is unloaded; Determine whether the wire rope tension after the bucket is unloaded is consistent with the wire rope tension when the bucket is empty; The residual analysis module 203 is used to analyze the bucket image information using a neural network model to determine the position and residual amount of the residual coal pile in the bucket if at least one of the judgment steps performed by the judgment module 202 is judged to be no; The air cannon treatment plan planning module 204 is used to determine the impact path and impact strength of the air cannon according to the location and residual amount of the residual coal pile; The execution module 205 is used to make the air cannon process the residual coal pile according to the impact path and impact intensity.

[0126] Further, the residue analysis module 203 is specifically used for: Obtain bucket image information corresponding to multiple continuous times; Determine the clarity of each bucket image information, and use the bucket image information with the highest clarity as the first image information; Inputting the first image information into a coal contour convolutional neural network model to determine the contour of the residual coal pile; Establishing a coordinate system on the first image information, determining a set of coordinate points within the coal material contour, and determining the set of coordinate points as the position of the residual coal pile; The point cloud data within the coal material outline is obtained, a virtual model of the skip is established according to the point cloud data, the volume of the residual coal pile is determined in the virtual model, and the residual amount of the residual coal pile is calculated according to the volume.

[0127] Furthermore, the air cannon treatment solution planning module 204 is specifically used to: Determine the residual quantity of each residual coal pile; Determine at least one cylindrical impact range according to the residual amount of each residual coal pile, the axis of the impact range is directly opposite to the air cannon, and adjust the size of the impact range according to a first ratio of a first residual amount of the residual coal pile within the impact range to a total residual amount of all residual coal piles until the first ratio reaches a first preset value; The impact path and impact intensity of the air cannon are determined according to the location of the air cannon, the location of each impact range and the size of each impact range.

[0128] When the residual analysis module 203 determines the impact path and impact strength of the air cannon according to the location of the air cannon, the location of each impact range, and the size of each impact range, it is specifically used to: Determine whether each impact range is greater than the maximum impact range corresponding to the air cannon at the maximum impact intensity; If it is not greater than the maximum impact range, the air cannon is placed directly opposite the impact range in the virtual model to determine the impact path of the air cannon, and the impact strength of the air cannon corresponding to the impact range is found according to the preset table; If it is greater than the maximum impact range, the axis of the impact range is overlapped with the axis of the maximum impact range, and a second ratio of a first residual amount of the residual coal pile within the impact range to a second residual amount of the residual coal pile within the maximum impact range is calculated; Determining whether the second ratio is greater than a second preset value; If the second ratio is greater than the second preset value, the impact path of the air cannon is determined by making the air cannon face the axis of the impact range in the virtual model, and the maximum impact intensity is adopted; If the second ratio is not greater than the second preset value, the impact path and impact strength of the air cannon are determined in the virtual model according to the shape of the residual coal pile.

[0129] Furthermore, the main well automatic loading and unloading device 200 also includes: A video information acquisition module, used to acquire video information of the loading station; An electronic fence generation module, used for generating an electronic fence in video information; The alarm module is used to identify the staff in the video information and generate an alarm message when the staff enters the electronic fence.

[0130] The various variations and specific examples of the methods in the aforementioned embodiments are also applicable to the main well automatic loading and unloading device of the present embodiment. Through the aforementioned detailed description of the main well automatic loading and unloading method, those skilled in the art can clearly know the implementation method of the main well automatic loading and unloading device of the present embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0131] In order to better implement the above method, the present application embodiment provides an electronic device, referring to Figure 6 , the electronic device 300 includes: a processor 301 and a memory 303. The memory 303 is connected to the processor 301, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0132] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0133] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 302 may be divided into an address bus, a data bus, a control bus, etc.

[0134] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0135] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0136] Figure 6 The electronic device 300 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0137] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the program is executed by the processor, the main shaft automatic loading and unloading method provided by the above embodiment is implemented, and the weight of the coal loaded each time is obtained and compared with the weight after the bucket is loaded. It can accurately verify whether the loading process is accurate and effectively prevent overloading or underloading. In addition, real-time monitoring of the bucket weight can dynamically grasp the changes in the coal in the bucket, and combine the two parameters of the bucket weight and the wire rope tension to determine whether the bucket is empty, thereby improving the accuracy and reliability of the judgment. The neural network model is used to analyze the bucket image information to accurately determine the position and residual amount of the residual coal pile. The residual coal pile is processed by an air cannon to ensure that the bucket can be completely emptied after each unloading, thereby avoiding transportation and unloading problems caused by residual coal piles, improving transportation efficiency, reducing manual intervention, and reducing labor costs.

[0138] In this embodiment, the computer-readable storage medium may be a tangible device that holds and stores instructions used by the instruction execution device. The computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, and any combination thereof.

[0139] The computer program in this embodiment includes program codes for executing all the aforementioned methods, and the program codes may include instructions corresponding to the steps of the methods provided in the above embodiments. The computer program can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network (such as the Internet, a local area network, a wide area network, and / or a wireless network). The computer program can be executed completely on the user's computer or as an independent software package.

[0140] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

[0141] In addition, it is to be understood that relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprises," "comprising," or any other variation thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or elements that are inherent to such process, method, article, or device.

Claims

1. A main well automatic loading and unloading method, applied to the main well automatic loading and unloading system, executed by electronic equipment, characterized in that: include: Obtain the coal weight of each load, the weight of the material in the bucket, the wire rope tension and the image information of the bucket after unloading; Execute a judgment step, the judgment step comprising: Determining whether the weight of the material delivered after the skip is loaded is consistent with the weight of the loaded coal; Determine whether the feeding weight is zero after the bucket is unloaded; Determine whether the wire rope tension after the bucket is unloaded is consistent with the wire rope tension when the bucket is empty; If at least one of the judgments in the judging step is negative, a neural network model is used to analyze the skip image information to determine the position and amount of the residual coal pile in the skip; Determine the impact path and impact strength of the air cannon according to the position and residual amount of the residual coal pile; The air cannon is used to process the residual coal pile according to the impact path and impact intensity.

2. The method according to claim 1, characterized in that The method of applying a neural network model to analyze the skip image information to determine the position and amount of the residual coal pile in the skip includes: Obtain bucket image information corresponding to multiple continuous times; Determine the clarity of each of the bucket image information, and use the bucket image information with the highest clarity as the first image information; Inputting the first image information into a coal contour convolutional neural network model to determine the contour of the residual coal pile; Establishing a coordinate system on the first image information, determining a set of coordinate points within the coal material contour, and determining the set of coordinate points as the position of the residual coal pile; The point cloud data within the coal material outline is obtained, a virtual model of the bucket is established according to the point cloud data, the volume of the residual coal pile is determined in the virtual model, and the residual amount of the residual coal pile is calculated according to the volume.

3. The method according to claim 1, characterized in that The step of determining the impact path and impact strength of the air cannon according to the position and residual amount of the residual coal pile further includes: Determine the residual quantity of each residual coal pile; Determine at least one cylindrical impact range according to the residual amount of each residual coal pile, the axis of the impact range is directly opposite to the air cannon, and adjust the size of the impact range according to a first ratio of a first residual amount of the residual coal pile within the impact range to a total residual amount of all residual coal piles, until the first ratio reaches a first preset value; The impact path and impact intensity of the air cannon are determined according to the location of the air cannon, the location of each impact range, and the size of each impact range.

4. The method according to claim 3, characterized in that Determining the impact path and impact strength of the air cannon according to the location of the air cannon, the location of each impact range, and the size of each impact range includes: Determine whether each of the impact ranges is greater than a maximum impact range corresponding to the air cannon at a maximum impact intensity; If it is not greater than the maximum impact range, the air cannon is placed directly opposite the impact range in the virtual model to determine the impact path of the air cannon, and the impact strength of the air cannon corresponding to the impact range is searched according to a preset table; If it is greater than the maximum impact range, the axis of the impact range is overlapped with the axis of the maximum impact range, and a second ratio of a first residual amount of the residual coal pile within the impact range to a second residual amount of the residual coal pile within the maximum impact range is calculated; Determining whether the second ratio is greater than a second preset value; If the second ratio is greater than a second preset value, the air cannon is made to face the axis of the impact range in the virtual model to determine the impact path of the air cannon, and the maximum impact intensity is adopted; If the second ratio is not greater than the second preset value, the impact path and impact strength of the air cannon are determined in the virtual model according to the shape of the residual coal pile.

5. The method according to claim 1, characterized in that The method further comprises: Get video information of loading station; generating an electronic fence in the video information; The staff in the video information is identified, and when the staff enters the electronic fence, an alarm message is generated.

6. A main well automatic loading and unloading device, characterized in that: include: An acquisition module is used to obtain the weight of coal loaded each time, the weight of material transported in the bucket, the tension of the wire rope, and the image information of the bucket after coal unloading; The judging module is used to execute the judging step, wherein the judging step includes: Determining whether the weight of the material delivered after the skip is loaded is consistent with the weight of the loaded coal; Determine whether the feeding weight is zero after the bucket is unloaded; Determine whether the wire rope tension after the bucket is unloaded is consistent with the wire rope tension when the bucket is empty; A residual analysis module, for analyzing the skip image information using a neural network model to determine the position and amount of the residual coal pile in the skip if at least one of the judgment steps performed by the judgment module is judged to be no; An air cannon treatment plan planning module is used to determine the impact path and impact strength of the air cannon according to the position and residual amount of the residual coal pile; An execution module is used to enable the air cannon to process the residual coal pile according to the impact path and impact intensity.

7. A main well automatic loading and unloading system, characterized in that: Applied to a loading station, comprising a PLC controller (1), an elevator and a coal feeder, wherein the elevator comprises a winch and a bucket, and the winch drives the bucket to rise and fall between the coal feeder and the unloading station; The coal feeder comprises a loading weighing sensor (2), the skip is provided with a feeding weighing sensor (3), the winch is provided with a wire rope tension detection sensor (4), and the system further comprises an air cannon (6) arranged on the unloading station facing the skip lifted to the highest point and emptying the skip after coal unloading, a pan / tilt (5) for adjusting the direction of the air cannon (6), and a laser radar camera (7) for photographing image information of the skip after coal unloading; The loading weighing sensor (2), the feeding weighing sensor (3), the wire rope tension detection sensor (4), the air cannon (6), the pan / tilt platform (5) and the laser radar camera (7) are all connected to the PLC controller (1); It also includes an electronic device, which is connected to the PLC controller (1) and executes the method according to any one of claims 1 to 5.

8. The system according to claim 7, characterized in that Also includes: The system adopts a dual redundant system; The loading station further comprises a coal feeder silo, wherein a radar level meter (8) is arranged in the coal feeder silo, and the radar level meter (8) is connected to the PLC controller (1); The PLC controller (1) is also connected to a display screen (9).

9. An electronic device, characterized in that: include: at least one processor; Memory; At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program being configured to: execute the method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 5.

Images