Crown block anti-collision automatic control method and system

Abstract

The invention relates to the technical field of crown block control, in particular to a crown block anti-collision automatic control method and system, and the method comprises the steps: collecting the operation data of each crown block in historical operation, calculating the swing distance of a load at the lower part of the crown block, and judging whether the operation state of a crown block braking system is abnormal or not; in response to the abnormal running state of the crown block braking system, the crown block stops running, and on the contrary, a preset neural network model is trained according to the running data during braking and the maximum swing distance to obtain a swing distance model; and inputting crown block operation data collected in real time into the swing distance model, calculating distance deviation during real-time braking, constructing and updating a loss function to obtain predicted maximum swing distances, adding the predicted maximum swing distances of two adjacent operating crown blocks as a reserved distance, and controlling the crown blocks to operate. The updating loss function of the swing distance model is continuously updated through the distance deviation, and the accuracy of model prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of overhead crane control, and more specifically, to an overhead crane anti-collision automatic control method and system. Background Art

[0002] Overhead crane is a heavy lifting equipment, usually used in the industrial field for handling and lifting heavy objects. It consists of a beam and several movable lifting mechanisms, which can move freely along the beam to cover a huge working area. The main components of the overhead crane include the beam and the lifting mechanism. The beam is the main part of the load-bearing and support lifting mechanism, usually made of steel structure, with sufficient strength and rigidity to bear the weight of heavy objects; the lifting mechanism is the most critical component of the overhead crane, usually composed of a winch, hook and wire rope. The winch drives the extension and retraction of the wire rope through an electric or hydraulic system to achieve the function of lifting and lowering heavy objects. A bridge crane is a type of overhead crane. It is horizontally mounted above workshops, warehouses and material yards for material lifting. Both ends are located on tall concrete columns or metal brackets. It is shaped like a bridge, so it is commonly known as a "overhead crane" or "travel crane".

[0003] The existing Chinese patent application document with publication number CN118619120A discloses an anti-collision control method and device for an overhead crane, which belongs to the field of semiconductor equipment technology. The anti-collision control method for an overhead crane in the embodiment of the application document obtains and analyzes point cloud data during the operation of the overhead crane, and then determines the track of the obstacle overhead crane and the track distance between the obstacle overhead crane and the target overhead crane from a complex overhead crane track network, so that the target overhead crane can accurately, quickly and flexibly identify the obstacle overhead crane in front, and then quickly take appropriate control measures to operate, avoid overhead crane collision, and ensure the safe operation of the overhead crane.

[0004] This application document ensures the safe operation of the crane by determining the crane coverage area of ​​the crane track area when there is an obstacle crane, thereby avoiding the occurrence of crane collisions. At present, the crane faces the risk of collision due to inertial swing of the load during braking, and the wire rope brake structure wears out after long-term use, which causes the crane to collide. Summary of the invention

[0005] In order to solve the problem that the overhead crane may collide due to the inertial swing of the load during braking, and the wire rope brake structure may wear out after long-term use, thus causing the overhead crane to collide, the present invention provides solutions in the following aspects.

[0006] In a first aspect, an automatic control method for anti-collision of an overhead crane comprises: collecting operation data of each overhead crane in historical operation, wherein the operation data comprises: speed, weight of a load and length of a lower swing, and calculating a swing distance of a load under the overhead crane; judging whether the operation state of the overhead crane braking system is abnormal according to the swing distance, and stopping the operation of the overhead crane in response to an abnormal operation state of the overhead crane braking system, and vice versa, training a preset neural network model according to the operation data during braking and the maximum swing distance to obtain a swing distance model; inputting the operation data of the overhead crane collected in real time into the swing distance model, calculating the distance deviation during real-time braking, and constructing an update loss function to obtain a predicted maximum swing distance, adding the predicted maximum swing distances of two adjacent overhead cranes as a reserved distance, and controlling the operation of the overhead crane; the update loss function Satisfies the following relationship: ; In the formula, Indicates Distance deviation of the first brake, Indicates the actual Maximum swing distance of the first braking, The predicted Maximum swing distance of the first braking, Indicates the actual Maximum swing distance of the first braking, The predicted Maximum swing distance of the first braking, Indicates The vector of the secondary brake, Indicates the actual The vector of the secondary brake, Represents the cosine function.

[0007] The effect is as follows: by real-time monitoring of the operating data of the overhead crane and calculating the swing distance, the method can effectively predict and evaluate the swing of the overhead crane during the braking process. When an abnormal operating state of the braking system is detected, the system will immediately stop the operation of the overhead crane, thereby avoiding possible collision accidents and significantly improving operation safety. Using a neural network model, training is performed based on historical braking operating data and maximum swing distances. The resulting swing distance model can more accurately predict the swing distance during real-time braking. By precisely controlling the braking process, equipment damage caused by emergency braking or excessive wear can be reduced, thereby reducing maintenance costs and extending the service life of the overhead crane.

[0008] Preferably, the swing distance includes: Take any moment as the marking moment, compare the ratio of the maximum tension on the wire rope at the marking moment to the load, use the inverse cosine function to obtain the angle between the wire rope and the vertical direction, determine the swing amplitude of the load, use the sine function for the swing amplitude, and calculate the product with the length of the wire rope at the lower part of the overhead crane at the marking moment, and obtain the swing distance of the overhead crane load at the marking moment.

[0009] The effect is that according to the swing distance calculated in real time, the overhead crane control system can dynamically adjust the operating state of the overhead crane, such as speed and braking timing, to reduce the impact of the swing on the operation of the overhead crane.

[0010] Preferably, judging whether the operating state of the overhead crane braking system is abnormal according to the swing distance includes: When the overhead crane starts braking, the swing distance of the overhead crane is obtained to obtain a swing distance sequence, and the minimum value in the swing distance sequence is taken as a cutting point. From the initial moment of braking to the first cutting point, the first swing cycle is obtained, and the subsequent swing cycles are composed of a swing cycle between two cutting points, so as to obtain a plurality of continuous swing cycles; The braking time of the overhead crane is obtained. The braking time is the time period from when the overhead crane brakes to when it stops completely without displacement. In response to the braking time being greater than or equal to the time period from the start time to the time corresponding to the maximum distance value in the first swing cycle, the safety response mechanism is triggered to stop the operation of the overhead crane.

[0011] The effect is: by comparing the braking time of the overhead crane with the key time period in the swing cycle, the safety risk in the braking process can be evaluated. By analyzing the swing cycle, the braking strategy of the overhead crane can be optimized to ensure that braking is completed before the load swings to a safe position, thereby improving braking efficiency.

[0012] Preferably, judging whether the operating state of the overhead crane braking system is abnormal according to the swing distance further includes: The operating data of the historical operating crane speed, the weight of the load and the maximum swing distance are obtained, and nonlinear fitting is performed to obtain the fitting result. The real-time crane load weight and crane speed are input into the fitted model to predict the maximum swing distance, and the deviation between the actual swing distance and the predicted swing distance is calculated. In response to the deviation being greater than the set deviation threshold, the safety response mechanism is triggered to stop the operation of the crane.

[0013] The effect is: by inputting the real-time collected overhead crane operation data into the fitted model, the maximum swing distance can be predicted in real time, thereby evaluating the swing risk during the operation of the overhead crane. By calculating the deviation between the actual swing distance and the predicted swing distance, it is possible to monitor whether the performance of the overhead crane braking system meets expectations. When the deviation exceeds the set threshold, the system will automatically trigger the safety response mechanism and stop the overhead crane operation to prevent possible collision accidents and ensure the safety of personnel and equipment.

[0014] Preferably, the swing distance model is: a bp neural network model, the input is: operating data and maximum swing distance, wherein the operating data during historical braking and the maximum swing distance constitute a vector as training data, and the output is: the output is the maximum swing distance, and the mean square error loss function is used. When the loss function is greater than a threshold or reaches a preset number of training times, the training is completed and the swing distance model is obtained.

[0015] Preferably, the distance deviation includes: Take any braking as the target braking, calculate the ratio of the actual swing distance of the target braking to the predicted swing distance, and take the absolute value of the complement of the ratio as the distance deviation of the target braking.

[0016] The effect is that by taking distance deviation into account, the system can handle different operating conditions and emergencies more robustly, improving overall safety and reliability. Long-term monitoring of distance deviation can help identify possible wear or failure of the overhead crane braking system, thereby optimizing maintenance and overhaul strategies.

[0017] Preferably, the distance deviation further includes: Take any braking as target braking, calculate the difference between the predicted swing distance of target braking and the actual swing distance, and take the ratio between the difference and the predicted swing distance value as the distance deviation of target braking.

[0018] In a second aspect, an automatic anti-collision control system for an overhead crane includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the automatic anti-collision control method for the overhead crane is implemented.

[0019] The present invention has the following effects: 1. The present invention can effectively identify the risk of possible collision by real-time monitoring and predicting the swing distance of the overhead crane load during braking, and trigger a safety response mechanism when an abnormal braking state is detected to stop the operation of the overhead crane, thereby reducing the possibility of collision accidents caused by the swing of the load during the operation of the overhead crane, thereby improving the safety of the working environment.

[0020] 2. The present invention continuously updates the update loss function of the swing distance model through the distance deviation, and can predict the maximum swing distance under different load weights and speeds. Taking into account the influence of the wear of the wire rope brake structure after long-term use of the overhead crane on the accuracy of the swing distance model, therefore, updating the loss function is beneficial to improving the accuracy of the model prediction, and is beneficial for the overhead crane operator to reasonably set the braking distance according to the prediction results, avoiding unnecessary braking reservation, thereby improving the operation efficiency of the overhead crane and reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a method flow chart of steps S1 to S3 in an automatic control method for avoiding collision of an overhead crane in an embodiment of the present invention.

[0022] Figure 2 It is a schematic diagram of the swing distance of the load carried by the lower part of the overhead crane in an automatic control method for anti-collision of an overhead crane according to an embodiment of the present invention.

[0023] Figure 3 The present invention is a structural block diagram of an automatic control system for preventing collisions of an overhead crane according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0026] Specific implementation scenario: When the overhead crane starts braking during travel, the load at the bottom will continue to swing forward due to the influence of inertia. Therefore, when the overhead crane is braking, if the two vehicles are closer, braking will occur at this time, and the load at the bottom may continue to swing along the direction of the overhead crane due to the influence of inertia. Therefore, it is necessary to first determine the swing amplitude. If the swing amplitude is too large, when the two overhead cranes are traveling towards each other and brake at the same time, the load will swing towards each other, and there is a risk of collision, resulting in damage to the load.

[0027] Reference Figure 1 A method for automatically controlling a crane to avoid collision includes steps S1 to S3, which are specifically as follows: S1: Collect the operation data of each overhead crane in historical operation, wherein the operation data includes: speed, weight of the load and swing length, and calculate the swing distance of the load under the overhead crane.

[0028] Reference Figure 2 In the figure, A represents the overhead crane, B represents the track, C represents the wire rope, D represents the swing distance, and E represents the load. When the overhead crane starts to brake, the load under the overhead crane drives the wire rope to swing left and right, and with the influence of gravity, that is, the swing distance is the largest at the first moment of braking, and the swing distance will become smaller and smaller until the load is perpendicular to the wire rope.

[0029] Swing distance, including: Take any moment as the marking moment, compare the ratio of the maximum tension on the wire rope at the marking moment to the load, use the inverse cosine function to obtain the angle between the wire rope and the vertical direction, determine the swing amplitude of the load, use the sine function for the swing amplitude, and calculate the product with the length of the wire rope at the lower part of the overhead crane at the marking moment, and obtain the swing distance of the overhead crane load at the marking moment.

[0030] Specifically, the swing distance satisfies the following relationship: ; In the formula, Indicates The swing distance of the overhead crane load at any moment, Indicates The length of the wire rope at the bottom of the overhead crane at all times. Indicates Real-time tension of the crane wire rope at all times. Indicates the gravity borne by the load. represents the sine function, represents the arccosine function, Represents the maximum value function.

[0031] That is to say, Indicated in The ratio of the maximum tension on the wire rope at a moment to the gravity of the load reflects the relative size of the tension on the wire rope. When the tension on the wire rope changes, this angle will also change, thereby affecting the swing of the load. The sine function is used to calculate the displacement of the swinging object relative to the equilibrium position during the swinging process. By multiplying the result of the sine function by the length of the wire rope, the horizontal distance that the load deviates from the vertical position due to the swing is obtained.

[0032] It should be noted that when the crane starts to brake, the load under the crane will swing left and right due to inertia, and a continuous swing distance sequence can be obtained. When the swing distance of the crane reaches a maximum value, the pulling force of the load on the crane may cause the crane to move slightly, causing the crane to move forward and there is a risk of collision with the load. When the swing distance of the crane reaches a minimum value, the load swings to the bottom of the crane, and there is no effect on the movement of the crane.

[0033] S2: judging whether the operating state of the overhead crane braking system is abnormal according to the swing distance, if the operating state of the overhead crane braking system is abnormal, the overhead crane stops running; otherwise, a preset neural network model is trained according to the operating data during braking and the maximum swing distance to obtain a swing distance model.

[0034] It should be noted that the purpose of judging whether the operating status of the overhead crane's braking system is abnormal is: if the swing distance of the overhead crane during braking exceeds the safety threshold, this may indicate that the braking system is not working as expected, which may be due to brake failure, insufficient braking force or problems with other components of the braking system. If the time required for the overhead crane to stop completely exceeds the normal range, it may mean that there is a problem with the braking system, such as brake wear, hydraulic system leakage or brake circuit failure. If the maximum swing distance is predicted at this time, the predicted result will deviate greatly from the actual result, and the predicted data will be meaningless.

[0035] Determine whether the operating status of the overhead crane braking system is abnormal, including: When the overhead crane starts to brake, the swing distance of the overhead crane is obtained to obtain a swing distance sequence, and the minimum value in the swing distance sequence is taken as a cutting point. From the initial moment of braking to the first cutting point, the first swing cycle is obtained, and the subsequent swing cycles are composed of a swing cycle between two cutting points, and multiple continuous swing cycles are obtained; The braking time of the overhead crane is obtained. The braking time is the time period from when the overhead crane brakes to when it stops completely without displacement. In response to the braking time being greater than or equal to the time period from the start time to the time corresponding to the maximum distance value in the first swing cycle, the safety response mechanism is triggered to stop the operation of the overhead crane.

[0036] By analyzing the swing distance sequence and identifying the minimum value as the cutting point, the swing cycle of the overhead crane load can be accurately identified. Understanding the swing cycle helps predict the swing behavior of the overhead crane load during the braking process, thereby better controlling the braking process and reducing the risk of collision. Based on the comparison of the swing cycle and the braking time, the braking strategy can be optimized to ensure that the braking is completed before the load swings to a safe position. If the braking time overlaps with the critical time period of the swing cycle, the system will trigger the safety response mechanism and stop the overhead crane operation, thereby avoiding possible collision accidents and improving operation safety.

[0037] In addition, another embodiment further includes: The operating data of the historical operating crane speed, the weight of the load and the maximum swing distance are obtained, and nonlinear fitting is performed to obtain the fitting result. The real-time crane load weight and crane speed are input into the fitted model to predict the maximum swing distance, and the deviation between the actual swing distance and the predicted swing distance is calculated. In response to the deviation being greater than the set deviation threshold, the safety response mechanism is triggered to stop the operation of the crane.

[0038] Exemplarily, the deviation threshold is 0.3.

[0039] Nonlinear fitting can better capture the complex relationship between the overhead crane speed, load weight and maximum swing distance, and improve the accuracy of swing distance prediction. By inputting the load weight and speed of the overhead crane into the model in real time, the swing distance can be predicted in real time, and the dynamic monitoring of the braking state of the overhead crane can be realized. By calculating the deviation between the actual swing distance and the predicted swing distance, abnormal changes in the performance of the braking system can be discovered in time. When the deviation exceeds the set threshold, the safety response mechanism is automatically triggered, such as stopping the overhead crane operation, to prevent potential collision or equipment damage.

[0040] The swing distance model is: bp neural network model, the input is: operating data and maximum swing distance, among which the historical braking operating data and the maximum swing distance constitute a vector as training data, and the output is: the output is the maximum swing distance, and the mean square error loss function is used. When the loss function is greater than the threshold or reaches the preset number of training times, the training is completed and the swing distance model is obtained.

[0041] It should be noted that as the use time of the overhead crane increases, the output result of the swing distance model will deviate, that is, the wire rope brake structure of the overhead crane will wear out, and the output maximum swing distance will be smaller than the actual maximum swing distance, which may cause accidents of collision of the loads. Therefore, it is necessary to construct a supplementary loss for the swing distance model to participate in the update of the swing distance model.

[0042] S3: Input the real-time collected overhead crane operation data into the swing distance model, calculate the distance deviation during real-time braking, and construct an updated loss function to obtain the predicted maximum swing distance. Add the predicted maximum swing distances of the two adjacent overhead cranes as the reserved distance, and control the operation of the overhead crane.

[0043] Distance deviation, including: Take any braking as the target braking, calculate the ratio of the actual swing distance of the target braking to the predicted swing distance, and take the absolute value of the complement of the ratio as the distance deviation of the target braking.

[0044] Specifically, the distance deviation satisfies the following relationship: ; In the formula, Indicates Distance deviation of the first brake, Indicates the actual Maximum swing distance of the first braking, The predicted The maximum swing distance of the first braking.

[0045] That is to say, after the vehicle has been used for a long time, due to the wear of the wire brake structure, the predicted swing distance may be smaller than the actual swing distance. The distance deviation can capture the impact of wear on the prediction accuracy. If the distance deviation is large, it indicates that the prediction error in this braking is large and needs to be focused on in the model. Accurate swing distance prediction is crucial to ensuring the safety of the load. The distance deviation helps the model identify and adjust prediction errors that may lead to safety risks.

[0046] In addition, another embodiment further includes: Take any braking as target braking, calculate the difference between the predicted swing distance of target braking and the actual swing distance, and take the ratio between the difference and the predicted swing distance value as the distance deviation of target braking.

[0047] Specifically, the distance deviation satisfies the following relationship: ; In the formula, Indicates Distance deviation of the first brake, Indicates the actual Maximum swing distance of the first braking, The predicted The maximum swing distance of the first braking.

[0048] Specifically, the updated loss function satisfies the following relationship: ; In the formula, represents the updated loss function, Indicates Distance deviation of the first brake, Indicates the actual Maximum swing distance of the first braking, The predicted Maximum swing distance of the first braking, Indicates the actual Maximum swing distance of the first braking, The predicted Maximum swing distance of the first braking, Indicates The vector of the secondary brake, Indicates the actual The vector of the secondary brake, Represents the cosine function.

[0049] That is to say, Indicates the history The difference between the swing distance predicted by the model and the actual swing distance in the first braking, Indicates The difference between the swing distance predicted by the model and the actual swing distance in the first braking, Indicates the history The second braking vector and the The similarity between the braking vectors is higher, indicating that the speed, load weight and wire rope length of the overhead crane in the two braking events are more consistent in numerical proportion, and the swing distance and braking time may also be very similar. When updating the loss function, braking events with high similarity will be given a greater weight, so that the model can make more accurate predictions when encountering similar real-time braking events.

[0050] Finally, when the two overhead cranes move towards each other under manual or non-manual operation, the corresponding maximum swing distance is obtained by inputting the real-time speed and the corresponding load weight. The sum of the two maximum swing distances is the braking reserved distance. This braking reserved distance is added to the existing braking distance to ensure the safety of the goods.

[0051] The present invention also provides an automatic control system for preventing a crane from collision. Figure 3 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an automatic control method for avoiding collision of an overhead crane according to the first aspect of the present invention is implemented.

[0052] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0053] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0054] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0055] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. An automatic control method for preventing a crane from collision, characterized in that: include: Collecting the operation data of each overhead crane in historical operation, wherein the operation data includes: speed, weight of the load and swing length, and calculating the swing distance of the load under the overhead crane; Judging whether the operation state of the crane braking system is abnormal according to the swing distance, the crane stops running in response to the abnormal operation state of the crane braking system, and vice versa, a preset neural network model is trained according to the operation data during braking and the maximum swing distance to obtain a swing distance model; Input the real-time collected overhead crane operation data into the swing distance model, calculate the distance deviation during real-time braking, and construct an update loss function to obtain the predicted maximum swing distance. Add the predicted maximum swing distances of the two adjacent overhead cranes as the reserved distance, and control the operation of the overhead crane. The updated loss function Satisfies the following relationship: ; In the formula, Indicates Distance deviation of the first brake, Indicates the actual Maximum swing distance of the first braking, The predicted Maximum swing distance of the first braking, Indicates the actual Maximum swing distance of the first braking, The predicted Maximum swing distance of the first braking, Indicates The vector of the secondary brake, Indicates the actual The vector of the secondary brake, Represents the cosine function.

2. The automatic control method for avoiding collision of an overhead crane according to claim 1, characterized in that: The swing distance includes: Take any moment as the marking moment, compare the ratio of the maximum tension on the wire rope at the marking moment to the load, use the inverse cosine function to obtain the angle between the wire rope and the vertical direction, determine the swing amplitude of the load, use the sine function for the swing amplitude, and calculate the product with the length of the wire rope at the lower part of the overhead crane at the marking moment, and obtain the swing distance of the overhead crane load at the marking moment.

3. The automatic control method for avoiding collision of an overhead crane according to claim 1, characterized in that: The step of judging whether the operating state of the overhead crane braking system is abnormal according to the swing distance includes: When the overhead crane starts braking, the swing distance of the overhead crane is obtained to obtain a swing distance sequence, and the minimum value in the swing distance sequence is taken as a cutting point. From the initial moment of braking to the first cutting point, the first swing cycle is obtained, and the subsequent swing cycles are composed of a swing cycle between two cutting points, so as to obtain a plurality of continuous swing cycles; The braking time of the overhead crane is obtained. The braking time is the time period from when the overhead crane brakes to when it stops completely without displacement. In response to the braking time being greater than or equal to the time period from the start time to the time corresponding to the maximum distance value in the first swing cycle, the safety response mechanism is triggered to stop the operation of the overhead crane.

4. The automatic control method for avoiding collision of an overhead crane according to claim 1, characterized in that: The step of judging whether the operating state of the overhead crane braking system is abnormal according to the swing distance also includes: The operating data of the historical operating crane speed, the weight of the load and the maximum swing distance are obtained, and nonlinear fitting is performed to obtain the fitting result. The real-time crane load weight and crane speed are input into the fitted model to predict the maximum swing distance, and the deviation between the actual swing distance and the predicted swing distance is calculated. In response to the deviation being greater than the set deviation threshold, the safety response mechanism is triggered to stop the operation of the crane.

5. The automatic control method for avoiding collision of an overhead crane according to claim 1, characterized in that: The swing distance model is: bp neural network model, the input is: operating data and maximum swing distance, wherein the historical braking operating data and the maximum swing distance constitute a vector as training data, the output is: the output is the maximum swing distance, and the mean square error loss function is used. When the loss function is greater than the threshold or reaches the preset number of training times, the training is completed to obtain the swing distance model.

6. The automatic control method for avoiding collision of an overhead crane according to claim 1, characterized in that: The distance deviation includes: Take any braking as the target braking, calculate the ratio of the actual swing distance of the target braking to the predicted swing distance, and take the absolute value of the complement of the ratio as the distance deviation of the target braking.

7. The automatic control method for avoiding collision of an overhead crane according to claim 1, characterized in that: The distance deviation also includes: Take any braking as target braking, calculate the difference between the predicted swing distance of target braking and the actual swing distance, and take the ratio between the difference and the predicted swing distance value as the distance deviation of target braking.

8. An automatic control system for preventing collision of an overhead crane, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the automatic control method for avoiding collision of an overhead crane according to any one of claims 1 to 7 is implemented.

Images