A method and system for optimizing control parameters of a boom crane, and a medium

Abstract

The application provides a control parameter optimization method and system for a boom crane, and a medium, comprising: obtaining basic information of a material to be lifted, including lifting start position information and lifting end position information; obtaining a set of images of the material to be lifted; obtaining a material quality evaluation result; obtaining a set of images of a lifting area for lifting path planning, and obtaining lifting path information; optimizing control parameters of the boom crane according to the material quality evaluation result and the lifting path information, obtaining control parameter optimization results, and sending the control parameter optimization results to a crane driver through a display interface. The application solves the technical problem of poor applicability in the prior art, i.e., an intelligent model needs a large amount of historical record data for training, but actual record data is less and difficult to train, and the stability is poor in an offline state.

Description

Technical Field

[0001] This invention belongs to the technical field of intelligent control, and in particular relates to a method, system and medium for optimizing control parameters of a boom crane. Background Technology

[0002] Cranes are multi-action machines used to move heavy objects within a certain vertical and horizontal range. Accurate and reasonable control of cranes during the lifting process is a prerequisite for ensuring stable handling. Traditionally, the operation parameters are selected based on the experience and judgment of professional operators. However, as the requirements for the precision of control gradually increase, traditional decision-making methods are difficult to adapt to the development trend.

[0003] With the rapid development of artificial intelligence, experts have proposed using intelligent models to make decisions on crane control parameters in different scenarios. Neural network models are the most widely used, but cranes have limited recorded data, while training neural network models requires a large amount of data, which is the first challenge. Secondly, complex handling environment factors can lead to low decision-making efficiency and insufficient response speed of offline neural network models, which is the second challenge. Therefore, there is an urgent need to propose a stable and efficient solution for optimizing crane control parameters offline.

[0004] Existing intelligent models require a large amount of historical data for training, but actual recorded data is scarce and difficult to train, and their stability is poor in offline conditions, resulting in poor applicability. Summary of the Invention

[0005] This invention provides a method, system, and medium for optimizing control parameters of a boom crane, which solves the technical problem that existing intelligent models have poor applicability due to the need for a large amount of historical data for training, but the actual recorded data is small and difficult to train, and poor stability in offline state.

[0006] In a first aspect, this application provides the following technical solution through a first embodiment:

[0007] A method for optimizing control parameters of a boom crane, characterized by comprising:

[0008] Obtain basic information about the material to be lifted, wherein the basic information about the material to be lifted includes the lifting start point position information and the lifting end point position information;

[0009] A set of images of the material to be lifted, containing the lifting start point position information;

[0010] The quality assessment of the material to be lifted is performed based on the image set of the material to be lifted, and the material quality assessment result is obtained.

[0011] Based on the lifting start point position information and the lifting end point position information, the image acquisition device is invoked to acquire regional images and obtain a set of lifting area images.

[0012] Lifting path planning is performed based on the set of images of the lifting area to obtain lifting path information;

[0013] The control parameters of the boom crane are optimized based on the material quality assessment results and the lifting path information to obtain the control parameter optimization results.

[0014] In some embodiments, the basic information of the material to be lifted further includes material density information, and the step of performing a quality assessment of the material to be lifted based on the image information of the material to be lifted and obtaining the material quality assessment result includes:

[0015] Based on the image information of the material to be lifted, obtain the material volume information;

[0016] Determine the material density information;

[0017] The material mass information is obtained based on the material volume information and the material density information.

[0018] In some embodiments, the step of planning the lifting path based on the lifting area image set and obtaining lifting path information includes:

[0019] The set of images of the lifting area is input into the simulation environment construction module to generate simulation results of the lifting area environment.

[0020] Obtain the boom crane position information, lifting height threshold range, boom position threshold range, and rotation angle threshold range;

[0021] Based on the boom crane position information, the lifting height threshold range, the boom position threshold range, and the rotation angle threshold range, the effective lifting area is separated from the lifting area environment simulation results to generate effective lifting area environment simulation results;

[0022] The lifting start point location information and the lifting end point location information are input into the environmental simulation results of the effective lifting area to perform lifting path planning and obtain the lifting path information.

[0023] In some embodiments, the step of inputting the lifting start point location information and the lifting end point location information into the environmental simulation results of the effective lifting area to perform lifting path planning and obtain the lifting path information includes:

[0024] Based on the lifting start point location information and the lifting end point location information, lifting sensitive element information is obtained, wherein the lifting sensitive element information includes a set of vacant elements;

[0025] The set of vacant elements is continuously spliced ​​from the lifting start point location information to the lifting end point location information to obtain multiple continuous vacant channels;

[0026] The multiple consecutive vacant passages are sorted from closest to furthest in terms of travel distance, and then filtered according to the closest consecutive vacant passages to obtain the lifting path information.

[0027] In some embodiments, optimizing the control parameters of the boom crane based on the material quality assessment results and the lifting path information, and obtaining the control parameter optimization results, includes:

[0028] Based on the lifting path information, obtain the sequence of obstacles along the lifting path;

[0029] Based on the obstacle sequence of the lifting path, obtain the boom position constraint interval sequence and the rotation angle constraint interval sequence;

[0030] Based on the boom position constraint range, the lifting mass threshold range is obtained;

[0031] Determine whether the material quality assessment result meets the lifting weight threshold range;

[0032] If the material quality assessment result meets the lifting mass threshold range, then the control parameters of the boom crane are optimized according to the boom position constraint range sequence and the rotation angle constraint range sequence to obtain the control parameter optimization result.

[0033] In some embodiments, determining whether the material quality assessment result meets the lifting weight threshold range further includes:

[0034] If the material quality assessment result does not meet the lifting weight threshold range, obtain a material batching instruction;

[0035] The materials to be lifted are divided into batches according to the lifting mass threshold range, and the batching results of the materials to be lifted are obtained.

[0036] Based on the batching results of the materials to be lifted, the control parameters of the boom crane are optimized using the boom position constraint interval sequence and the rotation angle constraint interval sequence to obtain the control parameter optimization results.

[0037] In some embodiments, optimizing the control parameters of the boom crane based on the boom position constraint interval sequence and the rotation angle constraint interval sequence, and obtaining the control parameter optimization result, includes:

[0038] The control parameters of the boom crane are obtained, wherein the control parameters include lifting height, boom position, rotation angle, lifting speed and boom movement speed;

[0039] A parameter optimization space is constructed based on the lifting height, the boom position, the rotation angle, the lifting speed, and the boom movement speed, wherein the dimension of the parameter optimization space is the same as the dimension of the control parameters;

[0040] Traverse the boom position constraint interval sequence and the rotation angle constraint interval sequence, input the parameter optimization space to optimize the lifting height, boom position, rotation angle, lifting speed and boom movement speed, and obtain the control parameter optimization results.

[0041] In some embodiments, traversing the boom position constraint interval sequence and the rotation angle constraint interval sequence, inputting the parameter optimization space to optimize the lifting height, the boom position, the rotation angle, the lifting speed, and the boom travel speed, and obtaining the control parameter optimization results includes:

[0042] When any set of boom position constraint intervals and rotation angle constraint intervals are input into the parameter optimization space, a filter particle swarm is obtained, wherein any particle in the filter particle swarm represents the historical selection record of the control parameter under the boom position constraint interval and rotation angle constraint interval;

[0043] Formula for obtaining particle acceptance:

[0044]

[0045] Wherein, p k+1 The acceptability of the (k+1)th particle is represented by f(k+1), and the selection frequency parameter of the (k+1)th particle in the particle swarm is represented by f(k+1). The sum of selection frequency parameters of all particles in the selected particle swarm is represented by K, where K is the total number of particles in the selected particle swarm, h represents the lifting height, s represents the boom position, d represents the rotation angle, v1 represents the lifting speed, v2 represents the boom moving speed, and α, β, γ, δ and ε represent the weight coefficients of the corresponding control parameters.

[0046] The particle acceptance formula is used to iterate through the selected particle swarm a preset number of times to obtain the particle with the highest acceptance, which is then added to the control parameter optimization result.

[0047] Secondly, based on the same inventive concept, this application provides the following technical solution through an embodiment:

[0048] A control parameter optimization system for a boom crane, the system comprising:

[0049] The information acquisition module is used to acquire basic information of the material to be lifted, wherein the basic information of the material to be lifted includes the lifting start point position information and the lifting end point position information;

[0050] The material image acquisition module is used to call the image acquisition device to acquire images of the material to be lifted based on the lifting starting point position information, and to obtain a set of images of the material to be lifted.

[0051] The quality assessment module is used to assess the quality of the material to be lifted based on the image information of the material to be lifted, and to obtain the material quality assessment result.

[0052] The lifting area image acquisition module is used to call the image acquisition device to acquire area images based on the lifting start point position information and the lifting end point position information, and obtain a set of lifting area images.

[0053] The lifting path planning module is used to plan the lifting path based on the set of images of the lifting area and obtain lifting path information.

[0054] The control parameter optimization module is used to optimize the control parameters of the boom crane based on the material quality assessment results and the lifting path information, and obtain the control parameter optimization results.

[0055] The information sending module is used to send the optimization results of the control parameters to the crane operator.

[0056] Thirdly, based on the same inventive concept, this application provides the following technical solution through an embodiment:

[0057] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the methods described above.

[0058] The one or more technical solutions provided in the embodiments of the present invention achieve at least the following technical effects or advantages:

[0059] This invention extracts the starting and ending point locations of the lifting point from the basic information of the material to be lifted; performs image acquisition and quality assessment of the material based on the starting point information; obtains a set of images of the lifting area based on the starting and ending point locations; plans the lifting path based on the image set, obtaining lifting path information; optimizes the control parameters of the boom crane based on the lifting path information and the material quality assessment results, obtaining optimized control parameter results; and further sends these results to a display interface for the crane operator to view and select from. By determining the lifting area, planning the path, and then optimizing the control parameters based on the material quality assessment and path planning results, the planned path is highly applicable to actual scenarios. Furthermore, in complex lifting environments, the control parameter optimization process exhibits greater stability compared to intelligent models, thus achieving a more versatile technical effect. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 This application provides a schematic flowchart of a method for optimizing control parameters of a boom crane.

[0062] Figure 2 This application provides a schematic flowchart of a material quality assessment method for optimizing control parameters of a boom crane, as shown in the embodiments of this application.

[0063] Figure 3 This application provides a schematic diagram of a control parameter optimization system for a boom crane. Detailed Implementation

[0064] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0065] In this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0066] The precision of crane control determines the lifting effect. Current crane control technology mainly relies on experience to make decisions on lifting parameters. This decision-making method is not very stable when facing complex lifting scenarios. Although some experts have proposed using intelligent models to match lifting parameters, its applicability is poor. Therefore, there is an urgent need to find a lifting parameter decision-making scheme with stronger stability.

[0067] To address the aforementioned technical problems, the overall approach of the technical solution provided in this application is as follows:

[0068] This application provides a method, system, and medium for optimizing control parameters of a boom crane. The method involves extracting the starting and ending point locations of the lifting material from its basic information; acquiring images and assessing the quality of the material based on the starting point information; obtaining a set of images of the lifting area based on the starting and ending point locations; planning the lifting path based on the image set; optimizing the control parameters of the boom crane based on the lifting path information and the material quality assessment results; and further sending the optimized results to a display interface for the crane operator to view and select. By determining the lifting area, planning the path, and then optimizing the control parameters based on the material quality assessment and path planning results, the method achieves strong applicability to actual scenarios. Furthermore, in complex lifting environments, the control parameter optimization process exhibits greater stability compared to intelligent models, thus achieving a more versatile technical effect.

[0069] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0070] Example 1

[0071] Firstly, such as Figure 1 As shown in the figure, this application provides a method for optimizing control parameters of a boom crane, including:

[0072] Specifically, boom cranes are one of the most widely used types of cranes. Their characteristic is that the rated lifting capacity can change with the position of the boom. They are commonly used in building construction and bridge construction. They are divided into fixed and mobile types. However, if the principle of the control parameter optimization method for other types of cranes is the same as that in this application, then it is also within the protection scope of this application.

[0073] S100: Obtain basic information of the material to be lifted, including the starting point position information and the ending point position information.

[0074] Specifically, the basic information of the material to be lifted refers to the dataset representing the basic information of the material being lifted, uploaded by the operator to the control parameter optimization system of the boom crane through a display device. This dataset includes, but is not limited to, the starting point location information, the ending point location information, the material type information, and the information of the personnel requesting the material. The preferred method for determining the starting point location information and the ending point location information is to construct a spatial coordinate system with the vertical plane of the crane boom at the fixed position of the boom crane as the first coordinate plane and the horizontal plane of the crane boom as the second coordinate plane. This spatial coordinate system radiates outward from the boom crane, enabling the positioning of surrounding people and objects, thereby obtaining the starting point location information and the ending point location information of the material to be lifted.

[0075] S200: Obtain a set of images of the material to be lifted, which is obtained by calling an image acquisition device to acquire images of the material to be lifted, which is based on the lifting start point position information.

[0076] Specifically, the image acquisition device refers to the equipment used to acquire images of the material to be lifted. Preferably, a high-definition industrial camera with movable and adjustable angle is used. The image set of the material to be lifted refers to the multi-dimensional image acquisition of the material to be lifted by the image acquisition device, which acquires images of the material at the starting point position information of the lifting. For example, the multi-dimensional image acquisition method is not limited: from top to bottom, from left to right, around the whole circle, multiple images of the material to be lifted are acquired and stored as the image set of the material to be lifted and set to a pending response state, waiting to be called in the next step.

[0077] S300: Based on the image information of the material to be lifted, perform a quality assessment of the material to be lifted and obtain the material quality assessment results;

[0078] Furthermore, such as Figure 2 As shown, the basic information of the material to be lifted also includes material density information. Based on the image information of the material to be lifted, a quality assessment is performed on the material to be lifted to obtain the material quality assessment result. Step S300 includes the following steps:

[0079] S310: Extract features from the image information of the material to be lifted, obtain the material shape feature information, and calculate the material volume information based on the material shape feature information;

[0080] S320: Determine material density information;

[0081] S330: Generate material quality assessment results based on material volume and density information.

[0082] Specifically, the material quality assessment result refers to the data representing the quality of the material to be lifted, determined based on the image information of the material to be lifted. Changes in the position of the crane boom will limit the rated lifting capacity. Therefore, collecting the material quality assessment result is one of the reference data for optimizing control parameters, so as to avoid obtaining control parameter optimization results where the rated lifting capacity is less than the material quality assessment result in the subsequent steps.

[0083] The preferred process for determining the material quality assessment results is as follows: Material shape characteristic information refers to the features that characterize the shape of the material to be lifted, including geometric features. The preferred method is to break down the material to be lifted based on its image information, obtaining multiple breakdown results. Each breakdown can be considered a regularly shaped graphic. Furthermore, the geometric dimensions of each breakdown result can be determined based on a spatial coordinate system, allowing for the calculation of the volume information. The volume information of multiple breakdown results is then summed to obtain the volume information of the material to be lifted. Next, material type information is extracted from the basic information of the material to be lifted, and material density information matching the material type is matched. The preferred method for obtaining material density information is through a material-density data table search. This material-density data table is uploaded to the system by staff at the start of the lifting project for quick retrieval.

[0084] After unifying the units of density and volume, the material quality assessment results can be determined and set to a pending response state, ready for subsequent calls.

[0085] S400: Based on the lifting start point position information and lifting end point position information, call the image acquisition device to perform regional image acquisition and obtain a set of images of the lifting area;

[0086] Specifically, the lifting area image set refers to the set of images within the lifting space determined based on the lifting start and end point location information and the crane's lifting range. An example of an unrestricted determination process is as follows: Determine the maximum lifting space based on the crane's lifting range. Then, extend vertical planes from the lifting start and end point location information, dividing the maximum lifting space. The space between these two vertical planes constitutes the lifting space. If the lifting start point is not within the maximum lifting space, it needs to be adjusted to fall within it. The lifting area image set is obtained by acquiring multi-dimensional images of the lifting space using an image acquisition device and is set to a pending response state, awaiting subsequent calls.

[0087] S500: Plans the lifting path based on the set of images of the lifting area and obtains the lifting path information;

[0088] Furthermore, based on the image set of the lifting area, lifting path planning is performed to obtain lifting path information. Step S500 includes the following steps:

[0089] S510: Input the set of images of the lifting area into the simulation environment construction module to generate the simulation results of the lifting area environment;

[0090] S520: Obtain the position information of the boom crane, the lifting height threshold range, the boom position threshold range, and the rotation angle threshold range;

[0091] S530: Based on the boom crane position information, lifting height threshold range, boom position threshold range and rotation angle threshold range, the effective lifting area is separated from the lifting area environment simulation results, and the effective lifting area environment simulation results are generated.

[0092] S540: Input the starting point and ending point location information of the crane into the environmental simulation results of the effective crane area to plan the crane path and obtain the crane path information.

[0093] Specifically, lifting path information refers to data representing the lifting route of the material to be lifted. The process of path planning based on the image set of the lifting area is as follows:

[0094] The simulation environment construction module refers to the functional module used to realize the construction of environment simulation. The simulation environment here only needs to determine the location information and spatial volume information of buildings, people or other objects, without detailed characterization. Therefore, the construction efficiency is relatively high. The 3D environment simulation technology has been developed quite maturely, so we will not go into details here. The simulation result of the lifting area environment refers to the simulation result that represents the location information and spatial volume information of each element obtained by inputting the lifting area image set into the simulation environment construction module.

[0095] The boom crane position information refers to the location of the boom crane body; the lifting height threshold range refers to the material lifting range; the boom position threshold range refers to the sliding range of the movable boom on the crane arm; and the rotation angle threshold range refers to the horizontal rotation angle range of the crane arm. By using the boom crane position information, lifting height threshold range, boom position threshold range, and rotation angle threshold range, the specific lifting space range of the boom crane can be determined.

[0096] The effective lifting area environment simulation result refers to the lifting area simulation result selected from the lifting area environment simulation results based on the specific lifting space range of the boom crane. By inputting the lifting start point location information and the lifting end point location information into the effective lifting area environment simulation result, the lifting path information is obtained through lifting path planning. This can prevent the lifting path from exceeding the specific lifting space range of the boom crane and ensure the rationality of the lifting path.

[0097] Furthermore, the lifting start point location information and lifting end point location information are input into the environmental simulation results of the effective lifting area to perform lifting path planning and obtain lifting path information. Step S540 includes the following steps:

[0098] S541: Based on the lifting start point location information and the lifting end point location information, obtain the lifting sensitive element information, wherein the lifting sensitive element information includes the set of vacant elements;

[0099] S542: Continuously splice the set of vacant elements from the starting point location information to the ending point location information of the crane to obtain multiple continuous vacant channels;

[0100] S543: Sort multiple consecutive vacant passages according to the distance from nearest to farthest, and filter the multiple consecutive vacant passages according to the closest consecutive vacant passage to obtain the lifting path information.

[0101] Specifically, the lifting sensitive element information refers to the set of elements that affect the material to be lifted, extracted from the environmental simulation results of the effective lifting area. This includes, but is not limited to: obstacle element set: physical objects or gaps that affect the movement of the material to be lifted; vacant element set: gaps that do not affect the movement of the material to be lifted. Multiple consecutive vacant channels refer to the vacant channels obtained by continuously splicing the vacant element sets from the lifting start point position information to the lifting end point position information. Any consecutive vacant channel refers to the splicing result of multiple vacant channels from the lifting start point position information to the lifting end point position information that can allow the material to be lifted to move. The sorting result refers to the result of sorting multiple consecutive vacant channels from smallest to largest according to the travel distance; the lifting path information refers to the highest-ranking consecutive vacant channel selected from the sorting result, designated as the lifting path information. By selecting the shortest path from all feasible paths, lifting efficiency is improved.

[0102] S600: Optimize the control parameters of the boom crane based on the material quality assessment results and lifting path information, and obtain the control parameter optimization results;

[0103] Furthermore, based on the material quality assessment results and lifting path information, the control parameters of the boom crane are optimized to obtain the control parameter optimization results. Step S600 includes the following steps:

[0104] S610: Obtain the sequence of obstacles along the lifting path based on the lifting path information;

[0105] S620: Based on the obstacle sequence of the lifting path, obtain the boom position constraint interval sequence and the rotation angle constraint interval sequence;

[0106] S630: Obtain the lifting mass threshold range based on the boom position constraint range;

[0107] S640: Determine whether the material quality assessment results meet the lifting capacity threshold range;

[0108] Furthermore, to determine whether the material quality assessment result meets the lifting capacity threshold range, step S640 also includes the following steps:

[0109] S641: If the material quality assessment result does not meet the lifting quality threshold range, obtain the material batching instruction;

[0110] S642: Divide the materials to be lifted into batches according to the lifting mass threshold range, and obtain the batching results of the materials to be lifted.

[0111] S643: Based on the batching results of the materials to be lifted, the control parameters of the boom crane are optimized using the boom position constraint interval sequence and the rotation angle constraint interval sequence, and the control parameter optimization results are obtained.

[0112] S650: If satisfied, optimize the control parameters of the boom crane according to the boom position constraint interval sequence and the rotation angle constraint interval sequence, and obtain the control parameter optimization results.

[0113] Specifically, the control parameter optimization result refers to the parameter optimization result obtained under the constraint of material quality assessment results and lifting path information. A preferred embodiment of the optimization process is as follows:

[0114] The lifting path obstacle sequence refers to the result of arranging the physical obstacles surrounding the lifting path information according to the lifting path; the boom position constraint interval sequence refers to the data that restricts the boom position determined by the lifting path obstacle sequence. The boom position constraint interval is different for different positions and corresponds one-to-one with the lifting path obstacle sequence; the rotation angle constraint interval sequence refers to the dataset that restricts the crane boom rotation angle determined by the lifting path obstacle sequence. The crane boom rotation angle constraint interval is different for different positions and corresponds one-to-one with the lifting path obstacle sequence; further, based on the boom position constraint interval, the maximum lifting mass of the crane boom at different positions can be determined, denoted as the lifting mass threshold interval. The lower limit of the lifting mass threshold interval is the minimum value of the maximum lifting mass among all boom position constraint intervals, and the upper limit of the lifting mass threshold interval is the maximum value of the maximum lifting mass among all boom position constraint intervals.

[0115] Determine whether the material quality assessment result is less than or equal to the lower limit of the lifting quality threshold range. If it is less than or equal to, the condition is met. Based on the boom position constraint range sequence and the rotation angle constraint range sequence, optimize the control parameters of the boom crane to obtain the control parameter optimization result.

[0116] If the value is greater than the specified value, the condition is not met. The material batching instruction is sent to the staff to batch the materials to be lifted. The batching result of the materials to be lifted is obtained. Based on the batching result of the materials to be lifted, the control parameters of the boom crane are optimized by combining the boom position constraint interval sequence and the rotation angle constraint interval sequence to obtain multiple sets of optimized control parameters, and the lifting is carried out in batches.

[0117] By evaluating the lifting mass threshold range along the lifting path and then adjusting the material to be lifted, the precision of parameter optimization is improved.

[0118] The preferred optimization process for control parameters is as follows:

[0119] Furthermore, the control parameters of the boom crane are optimized based on the boom position constraint interval sequence and the rotation angle constraint interval sequence to obtain the control parameter optimization results. Step S643 includes the following steps:

[0120] S643-1: Obtain the control parameters of the boom crane, including lifting height, boom position, rotation angle, lifting speed and boom movement speed;

[0121] S643-2: Construct a parameter optimization space based on lifting height, boom position, rotation angle, lifting speed, and boom movement speed. The dimension of the parameter optimization space is the same as the dimension of the control parameters.

[0122] S643-3: Traverse the boom position constraint interval sequence and rotation angle constraint interval sequence, input parameter optimization space to optimize lifting height, boom position, rotation angle, lifting speed and boom movement speed, and obtain the control parameter optimization results.

[0123] Furthermore, the boom position constraint interval sequence and rotation angle constraint interval sequence are traversed, and the lifting height, boom position, rotation angle, lifting speed, and boom travel speed are optimized in the input parameter optimization space to obtain the control parameter optimization results. Step S643-3 includes the following steps:

[0124] S643-31: When the input parameters of any set of boom position constraint interval and rotation angle constraint interval are optimized in the space, a filter particle group is obtained, wherein any particle in the filter particle group represents the historical selection record of the control parameter under the boom position constraint interval and rotation angle constraint interval.

[0125] S643-32: Formula for obtaining particle acceptance:

[0126]

[0127] Where, p k+1 The acceptability of the (k+1)th particle is represented by f(k+1), and the selection frequency parameter of the (k+1)th particle in the particle swarm is represented by f(k+1). The sum of selection frequency parameters of all particles in the selected particle swarm is represented by K, where K is the total number of particles in the selected particle swarm, h represents the lifting height, s represents the boom position, d represents the rotation angle, v1 represents the lifting speed, v2 represents the boom moving speed, and α, β, γ, δ and ε represent the weight coefficients of the corresponding control parameters.

[0128] S643-33: Based on the particle acceptance formula, traverse and filter the particle swarm a preset number of times to obtain the particle with the highest acceptance, and add it to the control parameters to optimize the result.

[0129] The optimization results of control parameters can also be sent to the crane operator through the display interface.

[0130] Specifically, the control parameters of a boom crane refer to the set of parameters used for lifting control of the boom crane, including but not limited to: lifting height, boom position, rotation angle, lifting speed, and boom travel speed. The parameter optimization space refers to the virtual functional space used for optimizing the control parameters of the boom crane. The dimensions of the parameter optimization space are the same as the dimensions of the control parameters. For example, when the control parameters have five dimensions: lifting height, boom position, rotation angle, lifting speed, and boom travel speed, the parameter optimization space has five dimensions. Each dimension stores historical value records of the boom crane under different constraints based on big data collection. Under the constraints of the boom crane, a parameter is selected from each dimension in the parameter optimization space, and the combination of these parameters constitutes a particle in the parameter optimization space.

[0131] Particle swarm selection refers to selecting multiple particle clusters that conform to the boom position constraint interval and rotation angle constraint interval when optimizing the space using any set of boom position constraint intervals and rotation angle constraint intervals as input parameters; according to the particle acceptance formula:

[0132]

[0133] Here, α, β, γ, δ, and ε represent the weight coefficients of the corresponding control parameters, indicating the difference in importance between different control parameters. The default value for all of them is 1, and they are customizable by the staff. The particle swarm is traversed and screened a preset number of times. During each traversal, particles with lower acceptance are removed, ensuring that the particle being traversed has the highest acceptance among the traversed particles. The particle being traversed is recorded as the highest acceptance particle and added to the control parameter optimization results. The particles in the parameter optimization space are periodically updated via a network to ensure its timeliness. A relatively stable control parameter optimization can be achieved by combining the ideas of particle swarm optimization algorithm with a custom optimization method.

[0134] Finally, the optimized control parameters are sent to the crane operator via the display interface. If the crane operator confirms the parameters, the crane will be controlled according to the optimized control parameters.

[0135] In summary, the control parameter optimization method and system for a boom crane provided in this application have the following technical effects:

[0136] 1. This system extracts the starting and ending point locations of the lifting material from its basic information. Based on the starting point information, images of the material are acquired and their quality assessed. An image set of the lifting area is obtained from the starting and ending point locations. A lifting path is planned based on this image set, yielding the lifting path information. The control parameters of the boom crane are optimized based on the lifting path information and the material quality assessment results, resulting in optimized control parameters. These optimized parameters are then sent to a display interface for the crane operator to view and select from. By determining the lifting area, planning the path, and then optimizing the control parameters based on the material quality assessment and path planning results, the planned path is highly adaptable to different scenarios.

[0137] 2. Based on this, when facing complex lifting environments, the control parameter optimization process is more stable than the intelligent model, thus achieving a more applicable technical effect.

[0138] Example 2

[0139] Based on the same inventive concept as the control parameter optimization method for a boom crane in the foregoing embodiments, such as Figure 3 As shown in the figure, this application provides a control parameter optimization system for a boom crane, the system including:

[0140] The information acquisition module 11 is used to acquire basic information of the material to be lifted, including the lifting start point position information and the lifting end point position information.

[0141] Material image acquisition module 12 is used to call the image acquisition device to acquire images of the material to be lifted from the lifting starting point position information and obtain a set of images of the material to be lifted.

[0142] The quality assessment module 13 is used to assess the quality of the material to be lifted based on the image information of the material to be lifted, and to obtain the material quality assessment results.

[0143] The lifting area image acquisition module 14 is used to call the image acquisition device to acquire area images based on the lifting start point position information and the lifting end point position information, and obtain a set of lifting area images.

[0144] The lifting path planning module 15 is used to plan the lifting path based on the lifting area image set and obtain lifting path information.

[0145] The control parameter optimization module 16 is used to optimize the control parameters of the boom crane based on the material quality assessment results and lifting path information, and obtain the control parameter optimization results.

[0146] The system also includes an information sending module 17, which is used to send the control parameter optimization results to the crane operator through the display interface.

[0147] Furthermore, the quality assessment module 13 performs the following steps:

[0148] Feature extraction is performed on the image information of the material to be lifted to obtain the shape feature information of the material;

[0149] Based on the basic information of the material to be lifted, obtain the material type information;

[0150] Calculate the material volume information based on the material shape characteristics information, and match the material density information based on the material type information;

[0151] Based on the material volume and density information, a material quality assessment result is generated.

[0152] Furthermore, the execution steps of the lifting path planning module 15 include:

[0153] Input the set of images of the lifting area into the simulation environment construction module to generate the simulation results of the lifting area environment.

[0154] Based on the boom crane, obtain the boom crane position information, lifting height threshold range, boom position threshold range, and rotation angle threshold range;

[0155] Based on the boom crane position information, lifting height threshold range, boom position threshold range, and rotation angle threshold range, the effective lifting area is separated from the lifting area environment simulation results, and the effective lifting area environment simulation results are generated.

[0156] The starting and ending point locations of the crane are input into the environmental simulation results of the effective crane area to plan the crane path and obtain the crane path information.

[0157] Furthermore, the execution steps of the lifting path planning module 15 also include:

[0158] Based on the lifting start point location information and lifting end point location information, obtain lifting sensitive element information, which includes a set of vacant elements.

[0159] The set of vacant elements is continuously spliced ​​from the starting point location information to the ending point location information of the crane to obtain multiple continuous vacant channels;

[0160] Sort multiple consecutive empty channels from smallest to largest according to the passage distance, and obtain the sorting results;

[0161] Based on the sorting results, multiple consecutive empty channels are filtered to obtain lifting path information.

[0162] Furthermore, the control parameter optimization module 16 performs the following steps:

[0163] Based on the lifting path information, obtain the sequence of obstacles along the lifting path;

[0164] Based on the obstacle sequence of the lifting path, obtain the boom position constraint interval sequence and the rotation angle constraint interval sequence;

[0165] Based on the boom position constraint range, obtain the lifting mass threshold range;

[0166] Determine whether the material quality assessment results meet the lifting capacity threshold range;

[0167] If satisfied, the control parameters of the boom crane are optimized based on the boom position constraint interval sequence and the rotation angle constraint interval sequence to obtain the control parameter optimization results.

[0168] Furthermore, the control parameter optimization module 16 also includes the following steps:

[0169] If the material quality assessment result does not meet the lifting weight threshold range, obtain a material batching instruction;

[0170] The materials to be lifted are divided into batches according to the lifting mass threshold range, and the batching results of the materials to be lifted are obtained.

[0171] Based on the batching results of the materials to be lifted, the control parameters of the boom crane are optimized using the boom position constraint interval sequence and the rotation angle constraint interval sequence to obtain the control parameter optimization results.

[0172] Furthermore, the control parameter optimization module 16 also includes the following steps:

[0173] Obtain the control parameters of the boom crane, including lifting height, boom position, rotation angle, lifting speed, and boom travel speed;

[0174] A parameter optimization space is constructed based on the lifting height, boom position, rotation angle, lifting speed, and boom movement speed. The dimension of the parameter optimization space is the same as that of the control parameters.

[0175] Traverse the sequence of constraints on boom position and rotation angle, input the parameter optimization space to optimize the lifting height, boom position, rotation angle, lifting speed and boom movement speed, and obtain the optimization results of the control parameters.

[0176] Furthermore, the control parameter optimization module 16 also includes the following steps:

[0177] When the input parameters of any set of boom position constraint interval and rotation angle constraint interval are optimized in the space, a filter particle swarm is obtained. Among them, any particle in the filter particle swarm represents the historical selection record of the control parameter under the boom position constraint interval and rotation angle constraint interval.

[0178] Formula for obtaining particle acceptance:

[0179]

[0180] Where, p k+1 The acceptability of the (k+1)th particle is represented by f(k+1), and the selection frequency parameter of the (k+1)th particle in the particle swarm is represented by f(k+1). The sum of selection frequency parameters of all particles in the selected particle swarm is represented by K, where K is the total number of particles in the selected particle swarm, h represents the lifting height, s represents the boom position, d represents the rotation angle, v1 represents the lifting speed, v2 represents the boom moving speed, and α, β, γ, δ and ε represent the weight coefficients of the corresponding control parameters.

[0181] The particle swarm is traversed and filtered a preset number of times according to the particle acceptance formula to obtain the particle with the highest acceptance, which is then added to the control parameters to optimize the result.

[0182] Example 3

[0183] Based on the same inventive concept as the big data-based computer speech recognition method in the foregoing embodiments, this application also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method in Embodiment 1.

[0184] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0185] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0186] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0187] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0188] The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for optimizing control parameters of a boom crane, characterized in that, include: Obtain basic information about the material to be lifted, wherein the basic information about the material to be lifted includes the lifting start point position information and the lifting end point position information; A set of images of the material to be lifted, containing the lifting start point position information; The quality assessment of the material to be lifted is performed based on the image set of the material to be lifted, and the material quality assessment result is obtained. Based on the lifting start point position information and the lifting end point position information, the image acquisition device is invoked to acquire regional images and obtain a set of lifting area images. Lifting path planning is performed based on the set of images of the lifting area to obtain lifting path information; Based on the lifting path information, obtain the sequence of obstacles along the lifting path; Based on the obstacle sequence of the lifting path, obtain the boom position constraint interval sequence and the rotation angle constraint interval sequence; Based on the boom position constraint interval sequence, the lifting mass threshold interval is obtained; If the material quality assessment result does not meet the lifting weight threshold range, then a material batching instruction is obtained; The materials to be lifted are divided into batches according to the lifting mass threshold range, and the batching results of the materials to be lifted are obtained. Based on the batching results of the materials to be lifted, the control parameters of the boom crane are optimized using the boom position constraint interval sequence and the rotation angle constraint interval sequence to obtain the control parameter optimization results. If the material quality assessment result meets the lifting quality threshold range, then the control parameters of the boom crane are obtained, wherein the control parameters include lifting height, boom position, rotation angle, lifting speed and boom movement speed. A parameter optimization space is constructed based on the lifting height, the boom position, the rotation angle, the lifting speed, and the boom movement speed, wherein the dimension of the parameter optimization space is the same as the dimension of the control parameters; When any set of boom position constraint intervals and rotation angle constraint intervals are input into the parameter optimization space, a filter particle swarm is obtained, wherein any particle in the filter particle swarm represents the historical selection record of the control parameter under the boom position constraint interval and the rotation angle constraint interval; Formula for obtaining particle acceptance: Among them, the Characterizes the acceptance level of the (k+1)th particle. The parameter characterizing the selection frequency of the (k+1)th particle in the particle swarm is used. The sum of selection frequency parameters characterizing all particles in the selected particle swarm. To filter the total number of particles in the particle swarm, The lifting height is represented by s, the boom position by d, the rotation angle by v1, the lifting speed by v2, and the boom travel speed by v2. , , , and The weighting coefficient characterizing the corresponding control parameter; The particle swarm is traversed and filtered a preset number of times according to the particle acceptance formula to obtain the particle with the highest acceptance, and then added to the control parameter optimization result.

2. The method according to claim 1, characterized in that, The basic information of the material to be lifted also includes material density information. The step of performing a quality assessment on the material to be lifted based on the image set of the material to be lifted, and obtaining the material quality assessment result, includes: Based on the image set of the material to be lifted, obtain the material volume information; Determine the material density information; The material quality assessment result is obtained based on the material volume information and the material density information.

3. The method according to claim 1, characterized in that, The step of planning the lifting path based on the lifting area image set and obtaining lifting path information includes: The set of images of the lifting area is input into the simulation environment construction module to generate simulation results of the lifting area environment. Obtain the boom crane position information, lifting height threshold range, boom position threshold range, and rotation angle threshold range; Based on the boom crane position information, the lifting height threshold range, the boom position threshold range, and the rotation angle threshold range, the effective lifting area is separated from the lifting area environment simulation results to generate effective lifting area environment simulation results; The lifting start point location information and the lifting end point location information are input into the environmental simulation results of the effective lifting area to perform lifting path planning and obtain the lifting path information.

4. The method according to claim 3, characterized in that, The step of inputting the lifting start point location information and the lifting end point location information into the environmental simulation results of the effective lifting area to perform lifting path planning and obtain the lifting path information includes: Based on the lifting start point location information and the lifting end point location information, lifting sensitive element information is obtained, wherein the lifting sensitive element information includes a set of vacant elements; The set of vacant elements is continuously spliced ​​from the lifting start point location information to the lifting end point location information to obtain multiple continuous vacant channels; The multiple consecutive vacant passages are sorted from closest to furthest in terms of travel distance, and then filtered according to the closest consecutive vacant passages to obtain the lifting path information.

5. A control parameter optimization system for a boom crane, implemented based on the method described in claim 1, characterized in that, The system includes: The information acquisition module is used to acquire basic information of the material to be lifted, wherein the basic information of the material to be lifted includes the lifting start point position information and the lifting end point position information; The material image acquisition module is used to call the image acquisition device to acquire images of the material to be lifted based on the lifting starting point position information, and to obtain a set of images of the material to be lifted. The quality assessment module is used to assess the quality of the material to be lifted based on the image set of the material to be lifted, and to obtain the material quality assessment result. The lifting area image acquisition module is used to call the image acquisition device to acquire area images based on the lifting start point position information and the lifting end point position information, and obtain a set of lifting area images. The lifting path planning module is used to plan the lifting path based on the set of images of the lifting area and obtain lifting path information. The control parameter optimization module is used to: obtain a sequence of obstacles along the lifting path based on the lifting path information; obtain a sequence of boom position constraints and a sequence of rotation angle constraints based on the sequence of obstacles along the lifting path; obtain a lifting mass threshold range based on the sequence of boom position constraints; if the material quality assessment result does not meet the lifting mass threshold range, obtain a material batching instruction; batch the material to be lifted according to the lifting mass threshold range and obtain the batching result of the material to be lifted; optimize the control parameters of the boom crane based on the batching result of the material to be lifted, using the sequence of boom position constraints and the sequence of rotation angle constraints, and obtain the control parameter optimization result; if the material quality assessment result meets the lifting mass threshold range, optimize the control parameters of the boom crane based on the sequence of boom position constraints and the sequence of rotation angle constraints, and obtain the control parameter optimization result.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-4.

Images