CN119143021B - Motion trail control method and system for container front crane - Google Patents
Motion trail control method and system for container front crane Download PDFInfo
- Publication number
- CN119143021B CN119143021B CN202411616684.8A CN202411616684A CN119143021B CN 119143021 B CN119143021 B CN 119143021B CN 202411616684 A CN202411616684 A CN 202411616684A CN 119143021 B CN119143021 B CN 119143021B
- Authority
- CN
- China
- Prior art keywords
- path
- crane
- fitting
- scene
- dimensional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012544 monitoring process Methods 0.000 claims abstract description 25
- 230000003068 static effect Effects 0.000 claims abstract description 25
- 238000005457 optimization Methods 0.000 claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims description 33
- 238000012216 screening Methods 0.000 claims description 25
- 230000004044 response Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 claims description 7
- 238000013459 approach Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 1
- 230000003993 interaction Effects 0.000 abstract description 4
- 230000001133 acceleration Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 238000007781 pre-processing Methods 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66C—CRANES; LOAD-ENGAGING ELEMENTS OR DEVICES FOR CRANES, CAPSTANS, WINCHES, OR TACKLES
- B66C13/00—Other constructional features or details
- B66C13/18—Control systems or devices
- B66C13/48—Automatic control of crane drives for producing a single or repeated working cycle; Programme control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66C—CRANES; LOAD-ENGAGING ELEMENTS OR DEVICES FOR CRANES, CAPSTANS, WINCHES, OR TACKLES
- B66C15/00—Safety gear
- B66C15/06—Arrangements or use of warning devices
- B66C15/065—Arrangements or use of warning devices electrical
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Control And Safety Of Cranes (AREA)
Abstract
The application provides a motion trail control method and a motion trail control system for a container front crane, which relate to the technical field of intelligent control, and comprise the following steps: executing data acquisition, constructing a hoisting area into a three-dimensional fitting scene, then executing three-dimensional scene identification, establishing an article sensitive factor, performing sensitive monitoring through a static sensor group, updating the three-dimensional fitting scene in real time, then performing path fitting optimizing to establish an optimizing path, establishing M grades of early warning limit, controlling a crane to execute track control fitting, then executing real-time track tracking, generating tracking compensation and performing motion track control. The application can solve the technical problems that the prior art is inaccurate in motion track control and lacks real-time data information interaction, so that safe limit cannot be timely and accurately carried out according to track positions, and control precision and efficiency are further affected, realizes accurate control and optimization of crane motion tracks, and improves operation efficiency, safety and reliability.
Description
Technical Field
The application relates to the technical field of intelligent control, in particular to a method and a system for controlling a motion trail of a container front crane.
Background
The front crane for container is one kind of important loading and unloading equipment for port, wharf, cargo yard, etc. and has the main functions of hoisting, transporting and stacking container. Along with the rapid development of the logistics industry and the continuous increase of the container transportation quantity, higher requirements are put on the motion trail control of the container front crane. In places such as ports and wharfs, the working environment is complex and changeable, and factors such as wind power, uneven ground and the like can influence the movement track of the crane. Therefore, a motion trajectory control method capable of adapting to environmental changes is required to ensure stable operation of the crane.
At present, in the actual crane operation process, the crane control method is more dependent on the operation and judgment of a driver and the independent sensing data monitoring of the crane, and the technical problem that the motion track control is not accurate enough and the safe limit cannot be performed timely and accurately according to the track position exists.
In summary, the prior art is inaccurate in motion track control, and lacks real-time data information interaction, so that safety limit cannot be timely and accurately performed according to track positions, and further control accuracy and efficiency are affected.
Disclosure of Invention
The application aims to provide a motion trail control method and system of a container front crane, which are used for solving the technical problems that the prior art is inaccurate in motion trail control and lacks real-time data information interaction, so that safe limit cannot be timely and accurately carried out according to trail positions, and further control accuracy and efficiency are affected.
In view of the above problems, the application provides a method and a system for controlling the motion trail of a container front crane.
The application provides a motion trail control method of a container front crane, which is realized by a motion trail control system of the container front crane, and comprises the steps of executing data acquisition through a static sensor group arranged in a lifting area, constructing the lifting area into a three-dimensional fitting scene, executing three-dimensional scene identification according to article characteristics in the three-dimensional fitting scene, establishing an article sensitive factor with the movable article identification, performing sensitive monitoring through the static sensor group, updating the three-dimensional fitting scene in real time, performing path fitting optimizing based on the three-dimensional fitting scene and the lifting task, establishing M grades of early warning limit according to the three-dimensional fitting scene and the three-dimensional scene identification, controlling the crane to execute trail control fitting of the optimizing path, executing real-time trail tracking of the crane through the dynamic sensor group, inputting a tracking result, the optimizing path and the early warning limit trail compensation network, generating path following compensation, and completing motion trail control of the crane through the path following compensation.
The application further provides a motion track control system of the container front crane, which is used for executing the motion track control method of the container front crane according to the first aspect, wherein the system comprises a data acquisition module, a track control fitting module and a track control fitting module, wherein the data acquisition module is used for executing data acquisition through a static sensor group arranged in a lifting area, setting the lifting area as a three-dimensional fitting scene and executing three-dimensional scene identification according to the characteristics of articles in the three-dimensional fitting scene, the three-dimensional scene identification comprises a movable article identification and a fixed article identification, the sensitive monitoring module is used for establishing an article sensitive factor with the movable article identification, the static sensor group is used for conducting sensitive monitoring, the three-dimensional fitting scene is updated in real time, the optimizing path is established, the optimizing path establishment module is used for conducting path fitting optimizing based on the three-dimensional fitting scene and the lifting task, the track control fitting module is used for establishing M grades of pre-warning limit according to the three-dimensional fitting scene and the three-dimensional fitting scene identification, and controlling the crane to execute track control fitting of the optimizing path, and the track compensation module is used for tracking the path to follow the fitting path through the dynamic compensation sensor group and the pre-warning limiting crane, and the path is used for completing the real-time network tracking and the optimizing path.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The method comprises the steps of executing data acquisition through a static sensor group arranged in a lifting area, constructing the lifting area into a three-dimensional fitting scene, executing three-dimensional scene identification according to article characteristics in the three-dimensional fitting scene, wherein the three-dimensional scene identification comprises a movable article identification and a fixed article identification, establishing an article sensitivity factor with the movable article identification, carrying out sensitive monitoring through the static sensor group, updating the three-dimensional fitting scene in real time, carrying out path fitting optimizing based on the three-dimensional fitting scene and a lifting task, establishing an optimizing path, establishing M grades of early warning limit according to the real-time updating three-dimensional fitting scene and the three-dimensional scene identification, controlling a crane to execute track control fitting of the optimizing path, executing real-time track tracking of the crane through the dynamic sensor group, inputting a tracking result, the optimizing path and the early warning limit into a track compensation network, generating path following compensation, and completing the motion track control of the crane through the path following compensation, thereby effectively solving the technical problems that the prior art is inaccurate in motion track control and lacks real-time data information, leading to not to carrying out safe limit according to track positions in time, further influencing control accuracy and efficiency, realizing accurate control and optimizing of the crane motion track, improving safety and reliability.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent. It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the application or the technical solutions of the prior art, the following brief description will be given of the drawings used in the description of the embodiments or the prior art, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained from the drawings provided without the inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for controlling the motion trail of a container front crane according to the present application;
fig. 2 is a schematic diagram of a motion trail control system of a container front crane according to the present application.
Reference numerals illustrate:
The system comprises a data acquisition module 11, a sensitive monitoring module 12, an optimizing path establishing module 13, a track control fitting module 14 and a path following compensation module 15.
Detailed Description
The application solves the technical problems that the prior art is inaccurate in motion track control and lacks real-time data information interaction, so that safe limit cannot be timely and accurately carried out according to track positions, and control precision and efficiency are further affected, realizes accurate control and optimization of the motion track of the crane, and improves operation efficiency, safety and reliability.
In the following, the technical solutions of the present application will be clearly and completely described with reference to the accompanying drawings, and it should be understood that the described embodiments are only some embodiments of the present application, but not all embodiments of the present application, and that the present application is not limited by the exemplary embodiments described herein. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. It should be further noted that, for convenience of description, only some, but not all of the drawings related to the present application are shown.
Example 1
Referring to fig. 1, the application provides a motion trail control method of a container front crane, wherein the method is applied to a motion trail control system of the container front crane, the system is integrated with an intelligent processor, the intelligent processor is in digital communication with a static sensor group and a dynamic sensor group, the dynamic sensor group is arranged on the crane, and the method specifically comprises the following steps:
the method comprises the steps of firstly, executing data acquisition through a static sensor group arranged in a lifting area, constructing the lifting area into a three-dimensional fitting scene, and executing three-dimensional scene identification according to object characteristics in the three-dimensional fitting scene, wherein the three-dimensional scene identification comprises a movable object identification and a fixed object identification;
Specifically, a static sensor group is arranged in a hoisting area, and real-time sensing and data acquisition of the environment of the hoisting area are performed. Such sensors may include laser scanners, cameras, infrared sensors, etc., to capture information about the shape, size, location, etc., of various items within the lifting area. By arranging these sensors in strategic locations, full coverage of the entire lifting area can be ensured, thereby obtaining complete environmental data. Based on the collected environmental data, a three-dimensional fitting scene of the lifting area can be constructed. The data preprocessing and the feature extraction are carried out on the collected data. The preprocessed sensor data is converted into a point cloud format, each point in the point cloud representing a position in a three-dimensional space. The point cloud data is converted into a continuous three-dimensional surface model through algorithm processing such as poisson surface reconstruction, greedy projection triangularization and the like, so that the spatial structure of the lifting area is clearer and more accurate. Key features of each item are extracted from the three-dimensional fitted scene, including the shape, size, location, color, texture, etc. of the item. According to the extracted key characteristics, the articles are divided into movable articles and fixed articles, wherein the movable articles are objects which need to be operated or moved in the working process, such as containers, and the fixed objects can be obstacles of scenes, such as buildings and road marks. For moving objects, the motion state of the moving object, such as position change, moving speed, direction and the like, is monitored in real time through sensor data or video streams. Each movable item is assigned a unique identification code so as to be accurately identified and managed in subsequent track control and safety limiting. The identification code may be a number, two-dimensional code, or other form of identifier. By tracking the position and state of these items in real time, it is ensured that the crane can accurately identify and grasp the target container during operation. Meanwhile, the future position of the movable object can be predicted according to the information such as the moving track and the speed of the movable object, so that the moving path of the crane can be planned in advance. For a stationary item, its static characteristics, such as position, shape, size, etc., are monitored. These features are typically relatively stable in a three-dimensional fit scene, do not change significantly over time, and do not require frequent updates. By identifying the stationary items in a three-dimensional scene, the identification code may be a number, two-dimensional code, or other form of identifier. The crane can be prevented from colliding or rubbing with them during operation.
Establishing an article sensitive factor with a movable article identifier, performing sensitive monitoring through a static sensor group, and updating a three-dimensional fitting scene in real time;
Specifically, a sensitivity factor affecting the motion trail of the movable object is determined according to the characteristics of the movable object. The sensitivity factors may include dynamic factors such as the moving speed, acceleration, direction change of the object, and static factors such as the relative position and distance of the object from the surrounding environment. And selecting a sensor suitable for monitoring movable objects, such as a laser radar, a high-definition camera, an infrared sensor and the like, and reasonably arranging according to the actual environment of a lifting area. The static sensor group is used for collecting the motion data of the movable object in real time, including the position, the speed, the direction and the like. Preprocessing, such as filtering, denoising and the like, is performed on the acquired data so as to improve the accuracy and reliability of the data. And monitoring the motion state of the movable object in real time according to the object sensitivity factor. Sensor data is processed by algorithmic analysis, for example, using a support vector machine or decision tree algorithm to identify the location and type of the item, and regression algorithms are used to predict changes in velocity and acceleration of the item. Thereby extracting characteristic information related to the sensitive factors, including the position, speed, acceleration, direction and other characteristics of the object. And continuously updating the position and state information of the movable object in the three-dimensional fitting scene according to the data acquired by the static sensor group in real time. It is ensured that the scene model remains synchronized with the actual environment to reflect the latest state of the active item.
Step three, carrying out path fitting optimizing based on the three-dimensional fitting scene and the hoisting task, and establishing an optimizing path;
Specifically, first, a detailed analysis of the hoisting task is required, and the task objective, constraint conditions, and optimization index are defined. For example, a task goal may be to move an item from a starting point to an ending point, constraints may include avoiding collisions, maintaining speed within a certain range, etc., and optimization criteria may be shortest path, shortest time, or lowest energy consumption, etc. And setting a target and constraint conditions of path planning according to the result of task analysis. The target is used for quantitatively evaluating the advantages and disadvantages of different paths, and the constraint condition is used for limiting the range of path planning so as to ensure that the planned path meets the actual requirement. And taking the three-dimensional fitting scene as a basis of path planning. This scenario contains information on the location, shape and size of all stationary and moving items within the lifting area. By using this information, various potential obstacles and constraints may be considered when planning the path. And selecting a proper path fitting optimizing algorithm according to the target and constraint conditions of path planning. The algorithms may be graph-based search algorithms such as a-algorithm, dijkstra algorithm, etc., or sample-based planning algorithms such as RRT algorithm, PRM algorithm, etc., or optimization-based planning algorithms such as gradient descent method, genetic algorithm, etc. And carrying out path fitting optimization in the three-dimensional fitting scene by using the selected algorithm. The algorithm searches the scene for possible paths according to the targets and constraints, and evaluates the quality of each path. Through iterative optimization, the algorithm gradually converges to an optimizing path meeting the requirement. And after the algorithm converges, obtaining an optimizing path meeting the task requirement.
Step four, establishing M grades of early warning limit according to the real-time updated three-dimensional fitting scene and the three-dimensional scene mark, and controlling a crane to execute track control fitting of the optimizing path;
Specifically, according to the real-time updated three-dimensional fitting scene and the three-dimensional scene identification, the positions, states and relative relations of the movable objects and the fixed objects in the hoisting area are analyzed. And according to the result of scene analysis, determining M different early warning levels by combining the motion capability and the operation requirement of the crane. Wherein M is a positive integer. These grades may be classified according to factors such as distance of the article from the crane, moving speed of the article, operation priority of the crane, etc. And setting corresponding early warning limit under each early warning level. The early warning limit may be a boundary in space, a threshold in distance, or a limit in time, e.g., a safe operating zone, a dangerous approaching zone, a forbidden entering zone, etc., for triggering different early warning responses and trajectory adjustment strategies. Based on the real-time updated three-dimensional fitting scene and the three-dimensional scene identification, generating an optimizing path from the current position to the target position for the crane by using a path planning algorithm. The path should avoid collision with movable and fixed articles as much as possible and shorten working time as much as possible. And fitting the motion trail of the crane through a trail control algorithm according to the planned optimizing trail. This includes controlling the speed, acceleration, direction, etc. of the crane to ensure that it can move exactly in the planned path. During the movement of the crane, the distance and the relative position between the crane and surrounding articles are monitored in real time. When approaching or reaching a certain early warning limit, triggering corresponding early warning response, such as decelerating, avoiding or rescheduling a path, and the like. By continuously adjusting the motion trail of the crane, the crane can safely and efficiently finish the operation task.
And fifthly, executing real-time track tracking of the crane through the dynamic sensor group, inputting a tracking result, an optimizing path and early warning limit information into a track compensation network, generating path following compensation, and completing motion track control of the crane through the path following compensation.
Specifically, a dynamic sensor group including, but not limited to, a gyroscope, an accelerometer, a displacement sensor, etc. is mounted on the crane for monitoring the motion state of the crane in real time. The dynamic sensor group collects the motion data such as the position, the speed, the acceleration and the like of the crane in real time, and performs filtering, denoising and calibration through a data processing algorithm, so that the accuracy and the reliability of the data are ensured. Based on the acquired motion data, calculating the actual motion trail of the crane in real time through a trail tracking algorithm, and comparing the actual motion trail with a planned optimizing route. A trajectory compensation network is established, which may be a deep learning model or other type of machine learning model, for generating path-following compensation based on real-time trajectory tracking results, optimized paths, and pre-warning limits. And taking a real-time track tracking result, an optimizing path and an early warning limit as input characteristics, and preprocessing so as to adapt to the input requirement of a track compensation network. The track compensation network learns and generates a path following compensation according to the input characteristics, wherein the compensation can be an adjustment quantity of crane motion parameters, such as speed, acceleration or direction adjustment. The generated path following compensation is applied to a motion control system of the crane, and the motion parameters of the crane are adjusted to enable the crane to better follow the planned optimizing path and avoid collision with early warning limit.
Further, the application also comprises:
performing network initialization of the trajectory compensation network, the specific initialization including:
a1, acquiring real-time weather data and lifting data, wherein the lifting data comprises lifting mass data and lifting object volume data, and the real-time weather data is acquired;
And A2, resetting constraint layer data by using the real-time weather data and the hoisting data, wherein the constraint layer is an implicit layer of a track compensation network, and completing network initialization according to the reset of the constraint layer data.
Specifically, real-time weather information, such as wind speed, wind direction, temperature, humidity, etc., is acquired by the meteorological sensors. These weather factors can directly influence the working environment of the crane, and further influence the movement track and stability of the crane. Lifting data, including quality data and volume data of the lifting object, are obtained by a weight sensor. These data describe the load conditions that the current crane needs to handle and are critical to determining the crane motion parameters and trajectory compensation strategy. The constraint layer data of the trajectory compensation network is reset using the collected real-time weather data and lifting data. The constraint layer here refers to an implicit layer in the network that is responsible for extracting features from the input data and passing it to the output layer. The real-time weather data and the hoisting data are preprocessed, e.g. normalized, standardized or encoded, to adapt them to the input requirements of the network. Features having a significant impact on trajectory compensation, such as temperature, humidity, wind speed, lift mass, volume, etc., are selected from the preprocessed data. The features are spliced in a sequence to form a composite feature vector. The length of the vector should be equal to the total number of selected features. This vector will serve as input to the constraint layer. And randomly initializing weights for each neuron of the constraint layer according to the dimension of the fused feature vector. Including uniform distribution initialization, normal distribution initialization, or He/Glorot-based initialization methods. Bias values are randomly initialized for each neuron of the constraint layer. The initialization of the bias is typically a small constant. The selection can introduce nonlinear activation functions, which can be ReLU, sigmoid, and the like, and fine-tuning the weight of the constraint layer according to the fused feature vector and specific constraint conditions such as a safety threshold, an operation requirement, and the like.
Further, the application also comprises:
Performing deviation evaluation on the optimizing path and the tracking result through a tracking fitting layer, configuring N levels of pretightening distances according to the deviation evaluation result, respectively establishing corresponding N pretightening points according to the N levels of pretightening distances, performing track compensation fitting according to the N pretightening points, and generating N path compensation results, wherein the tracking fitting layer is an implicit layer coupled in a track compensation network and used for executing track fitting processing;
sharing N path compensation results to a limiting constraint layer, wherein the limiting constraint layer is updated by early warning and limiting, limiting evaluation of the N path compensation results is performed based on the early warning and limiting, and one-round screening is completed;
continuing to screen the first round of screening through the constraint layer to obtain the second round of screening;
and generating path following compensation according to the two rounds of screening.
Specifically, the tracking fitting layer receives as input a real-time trajectory tracking result and a planned optimizing path. The layer is responsible for executing track fitting processing and quantitatively evaluating deviation of the track fitting processing and the track fitting processing. Based on the processing result of the tracking fitting layer, calculating the deviation value between the real-time track and the optimizing path, and calculating the deviation value in a manner of Euclidean distance and Manhattan distance deviation measurement. These deviation values reflect the difference between the actual motion of the crane and the ideal path. And evaluating the current track tracking performance according to the calculated deviation value, and providing a basis for the subsequent pre-aiming distance configuration. Based on the deviation evaluation result, N different levels of pretightening distances are dynamically configured. Wherein N is a positive integer. The pretightening distance can be adjusted according to the deviation, the motion state of the crane, the working environment and other factors. And establishing a corresponding pretightening point on the optimizing path according to each pretightening distance. These pretightening points will serve as reference points for track compensation. Fitting the pretighted points with a tracking fit layer may include interpolation, curve fitting to generate a smooth and constraint-compliant compensated trajectory. And generating a corresponding path compensation result for each pre-aiming point. These results will be used as candidate compensation paths for subsequent screening and selection. The limit constraint layer dynamically updates the early warning limit according to the current state of the crane, the operation environment, the safety requirement and other factors. And inputting N path compensation results into a limiting constraint layer, and carrying out limiting evaluation based on early warning limiting. This includes checking whether each compensation path exceeds a physical limit, a safety threshold, or other constraint. And screening out path compensation results which do not meet the limit requirements according to the limit evaluation results. And inputting the path compensation result screened by the limiting constraint layer into the constraint layer for further processing and screening. The constraint layer may contain other types of constraints, such as smoothness constraints, speed constraints, and the like. And the constraint layer performs two-round screening on the path compensation result according to the constraint condition of the constraint layer, and further screens out better candidate paths. Based on the final candidate paths through the two rounds of screening, final path-following compensation is generated. This compensation will be used to adjust the motion profile of the crane to achieve a more accurate and safe profile control.
Further, the application also comprises:
configuring an evaluation distribution proportion of an evaluation layer, wherein the evaluation distribution proportion is a normalized weight proportion of limit early warning and approaching speed;
And carrying out path optimization of the two rounds of screening according to the path approaching speed, the path limiting early warning and the evaluation allocation proportion of the two rounds of screening, and constructing path following compensation according to a path optimizing result.
Specifically, first, a main evaluation factor affecting path optimization is identified. The main evaluation factors comprise displacement limit early warning and approaching speed. Each evaluation factor is normalized to determine their weight ratio. The normalized weight ratio should reflect the relative importance of each factor in the path optimization process. May be obtained by a machine learning method or the like. And setting an evaluation allocation proportion of an evaluation layer based on the normalized weight proportion. And extracting the approximation speed information of each path from the results of the two rounds of screening. The approaching speed reflects how fast the crane is moving towards the target position. And meanwhile, acquiring limit early warning information of each path. The limit early warning indicates the approach degree of the path and the early warning limit, and is an important index for ensuring safe operation. And combining the path approaching speed, the path limiting early warning and the evaluation allocation proportion of the evaluation layer to perform path optimizing calculation. The specific calculation mode can be such as weighted summation, weighted product and the like. And determining an optimal path based on the path optimizing result. The optimal path should comprehensively consider factors such as approaching speed, limiting early warning and the like, so that the crane can meet the safety requirement while operating efficiently. And constructing path following compensation according to the optimal path. The path following compensation can guide the crane to move according to the optimal path, so that the accurate tracking of the target position is realized.
Further, the fifth step of the present application further comprises:
Analyzing the three-dimensional scene identifier, and establishing an article grade, wherein the article grade is an important grade evaluated according to the importance degree of the article, and comprises a movable article grade and a fixed article grade;
and finishing the early warning limit construction of M grades by using the article grade and updating the three-dimensional fitting scene in real time.
Specifically, three-dimensional scene data including a crane working environment is acquired. The data may be from lidar, cameras or other sensors that together construct a three-dimensional, real-time model of the work environment. In the three-dimensional scene data, identification information of various articles is identified and extracted. Such identifying information may include the location, size, shape, material, etc. of the item, as well as any labels associated with the importance or function of the item. And evaluating the importance degree of the objects in the scene according to the extracted identification information. The basis for the evaluation may include factors such as the value of the item, the impact on the workflow, safety, etc. The items are classified into different grades based on the importance level evaluation result. Including a movable item level and a fixed item level. The movable item may be a load being handled by a crane and the stationary item may be a stationary obstacle or structure in the work environment. And determining the type and the quantity of the early warning limit required by the articles of different grades according to the grade of the articles. For example, for high value or high security risk items, more stringent, denser warning limits are set. Because the working environment can change at any time, such as the addition of new articles, the removal of old articles, the change of the environment and the like, the three-dimensional fitting scene is updated in real time so as to ensure the accuracy of early warning limit. And constructing M early warning limits of different grades based on the real-time updated three-dimensional fitting scene and the grade information of the articles. Wherein M is a positive integer. These warning limits may include distance limits, height limits, speed limits, etc., which will form a multi-level safety protection net to prevent the crane from colliding with or dangerously approaching different levels of items.
Further, the application also comprises:
Real-time data monitoring is carried out through the dynamic sensor group, and path obstacle triggering verification is carried out according to a real-time monitoring result and path following compensation;
If the preset trigger threshold is met, reporting an abnormal operation and generating a shutdown instruction;
And controlling the crane to stop according to the stop instruction, and carrying out abnormality early warning according to the reported operation abnormality.
Specifically, the dynamic sensor group includes a weight sensor, a height sensor, a tilt sensor, etc. to collect various operation data of the crane, such as weight, height, speed, angle, etc., in real time. The collected data is transmitted to a data processing unit of the trajectory compensation network for necessary preprocessing and conversion for subsequent analysis and judgment. And comparing the real-time monitoring result with the path following compensation, and analyzing the difference between the current actual running track and the expected track of the crane. Judging whether the current condition of path obstacle triggering exists or not according to preset obstacle triggering conditions such as a deviation threshold value, a speed threshold value, an angle threshold value and the like. These thresholds may be set according to the type of crane, the working environment, safety requirements, etc. And if the real-time monitoring result meets a preset trigger threshold, judging that the running abnormality or the path obstacle exists. Immediately reporting the abnormal operation and generating a corresponding shutdown instruction. And immediately executing stopping operation by the control system according to the generated stopping instruction, so that the crane is stopped at the current position and kept in a static state. Meanwhile, the reported abnormal operation information is sent to related personnel or equipment to perform abnormal early warning. The method can be realized by means of audible and visual alarm, short message notification, mail reminding and the like, so that related personnel can know and process abnormal conditions in time.
Further, the application also comprises:
Collecting response feedback of a user, wherein the response feedback is a feedback result of an actual control result of the crane;
transmitting the response feedback to the track compensation network, and executing additional constraint of the track compensation network;
and carrying out subsequent track control adjustment according to the track compensation network after the additional constraint.
Specifically, after the user completes the work task using the crane, response feedback from the user is collected. The feedback data may include user assessment of control accuracy, satisfaction with the crane motion trajectory, whether a collision has occurred or safety limits have been exceeded, etc. After the feedback data is collected, it is collated and analyzed to extract information useful for the trajectory compensation network. Including classification, statistics, and quantization processing of the feedback data. Before the user's response feedback is sent to the track compensation network, some preprocessing operations, such as data cleansing, normalization or transcoding, are performed on the feedback data to ensure that the data format matches the input requirements of the network. The preprocessed feedback data will be integrated into the input of the trajectory compensation network. After integrating the feedback data into the trajectory compensation network, additional constraint operations are performed. Constraints include limitations in terms of speed of operation, accuracy, stability, or optimization requirements. Based on the user's response feedback and additional constraints, parameters of the trajectory compensation network are updated. The method comprises the step of adjusting the weight, bias or other super parameters of the network through optimization algorithms such as gradient descent, back propagation and the like so as to improve the performance and accuracy of the network. And re-applying the updated network parameters to crane operation, collecting new feedback data, and repeating the steps to perform iterative optimization. Through continuous iteration and optimization, the track compensation network can gradually adapt to different operation environments and user requirements, and more accurate and safer track control is realized.
In summary, the motion trail control method of the container front crane provided by the application has the following technical effects:
The method comprises the steps of executing data acquisition through a static sensor group arranged in a lifting area, constructing the lifting area into a three-dimensional fitting scene, executing three-dimensional scene identification according to article characteristics in the three-dimensional fitting scene, wherein the three-dimensional scene identification comprises a movable article identification and a fixed article identification, establishing an article sensitivity factor with the movable article identification, carrying out sensitive monitoring through the static sensor group, updating the three-dimensional fitting scene in real time, carrying out path fitting optimizing based on the three-dimensional fitting scene and a lifting task, establishing an optimizing path, establishing M grades of early warning limit according to the real-time updating three-dimensional fitting scene and the three-dimensional scene identification, controlling a crane to execute track control fitting of the optimizing path, executing real-time track tracking of the crane through the dynamic sensor group, inputting a tracking result, the optimizing path and the early warning limit into a track compensation network, generating path following compensation, and completing the motion track control of the crane through the path following compensation, thereby effectively solving the technical problems that the prior art is inaccurate in motion track control and lacks real-time data information, leading to not to carrying out safe limit according to track positions in time, further influencing control accuracy and efficiency, realizing accurate control and optimizing of the crane motion track, improving safety and reliability.
Example two
Based on the same inventive concept as the motion trail control method of the container front crane in the foregoing embodiment, the application also provides a motion trail control system of the container front crane, referring to fig. 2, the system comprises:
the data acquisition module 11 is used for executing data acquisition through a static sensor group arranged in a lifting area, constructing the lifting area into a three-dimensional fitting scene, and executing three-dimensional scene identification according to the characteristics of articles in the three-dimensional fitting scene, wherein the three-dimensional scene identification comprises a movable article identification and a fixed article identification;
The sensitive monitoring module 12 is used for establishing an article sensitive factor with a movable article identifier, performing sensitive monitoring through a static sensor group, and updating a three-dimensional fitting scene in real time;
The optimizing path establishing module 13 is used for carrying out path fitting optimizing based on the three-dimensional fitting scene and the lifting task to establish an optimizing path;
The track control fitting module 14 is used for establishing M levels of early warning limit according to the real-time updated three-dimensional fitting scene and the three-dimensional scene mark and controlling a crane to execute track control fitting of the optimizing path;
The path following compensation module 15 is used for executing real-time track tracking of the crane through the dynamic sensor group, inputting a tracking result, an optimizing path and early warning limit information into a track compensation network, generating path following compensation, and completing motion track control of the crane through the path following compensation.
Further, the system also includes a network initialization module for:
performing network initialization of the trajectory compensation network, the specific initialization including:
a1, acquiring real-time weather data and lifting data, wherein the lifting data comprises lifting mass data and lifting object volume data, and the real-time weather data is acquired;
And A2, resetting constraint layer data by using the real-time weather data and the hoisting data, wherein the constraint layer is an implicit layer of a track compensation network, and completing network initialization according to the reset of the constraint layer data.
Further, the system further includes a path following compensation generation module for:
Performing deviation evaluation on the optimizing path and the tracking result through a tracking fitting layer, configuring N levels of pretightening distances according to the deviation evaluation result, respectively establishing corresponding N pretightening points according to the N levels of pretightening distances, performing track compensation fitting according to the N pretightening points, and generating N path compensation results, wherein the tracking fitting layer is an implicit layer coupled in a track compensation network and used for executing track fitting processing;
sharing N path compensation results to a limiting constraint layer, wherein the limiting constraint layer is updated by early warning and limiting, limiting evaluation of the N path compensation results is performed based on the early warning and limiting, and one-round screening is completed;
continuing to screen the first round of screening through the constraint layer to obtain the second round of screening;
and generating path following compensation according to the two rounds of screening.
Further, the system further comprises a path optimizing module, wherein the path optimizing module is used for:
configuring an evaluation distribution proportion of an evaluation layer, wherein the evaluation distribution proportion is a normalized weight proportion of limit early warning and approaching speed;
And carrying out path optimization of the two rounds of screening according to the path approaching speed, the path limiting early warning and the evaluation allocation proportion of the two rounds of screening, and constructing path following compensation according to a path optimizing result.
Further, the system trajectory control fitting module 14 is configured to:
Analyzing the three-dimensional scene identifier, and establishing an article grade, wherein the article grade is an important grade evaluated according to the importance degree of the article, and comprises a movable article grade and a fixed article grade;
and finishing the early warning limit construction of M grades by using the article grade and updating the three-dimensional fitting scene in real time.
Further, the system also includes a shutdown instruction generation module for:
Real-time data monitoring is carried out through the dynamic sensor group, and path obstacle triggering verification is carried out according to a real-time monitoring result and path following compensation;
If the preset trigger threshold is met, reporting an abnormal operation and generating a shutdown instruction;
And controlling the crane to stop according to the stop instruction, and carrying out abnormality early warning according to the reported operation abnormality.
Further, the system also includes a trajectory control adjustment module for:
Collecting response feedback of a user, wherein the response feedback is a feedback result of an actual control result of the crane;
transmitting the response feedback to the track compensation network, and executing additional constraint of the track compensation network;
and carrying out subsequent track control adjustment according to the track compensation network after the additional constraint.
In this description, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the motion trail control method and specific example of a container front crane in the first embodiment of fig. 1 are also applicable to the motion trail control system of a container front crane in this embodiment, and by the foregoing detailed description of the motion trail control method of a container front crane, those skilled in the art can clearly know the motion trail control system of a container front crane in this embodiment, so that, for brevity of description, they will not be described in detail herein. For the system disclosed in the embodiment, since the system corresponds to the method disclosed in the embodiment, the description is simpler, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalent techniques thereof, the present application is also intended to include such modifications and variations.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411616684.8A CN119143021B (en) | 2024-11-13 | 2024-11-13 | Motion trail control method and system for container front crane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411616684.8A CN119143021B (en) | 2024-11-13 | 2024-11-13 | Motion trail control method and system for container front crane |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119143021A CN119143021A (en) | 2024-12-17 |
| CN119143021B true CN119143021B (en) | 2025-04-04 |
Family
ID=93817239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411616684.8A Active CN119143021B (en) | 2024-11-13 | 2024-11-13 | Motion trail control method and system for container front crane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119143021B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119369413B (en) * | 2024-12-25 | 2025-03-21 | 龙岩学院 | A data collection method for simulation learning |
| CN119358799A (en) * | 2024-12-26 | 2025-01-24 | 山东铁鹰建设工程有限公司 | Construction management method and device for upward bridge-building machine |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2027214A1 (en) * | 1989-10-10 | 1991-04-11 | Arthur Zuehlke | Control and hydraulic system for liftcrane |
| AT14237U1 (en) * | 2014-01-31 | 2015-06-15 | Palfinger Ag | crane control |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101665216B (en) * | 2009-09-29 | 2012-02-08 | 三一集团有限公司 | A method, system and device for controlling the running track of a quay crane container spreader |
| CN102001587B (en) * | 2010-11-17 | 2012-02-15 | 武汉船用机械有限责任公司 | Automatic control method and control device for ship rotary crane jib laying |
| CN106429851B (en) * | 2016-12-15 | 2017-11-17 | 南开大学 | Overhead crane automatic control system based on remote tele-operation |
-
2024
- 2024-11-13 CN CN202411616684.8A patent/CN119143021B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2027214A1 (en) * | 1989-10-10 | 1991-04-11 | Arthur Zuehlke | Control and hydraulic system for liftcrane |
| AT14237U1 (en) * | 2014-01-31 | 2015-06-15 | Palfinger Ag | crane control |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119143021A (en) | 2024-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119143021B (en) | Motion trail control method and system for container front crane | |
| US11615655B2 (en) | Dynamic industrial vehicle measure | |
| US20200109963A1 (en) | Selectively Forgoing Actions Based on Fullness Level of Containers | |
| US20210056492A1 (en) | Providing information based on detection of actions that are undesired to waste collection workers | |
| US20210072397A1 (en) | Generation of synthetic lidar signals | |
| JP7277256B2 (en) | Work analysis system, work analysis device, and work analysis program | |
| CN116075846A (en) | System and method for mapping risk in warehouse environment | |
| CN117519215A (en) | Multi-AGV driving control method, device, equipment and storage medium | |
| Chen et al. | A novel background filtering method with automatic parameter adjustment for real-time roadside-LiDAR sensing system | |
| CN115716603A (en) | Bucket wheel machine material taking path planning method and system | |
| CN116520856B (en) | Quantitative safety avoidance system for terminal transport vehicles based on IGV smart navigation | |
| CN119717828B (en) | An intelligent obstacle avoidance and path optimization method and system for AGV | |
| Wunderle et al. | Safe object detection in AMRs-a Survey | |
| Santos et al. | Counting vehicle by axes with high-precision in brazilian roads with deep learning methods | |
| Hireche et al. | Machine Learning Techniques for Road Traffic | |
| CN119683480B (en) | Intelligent loading control method for shaft excavation bucket | |
| KR102670646B1 (en) | Method for detecting object and System for detecting object | |
| CN114972826A (en) | Method and device for determining target state, electronic equipment and computer storage medium | |
| CN119784280A (en) | An unmanned shipping system based on intelligent weighing | |
| CN120039807A (en) | Intelligent forklift management system and method based on AI anti-collision | |
| CN119919821A (en) | Safety analysis method and system applied to storage robot complex driving scene | |
| CN119996941A (en) | Asset twin management method and asset twin management server integrating indoor positioning | |
| CN118760996A (en) | Smart yard multi-level safety control device with no blind spots | |
| CN119339332A (en) | Port area mobile security detection method, terminal and storage medium based on image recognition | |
| CN119831180A (en) | Electric power engineering construction safety monitored control system based on degree of depth study |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |