Trajectory planning method and system for bridge crane

Abstract

The invention relates to a track planning method and system for a bridge crane, and the method comprises the steps: collecting motion signals of a main beam and a trolley through an electromagnetic field intensity detection sensor array, carrying out the denoising of the motion signals, extracting features, decomposing the features into component signal groups, building the incidence relation between the component signal groups and the motion state of a joint, and achieving the high-precision dynamic positioning. A time sequence model is constructed based on position data to analyze displacement and speed characteristics, a multi-dimensional constraint condition set including speed limitation and position boundaries is generated, a final trajectory scheme is output through iterative adjustment of an optimization calculation framework, a dynamic feedback mechanism is adopted, electromagnetic field intensity signals and planning data are compared in real time, and the optimal position is obtained. And when the deviation threshold is exceeded, readjusting the parameters, and generating a coordinated motion instruction to drive the crane to operate. Accurate positioning is achieved based on electromagnetic field intensity detection, the problems of accumulative errors and environmental interference of a traditional method are effectively solved, and the stability, accuracy and self-adaptive capacity of crane movement are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge crane trajectory planning, and in particular to a bridge crane trajectory planning method and system. Background Art

[0002] Bridge cranes are heavy-duty lifting equipment widely used in industrial production and logistics. Consisting primarily of a main girder, trolley, and hoisting mechanism, they are capable of lifting and precisely positioning cargo in three dimensions. Due to their complex structure, heavy loads, and significant inertia, planning efficient, smooth, and safe motion trajectories has always been a technical challenge in practical operations. Traditional bridge crane trajectory planning methods rely primarily on preset paths or open-loop control based on simple kinematic models, making them difficult to adapt to the precise control requirements of dynamic environments.

[0003] Existing technologies typically use encoder-based or laser-based positioning methods for bridge crane path planning, but these methods have limitations. For example, encoders are susceptible to mechanical wear and accumulated errors, resulting in a decrease in positioning accuracy over time. While laser ranging offers high accuracy, it is susceptible to interference from dust and vibration in complex industrial environments, compromising data reliability. Furthermore, existing methods often rely on offline planning and lack real-time dynamic adjustment capabilities, potentially leading to vibration, overshoot, and delayed response during crane operation, impacting operational efficiency and safety. Summary of the Invention

[0004] To this end, the technical problem to be solved by the present invention is to overcome the problems existing in the path planning of bridge cranes in the prior art, and to provide a bridge crane trajectory planning method and system, which locates the bridge crane based on electromagnetic field strength detection, thereby realizing the path planning of the bridge crane, effectively overcoming the cumulative errors and environmental interference problems of traditional positioning methods, and significantly improving the smoothness, accuracy and adaptability of the crane movement.

[0005] To solve the above technical problems, the present invention provides a bridge crane trajectory planning method, comprising: The electromagnetic field strength detection sensor array is used to collect electromagnetic field strength signal data during the movement of the main beam and the trolley, and the electromagnetic field strength signal data is denoised to obtain a purified electromagnetic field strength signal data set; Extracting features from the purified electromagnetic field strength signal data set and decomposing the data set into a plurality of component signal groups, and determining correlations between the component signal groups and joint motion states; According to the correlation between the component signal group and the joint motion state, the dynamic position coordinates of the main beam and the trolley are mapped to obtain high-precision dynamic position data records; Based on the high-precision dynamic position data records, a time-series-based position change model is constructed to analyze the displacement and velocity characteristics of the main beam and the trolley at different time points, and determine the real-time motion state description of each joint; Based on the real-time motion state description, a multi-dimensional constraint condition set including speed limit and position boundary is generated to obtain a basic parameter set of trajectory planning suitable for complex scenarios; According to the trajectory planning basic parameter set, a preset optimization calculation framework is applied to perform iterative adjustments and output the final trajectory planning solution data; Based on the final trajectory planning scheme data, a dynamic feedback mechanism is constructed to compare the real-time collected electromagnetic field strength signal with the trajectory planning scheme data. If the comparison result exceeds a preset deviation threshold, the trajectory planning basic parameter set is triggered to readjust to obtain updated trajectory planning data; According to the updated trajectory planning data, a coordinated motion instruction set of each joint is generated, and the crane is driven to perform trajectory motion through the instruction set to determine the state stability during the motion process.

[0006] In one embodiment of the present invention, electromagnetic field strength signal data during the movement of the main beam and the trolley is collected by an electromagnetic field strength detection sensor array, and the electromagnetic field strength signal data is denoised to obtain a purified electromagnetic field strength signal data set, including: Multiple electromagnetic field strength detection sensors are arranged along the track to form a sensor array covering the movement path of the main beam and the trolley. When the main beam and the trolley are moving, the electromagnetic field strength signal data is collected in real time to obtain the initial electromagnetic field strength signal set; For the initial electromagnetic field strength signal set, a preset filtering mechanism is used to process the signal to remove noise interference and generate a purified electromagnetic field strength signal data set; The purified electromagnetic field strength signal data set is segmented to divide the continuous signal data into signal subsets of multiple time segments, so that more precise data calibration can be performed on the signal subset of each time segment later; For the divided signal subsets, data smoothing processing is performed one by one to further eliminate small fluctuations in the signal and obtain the final optimized electromagnetic field strength signal data set for subsequent motion status monitoring of the main beam and trolley.

[0007] In one embodiment of the present invention, extracting features from the purified electromagnetic field strength signal dataset and decomposing the features into multiple component signal groups, and determining the association between the component signal groups and the joint motion state, includes: Extracting time series features and spatial distribution features from the purified electromagnetic field strength signal dataset, and using a preset signal decomposition method to split the purified electromagnetic field strength signal dataset into multiple independent component signal groups in response to nonlinear changes in the signal caused by the multi-degree-of-freedom structure, thereby preliminarily separating signal components related to different motion dimensions; For the component signal groups, in combination with a pre-established motion state association database, by comparing the fluctuation characteristics of each component signal group with the joint motion patterns recorded in the database, the corresponding relationship between each component signal group and the specific joint motion state is determined, and a mapping table between component signals and motion states is formed; According to the mapping table between the component signals and the motion states, the variation pattern of each component signal group in the time dimension is extracted. The nonlinear characteristics presented in the variation pattern are smoothed using a preset signal processing tool to generate a smoothed component signal feature set for further verification of the subsequent correlation relationship; By utilizing the smoothed component signal feature set and combining it with the mapping table of joint motion state, the correlation between the component signal group and the joint motion state is refined by comparing the signal changes in the feature set with the dynamic changes of the motion state one by one, ensuring the accuracy and reliability of the correlation, and completing the feature decomposition and state association goals of the purified electromagnetic field strength signal data set.

[0008] In one embodiment of the present invention, the dynamic position coordinates of the main beam and the trolley are mapped based on the correlation between the component signal group and the joint motion state to obtain high-precision dynamic position data records, including: Based on the correlation between the component signal group and the joint motion state, combined with a preset database of mapping relationships between electromagnetic field intensity changes and position coordinates, a nonlinear regression analysis method is used to map the component signal group to the dynamic position coordinates of the main beam and the trolley to generate preliminary position data records; For the preliminary position data records, Kalman filtering is applied to smooth the dynamic position coordinates to eliminate random errors in the coordinate data and obtain high-precision dynamic position data records; According to the high-precision dynamic position data records, a time series-based position change model is constructed to calculate the displacement and speed of the main beam and the trolley at different time points, and generate dynamic position data records.

[0009] In one embodiment of the present invention, a time series-based position change model is constructed based on the high-precision dynamic position data records, and the displacement and velocity characteristics of the main beam and the trolley at different time points are analyzed to determine the real-time motion state description of each joint, including: Obtaining position coordinate information of the main beam and the trolley at multiple time points from the high-precision dynamic position data records, organizing the position data set based on a time series, performing preliminary processing on the set, and arranging the position data in chronological order to form a continuous time position sequence; For the continuous time position sequence, the displacement of the main beam and the trolley between adjacent time points is calculated, the speed characteristics of each time point are further determined by the ratio of the displacement to the time interval, and a characteristic curve reflecting the change of displacement and speed over time is constructed; From the characteristic curve, the displacement change trend and speed change trend of the main beam and the trolley at different time points are extracted. Combined with the preset joint motion range parameters, it is judged whether the motion state of each joint at the corresponding time point meets the expectation, forming a preliminary motion state description; Based on the preliminary motion state description, combined with the time series position data set, the real-time motion state of each joint is refined and annotated, and the specific motion posture of the main beam and the trolley at each time point is determined. Finally, the position change model based on the time series and the real-time motion state description of each joint are completed.

[0010] In one embodiment of the present invention, a multidimensional constraint set including speed limits and position boundaries is generated based on the real-time motion state description, and a basic parameter set for trajectory planning suitable for complex scenarios is obtained, including: The crane's current speed and position data are obtained from the real-time motion state description. Based on this data, a constraint range with upper and lower speed limits is constructed, and the position boundary range is determined to form an initial set of multi-dimensional constraint conditions. Perform scenario adaptation adjustments on the initial set of multi-dimensional constraints. Combined with the obstacle distribution and operating area restrictions in complex scenarios, speed constraints and position boundaries are refined to form an adapted set of constraints. Extract key parameters from the adapted constraint set to construct a basic trajectory planning parameter set suitable for complex scenarios, ensuring that this parameter set can cover the multi-dimensional constraint requirements of speed limits and position boundaries; Data integration is performed on the basic parameter set for trajectory planning, and it is compared with the real-time motion state description. If it is found that the deviation between the parameter set and the actual state exceeds the preset threshold, the parameter set is locally adjusted to ensure that the final parameter set is suitable for the trajectory planning requirements of complex scenarios.

[0011] In one embodiment of the present invention, based on the trajectory planning basic parameter set, a preset optimization calculation framework is applied to perform iterative adjustments and output the final trajectory planning solution data, including: Initial parameters are obtained from a preset trajectory planning basic parameter set, including the range of motion and speed constraints of the crane joints. A preliminary geometric path of the target trajectory is constructed based on the initial parameters. The positions and angles of the path nodes are adjusted through iterative calculation. It is determined whether the adjusted path meets the preset convergence conditions. If so, preliminary trajectory planning solution data is generated. Based on the preliminary trajectory planning data, the coordinates and speed information of the path nodes are extracted, a path smoothness evaluation function is constructed, and the path nodes are smoothed by the least squares method to generate the smoothed trajectory planning data; Based on the smoothed trajectory planning data, the time series distribution of each path node is calculated. Combined with the dynamic constraints of the crane, the coordinated motion time series of each joint is generated to ensure that the time series meets the continuity requirements. According to the coordinated motion time sequence, a motion instruction set for each joint is generated. The instruction set includes control parameters of joint angle and speed, which are used to drive the crane to execute trajectory motion and output the final trajectory planning scheme data.

[0012] In one embodiment of the present invention, a dynamic feedback mechanism is constructed based on the final trajectory planning scheme data to compare the real-time collected electromagnetic field strength signal with the trajectory planning scheme data. If the comparison result exceeds a preset deviation threshold, the trajectory planning basic parameter set is triggered to be readjusted to obtain updated trajectory planning data, including: Acquiring signal strength data from electromagnetic field strength signals collected in real time, constructing an electromagnetic field strength distribution data set including a timestamp and position coordinates, and performing standardization processing on the electromagnetic field strength distribution data set to generate a standardized electromagnetic field strength distribution matrix; Compare the standardized electromagnetic field intensity distribution matrix with the final trajectory planning scheme data, calculate the deviation value of the two in position coordinates, and generate the deviation distribution vector; For the deviation distribution vector, determine whether it exceeds the preset deviation threshold. If so, adjust the speed and direction parameters in the trajectory planning basic parameter set according to the value of the deviation distribution vector to generate an adjusted parameter set; According to the adjusted parameter set, the preset optimization calculation framework is applied to iteratively update the trajectory planning data to generate updated trajectory planning data.

[0013] In one embodiment of the present invention, generating a coordinated motion instruction set for each joint based on the updated trajectory planning data, driving the crane to perform trajectory motion using the instruction set, and determining state stability during the motion process includes: Obtain the expected position and velocity parameters of each joint from the updated trajectory planning data, discretize the motion trajectory of each joint based on the time series, and generate an initial motion instruction set containing timestamps, position coordinates, and velocity vectors; Based on the initial motion instruction set, a constraint set including speed limits and position boundaries is constructed for the dynamic characteristics of each crane joint, and a coordinated motion instruction set is generated to ensure the synchronization and smoothness of each joint during the movement. The crane control system is driven by a coordinated motion instruction set, which collects real-time displacement and velocity data of the main beam and trolley, builds a time-series-based position change model, and records the real-time motion status of each joint. The displacement and velocity characteristics of the main beam and trolley are extracted from the position change model. Combined with the constraint condition set, the state stability during the motion process is judged to generate a basic parameter set for trajectory planning suitable for complex scenarios.

[0014] To solve the above technical problems, the present invention further provides a bridge crane trajectory planning system for implementing the above method, comprising: The sensor array module collects electromagnetic field strength signal data during the movement of the main beam and the trolley through the electromagnetic field strength detection sensor array, and performs denoising on the electromagnetic field strength signal data to obtain a purified electromagnetic field strength signal data set; a feature extraction module, which extracts features from the purified electromagnetic field strength signal data set and decomposes the data into multiple component signal groups, and determines the correlation between the component signal groups and the joint motion state; A position mapping module maps the dynamic position coordinates of the main beam and the trolley according to the correlation between the component signal group and the joint motion state to obtain high-precision dynamic position data records; A modeling and analysis module, which constructs a time-series position change model based on the high-precision dynamic position data records, analyzes the displacement and velocity characteristics of the main beam and the trolley at different time points, and determines the real-time motion state description of each joint; A constraint generation module generates a multi-dimensional constraint condition set including speed limits and position boundaries based on the real-time motion state description, thereby obtaining a basic parameter set for trajectory planning suitable for complex scenarios; An optimization and adjustment module, which applies a preset optimization calculation framework to iteratively adjust the trajectory planning basic parameter set and outputs the final trajectory planning solution data; A feedback adjustment module, which constructs a dynamic feedback mechanism based on the final trajectory planning scheme data, compares the real-time collected electromagnetic field strength signal with the trajectory planning scheme data, and triggers the readjustment of the trajectory planning basic parameter set if the comparison result exceeds a preset deviation threshold to obtain updated trajectory planning data; The motion control module generates a coordinated motion instruction set for each joint according to the updated trajectory planning data, drives the crane to execute trajectory motion through the instruction set, and determines the state stability during the motion process.

[0015] The above technical solution of the present invention has the following advantages over the prior art: The present invention proposes a trajectory planning method for a bridge crane. A sensor array arranged along the track collects electromagnetic field strength signal data from the main beam and trolley in real time and performs denoising processing on the data to improve signal quality. Subsequently, feature extraction and signal decomposition techniques are used to establish an association between component signal groups and joint motion states, thereby accurately mapping the dynamic position coordinates of the main beam and trolley and forming a high-precision dynamic position data record. This process effectively overcomes the error accumulation and environmental interference problems of traditional encoders or laser ranging, and improves the real-time and robustness of positioning.

[0016] Furthermore, this method constructs a position change model based on high-precision dynamic position data, analyzes displacement and velocity characteristics, adjusts the motion state description in real time, and generates a multi-dimensional constraint condition set to provide an optimization basis for trajectory planning. Through the dynamic feedback mechanism, it can continuously adjust and coordinate motion instructions to ensure that the crane maintains stability and accuracy during operation. Compared with traditional methods, this technical solution realizes the transition from static planning to dynamic optimization, can adaptively adjust the trajectory, reduce vibration and overshoot, and improve operating efficiency.

[0017] From a technical perspective, the beneficial effects of the present invention are mainly reflected in the following aspects: First, the electromagnetic field strength signal acquisition and denoising processing based on the sensor array improves data reliability and reduces the impact of environmental interference; second, through signal decomposition and dynamic position mapping, high-precision real-time positioning is achieved, avoiding the cumulative error problem of traditional methods; finally, the introduction of a dynamic feedback mechanism enables trajectory planning to be optimized in real time, thereby improving the crane's motion smoothness and control accuracy, making it suitable for high-demand industrial application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below based on specific embodiments of the present invention in conjunction with the accompanying drawings, wherein: Figure 1 is a flow chart of the steps of the bridge crane trajectory planning method of the present invention; Figure 2 It is a flow chart of the steps of the electromagnetic field strength signal data acquisition and preprocessing method of the present invention; Figure 3 It is a flowchart of the steps of the method for associating electromagnetic field intensity signal feature decomposition with motion state of the present invention; Figure 4is a flowchart of the steps of the dynamic position coordinate mapping and optimization method of the present invention; Figure 5 is a flowchart of the steps of the real-time motion state modeling and analysis method of the present invention; Figure 6 It is a flowchart of the steps of the multi-dimensional constraint condition generation and optimization method of the present invention; Figure 7 It is a flowchart of the steps of the trajectory planning optimization and generation method of the present invention; Figure 8 is a flow chart of the steps of the dynamic feedback and trajectory adjustment method of the present invention; Figure 9 is a flowchart of the steps of the coordinated motion control and stability determination method of the present invention; Figure 10 It is a structural framework diagram of the bridge crane trajectory planning system of the present invention. DETAILED DESCRIPTION

[0019] The present invention will be further described below with reference to the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it. However, the embodiments are not intended to limit the present invention.

[0020] Reference Figure 1 As shown, the present invention discloses a bridge crane trajectory planning method, comprising the following steps: S10. Collect electromagnetic field strength signal data during the movement of the main beam and the trolley through an electromagnetic field strength detection sensor array, and perform denoising on the electromagnetic field strength signal data to obtain a purified electromagnetic field strength signal data set.

[0021] Reference Figure 2 As shown, the specific steps include: S101. Arrange multiple electromagnetic field strength detection sensors along the track to form a sensor array covering the movement path of the main beam and the trolley. When the main beam and the trolley are moving, collect electromagnetic field strength signal data in real time to obtain an initial electromagnetic field strength signal set.

[0022] In one possible implementation, when multiple electromagnetic field strength detection sensors are arranged along the track, a uniformly spaced arrangement can be selected. For example, sensors are placed on each length of the track to ensure that the array covers the entire movement path of the main beam and the trolley. This can bring the beneficial effect of fully capturing signal changes. Because the electromagnetic field strength will fluctuate with different positions during movement, the real-time collection of the initial electromagnetic field strength signal set will help provide a complete data basis for subsequent processing.

[0023] For example, if the total length of the track is a certain distance, the sensor array collects the signals through wireless transmission to avoid missing key points, thereby improving the reliability of data collection.

[0024] S102 : Processing the initial electromagnetic field strength signal set using a preset filtering mechanism to remove noise interference and generate a purified electromagnetic field strength signal data set.

[0025] Specifically, a preset filtering mechanism is used to process the initial electromagnetic field strength signal set. For example, low-pass filtering is used to remove high-frequency noise interference. This mechanism filters out environmental interference such as electromagnetic wave strays by setting a frequency threshold to generate a purified electromagnetic field strength signal data set. This can have the beneficial effect of improving signal purity, because noise will distort the true electromagnetic field strength value. The purified data more accurately reflects the actual motion state of the main beam and the trolley, supporting the accuracy of subsequent analysis.

[0026] S103 , performing segmentation processing on the purified electromagnetic field strength signal data set, dividing the continuous signal data into signal subsets of multiple time segments, so as to subsequently perform more precise data calibration on the signal subset of each time segment.

[0027] For example, data can be divided into segments of fixed length based on movement speed. This segmentation helps to independently calibrate each subset and avoid overall data deviation. This can bring the beneficial effect of refined processing. Because different time segments may be affected by local interference, segmentation can enable more targeted optimization to ensure the stability of the entire data set.

[0028] S104. Perform data smoothing on each of the divided signal subsets to further eliminate small fluctuations in the signal and obtain a final optimized electromagnetic field strength signal data set for subsequent motion status monitoring of the main beam and the trolley.

[0029] For example, the moving average method is applied to eliminate small fluctuations. This processing is to smooth the curve by calculating the average value of adjacent data points to obtain the final optimized electromagnetic field strength signal data set. This can bring the beneficial effect of enhancing signal smoothness, because small fluctuations may cause position inference errors. When the optimized data set is used for motion status monitoring of the main beam and the trolley, it can provide more reliable input and support the improvement of the accuracy of the overall system.

[0030] From multiple perspectives, the above-mentioned arrangement and acquisition process support each other with the filtering mechanism. For example, the comprehensive coverage of the sensor array ensures rich initial signals, while filtering purifies these signals to prevent noise from affecting the accuracy of segmentation processing. At the same time, the combination of segmentation and smoothing refines the data from the time dimension, jointly supporting the optimization of the final data set. For example, in high-speed motion scenes, smoothing can reduce fluctuations caused by vibration, while segmentation allows for adjustments to specific fragments. Overall, these steps are progressive, forming a complete data processing chain, which is beneficial to achieving the goal of high-precision electromagnetic field strength signal acquisition.

[0031] S20 . Extract features from the purified electromagnetic field strength signal data set and decompose the data into multiple component signal groups, and determine the correlation between the component signal groups and the joint motion state.

[0032] Reference Figure 3 As shown, the specific steps include: S201. Extract time series features and spatial distribution features from the purified electromagnetic field strength signal data set, and use a preset signal decomposition method to split the purified electromagnetic field strength signal data set into multiple independent component signal groups in response to nonlinear changes in signals caused by multi-degree-of-freedom structures, and preliminarily separate signal components related to different motion dimensions.

[0033] Specifically, the process of extracting time series characteristics and spatial distribution characteristics from the purified electromagnetic field strength signal data set can be achieved by analyzing the intensity fluctuations and spatial distribution patterns of the signal at different time points. This helps to identify nonlinear changes caused by multi-degree-of-freedom structures, thereby providing basic data support for subsequent decomposition and helping to improve the accuracy of signal processing.

[0034] For example, separating the signal components related to the main beam motion can effectively reduce interference and ensure that each component signal group focuses on a specific motion dimension, thereby bringing a more reliable preliminary separation effect.

[0035] S202. For the component signal groups, in combination with a pre-established motion state association database, by comparing the fluctuation characteristics of each component signal group with the joint motion patterns recorded in the database, determine the correspondence between each component signal group and the specific joint motion state, and form a mapping table between component signals and motion states.

[0036] Specifically, by matching the fluctuation characteristics with the joint motion patterns, the corresponding relationship is determined to form a mapping table. This can verify the association between the signal and the state from multiple aspects. For example, in the car motion scenario, comparing the signal peak value with the joint rotation pattern can support the accuracy of the association, which is beneficial to avoid misjudgment and enhance the robustness of the system.

[0037] It should be noted that this comparison can also support each other in both time and space. For example, continuous fluctuations in time correspond to changes in position in space, thereby forming a consistent mapping result and bringing a more comprehensive state recognition effect.

[0038] S203. Extract the variation pattern of each component signal group in the time dimension based on the mapping table between the component signals and the motion states. Use a preset signal processing tool to perform smoothing on the nonlinear features presented in the variation pattern to generate a smoothed component signal feature set for further verification of the subsequent correlation relationship.

[0039] It is understandable that this smoothing can remove noise mutations and make the change pattern clearer. For example, when processing the main beam vibration signal, the smoothed feature set is used to verify the association, which is beneficial to improving the reliability of subsequent refinement. This processing considers nonlinear problems from multiple aspects, such as combining historical data patterns for smoothing, which can support the stability of the feature set and provide a more accurate verification basis.

[0040] S204. Utilize the smoothed component signal feature set in combination with the mapping table of the joint motion state, and refine the correlation between the component signal group and the joint motion state by comparing the signal changes in the feature set with the dynamic changes of the motion state one by one, thereby ensuring the accuracy and reliability of the correlation and completing the feature decomposition and state correlation goal of the purified electromagnetic field strength signal data set.

[0041] For example, in a multi-degree-of-freedom structure, comparing the vehicle displacement signal with the joint velocity changes can support each other from the speed and position aspects, forming a strict correlation logic. This is beneficial to achieving the goal of feature decomposition and state association, and overall improving the processing efficiency of the signal data set.

[0042] S30. Map the dynamic position coordinates of the main beam and the trolley according to the correlation between the component signal group and the joint motion state to obtain high-precision dynamic position data records.

[0043] Reference Figure 4 As shown, the specific steps include: S301. Based on the correlation between the component signal group and the joint motion state, combined with the preset electromagnetic field intensity change and position coordinate mapping relationship database, a nonlinear regression analysis method is used to map the component signal group to the dynamic position coordinates of the main beam and the trolley to generate preliminary position data records.

[0044] Specifically, nonlinear regression analysis is a statistical method that fits the nonlinear functional relationship between electromagnetic field strength values ​​and positions. For example, a polynomial function or a neural network model is used to establish a mapping. The corresponding data of historical electromagnetic field strength and coordinates are stored in the database. The parameters are optimized through the least squares method to generate preliminary position data records. This can support the accuracy of position estimation from multiple aspects and is beneficial for capturing nonlinear dynamics in motion.

[0045] S302: Apply Kalman filtering to smooth the dynamic position coordinates for the preliminary position data record, eliminate random errors in the coordinate data, and obtain high-precision dynamic position data records.

[0046] Specifically, Kalman filtering is a recursive estimation algorithm that combines prediction and measurement updates to eliminate random errors. For example, it first predicts the current state, then uses the measurement value to correct the prediction, and iteratively calculates the state covariance to minimize the error, obtaining a high-precision dynamic position data record. This method supports each other from the perspectives of prediction accuracy and noise suppression, which is beneficial to providing more reliable position tracking, especially in vibrating environments.

[0047] S303. Based on the high-precision dynamic position data records, a time series-based position change model is constructed to calculate the displacement and speed of the main beam and the trolley at different time points, and generate dynamic position data records.

[0048] For example, the displacement difference and velocity vector are obtained through the differential method. The model considers the autocorrelation of the time series to predict the trend. This can analyze the motion characteristics, which is beneficial for real-time monitoring and optimized control, and support the overall system performance in terms of displacement stability and velocity consistency, and together form a complete utilization of position data.

[0049] S40. Based on the high-precision dynamic position data records, a time series-based position change model is constructed to analyze the displacement and velocity characteristics of the main beam and the trolley at different time points, and determine the real-time motion state description of each joint.

[0050] Reference Figure 5 As shown, the specific steps include: S401. Obtain the position coordinate information of the main beam and the trolley at multiple time points from the high-precision dynamic position data records, organize them into a time-series-based position data set, perform preliminary processing on the set, and arrange the position data in chronological order to form a continuous time position sequence.

[0051] Specifically, when obtaining the position coordinate information of the main beam and the trolley from high-precision dynamic position data records, the scenario of the crane in actual lifting operations can be considered, where the coordinates of the main beam may be collected in real time by a laser sensor, while the coordinates of the trolley are provided by an encoder. Organizing this into a time-series-based position data set helps capture the continuity of the motion, thereby providing a reliable basis for subsequent analysis. This processing method can improve the accuracy of data processing because it ensures the integrity of the time sequence and avoids errors caused by data confusion.

[0052] S402. For the continuous time position sequence, calculate the displacement of the main beam and the trolley between adjacent time points, further determine the speed characteristics of each time point by the ratio of the displacement to the time interval, and construct a characteristic curve reflecting the change of displacement and speed over time.

[0053] Specifically, when calculating displacement for a continuous time position sequence, for example, the displacement of the main beam from one time point to the next can be obtained through coordinate difference, and the velocity characteristic is obtained by dividing the displacement by the time interval. The purpose of constructing a characteristic curve is to intuitively reflect the law of change, which not only facilitates the identification of abnormal fluctuations, but also provides data support for optimizing crane control. The beneficial effect is to improve the accuracy of motion prediction.

[0054] S403. Extract the displacement change trend and speed change trend of the main beam and the trolley at different time points from the characteristic curve, and combine with the preset joint motion range parameters to determine whether the motion state of each joint at the corresponding time point meets the expectation, so as to form a preliminary motion state description.

[0055] When extracting displacement and speed change trends from characteristic curves, in the example of a crane crossing an obstacle, if the trend shows a sudden increase in speed, combined with the preset joint motion range parameters, it can be used to determine whether the status meets expectations. This can identify potential risks early and form a preliminary description of the motion status. This method supports operational stability from a safety perspective because it converts abstract data into actionable judgment basis.

[0056] S404. Based on the preliminary motion state description, combined with the time series position data set, the real-time motion state of each joint is refined and annotated to determine the specific motion posture of the main beam and the trolley at each time point, and finally complete the construction of the position change model based on the time series and the real-time motion state description of each joint.

[0057] Specifically, when refining the annotation of the preliminary motion state description, for example, combining the position data set to annotate the tilt posture of the main beam and the lateral movement posture of the trolley at a specific time point, and finally completing the construction of the position change model, this refinement can bring more accurate real-time motion state description. The beneficial effect is to enhance the adaptability of the crane in complex environments, and ensure the comprehensiveness and consistency of the description through the mutual support of multiple aspects such as displacement, speed and posture.

[0058] In practical applications, the connectivity of the above process is reflected in the direct input of the acquired position data set into the displacement calculation, and then to the trend extraction and detailed annotation, forming a closed-loop thinking chain. For example, when the data set shows abnormal displacement of the main beam, the velocity characteristic curve will highlight the problem, the trend judgment will confirm the status, and the detailed annotation will finally determine the posture. This supports each other from multiple directions, such as data continuity and status judgment, and jointly enhances the practical value of the model, which is beneficial to reducing operational failures.

[0059] S50 : Generate a multi-dimensional constraint condition set including speed limits and position boundaries based on the real-time motion state description, and obtain a trajectory planning basic parameter set suitable for complex scenarios.

[0060] Reference Figure 6 As shown, the specific steps include: S501. Obtain the current speed and position data of the crane from the real-time motion state description, construct a constraint range including the upper and lower speed limits for these data, and simultaneously determine the position boundary range to form an initial multi-dimensional constraint condition set.

[0061] Specifically, the crane's current speed and position data are obtained from the real-time motion state description. For example, in a construction site scenario, when the crane is moving its boom at a moderate speed, its speed value is obtained as several meters per second and its position coordinates are obtained as specific points. This ensures that subsequent constraint construction is based on accurate and real-time information, which helps improve the real-time and safety of trajectory planning. Based on this data, a constraint range containing upper and lower speed limits is constructed, and the position boundary range is determined at the same time, forming an initial set of multidimensional constraints. For example, the upper speed limit is set to a threshold to avoid collisions, the lower limit ensures smooth operation, and the position boundary is confined to the construction site fence. This process defines a multidimensional space by integrating data points, which helps prevent the crane from exceeding the safe zone and causing accidents.

[0062] S502: Perform scene adaptation adjustment on the initial multi-dimensional constraint condition set, and refine the speed constraint and position boundary in combination with the obstacle distribution and operation area restrictions in the complex scene to form an adapted constraint condition set.

[0063] For example, in a port environment with multiple obstacles, speed constraints can be adjusted to avoid stacked containers, and position boundaries can be refined to avoid ship berthing areas. This can make the constraints more suitable for the actual environment and help improve the crane's operating efficiency and obstacle avoidance capabilities in crowded scenarios.

[0064] S503: Extract key parameters from the adapted constraint condition set to construct a trajectory planning basic parameter set suitable for complex scenarios, ensuring that the parameter set can cover the multi-dimensional constraint requirements of speed limit and position boundary.

[0065] For example, speed upper limit parameters and boundary coordinate parameters are extracted and constructed into a parameter set for path planning. This extraction process involves screening core constraint elements, which is beneficial to simplify planning calculations and maintain comprehensive coverage, making the trajectory more reliable.

[0066] S504: Data integration is performed on the basic parameter set for trajectory planning, and it is compared with the real-time motion state description. If it is found that the deviation between the parameter set and the actual state exceeds a preset threshold, the parameter set is locally adjusted to ensure that the final parameter set is suitable for trajectory planning requirements in complex scenarios.

[0067] For example, in an outdoor scene with wind interference, when the comparison shows a large speed deviation, the upper limit value is adjusted locally to adapt to the change. This can dynamically optimize the parameters, which is beneficial to maintaining motion stability and adapting to sudden environmental factors.

[0068] It should be noted that the above process forms a closed loop from data acquisition to final adjustment. For example, the initial constraint construction relies on real-time data, adaptive adjustment expands its applicability, and parameter extraction and integration further enhance the effectiveness of the constraints. This logical chain ensures that each link supports each other, which is beneficial to the accuracy and robustness of the overall trajectory planning. For example, in a factory with multiple machines collaborating, this method can coordinate the speed and position of multiple cranes to avoid interference.

[0069] S60: Based on the trajectory planning basic parameter set, apply a preset optimization calculation framework to perform iterative adjustments and output final trajectory planning solution data.

[0070] Reference Figure 7 As shown, the specific steps include: S601. Initial parameters are obtained from a preset trajectory planning basic parameter set, including the range of motion and speed constraints of the crane joints. A preliminary geometric path of the target trajectory is constructed based on the initial parameters. The positions and angles of the path nodes are adjusted through iterative calculation. It is determined whether the adjusted path meets the preset convergence conditions. If so, preliminary trajectory planning solution data is generated.

[0071] Specifically, the process of obtaining initial parameters from the preset trajectory planning basic parameter set can be understood as first identifying the motion range and speed constraints of the crane joints. These parameters serve as basic inputs to ensure that joint overload or speed limit is avoided during trajectory construction. This can improve the trajectory safety, because if these constraints are ignored, the crane may jitter or malfunction during movement.

[0072] Specifically, a path framework is formed by connecting the straight or curved segments of the starting point and the end point, and then the positions and angles of the path nodes are adjusted through iterative calculation. For example, during the adjustment, the distance between nodes is gradually optimized to make the path closer to the ideal curve. It is judged whether the adjusted path meets the preset convergence conditions. If so, preliminary trajectory planning scheme data is generated. The purpose of this iterative adjustment is to gradually approach the optimal path, bring about improved trajectory efficiency, and avoid energy waste caused by directly using a rough path.

[0073] S602: Based on the preliminary trajectory planning scheme data, the coordinates and speed information of the path nodes are extracted, a path smoothness evaluation function is constructed, and the path nodes are smoothed by the least squares method to generate smoothed trajectory planning scheme data.

[0074] Specifically, after extracting the coordinates and speed information of the path nodes based on the preliminary trajectory planning scheme data, the process of constructing the path smoothness evaluation function is actually to use the coordinates and speed as variables. The evaluation function measures the curvature change between nodes. For example, if the path has sharp turns, the function value will be higher. The path nodes are smoothed by the least squares method. The specific method is to fit a curve with minimum error to generate smoothed trajectory planning scheme data. The beneficial effect of this is to reduce crane vibration, ensure smooth movement, and support the reliability of long-term operation.

[0075] S603. Calculate the time series distribution of each path node for the smoothed trajectory planning data, generate the coordinated motion time series of each joint in combination with the dynamic constraints of the crane, and ensure that the time series meets the continuity requirement.

[0076] Specifically, the time series allocation of each path node is calculated based on the smoothed trajectory planning scheme data. Combined with the dynamic constraints of the crane, such as acceleration limits, the coordinated motion time series of each joint is generated, and it is determined that the time series meets the continuity requirements. For example, when allocating time, the speed between adjacent nodes is ensured to be continuous and sudden changes are avoided. This can enhance coordination, because discontinuous time series may cause joint jams and affect overall execution efficiency.

[0077] S604: Generate a motion instruction set for each joint based on the coordinated motion time sequence. The instruction set includes control parameters of joint angles and speeds, and is used to drive the crane to execute trajectory motion and output final trajectory planning solution data.

[0078] Specifically, the process of generating motion instruction sets for each joint based on the coordinated motion time series includes converting the time series into control parameters of joint angles and speeds, which are used to drive the crane to execute trajectory motion and finally output the final trajectory planning scheme data. The role of this generated instruction set is to convert abstract plans into executable commands, bringing about an improvement in the actual motion accuracy. For example, in complex environments, the instruction set can support obstacle avoidance operations and support the application of multi-task scenarios.

[0079] It should be noted that the above steps support each other. For example, the adjustment of the initial path provides the basis for subsequent smoothing, and the smoothed data is the input for time series calculation, ensuring the consistency of the entire process from parameter acquisition to command output, and jointly achieving the goal of trajectory optimization.

[0080] S70: Based on the final trajectory planning scheme data, a dynamic feedback mechanism is established to compare the real-time collected electromagnetic field strength signal with the trajectory planning scheme data. If the comparison result exceeds a preset deviation threshold, the trajectory planning basic parameter set is triggered to readjust to obtain updated trajectory planning data; Reference Figure 8As shown, the specific steps include: S701. Acquire signal strength data from electromagnetic field strength signals collected in real time, construct an electromagnetic field strength distribution data set including a timestamp and position coordinates, and perform standardization processing on the electromagnetic field strength distribution data set to generate a standardized electromagnetic field strength distribution matrix.

[0081] Specifically, in the process of real-time collection of electromagnetic field strength signals, key indicators are extracted from the signal strength data, such as the radio wave intensity values ​​captured by sensors. These values ​​are combined with timestamps and location coordinates to form an electromagnetic field strength distribution dataset. This construction method helps to capture the changes in the signal in the time and space dimensions, thereby providing a complete foundation for subsequent standardization processing.

[0082] It should be noted that normalization involves mapping the intensity values ​​in a dataset to a uniform scale, for example by subtracting the mean and dividing by the standard deviation, to ensure that signals at different locations are comparable. The resulting normalized electromagnetic field intensity distribution matrix eliminates dimensional differences, which helps improve the accuracy of the comparison. This process enhances the robustness of the data, allowing the system to more reliably identify signal patterns in complex environments. For example, in urban environments, where signals may be interfered with by buildings, normalization can highlight true deviations rather than noise, thereby improving the adaptability of trajectory planning.

[0083] S702: Compare the standardized electromagnetic field intensity distribution matrix with the final trajectory planning solution data, calculate the deviation value between the two in position coordinates, and generate a deviation distribution vector.

[0084] For example, for each coordinate point, the difference between the corresponding electromagnetic field strength value in the matrix and the preset value of the planning scheme is calculated and summarized into a deviation distribution vector. This vector represents the degree of deviation between the actual signal distribution and the plan, which is helpful for quantifying inconsistency.

[0085] It should be noted that this comparison process can be verified from multiple aspects, such as checking signal fluctuations from a time series perspective, or evaluating coverage uniformity from a spatial perspective. The deviation distribution vector generated in this way not only supports the judgment threshold, but also reveals the potential causes of environmental changes. For example, if the vector shows that the deviation in a specific area increases, it indicates that the planning scheme needs to be optimized to cope with sudden interference, thereby ensuring the real-time effectiveness of the trajectory.

[0086] S703 : Determine whether the deviation distribution vector exceeds a preset deviation threshold. If so, adjust the speed and direction parameters in the trajectory planning basic parameter set according to the value of the deviation distribution vector to generate an adjusted parameter set.

[0087] For example, in high-deviation areas, speed parameters can be reduced to increase signal acquisition time, or direction parameters can be modified to avoid areas with weak electromagnetic fields, generating an adjusted parameter set. This adjustment dynamically responds to actual signal feedback and helps maintain the optimal trajectory.

[0088] S704: Apply a preset optimization calculation framework to iteratively update the trajectory planning data according to the adjusted parameter set to generate updated trajectory planning data.

[0089] For example, the framework evaluates the impact of parameters on the trajectory through multiple cycles until the convergence conditions are met and outputs updated data. This iterative process includes initial parameter input, deviation minimization calculation and path replanning steps in detail, which is beneficial for generating more accurate trajectory data.

[0090] S80 , generating a coordinated motion instruction set for each joint according to the updated trajectory planning data, driving the crane to execute trajectory motion through the instruction set, and determining state stability during the motion process.

[0091] Reference Figure 9 As shown, the specific steps include: S801. Obtain the expected position and velocity parameters of each joint from the updated trajectory planning data, discretize the motion trajectory of each joint based on the time series, and generate an initial motion instruction set including a timestamp, position coordinates, and velocity vector.

[0092] Specifically, when obtaining the expected position and velocity parameters of each joint from the updated trajectory planning data, the actual operation of the crane in the warehouse environment can be taken into consideration. For example, the main beam needs to move horizontally to the specified shelf position, while the trolley needs to adjust its height vertically. In this way, through time series-based discretization processing, the continuous trajectory can be decomposed into discrete points at multiple timestamps, thereby generating an initial motion instruction set, which is beneficial to improving the accuracy and executability of the instructions.

[0093] Specifically, this discretization process involves dividing the trajectory curve into equally spaced time periods, calculating the position coordinates and velocity vector in each segment, ensuring that the instruction set covers the entire motion path, thereby avoiding calculation errors in continuous motion and bringing more stable control effects; if the trajectory planning data is updated to show that the main beam needs to move 5 meters within 10 seconds, it is discretized into one point per second, and instructions containing timestamps such as 0 seconds, 1 second, etc. are generated, which is beneficial to subsequent coordination.

[0094] It should be noted that this method can also adapt to sudden changes. For example, when data updates reflect the appearance of obstacles, parameters can be adjusted in time to maintain safety.

[0095] S802: Based on the initial motion instruction set and targeting the dynamic characteristics of each crane joint, a constraint condition set including speed limits and position boundaries is constructed to generate a coordinated motion instruction set to ensure synchronization and smoothness of each joint during motion.

[0096] For example, the inertia of the main beam and the load response of the trolley can introduce speed limits such as a maximum of 2 meters per second and position boundaries such as not exceeding the end of the track. This generates a coordinated motion instruction set to ensure synchronization, which is beneficial to preventing jitter caused by conflicts between joints.

[0097] Among them: dynamic characteristics refer to the torque distribution of the joint during acceleration. The instructions are adjusted through the constraint set to match the speed of the main beam and the trolley. For example, the speed of the trolley does not exceed 50% of the main beam, thereby achieving smooth movement, bringing higher operating efficiency and extending the life of the equipment.

[0098] Specifically, in a bridge construction scenario, if the instruction set is not constrained, the rapid movement of the main beam may cause the trolley to become unstable. However, after adding boundaries, the instruction set coordinates the joints to maintain overall balance, which is beneficial to reliability in complex environments.

[0099] S803. Drive the crane control system by coordinating the motion instruction set, collect the displacement and speed data of the main beam and trolley in real time, build a position change model based on time series, and record the real-time motion status of each joint.

[0100] Specifically, the displacement and speed of the main beam and trolley can be recorded every second during the operation of the crane. For example, sensors can be used to capture position changes and a time-series-based position change model can be constructed. This model organizes the collected data into a sequence in chronological order and records the displacement curve from the starting point to the end point, which is helpful in capturing dynamic characteristics.

[0101] The model building process involves fitting the collected displacement data into a functional form and analyzing the time points at which velocity peaks occur, thereby recording the real-time motion state and enabling timely detection of anomalies, such as sudden speed changes that indicate potential faults.

[0102] S804. Extract the displacement and velocity characteristics of the main beam and the trolley from the position change model, combine them with the constraint condition set, judge the state stability during the movement process, and generate a basic parameter set for trajectory planning suitable for complex scenarios.

[0103] For example, the average speed and maximum displacement deviation of the main beam are extracted. If the deviation is less than the boundary threshold, it is judged to be stable, thereby generating a basic parameter set for trajectory planning, which is beneficial for applications in complex scenarios such as multi-obstacle environments.

[0104] Specifically, the extraction process involves calculating feature values ​​from the model sequence, such as the variance of speed, combining it with constraints such as the position not exceeding 5 meters, judging whether it is stable, and generating a parameter set including an optimized speed cap, resulting in more robust planning.

[0105] Specifically, in factory automation, if the model shows that the vehicle's speed characteristics exceed the limit and are judged to be unstable, the parameter set is adjusted to reduce the speed to ensure state stability during movement.

[0106] Reference Figure 10 As shown, in order to implement the above-mentioned bridge crane trajectory planning method, the present invention also provides a bridge crane trajectory planning system for implementing the above-mentioned trajectory planning method, comprising: The sensor array module collects electromagnetic field strength signal data during the movement of the main beam and the trolley through the electromagnetic field strength detection sensor array, and performs denoising on the electromagnetic field strength signal data to obtain a purified electromagnetic field strength signal data set; a feature extraction module, which extracts features from the purified electromagnetic field strength signal data set and decomposes the data into multiple component signal groups, and determines the correlation between the component signal groups and the joint motion state; A position mapping module maps the dynamic position coordinates of the main beam and the trolley according to the correlation between the component signal group and the joint motion state to obtain high-precision dynamic position data records; A modeling and analysis module, which constructs a time-series position change model based on the high-precision dynamic position data records, analyzes the displacement and velocity characteristics of the main beam and the trolley at different time points, and determines the real-time motion state description of each joint; A constraint generation module generates a multi-dimensional constraint condition set including speed limits and position boundaries based on the real-time motion state description, thereby obtaining a basic parameter set for trajectory planning suitable for complex scenarios; An optimization and adjustment module, which applies a preset optimization calculation framework to iteratively adjust the trajectory planning basic parameter set and outputs the final trajectory planning solution data; A feedback adjustment module, which constructs a dynamic feedback mechanism based on the final trajectory planning scheme data, compares the real-time collected electromagnetic field strength signal with the trajectory planning scheme data, and triggers the readjustment of the trajectory planning basic parameter set if the comparison result exceeds a preset deviation threshold to obtain updated trajectory planning data; The motion control module generates a coordinated motion instruction set for each joint according to the updated trajectory planning data, drives the crane to execute trajectory motion through the instruction set, and determines the state stability during the motion process.

[0107] Obviously, the above embodiments are merely examples for clarity of explanation and are not intended to limit the implementation methods. Those skilled in the art will appreciate that other variations or modifications can be made based on the above description. It is not necessary and impossible to enumerate all implementation methods here. Obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A bridge crane trajectory planning method, characterized by: include: The electromagnetic field strength detection sensor array is used to collect electromagnetic field strength signal data during the movement of the main beam and the trolley, and the electromagnetic field strength signal data is denoised to obtain a purified electromagnetic field strength signal data set; Extracting features from the purified electromagnetic field strength signal data set and decomposing the data set into a plurality of component signal groups, and determining correlations between the component signal groups and joint motion states; According to the correlation between the component signal group and the joint motion state, the dynamic position coordinates of the main beam and the trolley are mapped to obtain high-precision dynamic position data records; Based on the high-precision dynamic position data records, a time-series-based position change model is constructed to analyze the displacement and velocity characteristics of the main beam and the trolley at different time points, and determine the real-time motion state description of each joint; Based on the real-time motion state description, a multi-dimensional constraint condition set including speed limit and position boundary is generated to obtain a basic parameter set of trajectory planning suitable for complex scenarios; According to the trajectory planning basic parameter set, a preset optimization calculation framework is applied to perform iterative adjustments and output the final trajectory planning solution data; Based on the final trajectory planning scheme data, a dynamic feedback mechanism is constructed to compare the real-time collected electromagnetic field strength signal with the trajectory planning scheme data. If the comparison result exceeds a preset deviation threshold, the trajectory planning basic parameter set is triggered to readjust to obtain updated trajectory planning data; According to the updated trajectory planning data, a coordinated motion instruction set of each joint is generated, and the crane is driven to perform trajectory motion through the instruction set to determine the state stability during the motion process.

2. The bridge crane trajectory planning method according to claim 1, characterized in that: The electromagnetic field strength detection sensor array is used to collect electromagnetic field strength signal data during the movement of the main beam and the trolley, and the electromagnetic field strength signal data is denoised to obtain a purified electromagnetic field strength signal data set, including: Multiple electromagnetic field strength detection sensors are arranged along the track to form a sensor array covering the movement path of the main beam and the trolley. When the main beam and the trolley are moving, the electromagnetic field strength signal data is collected in real time to obtain the initial electromagnetic field strength signal set; For the initial electromagnetic field strength signal set, a preset filtering mechanism is used to process the signal to remove noise interference and generate a purified electromagnetic field strength signal data set; The purified electromagnetic field strength signal data set is segmented to divide the continuous signal data into signal subsets of multiple time segments, so that more precise data calibration can be performed on the signal subset of each time segment later; For the divided signal subsets, data smoothing processing is performed one by one to further eliminate small fluctuations in the signal and obtain the final optimized electromagnetic field strength signal data set for subsequent motion status monitoring of the main beam and trolley.

3. The bridge crane trajectory planning method according to claim 1, wherein: Extracting features from the purified electromagnetic field strength signal data set and decomposing the data set into a plurality of component signal groups, and determining the correlation between the component signal groups and the joint motion state, including: Extracting time series features and spatial distribution features from the purified electromagnetic field strength signal dataset, and using a preset signal decomposition method to split the purified electromagnetic field strength signal dataset into multiple independent component signal groups in response to nonlinear changes in the signal caused by the multi-degree-of-freedom structure, thereby preliminarily separating signal components related to different motion dimensions; For the component signal groups, in combination with a pre-established motion state association database, by comparing the fluctuation characteristics of each component signal group with the joint motion patterns recorded in the database, the corresponding relationship between each component signal group and the specific joint motion state is determined, and a mapping table between component signals and motion states is formed; According to the mapping table between the component signals and the motion states, the variation pattern of each component signal group in the time dimension is extracted. The nonlinear characteristics presented in the variation pattern are smoothed using a preset signal processing tool to generate a smoothed component signal feature set for further verification of the subsequent correlation relationship; By utilizing the smoothed component signal feature set and combining it with the mapping table of joint motion state, the correlation between the component signal group and the joint motion state is refined by comparing the signal changes in the feature set with the dynamic changes of the motion state one by one, ensuring the accuracy and reliability of the correlation, and completing the feature decomposition and state association goals of the purified electromagnetic field strength signal data set.

4. The bridge crane trajectory planning method according to claim 1, wherein: Based on the correlation between the component signal group and the joint motion state, the dynamic position coordinates of the main beam and the trolley are mapped to obtain high-precision dynamic position data records, including: Based on the correlation between the component signal group and the joint motion state, combined with a preset database of mapping relationships between electromagnetic field intensity changes and position coordinates, a nonlinear regression analysis method is used to map the component signal group to the dynamic position coordinates of the main beam and the trolley to generate preliminary position data records; For the preliminary position data records, Kalman filtering is applied to smooth the dynamic position coordinates to eliminate random errors in the coordinate data and obtain high-precision dynamic position data records; According to the high-precision dynamic position data records, a time series-based position change model is constructed to calculate the displacement and speed of the main beam and the trolley at different time points, and generate dynamic position data records.

5. The bridge crane trajectory planning method according to claim 1, characterized in that: Based on the high-precision dynamic position data records, a time-series-based position change model is constructed to analyze the displacement and velocity characteristics of the main beam and the trolley at different time points, and determine the real-time motion state description of each joint, including: Obtaining position coordinate information of the main beam and the trolley at multiple time points from the high-precision dynamic position data records, organizing the position data set based on a time series, performing preliminary processing on the set, and arranging the position data in chronological order to form a continuous time position sequence; For the continuous time position sequence, the displacement of the main beam and the trolley between adjacent time points is calculated, the speed characteristics of each time point are further determined by the ratio of the displacement to the time interval, and a characteristic curve reflecting the change of displacement and speed over time is constructed; From the characteristic curve, the displacement change trend and speed change trend of the main beam and the trolley at different time points are extracted. Combined with the preset joint motion range parameters, it is judged whether the motion state of each joint at the corresponding time point meets the expectation, forming a preliminary motion state description; Based on the preliminary motion state description, combined with the time series position data set, the real-time motion state of each joint is refined and annotated, and the specific motion posture of the main beam and the trolley at each time point is determined. Finally, the position change model based on the time series and the real-time motion state description of each joint are completed.

6. The bridge crane trajectory planning method according to claim 1, characterized in that: Based on the real-time motion state description, a multi-dimensional constraint set including speed limits and position boundaries is generated to obtain a basic parameter set for trajectory planning suitable for complex scenarios, including: The crane's current speed and position data are obtained from the real-time motion state description. Based on this data, a constraint range with upper and lower speed limits is constructed, and the position boundary range is determined to form an initial set of multi-dimensional constraint conditions. Perform scenario adaptation adjustments on the initial set of multi-dimensional constraints. Combined with the obstacle distribution and operating area restrictions in complex scenarios, speed constraints and position boundaries are refined to form an adapted set of constraints. Extract key parameters from the adapted constraint set to construct a basic trajectory planning parameter set suitable for complex scenarios, ensuring that this parameter set can cover the multi-dimensional constraint requirements of speed limits and position boundaries; Data integration is performed on the basic parameter set for trajectory planning, and it is compared with the real-time motion state description. If it is found that the deviation between the parameter set and the actual state exceeds the preset threshold, the parameter set is locally adjusted to ensure that the final parameter set is suitable for the trajectory planning requirements of complex scenarios.

7. The bridge crane trajectory planning method according to claim 1, characterized in that: Based on the trajectory planning basic parameter set, the preset optimization calculation framework is applied to perform iterative adjustments and output the final trajectory planning solution data, including: Initial parameters are obtained from a preset trajectory planning basic parameter set, including the range of motion and speed constraints of the crane joints. A preliminary geometric path of the target trajectory is constructed based on the initial parameters. The positions and angles of the path nodes are adjusted through iterative calculation. It is determined whether the adjusted path meets the preset convergence conditions. If so, preliminary trajectory planning solution data is generated. Based on the preliminary trajectory planning data, the coordinates and speed information of the path nodes are extracted, a path smoothness evaluation function is constructed, and the path nodes are smoothed by the least squares method to generate the smoothed trajectory planning data; Based on the smoothed trajectory planning data, the time series distribution of each path node is calculated. Combined with the dynamic constraints of the crane, the coordinated motion time series of each joint is generated to ensure that the time series meets the continuity requirements. According to the coordinated motion time sequence, a motion instruction set for each joint is generated. The instruction set includes control parameters of joint angle and speed, which are used to drive the crane to execute trajectory motion and output the final trajectory planning scheme data.

8. The bridge crane trajectory planning method according to claim 1, characterized in that: Based on the final trajectory planning data, a dynamic feedback mechanism is constructed to compare the real-time collected electromagnetic field strength signal with the trajectory planning data. If the comparison result exceeds the preset deviation threshold, the trajectory planning basic parameter set is triggered to readjust, and the updated trajectory planning data is obtained, including: Acquiring signal strength data from electromagnetic field strength signals collected in real time, constructing an electromagnetic field strength distribution data set including a timestamp and position coordinates, and performing standardization processing on the electromagnetic field strength distribution data set to generate a standardized electromagnetic field strength distribution matrix; Compare the standardized electromagnetic field intensity distribution matrix with the final trajectory planning scheme data, calculate the deviation value of the two in position coordinates, and generate the deviation distribution vector; For the deviation distribution vector, determine whether it exceeds the preset deviation threshold. If so, adjust the speed and direction parameters in the trajectory planning basic parameter set according to the value of the deviation distribution vector to generate an adjusted parameter set; According to the adjusted parameter set, the preset optimization calculation framework is applied to iteratively update the trajectory planning data to generate updated trajectory planning data.

9. The bridge crane trajectory planning method according to claim 1, characterized in that: Generate a coordinated motion instruction set for each joint based on the updated trajectory planning data, drive the crane to perform trajectory motion using the instruction set, and determine the state stability during the motion process, including: Obtain the expected position and velocity parameters of each joint from the updated trajectory planning data, discretize the motion trajectory of each joint based on the time series, and generate an initial motion instruction set containing timestamps, position coordinates, and velocity vectors; Based on the initial motion instruction set, a constraint set including speed limits and position boundaries is constructed for the dynamic characteristics of each crane joint, and a coordinated motion instruction set is generated to ensure the synchronization and smoothness of each joint during the movement. The crane control system is driven by a coordinated motion instruction set, which collects real-time displacement and velocity data of the main beam and trolley, builds a time-series-based position change model, and records the real-time motion status of each joint. The displacement and velocity characteristics of the main beam and trolley are extracted from the position change model. Combined with the constraint condition set, the state stability during the motion process is judged to generate a basic parameter set for trajectory planning suitable for complex scenarios.

10. A bridge crane trajectory planning system, used to implement the method according to any one of claims 1 to 9, characterized in that: include: The sensor array module collects electromagnetic field strength signal data during the movement of the main beam and the trolley through the electromagnetic field strength detection sensor array, and performs denoising on the electromagnetic field strength signal data to obtain a purified electromagnetic field strength signal data set; a feature extraction module, which extracts features from the purified electromagnetic field strength signal data set and decomposes the data into multiple component signal groups, and determines the correlation between the component signal groups and the joint motion state; A position mapping module maps the dynamic position coordinates of the main beam and the trolley according to the correlation between the component signal group and the joint motion state to obtain high-precision dynamic position data records; A modeling and analysis module, which constructs a time-series position change model based on the high-precision dynamic position data records, analyzes the displacement and velocity characteristics of the main beam and the trolley at different time points, and determines the real-time motion state description of each joint; A constraint generation module generates a multi-dimensional constraint condition set including speed limits and position boundaries based on the real-time motion state description, thereby obtaining a basic parameter set for trajectory planning suitable for complex scenarios; An optimization and adjustment module, which applies a preset optimization calculation framework to iteratively adjust the trajectory planning basic parameter set and outputs the final trajectory planning solution data; A feedback adjustment module, which constructs a dynamic feedback mechanism based on the final trajectory planning scheme data, compares the real-time collected electromagnetic field strength signal with the trajectory planning scheme data, and triggers the readjustment of the trajectory planning basic parameter set if the comparison result exceeds a preset deviation threshold to obtain updated trajectory planning data; The motion control module generates a coordinated motion instruction set for each joint according to the updated trajectory planning data, drives the crane to execute trajectory motion through the instruction set, and determines the state stability during the motion process.

Images