A method and device for correcting deviation of a stacker, an electronic device and a storage medium

Abstract

The present application relates to the technical field of intelligent control, and provides a stacking machine operation deviation correction method and device, electronic equipment and storage medium, the method comprises the following steps: in response to a target position parking instruction, collecting real-time deformation data between the actual track of a preset distance and the pre-established reference track map; calling the predicted deformation data of the preset distance in the same period, obtaining the predicted deviation based on the real-time deformation data and the predicted deformation data; correcting the predicted deformation data of the interval track based on the predicted deviation to obtain the interval deformation data, compensating the deviation of the target position according to the interval deformation data and the real-time deformation data; and driving the stacking machine to run according to the compensated target position. The present application realizes online continuous monitoring and dynamic real-time compensation of track deformation, realizes deformation pre-compensation of the unknown section in front, has the ability of active prediction by combining with environmental information to predict deformation trend, and enables the stacking machine to maintain high-precision positioning when the track slowly deforms.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and more specifically, to a method, apparatus, electronic device, and storage medium for correcting the operation of a stacker crane. Background Technology

[0002] As the core equipment of automated storage and retrieval systems (AS / RS), the horizontal running accuracy of stacker cranes directly determines the accuracy and efficiency of storage and retrieval operations. In practical engineering applications, factors such as foundation settlement, long-term load, and temperature changes can cause horizontal bending and vertical elevation changes in the stacker crane's running track. This leads to additional positioning errors during operation and can even cause problems such as jamming of the traveling mechanism, abnormal noise, and accelerated wheel and rail wear. Therefore, achieving precise correction during stacker crane operation is of great significance for ensuring the safety of goods storage and retrieval and improving warehousing efficiency.

[0003] Currently, stacker cranes commonly use laser rangefinders or encoders for horizontal positioning, achieving an accuracy of ±3mm. Existing technologies typically rely on periodic manual measurement and adjustment of the track to address track deformation. This involves periodically checking the track geometry using specialized measuring equipment and making mechanical adjustments based on the results. However, this periodic manual measurement method is time-consuming and labor-intensive, and track deformation cannot be detected in time during the measurement intervals. When track deformation exceeds the allowable range, the stacker crane's positioning accuracy will be affected, consequently impacting the safety of goods storage and retrieval. Summary of the Invention

[0004] The problem solved by this invention is how to achieve precise operation of a stacker crane.

[0005] To address the aforementioned problems, this invention provides a stacker crane operation correction method, apparatus, electronic device, and storage medium.

[0006] In a first aspect, the present invention provides a method for correcting the movement of a stacker crane, comprising: In response to a docking command at a target location, real-time deformation data is collected between the actual trajectory of the track at a preset distance and a pre-established baseline track map. The stacker crane obtains the actual trajectory of the track by acquiring track information in real time during operation. The preset distance is less than the target distance between the starting point and the target location. Retrieve the predicted deformation data of the preset distance within the same time period, and obtain the prediction deviation based on the real-time deformation data and the predicted deformation data, wherein the predicted deformation data is predicted based on the orbital environment information; Based on the predicted deformation data of the predicted deviation correction spacing track, the spacing deformation data is obtained. The target position is compensated for deviation based on the spacing deformation data and the real-time deformation data. The spacing track is the track between the target position and the current mileage point. The stacker crane is driven to run at the compensated target position.

[0007] Optionally, the acquisition of real-time deformation data between the actual trajectory of the track at a preset distance and the pre-established reference track map includes: During the process of the stacker crane running the preset distance, the mileage data of the stacker crane and the local tilt data of the track are collected in real time as the actual trajectory of the track; Based on the mileage data and the tilt data, the deformation deviation between the actual trajectory of the track and the reference track map is determined as the deformation data.

[0008] Optionally, the deformation data includes elevation deviation and horizontal deviation; determining the deformation deviation between the actual track shape and the reference track map based on the mileage data and the tilt data as the deformation data includes: The elevation change value of the corresponding track position is obtained based on the tilt data. The historical elevation curve is updated based on the elevation change value and the mileage data to obtain the actual elevation curve. The historical elevation curve is the elevation curve in the historical track map obtained from the previous measurement. The elevation deviation is obtained by comparing the actual elevation curve of the track with the reference elevation curve in the reference track map. The mileage error is obtained by comparing the mileage data with the straight mileage data. The deviation direction is determined based on the tilt data. The horizontal deviation of the track is derived by fusing the mileage error, the tilt data, and the deviation direction. The straight mileage is obtained by collecting the straight distance between the starting point and the ending point of the track using a laser rangefinder.

[0009] Optionally, the step of predicting the predicted deformation data based on orbital environment information includes: The orbital environment information is input into a pre-trained time-series prediction model to predict the orbital deformation trend in future periods, thus obtaining the predicted deformation data. The orbital environment information includes temperature, ground settlement rate, operating load, and historical deformation deviation. The time-series prediction model is trained based on historical environmental information and historical orbital maps.

[0010] Optionally, obtaining the spacing deformation data based on the predicted deformation data of the spacing track after correcting the predicted deviation includes: The predicted deviation is input into a pre-trained correction model to obtain the spacing deformation data of the spacing track. The correction model is trained based on historical prediction bias and historical spacing deformation data.

[0011] Optionally, the step of compensating for the deviation of the target position based on the spacing deformation data and the real-time deformation data includes: The sum of the spacing deformation data and the real-time deformation data is obtained to obtain the comprehensive deformation data; The target position is compensated for based on the comprehensive variable data as a deviation.

[0012] Optionally, the stacker crane operation correction method further includes: In response to real-time deformation data exceeding a preset deviation threshold, an early warning is issued, wherein the preset deviation threshold includes a first deviation threshold and a second deviation threshold; When the absolute value of the horizontal deviation exceeds the first deviation threshold, and / or the absolute value of the elevation deviation exceeds the second deviation threshold, a real-time alarm signal is issued; The predicted deformation data includes predicted horizontal deviation and predicted elevation deviation. When the predicted horizontal deviation exceeds the first deviation threshold and / or the absolute value of the predicted elevation deviation exceeds the second deviation threshold, an early warning signal is issued, and a maintenance cycle recommendation is generated based on the predicted deformation data.

[0013] In a second aspect, the present invention provides a stacker crane operation correction device, comprising: The measurement module is used to respond to the stop command at the target position and acquire real-time deformation data between the actual trajectory of the track at a preset distance and the pre-established reference track map. The stacker crane acquires track information in real time to obtain the actual trajectory of the track, and the preset distance is less than the target distance between the starting point and the target position. The deviation module is used to retrieve the predicted deformation data of the preset distance in the same time period, and to obtain the predicted deviation based on the real-time deformation data and the predicted deformation data, wherein the predicted deformation data is predicted based on the orbital environment information. The compensation module is used to obtain spacing deformation data based on the predicted deformation data of the spacing track, and to perform deviation compensation on the target position according to the spacing deformation data and the real-time deformation data, wherein the spacing track is the track between the target position and the current mileage point; The correction module is used to drive the stacker crane to run according to the compensated target position.

[0014] Thirdly, the present invention provides an electronic device, including a memory and a processor; The memory is used to store computer programs; The processor is configured to implement the stacker crane operation correction method as described in the first aspect when executing the computer program.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the stacker crane operation correction method as described in the first aspect.

[0016] The beneficial effects of the stacker crane operation correction method of the present invention are as follows: By responding to the stop command at the target position, real-time deformation data between the actual track trajectory and the reference track map within a preset distance is acquired. Compared with the existing technology that relies on periodic manual measurement of track deformation and cannot detect deformation in time during the measurement interval, the method acquires track deformation data in real time during the operation of the stacker crane, realizing online continuous monitoring of track deformation. Because the preset distance is reasonably set to be less than the target distance between the starting point and the target position, the stacker crane can acquire track deformation information of this section in advance before reaching the target position, reserving sufficient processing time for subsequent compensation and avoiding the problem of not being able to compensate in time due to the lag in real-time data acquisition. Predicted deformation data of the same preset distance within the same time period is retrieved, and the predicted deviation is obtained based on the real-time deformation data and the predicted deformation data. Compared to existing technologies that rely solely on measured data for correction and cannot predict future deformation trends, this method compares real-time acquired data with predicted data to accurately assess the current accuracy of the prediction model and quantify the prediction deviation. This deviation reflects the systematic error of the prediction model in the current time period and segment, providing a reliable basis for subsequent correction of the spacing track prediction data and making the compensation calculation more precise. Based on the predicted deformation data of the spacing track corrected by the prediction deviation, spacing deformation data is obtained. Based on the spacing deformation data and real-time deformation data, deviation compensation is performed on the target position. Using the prediction deviation calculated at a preset distance, the predicted deformation data of the spacing track (i.e., the segment not yet reached) is corrected in reverse, achieving pre-compensation for deformation in unknown segments ahead. Simultaneously, the spacing deformation data is fused with real-time deformation data, comprehensively considering both current measured information and future prediction information, making the compensation decision more comprehensive and reliable. The stacker crane is driven to run according to the compensated target position, using the compensated target position as the final position command of the servo drive. This ensures that the stacker crane can accurately stop at the target position even when the track deforms, effectively guaranteeing the accuracy and safety of storage and retrieval operations.

[0017] This invention achieves online continuous monitoring of track deformation by acquiring real-time deformation data within a preset distance in response to a target position stopping command. Track deformation information for a given section can be obtained before the stacker crane reaches the target position, allowing sufficient processing time for subsequent compensation. By retrieving predicted deformation data at the preset distance and comparing it with real-time deformation data to obtain the prediction deviation, the current accuracy of the prediction model can be accurately assessed, providing a reliable basis for correcting the spacing track data. By correcting the predicted deformation data of the spacing track based on the prediction deviation, pre-compensation for deformation in sections not yet reached is achieved. Simultaneously, the spacing deformation data is fused with real-time deformation data, comprehensively considering both current measured information and future prediction information. By driving the stacker crane to operate at the compensated target position, the stacker crane can still accurately stop at the target position even when track deformation occurs, ensuring the accuracy and safety of storage and retrieval operations. This invention enables online continuous monitoring and dynamic real-time compensation of track deformation, achieves pre-compensation for deformation in unknown sections ahead, and combines environmental information to predict deformation trends, thus possessing proactive prediction capabilities. This allows the stacker crane to maintain high-precision positioning even when the track undergoes slow deformation, improving the accuracy of storage and retrieval operations and the reliability of system operation, while reducing the cost of manual periodic measurement and maintenance. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the stacker crane operation correction method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the stacker crane operation correction device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0019] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0020] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0021] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to"; the term "based on" means "at least partially based on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; and the term "optionally" means "optional embodiments". Definitions of other terms will be given in the description below. It should be noted that the concepts of "first," "second," etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0022] It should be noted that the terms "one" and "more" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0023] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0024] like Figure 1As shown in the figure, an embodiment of the present invention provides a method for correcting the movement of a stacker crane. Based on a correction device, the device may include a laser rangefinder, a dual-axis tilt sensor, a data processing unit, a servo driver, a storage unit, and an environmental acquisition module. The data processing unit is installed inside the stacker crane control cabinet and is connected to the laser rangefinder, tilt sensor, servo driver, storage unit, and environmental acquisition module via signal lines. It receives data from the laser rangefinder and tilt sensor, identifies movement deformation, performs prediction and compensation algorithms, calculates the compensated target position, sends position commands to the servo driver, and manages data read / write operations in the storage unit. The laser rangefinder can be installed on the fixed side of the stacker crane to measure the absolute straight-line distance between the stacker crane and its starting point. The dual-axis tilt sensor can be installed on the base frame of the stacker crane's horizontal traveling mechanism to measure the lateral tilt angle (left-right tilt) and longitudinal tilt angle (front-back tilt) of the track in real time, providing tilt data for track elevation calculation and assisting in deducing the horizontal bending direction of the track. The servo driver is installed inside the stacker crane control cabinet. It receives the compensated target position command from the data processing unit, controls the speed and position of the travel motor, drives the stacker crane along the track, and provides real-time feedback on the motor's operating status. The storage unit is installed inside the stacker crane control cabinet or integrated into the data processing unit. It saves track reference maps (horizontal offset and elevation data), historical deformation data, and LSTM prediction model parameters (such as extended configurations). The environmental acquisition module includes temperature sensors, load sensors, and settlement sensors, installed in corresponding locations. For example, the temperature sensor is installed near the track inside the warehouse to collect environmental information near the track. Stacker crane operation correction methods include: Step S1: In response to the stop command at the target location, acquire real-time deformation data between the actual track trajectory at a preset distance and the pre-established reference track map. The stacker crane acquires track information in real time to obtain the actual track trajectory, and the preset distance is less than the target distance between the starting point and the target location.

[0025] Specifically, when the stacker crane starts running, in response to the target position stopping command sent by the data processing unit, the stacker crane is controlled to run a preset distance, where the preset distance is the track length between the starting point and the current mileage point. For example, if the starting point is 0 meters, the target position is 100 meters, and the stacker crane is currently at 30 meters, then the preset distance is 30 meters. During operation, the running distance of the stacker crane relative to the starting point is recorded in real time, and the current position mileage is output to control the stacker crane to stop after running the preset distance. The dual-axis tilt sensor outputs the tilt information of the vehicle body relative to the horizontal plane. The data processing unit receives the above data, integrates the longitudinal tilt angle along the mileage to obtain the actual track trajectory, compares the actual track trajectory with the reference track map stored in the storage unit to obtain deformation data, which may include track height deviation and horizontal deviation in the horizontal direction. Alternatively, an inertial navigation unit (IMU) can be used to replace the tilt sensor, obtaining attitude changes by integrating angular velocity; a visual sensor combined with QR codes along the track can be used to obtain position and deformation information through image recognition; a lidar can be used to scan the track contour and match it with the reference contour to obtain deformation deviation; or an ultrasonic sensor array can be used to measure the track surface undulation. By responding to the docking command at the target position and acquiring real-time deformation data within a preset distance, online continuous monitoring of track deformation is achieved. Track deformation information of this section can be obtained in advance before the stacker crane reaches the target position, which reserves sufficient processing time for subsequent compensation and avoids the problem of not being able to compensate in time due to the lag in real-time data acquisition.

[0026] Step S2: Retrieve the predicted deformation data of the preset distance during the same time period, and obtain the prediction deviation based on the real-time deformation data and the predicted deformation data, wherein the predicted deformation data is predicted based on the orbital environment information.

[0027] Specifically, real-time deformation data can only reveal the deformation of sections already traversed, and cannot predict the deformation of sections yet to be reached. To compensate for unknown sections ahead, predictive data is needed. Predictive deformation data from the same time period as the preset distance is retrieved, and the real-time collected data is compared with the predicted data to calculate the prediction deviation and evaluate the accuracy of the prediction model in the current time period and current section. Temperature sensors, load sensors, and settlement sensors in the environmental acquisition module collect real-time environmental information near the track. The storage unit stores a historical track deformation database, containing time-series data such as temperature, load, settlement rate, and deformation deviation from the past several weeks or even months. The data processing unit uses the time-series data from the historical database as input to train a model such as a Long Short-Term Memory (LSTM) network, enabling the model to learn the evolution of track deformation with time and environmental factors. After training, real-time collected environmental temperature, operating load, and other data are input into the LSTM model, and the model outputs the predicted deformation values ​​for each mileage point within the preset distance. The data processing unit compares the real-time deformation value and the predicted deformation value at the same mileage point, calculating the difference as the prediction deviation. Among these methods, Gated Recurrent Units (GRUs) can be used instead of LSTMs, resulting in fewer parameters and higher computational efficiency; Transformer time series prediction models can be used to capture longer-term historical dependencies; Autoregressive Integral Moving Average (ARIMA) models can be used for statistical time series prediction without training neural networks; Support Vector Regression (SVR) combined with environmental features can be used for deformation prediction; and Physical Information Neural Networks (PINN) can be used to combine mechanical mechanisms with data-driven approaches.

[0028] Step S3: Obtain spacing deformation data based on the predicted deformation data of the spacing track with the predicted deviation correction, and perform deviation compensation on the target position according to the spacing deformation data and the real-time deformation data, wherein the spacing track is the track between the target position and the current mileage point.

[0029] Specifically, the prediction deviation at the preset distance reflects the systematic error of the prediction model under the current environment. Due to the continuity of track deformation, this error exhibits similar behavior on the gap track (the section not yet reached). Using the prediction deviation calculated at the preset distance, the original predicted deformation data of the gap track is corrected, and then fused with real-time deformation data to compensate for the deviation at the target position. For example, the data processing unit calculates the average prediction deviation of each mileage point within the preset distance and obtains the prediction deviation of the current mileage point (the endpoint of the preset distance). Based on the average prediction deviation and the current position prediction deviation, correction amounts are generated for each mileage point on the gap track according to distance weights. These correction amounts are superimposed on the original predicted deformation data of the gap track to obtain the gap deformation data. The real-time deformation data of the current mileage point and the gap deformation data of the target mileage point are obtained and weighted to obtain the comprehensive horizontal deviation and comprehensive elevation deviation. Finally, the compensated target position Scomp = Starget + ΔXtotal + k × ΔYtotal is calculated based on the comprehensive deviation, where k is the conversion coefficient from elevation deviation to horizontal compensation, determined according to the mechanical geometry of the stacker crane. By using the predicted deformation data of the track spacing based on the predicted deviation correction, pre-compensation for deformation of sections that have not yet been reached is achieved. At the same time, the spacing deformation data is fused with real-time deformation data, taking into account both current measured information and future predicted information, making the compensation decision more comprehensive and reliable, and effectively solving the technical problem of not being able to compensate for unknown sections ahead.

[0030] Step S4: Drive the stacker crane to run according to the compensated target position.

[0031] Specifically, the data processing unit sends the calculated compensated target position to the servo driver via a signal line. Upon receiving the position command, the servo driver drives the travel motor to operate according to the compensated target position. The stacker crane runs along the track under the motor's drive until its actual position matches the compensated target position, at which point it stops. At this point, the stacker crane's actual stopping position is exactly the original target position (because the deformation deviation has been offset by the compensation). By driving the stacker crane to run according to the compensated target position, the stacker crane can still accurately stop at the original target position even when the track deforms, ensuring the accuracy and safety of storage and retrieval operations, and achieving complete closed-loop control from track deformation detection to compensation.

[0032] This invention, in response to a docking command at a target location, acquires real-time deformation data between the actual track trajectory and a reference track map within a preset distance. Compared to existing technologies that rely on periodic manual measurements of track deformation and fail to detect deformation in a timely manner during measurement intervals, this invention acquires track deformation data in real-time during stacker crane operation, achieving continuous online monitoring of track deformation. Because the preset distance is reasonably set to be less than the target distance between the starting point and the target location, the stacker crane can acquire track deformation information for that section before reaching the target location, reserving sufficient processing time for subsequent compensation and avoiding the problem of delayed compensation due to lagging real-time data acquisition. Predicted deformation data for the same preset distance within the same time period is retrieved, and the prediction deviation is obtained based on the real-time deformation data and the predicted deformation data. Compared to existing technologies that rely solely on measured data for correction and cannot predict future deformation trends, this method compares real-time acquired data with predicted data to accurately assess the current accuracy of the prediction model and quantify the prediction deviation. This deviation reflects the systematic error of the prediction model in the current time period and segment, providing a reliable basis for subsequent correction of the spacing track prediction data and making the compensation calculation more precise. Based on the predicted deformation data of the spacing track corrected by the prediction deviation, spacing deformation data is obtained. Based on the spacing deformation data and real-time deformation data, deviation compensation is performed on the target position. Using the prediction deviation calculated at a preset distance, the predicted deformation data of the spacing track (i.e., the segment not yet reached) is corrected in reverse, achieving pre-compensation for deformation in unknown segments ahead. Simultaneously, the spacing deformation data is fused with real-time deformation data, comprehensively considering both current measured information and future prediction information, making the compensation decision more comprehensive and reliable. The stacker crane is driven to run according to the compensated target position, using the compensated target position as the final position command of the servo drive. This ensures that the stacker crane can accurately stop at the target position even when the track deforms, effectively guaranteeing the accuracy and safety of storage and retrieval operations.

[0033] This invention achieves online continuous monitoring of track deformation by acquiring real-time deformation data within a preset distance in response to a target position stopping command. Track deformation information for a given section can be obtained before the stacker crane reaches the target position, allowing sufficient processing time for subsequent compensation. By retrieving predicted deformation data at the preset distance and comparing it with real-time deformation data to obtain the prediction deviation, the current accuracy of the prediction model can be accurately assessed, providing a reliable basis for correcting the spacing track data. By correcting the predicted deformation data of the spacing track based on the prediction deviation, pre-compensation for deformation in sections not yet reached is achieved. Simultaneously, the spacing deformation data is fused with real-time deformation data, comprehensively considering both current measured information and future prediction information. By driving the stacker crane to operate at the compensated target position, the stacker crane can still accurately stop at the target position even when track deformation occurs, ensuring the accuracy and safety of storage and retrieval operations. This invention enables online continuous monitoring and dynamic real-time compensation of track deformation, achieves pre-compensation for deformation in unknown sections ahead, and combines environmental information to predict deformation trends, thus possessing proactive prediction capabilities. This allows the stacker crane to maintain high-precision positioning even when the track undergoes slow deformation, improving the accuracy of storage and retrieval operations and the reliability of system operation, while reducing the cost of manual periodic measurement and maintenance.

[0034] Optionally, the acquisition of real-time deformation data between the actual trajectory of the track at a preset distance and the pre-established reference track map includes: During the process of the stacker crane running the preset distance, the mileage data of the stacker crane and the local tilt data of the track are collected in real time as the actual trajectory of the track; Based on the mileage data and the tilt data, the deformation deviation between the actual trajectory of the track and the reference track map is determined as the deformation data.

[0035] Optionally, the deformation data includes elevation deviation and horizontal deviation; determining the deformation deviation between the actual track shape and the reference track map based on the mileage data and the tilt data as the deformation data includes: The elevation change value of the corresponding track position is obtained based on the tilt data. The historical elevation curve is updated based on the elevation change value and the mileage data to obtain the actual elevation curve. The historical elevation curve is the elevation curve in the historical track map obtained from the previous measurement.

[0036] The elevation deviation is obtained by comparing the actual elevation curve of the track with the reference elevation curve in the reference track map.

[0037] Specifically, the dual-axis tilt sensor collects the longitudinal tilt angle in real time. The data processing unit integrates the longitudinal tilt angle along the corresponding mileage data, calculates the height change value for each small segment using the formula Δh = Δs × φ (radians), where Δh represents the height change value and Δs represents the longitudinal tilt angle. The system reads the historical elevation curve from the previous measurement from the storage unit, adds the calculated height change value to the historical elevation curve obtained from the previous actual measurement, and updates the current actual elevation curve point by point. Finally, the system reads the reference elevation curve from the reference track map from the storage unit, subtracts the actual elevation curve from the reference elevation curve at the same mileage point, and calculates the difference to obtain the elevation deviation.

[0038] The mileage error is obtained by comparing the mileage data with the straight mileage data. The deviation direction is determined based on the tilt data. The horizontal deviation of the track is derived by fusing the mileage error, the tilt data, and the deviation direction. The straight mileage is obtained by collecting the straight distance between the starting point and the ending point of the track using a laser rangefinder.

[0039] Specifically, the laser rangefinder collects the straight-line distance between the starting and ending points of the track, serving as the straight-line mileage data. The encoder in the data processing unit measures the actual curved distance of the stacker crane wheels, serving as the encoder mileage. The data processing unit calculates the mileage error, which reflects the cumulative length change caused by track curvature. A dual-axis tilt sensor provides the lateral tilt angle, reflecting the direction of track curvature on the horizontal plane (positive to the left, negative to the right). The mileage error provides the total curvature (scalar), and the lateral tilt angle provides the curvature direction (vector). The data processing unit merges these two values ​​and, through integration, calculates the horizontal deviation at each mileage point. That is, it determines the curvature direction based on the lateral tilt angle, distributes the mileage error according to direction to each mileage point, obtains the horizontal deviation curve, and compares it with historical horizontal deviation curves.

[0040] This embodiment decomposes deformation data into elevation deviation and horizontal deviation, processing them separately. Elevation deviation is obtained through tilt angle integration, while horizontal deviation is derived by fusing mileage error and lateral tilt angle, achieving independent calculation and accurate identification of the two deformation components. Elevation deviation calculation uses tilt angle integration and accumulation, obtaining a continuous actual elevation curve. Horizontal deviation derivation utilizes mileage error and tilt angle direction fusion, leveraging both the advantage of mileage error accurately reflecting the total bending and the advantage of lateral tilt angle providing bending direction information, ensuring the horizontal deviation has both accurate amplitude and correct direction. Compared to single-sensor solutions, multi-source data fusion significantly improves the accuracy and robustness of deformation identification.

[0041] Optionally, the step of predicting the predicted deformation data based on orbital environment information includes: The orbital environment information is input into a pre-trained time-series prediction model to predict the orbital deformation trend in future periods, thus obtaining the predicted deformation data. The orbital environment information includes temperature, ground settlement rate, operating load, and historical deformation deviation. The time-series prediction model is trained based on historical environmental information and historical orbital maps.

[0042] Specifically, during the long-term operation of the stacker crane, the environmental acquisition module continuously collects environmental information near the track. For example, temperature sensors record the ambient temperature at regular intervals (e.g., hourly), load sensors record the load of the stacker crane during each operation, and settlement sensors (or through periodic measurements) record the foundation settlement rate. Simultaneously, the identified deformation deviations are also stored. All data is organized by timestamp, forming a historical track deformation database covering deformation records at different temperatures, loads, and settlement stages. The data processing unit uses time-series data from the historical database as training samples. Input features include ambient temperature, operating load, foundation settlement rate, and historical deformation deviations; the output label is the deformation measurement value for the corresponding time period. A Long Short-Term Memory (LSTM) network model is trained, and the network weights are optimized using the backpropagation algorithm, enabling the model to learn the evolution of track deformation over time and with environmental factors. The LSTM model is specifically designed to process time-series data; its internal memory units can capture long-term dependencies, such as the cumulative effect of temperature over the past week on the current deformation. After training, the model parameters are saved to the storage unit. During the operation of the stacker crane, real-time collected ambient temperature, operating load, foundation settlement rate, and recent deformation deviation are used as input features and fed into a trained LSTM model. After forward computation, the model outputs predicted deformation values ​​for each mileage point in future time periods (such as the next 24 hours or the next 7 days). The predicted deformation data covers expansion deformation caused by temperature rise, bending deformation caused by increased load, and subsidence deformation caused by foundation settlement.

[0043] This embodiment achieves proactive prediction of track deformation trends by inputting environmental information into a time-series prediction model, enabling the system to possess feedforward pre-compensation capabilities. Compared to schemes that rely solely on real-time feedback, the prediction mechanism can output compensation amounts before deformation actually occurs, eliminating positioning drift caused by slow deformation. The historical database covers deformation records under different temperatures, loads, and settlement stages, ensuring sufficient model training and reliable prediction accuracy. The predicted deformation data provides a reliable estimate of future deformation for subsequent track spacing corrections, allowing the stacker crane to proactively adjust its compensation strategy before deformation caused by environmental changes occurs.

[0044] Optionally, obtaining the spacing deformation data based on the predicted deformation data of the spacing track after correcting the predicted deviation includes: The predicted deviation is input into a pre-trained correction model to obtain the spacing deformation data of the spacing track. The correction model is trained based on historical prediction bias and historical spacing deformation data.

[0045] Specifically, during the long-term operation of the stacker crane, each time a correction task is performed, a set of data is generated: the difference between the real-time deformation data and the predicted deformation data at the preset distance, i.e., the prediction deviation; and the difference between the actual deformation data measured when the stacker crane actually reaches each mileage point on the spacing track and the original predicted deformation data, i.e., the actual correction amount. This data is organized by timestamp and mileage coordinates to form a historical dataset. Each sample in the dataset contains input features (distribution characteristics of the prediction deviation, such as mean, variance, rate of change, etc.) and output labels (actual correction amounts at each mileage point on the spacing track). The data processing unit uses the prediction deviation features from the historical dataset as input and the corresponding actual correction amounts on the spacing track as output labels to train the correction model. The correction model can employ various machine learning algorithms, such as linear regression models learning the linear propagation law of the deviation, random forest models learning the nonlinear relationship between the deviation and mileage position, and neural network models learning complex error propagation patterns. After training, the correction model parameters are saved to the storage unit. The core function of the correction model is to learn the mapping relationship between "predicted deviation at the preset distance" and "correction amounts at each mileage point on the spacing track". During the operation of the stacker crane, the data processing unit inputs the currently calculated prediction deviation into the trained correction model. Based on the mapping rules learned during training, the model outputs the spacing deformation data for each mileage point on the track. This spacing deformation data directly reflects the corrected track deformation prediction value and can be used for subsequent target position compensation.

[0046] Optionally, the step of compensating for the deviation of the target position based on the spacing deformation data and the real-time deformation data includes: The sum of the spacing deformation data and the real-time deformation data is obtained to obtain the comprehensive deformation data; The target position is compensated for based on the comprehensive variable data as a deviation.

[0047] Specifically, the aforementioned real-time deformation data of the current mileage point (reflecting the actual deformation of the track already traversed) and the spacing deformation data of the intermediate tracks (reflecting the predicted deformation of the track to be traversed ahead) have already been acquired. The stacker crane ultimately needs to accurately stop at the target position, and the deformation of the target position is affected by both the real-time deformation of the current position (reflecting the current operating status) and the cumulative effect of the deformation of the intermediate tracks ahead (reflecting the deformation distribution of the remaining travel). The two are added together to obtain comprehensive deformation data, which serves as the basis for deviation compensation at the target position. This simple summation method has low computational complexity and fast response, making it suitable for industrial control scenarios with high real-time requirements. The data processing unit reads the real-time deformation data of the current mileage point from the storage unit, including the current horizontal deviation ΔXcur and the current elevation deviation ΔYcur. Simultaneously, it reads the spacing deformation data of the target mileage point from the correction model output, including the corrected horizontal deviation ΔXcorr(Starget) and the corrected elevation deviation ΔYcorr(Starget) at the target position. The data processing unit performs addition operations, summing the deformation data of corresponding types: Overall horizontal deviation ΔXtotal = ΔXcur + ΔXcorr(Starget), Overall elevation deviation ΔYtotal = ΔYcur + ΔYcorr(Starget). After obtaining the overall deformation data, the compensated target position is calculated according to the compensation formula: Scomp = Starget + ΔXtotal + k × ΔYtotal, where k is the conversion coefficient from elevation deviation to horizontal compensation. The data processing unit sends the compensated target position Scomp to the servo driver via a signal line, driving the stacker crane to move to the compensated target position.

[0048] Optionally, the stacker crane operation correction method further includes: In response to real-time deformation data exceeding a preset deviation threshold, an early warning is issued, wherein the preset deviation threshold includes a first deviation threshold and a second deviation threshold; When the absolute value of the horizontal deviation exceeds the first deviation threshold, and / or the absolute value of the elevation deviation exceeds the second deviation threshold, a real-time alarm signal is issued; The predicted deformation data includes predicted horizontal deviation and predicted elevation deviation. When the predicted horizontal deviation exceeds the first deviation threshold and / or the absolute value of the predicted elevation deviation exceeds the second deviation threshold, an early warning signal is issued, and a maintenance cycle recommendation is generated based on the predicted deformation data.

[0049] Specifically, if track deformation continues unchecked, it will eventually exceed the allowable range, leading to inaccurate stopping of the stacker crane, accelerated wheel and rail wear, and even safety accidents. If it's only discovered after deformation has exceeded limits, significant equipment damage and production disruptions have already occurred. Therefore, a tiered early warning mechanism is needed: immediate alarms when real-time deformation exceeds limits (post-event alarms), and early warnings when predicted deformation exceeds limits (pre-event warnings). By setting a first deviation threshold (horizontal) and a second deviation threshold (elevation), real-time and predicted deformation are monitored in stages, and corresponding alarm signals are issued when limits are exceeded. Simultaneously, maintenance cycle recommendations are generated based on the prediction results, achieving an upgrade from passive response to proactive maintenance. The data processing unit presets the first deviation threshold, corresponding to a horizontal deviation threshold, for example, ±3.0mm, and the second deviation threshold, corresponding to an elevation deviation threshold, for example, ±2.0mm. During stacker crane operation, the data processing unit monitors the horizontal and elevation deviations in real-time deformation data. When the absolute value of the horizontal deviation exceeds the first deviation threshold, or the absolute value of the elevation deviation exceeds the second deviation threshold, the data processing unit immediately generates a real-time alarm signal and sends it to the monitoring terminal or host computer system via the communication interface. The alarm signal includes information such as the type of over-limit (horizontal / elevation), the location of the over-limit (mileage coordinates s), and the magnitude of the over-limit (current deviation value). Upon receiving the alarm, the monitoring terminal displays a red warning on the interface and records the alarm log, prompting maintenance personnel to manually inspect and adjust the track.

[0050] Simultaneously, the data processing unit also monitors the predicted horizontal deviation and predicted elevation deviation Δ in the predicted deformation data. When the absolute value of the predicted horizontal deviation exceeds the first deviation threshold, or the absolute value of the predicted elevation deviation exceeds the second deviation threshold, the data processing unit generates a warning signal (rather than a real-time alarm). The warning signal is of a lower level than a real-time alarm, but it is still sent to the monitoring terminal. The warning signal includes information such as the expected time of exceeding the limit, the expected location of exceeding the limit, and the expected magnitude of exceeding the limit. In addition, the data processing unit calculates the remaining time before exceeding the limit based on the changing trend of the predicted deformation data (such as how many millimeters it increases per day) and generates a maintenance cycle recommendation. For example, "It is expected that the horizontal deviation will reach the 3.0 mm threshold in 7 days, and it is recommended to arrange track adjustment in 5 days." The warning signal and maintenance recommendation enable maintenance personnel to take preventive measures before the actual deformation exceeds the limit.

[0051] like Figure 2 As shown, an embodiment of the present invention provides a stacker crane operation correction device, comprising: The measurement module is used to respond to the stop command at the target position and acquire real-time deformation data between the actual trajectory of the track at a preset distance and the pre-established reference track map. The stacker crane acquires track information in real time to obtain the actual trajectory of the track, and the preset distance is less than the target distance between the starting point and the target position. The deviation module is used to retrieve the predicted deformation data of the preset distance in the same time period, and to obtain the predicted deviation based on the real-time deformation data and the predicted deformation data, wherein the predicted deformation data is predicted based on the orbital environment information. The compensation module is used to obtain spacing deformation data based on the predicted deformation data of the spacing track, and to perform deviation compensation on the target position according to the spacing deformation data and the real-time deformation data, wherein the spacing track is the track between the target position and the current mileage point; The correction module is used to drive the stacker crane to run according to the compensated target position.

[0052] like Figure 3 As shown in the figure, an electronic device provided by an embodiment of the present invention includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the stacker crane operation correction method as described above when the computer program is executed.

[0053] Alternatively, an electronic device includes a memory and a processor coupled to the memory; the memory is configured to store a computer program; the processor is configured to perform the following operations when the computer program is executed: In response to a docking command at a target location, real-time deformation data is collected between the actual trajectory of the track at a preset distance and a pre-established baseline track map. The stacker crane obtains the actual trajectory of the track by acquiring track information in real time during operation. The preset distance is less than the target distance between the starting point and the target location. Retrieve the predicted deformation data of the preset distance within the same time period, and obtain the prediction deviation based on the real-time deformation data and the predicted deformation data, wherein the predicted deformation data is predicted based on the orbital environment information; Based on the predicted deformation data of the predicted deviation correction spacing track, the spacing deformation data is obtained. The target position is compensated for deviation based on the spacing deformation data and the real-time deformation data. The spacing track is the track between the target position and the current mileage point. The stacker crane is driven to run at the compensated target position.

[0054] This invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the stacker crane operation correction method described above.

[0055] Alternatively, a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the following operations: In response to a docking command at a target location, real-time deformation data is collected between the actual trajectory of the track at a preset distance and a pre-established baseline track map. The stacker crane obtains the actual trajectory of the track by acquiring track information in real time during operation. The preset distance is less than the target distance between the starting point and the target location. Retrieve the predicted deformation data of the preset distance within the same time period, and obtain the prediction deviation based on the real-time deformation data and the predicted deformation data, wherein the predicted deformation data is predicted based on the orbital environment information; Based on the predicted deformation data of the predicted deviation correction spacing track, the spacing deformation data is obtained. The target position is compensated for deviation based on the spacing deformation data and the real-time deformation data. The spacing track is the track between the target position and the current mileage point. The stacker crane is driven to run at the compensated target position.

[0056] The present invention will now describe electronic devices that can serve as servers or clients of the present invention, which are examples of hardware devices that can be applied to various aspects of the present invention. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0057] Electronic devices include a computing unit that can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) or loaded from a storage unit into random access memory (RAM). The RAM can also store various programs and data required for device operation. The computing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0058] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. In this application, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention according to actual needs. Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units can be implemented in hardware or as software functional units.

[0059] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A method for correcting the movement of a stacker crane, characterized in that, include: In response to a docking command at a target location, real-time deformation data is collected between the actual trajectory of the track at a preset distance and a pre-established baseline track map. The stacker crane obtains the actual trajectory of the track by acquiring track information in real time during operation. The preset distance is less than the target distance between the starting point and the target location. Retrieve the predicted deformation data of the preset distance during the same time period, and obtain the prediction deviation based on the real-time deformation data and the predicted deformation data, wherein the predicted deformation data is predicted based on the orbital environment information; Based on the predicted deformation data of the predicted deviation correction spacing track, the spacing deformation data is obtained. The target position is compensated for deviation based on the spacing deformation data and the real-time deformation data. The spacing track is the track between the target position and the current mileage point. The stacker crane is driven to run at the compensated target position.

2. The stacker crane operation correction method according to claim 1, characterized in that, The acquisition of real-time deformation data between the actual trajectory of the track at a preset distance and the pre-established reference track map includes: During the process of the stacker crane running the preset distance, the mileage data of the stacker crane and the local tilt data of the track are collected in real time as the actual trajectory of the track; Based on the mileage data and the tilt data, the deformation deviation between the actual trajectory of the track and the reference track map is determined as the deformation data.

3. The stacker crane operation correction method according to claim 2, characterized in that, The deformation data includes elevation deviation and horizontal deviation; determining the deformation deviation between the actual track shape and the reference track map based on the mileage data and the tilt data as the deformation data includes: The elevation change value of the corresponding track position is obtained based on the tilt data. The historical elevation curve is updated based on the elevation change value and the mileage data to obtain the actual elevation curve. The historical elevation curve is the elevation curve in the historical track map obtained from the previous measurement. The elevation deviation is obtained by comparing the actual elevation curve of the track with the reference elevation curve in the reference track map. The mileage error is obtained by comparing the mileage data with the straight mileage data. The deviation direction is determined based on the tilt data. The horizontal deviation of the track is derived by fusing the mileage error, the tilt data, and the deviation direction. The straight mileage is obtained by collecting the straight distance between the starting point and the ending point of the track using a laser rangefinder.

4. The stacker crane operation correction method according to claim 1, characterized in that, The predicted deformation data obtained based on orbital environment information includes: The orbital environment information is input into a pre-trained time-series prediction model to predict the orbital deformation trend in future periods, thus obtaining the predicted deformation data. The orbital environment information includes temperature, ground settlement rate, operating load, and historical deformation deviation. The time-series prediction model is trained based on historical environmental information and historical orbital maps.

5. The stacker crane operation correction method according to claim 1, characterized in that, The method of obtaining spacing deformation data based on the predicted deformation data of the spacing track after correcting the predicted deviation includes: The predicted deviation is input into a pre-trained correction model to obtain the spacing deformation data of the spacing track. The correction model is trained based on historical prediction bias and historical spacing deformation data.

6. The stacker crane operation correction method according to claim 1, characterized in that, The step of compensating for the deviation of the target position based on the spacing deformation data and the real-time deformation data includes: The sum of the spacing deformation data and the real-time deformation data is obtained to obtain the comprehensive deformation data; The target position is compensated for based on the comprehensive variable data as a deviation.

7. The stacker crane operation correction method according to claim 3, characterized in that, Also includes: In response to real-time deformation data exceeding a preset deviation threshold, an early warning is issued, wherein the preset deviation threshold includes a first deviation threshold and a second deviation threshold; When the absolute value of the horizontal deviation exceeds the first deviation threshold, and / or the absolute value of the elevation deviation exceeds the second deviation threshold, a real-time alarm signal is issued; The predicted deformation data includes predicted horizontal deviation and predicted elevation deviation. When the predicted horizontal deviation exceeds the first deviation threshold and / or the absolute value of the predicted elevation deviation exceeds the second deviation threshold, an early warning signal is issued, and a maintenance cycle recommendation is generated based on the predicted deformation data.

8. A stacker crane operation correction device, characterized in that, include: The measurement module is used to respond to the stop command at the target position and acquire real-time deformation data between the actual trajectory of the track at a preset distance and the pre-established reference track map. The stacker crane acquires track information in real time to obtain the actual trajectory of the track, and the preset distance is less than the target distance between the starting point and the target position. The deviation module is used to retrieve the predicted deformation data of the preset distance in the same time period, and to obtain the predicted deviation based on the real-time deformation data and the predicted deformation data, wherein the predicted deformation data is predicted based on the orbital environment information. The compensation module is used to obtain spacing deformation data based on the predicted deformation data of the spacing track, and to perform deviation compensation on the target position according to the spacing deformation data and the real-time deformation data, wherein the spacing track is the track between the target position and the current mileage point; The correction module is used to drive the stacker crane to run according to the compensated target position.

9. An electronic device, characterized in that, Including memory and processor; The memory is used to store computer programs; The processor is configured to implement the stacker crane operation correction method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the stacker crane operation correction method as described in any one of claims 1 to 7.

Images