A method, apparatus and equipment for detecting shell occupancy

Abstract

This application provides a method, apparatus, and equipment for detecting shell occupancy, relating to the field of casting process and quality inspection technology. It addresses the technical problems in related technologies where, during the investment casting production process, the detection of abnormal occupancy of the loading pallet and the mold chamber pallet via an automatic transfer system for transferring cold and hot shells is inaccurate, and abnormal shell posture cannot be identified in a timely manner. The method includes: acquiring pallet image information; determining the pallet occupancy status and shell posture status based on the pallet image information; acquiring a transfer command signal; generating an abnormal status signal based on the pallet occupancy status, the transfer command signal, and the shell posture status; adjusting the transfer command signal based on the abnormal status signal and the pallet image information to generate a real-time control signal; and controlling the transfer system to perform corresponding operations based on the real-time control signal.

Description

Technical Field

[0001] This application relates to the fields of casting technology and quality inspection technology, and in particular to a method, apparatus and equipment for detecting the occupancy of a mold shell. Background Technology

[0002] With the continuous development of investment casting production technology, the application of automatic transfer systems in the transfer of cold and hot shells is gradually becoming more widespread. By detecting the occupancy of the feeding pallet and the mold chamber pallet, the probability of mechanical impact accidents can be reduced while improving production efficiency.

[0003] However, in actual production, abnormal stacking of shells on the loading pallet or obstruction of the material placement position on the mold chamber pallet frequently occur. This can affect the operation of the transfer system and consequently impact the stability of the overall production process. Furthermore, the accuracy of shell stacking and the stability of its posture during the transfer of hot shells to the mold chamber pallet are uncertain. For example, shells with sandbox bases may fail to be accurately placed on the pallet, or they may tilt or tip over after placement. These issues can pose challenges to the subsequent automatic casting process. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a shell occupancy detection method, apparatus, and equipment to solve the technical problems in related technologies where, during the investment casting production process, the abnormal occupancy detection of the loading tray and the mold chamber tray is inaccurate, and abnormal shell posture cannot be identified in a timely manner when transferring cold and hot shells through an automatic transfer system.

[0005] To achieve the above technical objectives, this application provides the following technical solution: In a first aspect, the present invention provides a shell occupancy detection method, the method comprising: acquiring pallet image information; determining pallet occupancy status and shell posture status based on the pallet image information; acquiring a transfer command signal; generating an abnormal status signal based on the pallet occupancy status, the transfer command signal, and the shell posture status; adjusting the transfer command signal based on the abnormal status signal and the pallet image information to generate a real-time control signal; and controlling the transfer system to perform corresponding operations based on the real-time control signal.

[0006] This solution utilizes industrial cameras to capture pallet images during the investment casting process. By combining machine vision and deep learning algorithms, it accurately identifies the pallet's positioning and the mold's posture. Upon receiving a control command from the transfer system, the system analyzes the pallet images to determine if any positioning or mold posture abnormalities exist. If an abnormality is detected, an abnormality signal is generated, and the transfer command is dynamically adjusted based on this signal, generating a new real-time control signal. This process ensures that the transfer system can flexibly adjust its action strategy according to the actual pallet status, avoiding mechanical impact accidents caused by positioning or mold posture abnormalities, and improving the stability and safety of the production process.

[0007] In one possible implementation, determining the pallet occupancy status and shell posture status based on the pallet image information includes: analyzing the pallet image information and extracting boundary features of the pallet area; calculating the occupancy ratio of the pallet area based on the boundary features; incorporating the occupancy ratio into the pallet occupancy status; extracting the contour features of the shell sandbox based on the pallet image information; calculating the tilt angle and offset distance of the shell sandbox based on the contour features; and incorporating the tilt angle and offset distance into the shell posture status.

[0008] This scheme processes pallet image information to extract boundary features of the pallet area and further calculates the occupancy ratio of the pallet area, thus reflecting the pallet's positioning status. Simultaneously, it extracts the contour features of the shell sandbox, calculating its tilt angle and offset distance to describe the shell's attitude state. The extraction of these parameters provides crucial data support for subsequent anomaly detection. By accurately modeling the pallet's positioning status and the shell's attitude state, it ensures that the detection results accurately reflect the actual state of the pallet, thereby providing a reliable basis for fundamental control decisions.

[0009] In one possible implementation, the pallet occupancy status includes the available pallet range, the transfer instruction signal includes an action start signal and an action stop signal, and the step of generating an abnormal status signal based on the pallet occupancy status, the transfer instruction signal, and the shell posture status includes: determining whether the pallet is in an empty state based on the available pallet range; if not empty, determining the shell distribution density on the pallet based on the pallet image information; determining whether there is a stacking abnormality based on the shell distribution density; if there is a stacking abnormality, determining the shell tilt angle and offset distance based on the shell posture status; determining whether the shell may tip over based on the tilt angle and offset distance; if tipping over is possible, generating an abnormal status signal and sending the abnormal status signal to the transfer control system.

[0010] This solution analyzes the available range of pallets to determine if they are empty. If the pallet is not empty, it further analyzes the density of shell distribution on the pallet to determine if there are any stacking anomalies. Based on this, it assesses the possibility of shell tipping by combining the tilt angle and offset distance in the shell's posture. If a potential risk is detected, an abnormal status signal is generated and sent to the transfer control system. This process, through multi-dimensional parameter analysis, ensures comprehensive monitoring of the pallet status and shell posture, effectively preventing safety hazards caused by abnormal stacking or unstable posture.

[0011] In one possible implementation, adjusting the transfer command signal based on the abnormal state signal and the pallet image information to generate a real-time control signal includes: determining the volume and height of the shell on the pallet based on the pallet image information; calculating the center of gravity position of the shell based on the abnormal state signal, the shell volume, and the shell height; determining the stability index of the shell based on the center of gravity position and the shell attitude state; generating a real-time control signal based on the stability index and the transfer command signal; and sending the real-time control signal to the transfer control system.

[0012] This solution analyzes pallet image information to determine the volume and height of the shell, and further calculates the shell's center of gravity. Combined with the shell's attitude state, the shell's stability index is evaluated. Based on the stability index and transfer command signals, real-time control signals are generated and sent to the transfer control system. This process, through precise modeling of the shell's physical characteristics, ensures that the transfer system can flexibly adjust its action strategy according to the actual state of the shell, reducing risks caused by shell instability and improving the safety of the transfer process.

[0013] In one possible implementation, determining the stability index of the shell based on the center of gravity position and the shell's attitude state includes: determining the contact area between the bottom of the shell and the tray based on the tray image information; calculating the overturning moment of the shell based on the contact area, the center of gravity position, and the shell height; and determining the stability index of the shell based on the overturning moment and the tilt angle in the shell's attitude state, calculated according to the following formula: S = (A∙h) / (M∙θ); Wherein, S represents the stability index, A represents the contact area, h represents the shell height, M represents the overturning moment, and θ represents the tilt angle.

[0014] This method calculates the stability index of the shell by measuring the contact area between the bottom of the shell and the pallet, combined with the shell height and overturning moment. The various variables in the formula collectively determine the stability characteristics of the shell; in particular, the introduction of the tilt angle further enhances the sensitivity to changes in the shell's attitude. This calculation provides a quantitative basis for the stability assessment of the transfer system, enabling it to make precise adjustments based on the actual state of the shell, significantly improving the system's responsiveness and safety.

[0015] In one possible implementation, after generating the real-time control signal based on the stability index and the transfer instruction signal, the method further includes: acquiring image information of the pallet's surrounding environment; determining whether there are obstacles based on the image information of the pallet's surrounding environment; if there are obstacles, determining the volume, position, and direction of movement of the obstacles based on the image information of the pallet's surrounding environment; calculating a safe distance for the transfer path based on the position of the obstacles and the real-time control signal; generating a path optimization signal based on the safe distance and the direction of movement of the obstacles; and incorporating the path optimization signal into the real-time control signal.

[0016] This solution analyzes the surrounding environment of the pallet to determine the presence of obstacles. If an obstacle is detected, its size, location, and direction of movement are further determined, and a safe distance for the transfer path is calculated using real-time control signals. Based on the safe distance and the obstacle's direction of movement, a path optimization signal is generated and incorporated into the real-time control signals. This process ensures that the transfer system can flexibly adjust its path in complex environments, avoiding collision risks caused by obstacles and improving the system's adaptability.

[0017] In one possible implementation, generating an abnormal state signal based on the pallet occupancy status, the transfer command signal, and the shell posture status includes: determining whether the shell has bounced based on the pallet image information; if it has bounced, determining the bounce height and direction of the shell based on the pallet image information; determining whether the shell may detach from the pallet based on the bounce height and direction; if it may detach from the pallet, predicting the shell's bounce trajectory based on the shell's volume and height; determining the trajectory contact point and contact time based on the bounce trajectory and the transfer path; and incorporating the trajectory contact point and contact time into the abnormal state signal.

[0018] This solution analyzes pallet image information to determine if the mold shell has bounced. If it has bounced, the bounce height and direction are further determined to assess the possibility of the shell detaching from the pallet. Based on this, the shell's volume and height are combined to predict its bounce trajectory, which is then compared with the transport path to determine the contact point and time. This process, through precise modeling of the shell's bounce behavior, ensures that the transport system can respond promptly to the risk of the shell detaching from the pallet, enhancing the system's emergency response capabilities.

[0019] In one possible implementation, adjusting the transfer command signal based on the abnormal state signal and the pallet image information to generate a real-time control signal includes: determining the relative position between the transfer system and the shell based on the pallet image information; calculating the avoidance distance of the transfer system based on the trajectory contact point, the contact time, the relative position, and the volume of the shell; generating the real-time control signal based on the avoidance distance and the transfer command signal; and sending the real-time control signal to the transfer control system.

[0020] This solution analyzes pallet image information to determine the relative position between the transfer system and the shell. Combining the trajectory contact point, contact time, relative position, and shell volume, the avoidance distance of the transfer system is calculated. Based on the avoidance distance and transfer command signal, a real-time control signal is generated and sent to the transfer control system. This process, through precise calculation of the avoidance distance, ensures that the transfer system maintains a safe distance during shell bouncing, avoiding collisions and improving the system's intelligence level.

[0021] Secondly, embodiments of this specification provide a shell occupancy detection device, comprising: The first acquisition unit is used to acquire pallet image information and determine the pallet occupancy status and shell posture status based on the pallet image information. The second acquisition unit is used to acquire the transfer instruction signal and generate an abnormal status signal based on the pallet occupancy status, the transfer instruction signal and the shell posture status. The processing unit is used to adjust the transfer instruction signal according to the abnormal status signal and the pallet image information, generate a real-time control signal, and control the transfer system to perform corresponding operations according to the real-time control signal.

[0022] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the shell occupancy detection method of the first aspect or any corresponding embodiment described above.

[0023] Fourthly, embodiments of this specification provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the shell occupancy detection method as described in any of the preceding claims.

[0024] Fifthly, embodiments of this specification provide a computer program product or a computer program, the computer program product including a computer program stored in a computer-readable storage medium; the processor of the computer device reads the computer program from the computer-readable storage medium, and when the processor executes the computer program, it implements the shell occupancy detection method as described in any of the preceding claims. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0026] Figure 1 A schematic flowchart illustrating a shell occupancy detection method provided for embodiments of this specification; Figure 2 A schematic diagram of a shell occupancy detection device provided for embodiments of this specification; Figure 3 This is a schematic diagram of the structure of an electronic device provided for the implementation of this specification. Detailed Implementation

[0027] Unless otherwise defined, the technical or scientific terms used in the embodiments of this specification shall have the ordinary meaning understood by one skilled in the art to which this specification pertains. The terms "first," "second," and similar terms used in the embodiments of this specification do not indicate any order, quantity, or importance, but are merely used to avoid confusion of constituent elements.

[0028] Unless the context otherwise requires, throughout this specification, "a plurality of" means "at least two," and "including" is interpreted as open-ended or encompassing, that is, "including, but not limited to." In the description of this specification, terms such as "one embodiment," "some embodiments," "exemplary embodiment," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this specification. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example.

[0029] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0030] Overview As mentioned in the background technology, with the continuous development of investment casting production technology, the application of automatic transfer systems in the transfer of cold and hot shells has gradually become widespread. By detecting the occupancy of the feeding tray and the mold chamber tray, the probability of mechanical impact accidents can be reduced while improving production efficiency.

[0031] However, in actual production, abnormal stacking of shells on the loading pallet or obstruction of the material placement position on the mold chamber pallet frequently occur. This can affect the operation of the transfer system and consequently impact the stability of the overall production process. Furthermore, the accuracy of shell stacking and the stability of its posture during the transfer of hot shells to the mold chamber pallet are uncertain. For example, shells with sandbox bases may fail to be accurately placed on the pallet, or they may tilt or tip over after placement. These issues can pose challenges to the subsequent automatic casting process.

[0032] Based on the above inventive concept, the shell occupancy detection method provided in the embodiments of this specification will be described exemplarily below.

[0033] Exemplary methods This specification provides a shell occupancy detection method, the core of which lies in acquiring pallet image information using an industrial camera and combining machine vision and deep learning algorithms to accurately identify the pallet occupancy status and shell posture status. In practical applications, it is first necessary to deploy industrial cameras to cover the entire pallet area, ensuring complete acquisition of image information of the pallet and the shell on it. The industrial camera is installed above the transfer system and connected to the control unit of the transfer system for real-time transmission of image data to the processing module. The processing module includes an image analysis unit, an anomaly detection unit, and a control signal generation unit, which work together to complete the detection and control tasks. The implementation of this method is described in detail below with reference to specific application scenarios, such as... Figure 1 As shown, it includes: S101. Obtain pallet image information, and determine the pallet occupancy status and shell posture status based on the pallet image information.

[0034] In practice, when a pallet enters the detection area, the industrial camera begins acquiring image information of the pallet and transmits this information to the image analysis unit. The image analysis unit preprocesses the received image, including noise reduction, contrast enhancement, and edge detection, to improve the accuracy of subsequent feature extraction. Subsequently, the image analysis unit extracts the boundary features of the pallet area and calculates the occupancy ratio of the pallet area. Specifically, the boundary features are obtained through a contour detection algorithm, while the occupancy ratio is calculated by the ratio of the number of pixels within the pallet area to the total number of pixels. This process accurately reflects whether the pallet is empty or if there are any abnormal stacking conditions.

[0035] Simultaneously, the image analysis unit extracts the contour features of the shell sandbox and calculates its tilt angle and offset distance. Contour feature extraction is based on an edge detection algorithm, while the tilt angle and offset distance are derived through geometric calculations. For example, the tilt angle can be obtained by calculating the angle between the two edge lines of the shell sandbox and the horizontal line, and the offset distance is the Euclidean distance between the center point of the shell sandbox and the center point of the tray. These parameters collectively constitute a detailed description of the shell's posture state, providing crucial support for subsequent anomaly detection. Specifically, when segmenting the shell sandbox, semantic segmentation can be used to obtain the occupied width and determine whether it is occupied. To improve detection accuracy and ensure high detection speed, the PP-LiteSeg semantic segmentation algorithm is preferred.

[0036] In this step, the acquisition of tray image information can be achieved by processing directly acquired images using a deep learning model. The training samples for the model can conform to a normal distribution in terms of extraction time. Uniform extraction under different lighting and weather conditions (daytime, nighttime, different lighting, different weather) increases sample diversity, which is beneficial for model training and ensures good performance under various conditions. Specifically, the deep learning algorithm used for accurately identifying the tray's occupancy status and shell posture can employ, for example, an improved convolutional neural network model based on YOLOv7. This model includes: an image input layer, a feature extraction backbone network (such as ResNet-50 or CSPDarknet53), a feature pyramid network (FPN), and a multi-scale detection head. The model's training dataset should contain a large number of labeled images acquired under different lighting conditions, backgrounds, shell types, occupancy statuses (empty, normal placement, abnormal placement), and posture statuses (normal, tilted, offset, tipped over, etc.). During training, stochastic gradient descent (SGD) or the Adam optimizer can be used, and loss functions (such as CIoU Loss or Focal Loss) can be used for iterative optimization until the model converges and reaches the preset recognition accuracy threshold. To further improve recognition accuracy and robustness, a self-attention mechanism or a spatial pyramid pooling module can be introduced into the model.

[0037] S102. Obtain the transfer instruction signal and generate an abnormal status signal based on the pallet occupancy status, the transfer instruction signal, and the shell posture status.

[0038] In practice, after analyzing the pallet's occupancy status and shell posture status, the anomaly detection unit determines whether the pallet is empty based on its available range. If the pallet is not empty, it further analyzes the shell distribution density on the pallet. The shell distribution density is calculated by statistically analyzing the ratio of the number of pixels occupied by shells within the pallet area to the total number of pixels. If the distribution density exceeds a preset threshold, it is determined to be an abnormal stacking. Based on this, the anomaly detection unit combines the tilt angle and offset distance in the shell posture status to assess whether the shell may tip over. For example, if the tilt angle exceeds a certain critical value or the offset distance exceeds the safe range, an anomaly status signal is generated and sent to the transfer control system.

[0039] S103. Adjust the transfer instruction signal according to the abnormal status signal and pallet image information, generate a real-time control signal, and control the transfer system to perform corresponding operations according to the real-time control signal.

[0040] In practical implementation, to further improve detection accuracy, the processing module also includes a center of gravity position calculation unit and a stability index evaluation unit. The center of gravity position calculation unit determines the volume and height of the shell by analyzing the pallet image information, and calculates the overturning moment based on the contact area between the bottom of the shell and the pallet. The contact area is obtained through a contour detection algorithm, while the overturning moment is calculated based on mechanical formulas. The stability index evaluation unit calculates the stability index of the shell based on the overturning moment, contact area, shell height, and tilt angle. The formula for calculating the stability index is S=(A∙h) / (M∙θ); Where S represents the stability index, A represents the contact area, h represents the shell height, M represents the overturning moment, and θ represents the tilt angle. This calculation result provides a quantitative basis for the stability assessment of the transfer system. The overturning moment M is calculated based on the shell's mass, center of gravity position, and current tilt angle, representing the overturning tendency of the shell relative to its bottom edge (as the potential overturning axis). The specific calculation formula is as follows: M, where m is the shell mass, g is the gravitational acceleration, d1 is the horizontal distance from the shell's center of gravity projection point to the overturning axis, and d2 is the correction distance. The stability index S can be defined, for example, as the ratio of the shell's restoring moment to the overturning moment, or as the safety threshold from the shell's center of gravity projection point to the overturning axis. A clear formula must be provided, ensuring it is physically reasonable and does not diverge when θ is zero.

[0041] After generating the abnormal status signal, the control signal generation unit adjusts the transfer command signal and generates a real-time control signal based on the abnormal status signal and pallet image information. Specifically, the control signal generation unit first determines the relative position between the transfer system and the shell, and calculates the avoidance distance of the transfer system by combining the trajectory contact point, contact time, relative position, and shell volume. The avoidance distance is calculated based on geometric relationships, such as determining the avoidance distance by calculating the intersection of the shell's bounce trajectory and the transfer path. Subsequently, the control signal generation unit generates a real-time control signal based on the avoidance distance and the transfer command signal and sends this signal to the transfer control system.

[0042] Furthermore, to address obstacle issues in complex environments, the processing module also includes a path optimization unit. This unit analyzes image information of the pallet's surrounding environment to determine the presence of obstacles. If an obstacle is detected, its size, location, and direction of movement are further determined, and a safe distance for the transfer path is calculated using real-time control signals. The safe distance is calculated based on the obstacle's size, location, and direction of movement; for example, it is determined by calculating the shortest distance between the obstacle's edge and the transfer path. The path optimization unit generates a path optimization signal based on the safe distance and the obstacle's direction of movement and incorporates this signal into the real-time control signals.

[0043] In practical applications, the above method can be applied to automated transfer systems in investment casting production lines. For example, in a precision casting workshop, cold and hot mold shells are transported between different workstations via an automated transfer system. Industrial cameras are mounted above the transfer system to capture real-time images of the pallets and transmit them to a processing module. The processing module detects the pallet occupancy status and mold shell posture status through the above steps and generates real-time control signals based on the detection results to guide the transfer system's actions. This process effectively avoids mechanical impact accidents caused by abnormal occupancy or abnormal mold shell posture, significantly improving the stability and safety of the production process.

[0044] In one example, such as in an investment casting workshop, an automated transfer system is responsible for transporting cold and hot mold shells from the loading station to the mold-setting station. An industrial camera is mounted above the transfer system and connected to a processing module to capture real-time images of the pallets and the shells on them. The processing module then executes the following steps sequentially based on the received image data.

[0045] First, when the pallet enters the detection area of ​​the industrial camera, the camera begins acquiring image information of the pallet and transmits this information to the image analysis unit. The image analysis unit performs preprocessing operations on the received image, including noise removal, contrast enhancement, and edge feature extraction. Through these preprocessing steps, the pallet boundaries and shell contours in the image are clearly presented. Subsequently, the image analysis unit uses a contour detection algorithm to extract the boundary features of the pallet area and calculates the occupancy ratio of the pallet area. The occupancy ratio is calculated by the ratio of the number of pixels within the pallet area to the total number of pixels, thereby determining whether the pallet is empty or has an abnormal stacking condition.

[0046] Simultaneously, the image analysis unit extracts the contour features of the shell sandbox and calculates its tilt angle and offset distance based on geometric relationships. The tilt angle is obtained by measuring the angle between the two edge lines of the shell sandbox and the horizontal line, while the offset distance is calculated by determining the Euclidean distance between the center point of the shell sandbox and the center point of the tray. These parameters collectively describe the attitude state of the shell, providing basic data for subsequent anomaly detection.

[0047] After analyzing the pallet occupancy status and shell posture status, the anomaly detection unit determines whether the pallet is empty based on its available area. If the pallet is not empty, it further analyzes the shell distribution density on the pallet. The shell distribution density is calculated by statistically analyzing the ratio of the number of pixels occupied by shells within the pallet area to the total number of pixels. If the distribution density exceeds a preset threshold, it is determined to be an abnormal stacking. Based on this, the anomaly detection unit combines the tilt angle and offset distance in the shell posture status to assess whether the shell may tip over. For example, if the tilt angle exceeds a certain critical value or the offset distance exceeds the safe range, an anomaly status signal is generated and sent to the transfer control system.

[0048] To further improve detection accuracy, the center of gravity position calculation unit determines the volume and height of the shell by analyzing the pallet image information, and calculates the overturning moment based on the contact area between the bottom of the shell and the pallet. The contact area is obtained through a contour detection algorithm, while the overturning moment is calculated based on mechanical formulas. The stability index evaluation unit calculates the stability index of the shell based on the overturning moment, contact area, shell height, and tilt angle.

[0049] After generating an abnormal status signal, the control signal generation unit adjusts the transfer command signal based on the abnormal status signal and pallet image information, and generates a real-time control signal. Specifically, the control signal generation unit first determines the relative position between the transfer system and the shell, and calculates the avoidance distance of the transfer system by combining the trajectory contact point, contact time, relative position, and shell volume. The avoidance distance is calculated based on geometric relationships, such as determining the avoidance distance by calculating the intersection of the shell's bounce trajectory and the transfer path. Subsequently, the control signal generation unit generates a real-time control signal based on the avoidance distance and the transfer command signal, and sends this signal to the transfer control system.

[0050] Furthermore, to address obstacle issues in complex environments, the path optimization unit analyzes image information of the pallet's surrounding environment to determine the presence of obstacles. If an obstacle is detected, its size, location, and direction of movement are further determined, and a safe distance for the transfer path is calculated in conjunction with real-time control signals. The safe distance is calculated based on the obstacle's size, location, and direction of movement; for example, it is determined by calculating the shortest distance between the obstacle's edge and the transfer path. The path optimization unit generates a path optimization signal based on the safe distance and the obstacle's direction of movement, and incorporates this signal into the real-time control signals.

[0051] Exemplary device In one exemplary embodiment of this specification, a shell occupancy detection device 700 is also provided, such as... Figure 2 As shown, it includes: The first acquisition unit 701 is used to acquire pallet image information and determine the pallet occupancy status and shell posture status based on the pallet image information. The second acquisition unit 702 is used to acquire the transfer instruction signal and generate an abnormal status signal based on the pallet occupancy status, the transfer instruction signal and the shell posture status. The processing unit 703 is used to adjust the transfer instruction signal according to the abnormal status signal and the pallet image information, generate a real-time control signal, and control the transfer system to perform corresponding operations according to the real-time control signal.

[0052] In one embodiment, the first acquisition unit 701 is specifically used for: Analyze the pallet image information and extract the boundary features of the pallet area; Calculate the occupancy ratio of the tray area based on the boundary characteristics; The occupancy rate will be included in the pallet occupancy status. Based on the pallet image information, extract the contour features of the shell sand box; Based on the contour features, calculate the tilt angle and offset distance of the shell sandbox; The tilt angle and offset distance are incorporated into the shell attitude state.

[0053] In one embodiment, the pallet occupancy status includes the available pallet area, the transfer instruction signal includes an action start signal and an action stop signal, and the second acquisition unit 702 is specifically used for: Determine whether the pallet is empty based on its availability. If the tray is not empty, the shell distribution density on the tray is determined based on the tray image information. Determine if there are any stacking anomalies based on the shell distribution density; If there is an abnormality in the stacking, the tilt angle and offset distance of the shell are determined according to the shell's posture. Based on the tilt angle and offset distance, determine whether the shell is likely to overturn. If a rollover is possible, an abnormal status signal is generated and sent to the transfer control system.

[0054] In one embodiment, the processing unit 703 is specifically used for: Based on the pallet image information, determine the volume and height of the shell on the pallet; Calculate the center of gravity of the shell based on the abnormal state signal, shell volume, and shell height. The stability index of the shell is determined based on the position of the center of gravity and the shell's attitude. Based on the stability index and transfer command signal, a real-time control signal is generated; Real-time control signals are sent to the transfer control system.

[0055] In one embodiment, the processing unit 703 is specifically used for: Determine the contact area between the bottom of the shell and the tray based on the tray image information; Calculate the overturning moment of the shell based on the contact area, center of gravity position, and shell height; Based on the overturning moment and the tilt angle in the shell's attitude state, the stability index of the shell is determined and calculated using the following formula: S = (A∙h) / (M∙θ); Wherein, S represents the stability index, A represents the contact area, h represents the shell height, M represents the overturning moment, and θ represents the tilt angle.

[0056] In one embodiment, the processing unit 703 is further configured to: Acquire image information of the surrounding environment of the pallet, and determine whether there are obstacles based on the image information of the surrounding environment of the pallet; If there are obstacles, the volume, location, and direction of movement of the obstacles are determined based on the image information of the surrounding environment of the tray. Calculate the safe distance of the transfer path based on the location of obstacles and real-time control signals; Based on the safe distance and the direction of obstacle movement, a path optimization signal is generated; Incorporate path optimization signals into real-time control signals.

[0057] In one embodiment, the second acquisition unit 702 is specifically used for: Based on the tray image information, determine whether the shell has bounced; If bouncing occurs, the bouncing height and direction of the shell are determined based on the tray image information. Based on the bounce height and direction, determine whether the shell may detach from the tray; If it is possible to detach from the tray, the bounce trajectory of the shell is predicted based on the shell volume and shell height. Based on the bounce trajectory and transfer path, determine the trajectory contact point and contact time; The trajectory contact point and contact time are included in the abnormal status signal.

[0058] In one embodiment, the second acquisition unit 702 is specifically used for: Based on the pallet image information, determine the relative position between the transfer system and the shell; Calculate the avoidance distance of the transfer system based on the trajectory contact point, contact time, relative position, and shell volume; Based on the avoidance distance and transfer instruction signal, generate real-time control signals; Real-time control signals are sent to the transfer control system.

[0059] The shell occupancy detection device provided in this embodiment belongs to the same application concept as the shell occupancy detection method provided in the above embodiments of this application. It can execute the shell occupancy detection method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects of executing the shell occupancy detection method. Technical details not described in detail in this embodiment can be found in the specific processing content of the shell occupancy detection method provided in the above embodiments of this application, and will not be repeated here.

[0060] Exemplary device In one exemplary embodiment of this specification, an electronic device is also provided, such as Figure 3As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a shell occupancy detection method, which includes: Acquire pallet image information, and determine the pallet occupancy status and shell posture status based on the pallet image information; Obtain the transfer instruction signal, and generate an abnormal status signal based on the pallet occupancy status, the transfer instruction signal, and the shell posture status; Based on the abnormal status signals and pallet image information, the transfer instruction signals are adjusted to generate real-time control signals, and the transfer system is controlled to perform corresponding operations according to the real-time control signals.

[0061] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0062] Exemplary computer program products and storage media In addition to the methods, apparatuses, and devices described above, the shell occupancy detection method provided in the embodiments of this specification can also be a computer program product, which includes computer program instructions that, when executed by a processor, cause the processor to perform the steps in the shell occupancy detection method according to various embodiments of this specification as described in the "Exemplary Methods" section above.

[0063] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this specification. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages.

[0064] Furthermore, embodiments of this specification also provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor of the steps in the shell occupancy detection method according to various embodiments of this specification as described in the "Exemplary Methods" section above.

[0065] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this specification can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0066] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0067] The embodiments described above are merely illustrative of several implementation methods outlined in this specification. While the descriptions are specific and detailed, they should not be construed as limiting the scope of the solutions provided in this specification. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this specification, and these all fall within the scope of protection of this specification. Therefore, the scope of protection for this patent should be determined by the appended claims.

Claims

1. A method for detecting shell occupancy, characterized in that, include: Acquire pallet image information, and determine the pallet occupancy status and shell posture status based on the pallet image information; Obtain the transfer instruction signal, and generate an abnormal status signal based on the pallet occupancy status, the transfer instruction signal, and the shell posture status; Based on the abnormal status signal and the pallet image information, the transfer instruction signal is adjusted to generate a real-time control signal, and the transfer system is controlled to perform corresponding operations according to the real-time control signal.

2. The method according to claim 1, characterized in that, The step of determining the pallet occupancy status and shell posture status based on the pallet image information includes: Analyze the tray image information and extract the boundary features of the tray area; Calculate the occupancy ratio of the tray area based on the boundary features; The occupancy ratio is incorporated into the tray occupancy status; Based on the pallet image information, extract the contour features of the shell sandbox; Based on the aforementioned contour features, calculate the tilt angle and offset distance of the shell sandbox; The tilt angle and the offset distance are incorporated into the shell posture state.

3. The method according to claim 2, characterized in that, The pallet occupancy status includes the available pallet range; the transfer command signal includes an action start signal and an action stop signal; the generation of an abnormal status signal based on the pallet occupancy status, the transfer command signal, and the shell posture status includes: Based on the available range of the pallet, determine whether the pallet is in an empty state; If the tray is not empty, the shell distribution density on the tray is determined based on the tray image information. Based on the shell distribution density and placement angle, determine whether there is any stacking abnormality; If there is an abnormality in the stacking, the tilt angle and offset distance of the shell are determined according to the shell posture state. Based on the tilt angle and the offset distance, it is determined whether the shell may tip over or deflect. If rollover or deflection is possible, an abnormal status signal is generated and sent to the transfer control system.

4. The method according to claim 3, characterized in that, The step of adjusting the transfer instruction signal based on the abnormal status signal and the pallet image information to generate a real-time control signal includes: Based on the tray image information, determine the volume and height of the shell on the tray; The center of gravity of the shell is calculated based on the abnormal state signal, the shell volume, and the shell height. Based on the center of gravity position and the shell's attitude state, the stability index of the shell is determined; Based on the stability index and the transfer command signal, a real-time control signal is generated; The real-time control signal is sent to the transfer control system.

5. The method according to claim 4, characterized in that, Determining the stability index of the shell based on the center of gravity position and the shell's attitude state includes: Based on the tray image information, determine the contact area between the bottom of the shell and the tray; Calculate the overturning moment of the shell based on the contact area, the center of gravity position, and the shell height; Based on the overturning moment and the tilt angle in the shell's attitude state, the stability index of the shell is determined and calculated using the following formula: S = (A∙h) / (M∙θ); Wherein, S represents the stability index, A represents the contact area, h represents the shell height, M represents the overturning moment, and θ represents the tilt angle.

6. The method according to claim 4, characterized in that, After generating the real-time control signal based on the stability index and the transfer command signal, the method further includes: Acquire image information of the surrounding environment of the pallet, and determine whether there are obstacles based on the image information of the surrounding environment of the pallet; If there is an obstacle, the volume, position and direction of movement of the obstacle are determined based on the image information of the surrounding environment of the tray; Calculate the safe distance of the transfer path based on the location of the obstacle and the real-time control signal; Based on the safety distance and the direction of movement of the obstacle, a path optimization signal is generated; The path optimization signal is incorporated into the real-time control signal.

7. The method according to claim 3, characterized in that, The step of generating an abnormal status signal based on the pallet occupancy status, the transfer command signal, and the shell posture status includes: Based on the tray image information, determine whether the shell has bounced; If bouncing occurs, the bouncing height and direction of the shell are determined based on the tray image information. Based on the bounce height and bounce direction, determine whether the shell may detach from the tray; If it is possible to detach from the tray, the bounce trajectory of the shell is predicted based on the shell volume and the shell height. Based on the bouncing trajectory and the transfer path, determine the trajectory contact point and contact time; The trajectory contact point and the contact time are included in the abnormal state signal.

8. The method according to claim 7, characterized in that, The step of adjusting the transfer instruction signal based on the abnormal status signal and the pallet image information to generate a real-time control signal includes: Based on the pallet image information, determine the relative position between the transfer system and the shell; Calculate the avoidance distance of the transfer system based on the trajectory contact point, the contact time, the relative position, and the shell volume; Based on the avoidance distance and the transfer command signal, a real-time control signal is generated; The real-time control signal is sent to the transfer control system.

9. A shell occupancy detection device, characterized in that, include: The first acquisition unit is used to acquire pallet image information and determine the pallet occupancy status and shell posture status based on the pallet image information. The second acquisition unit is used to acquire the transfer instruction signal and generate an abnormal status signal based on the pallet occupancy status, the transfer instruction signal and the shell posture status. The processing unit is used to adjust the transfer instruction signal according to the abnormal status signal and the pallet image information, generate a real-time control signal, and control the transfer system to perform corresponding operations according to the real-time control signal.

10. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the shell occupancy detection method according to any one of claims 1 to 8 by executing the computer instructions.

Images