Robot grinding allowance multi-time planning and force adjusting method and system

Abstract

The invention relates to a robot grinding allowance multi-time planning and force adjusting method and system. The method comprises the following steps: monitoring the change of the weld seam allowance in real time to obtain real-time actual weld seam allowance data; establishing a material removal rate model based on the historical polishing data and the material characteristics; wherein the historical polishing data comprises material removal amounts of materials with different material characteristics under different polishing parameters; the material removal rate model is used for predicting the material removal amount according to the actual polishing force and material characteristics; the grinding parameters comprise the grinding speed, the grinding path, the size and direction of grinding force and / or the inclination angle of a grinding tool; when deviation exists between the actual weld seam allowance data and the target allowance, grinding parameters are dynamically adjusted based on the material removal rate model; future polishing requirements are predicted according to the current polishing state, and polishing parameters are adjusted in advance. The grinding allowance consistency machining and grinding precision are improved, and the grinding quality and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of robot grinding, and in particular to a method and system for multiple planning and force adjustment of robot grinding allowance. Background Art

[0002] In the field of modern industrial manufacturing, robot polishing technology is gradually replacing traditional manual polishing methods to improve production efficiency and product quality. With the continuous development of industrial automation, robot polishing technology has been widely used in many fields such as automobile manufacturing, aerospace, and machinery manufacturing. However, the traditional robot polishing method still has the following defects in practical applications:

[0003] The grinding allowance control is unstable; the traditional grinding method usually sets the grinding allowance based on experience. If the weld contour of the workpiece is uneven or the equipment shakes, it is easy to cause inconsistent allowances, resulting in deviations in subsequent processing or assembly links.

[0004] The grinding accuracy is not high; traditional grinding is mostly pre-programmed fixed trajectories, and real-time adaptive adjustment to local differences in welds cannot be achieved, resulting in difficulty in ensuring indicators such as surface roughness and flatness after grinding.

[0005] The material removal rate is difficult to predict; materials with different material properties have different material removal rates under different grinding forces, grinding speeds and environmental conditions. If there is no accurate estimation of the material removal rate, over-grinding or under-grinding is very likely to occur. Summary of the invention

[0006] To this end, the present invention provides a robot grinding allowance multiple planning and force adjustment method and system, which improves the grinding allowance consistency processing and grinding accuracy, and improves the grinding quality and efficiency.

[0007] In order to solve the above technical problems, the present invention provides a robot grinding allowance multiple planning and force adjustment method, comprising:

[0008] Monitor the changes of weld allowance in real time and obtain the real-time actual weld allowance data;

[0009] A material removal rate model is established based on historical grinding data and material properties; wherein the historical grinding data includes material removal amounts of materials with different material properties under different grinding parameters; the material removal rate model is used to predict the material removal amount according to the actual grinding force and material properties; the grinding parameters include grinding speed, grinding path, magnitude and direction of grinding force and / or tilt angle of grinding tool;

[0010] When there is a deviation between the actual weld allowance data and the target allowance, dynamically adjusting the grinding parameters based on the material removal rate model;

[0011] Predict future grinding needs based on current grinding status and adjust grinding parameters in advance.

[0012] In one embodiment of the present invention, real-time monitoring of changes in weld allowance to obtain real-time actual weld allowance data includes:

[0013] Deploy a vision sensor, wherein the vision sensor includes at least one high-resolution camera to ensure that the entire processing area of ​​the weld can be covered;

[0014] The real-time image of the weld area is collected by the visual sensor, and the real-time image is preprocessed, including denoising, contrast enhancement and brightness adjustment, so as to improve the image quality and reduce the impact of ambient light changes on monitoring.

[0015] In one embodiment of the present invention, a material removal rate model is established based on historical grinding data and material properties, including:

[0016] Collect data on the amount of material removed from grinding materials with different material properties under different grinding parameters;

[0017] The material properties include hardness, brittleness, elastic modulus, and thermal conductivity.

[0018] In one embodiment of the present invention, the material removal amount is expressed as:

[0019] R removal = k·F·t,

[0020] Among them, R removal represents the amount of material removal, k represents the material removal rate coefficient, F represents the grinding force, and t represents the grinding time.

[0021] In one embodiment of the present invention, when there is a deviation between the actual weld allowance data and the target allowance, dynamically adjusting the grinding parameters based on the material removal rate model includes:

[0022] Adopt interpolation algorithm to smoothly adjust the grinding trajectory and parameters, avoid sudden changes during the grinding process, and ensure the continuity and stability of processing;

[0023] When the deviation exceeds the tolerance range, the global path re-planning is triggered, and the grinding path is recalculated according to the actual situation of the current weld to ensure accurate coverage of the processing;

[0024] Real-time adjustment of the grinding tool’s posture, including tilt angle and feed depth, to ensure the best fit between the tool and the weld surface, avoiding over-grinding or under-grinding;

[0025] After adjusting the grinding parameters, continue to monitor the changes in weld allowance to verify whether the parameter update is effective;

[0026] If the deviation is not significantly reduced, repeat the path update process or continue to adjust the processing parameters to adapt to the changes in weld shape until the deviation is within the tolerance range.

[0027] In one embodiment of the present invention, predicting future grinding requirements based on the current grinding state and adjusting grinding parameters in advance includes:

[0028] Real-time collection of multi-dimensional data during the weld grinding process, the multi-dimensional data is obtained by means of a visual sensor, a current and voltage sensor, a sound sensor and a force sensor; wherein the visual sensor is used to obtain the morphology and surface features of the weld, and a deep learning algorithm is used to extract geometric features, margin distribution and surface state from the weld image obtained by the visual sensor; the current and voltage sensor is used to collect current and voltage signals, and the current and voltage signals are processed by a frequency domain analysis method to identify abnormal working conditions including sudden changes in the spindle load; the sound sensor is used to collect sound signals, and features are extracted from the sound signals using Mel frequency cepstrum coefficients to detect tool wear and vibration problems; the force sensor is used to monitor the uniformity of the grinding force, and the smoothness and deviation of the grinding trajectory are analyzed in combination with the displacement data;

[0029] The multi-dimensional data are fused through a deep neural network to obtain a weld grinding quality prediction model, which outputs quality indicators including surface roughness, allowance consistency and defect probability in real time; based on the weld grinding quality prediction model, future grinding requirements are predicted and grinding parameters are adjusted in advance.

[0030] In one embodiment of the present invention, it also includes:

[0031] Install multiple cameras around the sanding work area to monitor the sanding process.

[0032] The present invention also provides a robot grinding allowance multiple planning and force adjustment system, comprising:

[0033] The weld allowance monitoring module is used to monitor the changes in weld allowance in real time and obtain real-time actual weld allowance data.

[0034] A material removal rate model building module, used to build a material removal rate model based on historical grinding data and material properties; wherein the historical grinding data includes material removal amounts of materials with different material properties under different grinding parameters; the material removal rate model is used to predict the material removal amount according to the actual grinding force and material properties; the grinding parameters include grinding speed, grinding path, magnitude and direction of grinding force and / or tilt angle of grinding tool;

[0035] A grinding parameter adjustment module, used for dynamically adjusting the grinding parameters based on the material removal rate model when there is a deviation between the actual weld allowance data and the target allowance;

[0036] The prediction module is used to predict future grinding needs based on the current grinding status and adjust the grinding parameters in advance.

[0037] In one embodiment of the present invention, a safety monitoring module is also included to monitor abnormal conditions during the grinding process and automatically stop the grinding operation when potential risks are detected.

[0038] The above technical solution of the present invention has the following advantages compared with the prior art:

[0039] The robot grinding allowance multiple planning and force adjustment method and system described in the present invention captures high-definition images of the weld area in real time through a high-resolution camera, combines software algorithms to improve image contrast and brightness, more accurately identify weld contours and allowances, achieve high-precision grinding, provide uniform lighting under different lighting conditions, reduce shadows and reflections, significantly improve image quality, and provide more reliable data for subsequent image processing and analysis.

[0040] The material removal rate model established by the present invention through historical data and material properties can predict the material removal amount under different grinding forces, provide a scientific basis for the optimization of grinding force and process parameters, and dynamically optimize parameters such as grinding speed, path, force size and direction, tool tilt angle, etc. to adapt to materials and weld characteristics with different material properties and achieve consistency processing of allowances.

[0041] The present invention improves the consistency and quality of the finished product by automatically adjusting the grinding force, reducing deviation, and updating the grinding path in real time to adapt to changes in the weld shape. The user interface allows the operator to monitor the grinding process and manually adjust the grinding parameters when necessary, thereby enhancing the flexibility of operation and the adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to make the contents of the present invention more clearly understood, the present invention is further described in detail below based on specific embodiments of the present invention in conjunction with the accompanying drawings.

[0043] Figure 1 It is a flow chart of the robot grinding allowance multiple planning and force adjustment method of the present invention. DETAILED DESCRIPTION

[0044] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0045] In the present invention, if directions (up, down, left, right, front and back) are described, it is only for the convenience of describing the technical solution of the present invention, and does not indicate or imply that the technical features referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, it cannot be understood as a limitation of the present invention.

[0046] In the present invention, "several" means one or more, "multiple" means more than two, "greater than", "less than", "exceed" and the like are understood to exclude the number itself; "above", "below", "within" and the like are understood to include the number itself. In the description of the present invention, if there is a description of "first" or "second", it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0047] In the present invention, unless otherwise clearly defined, the words "set", "install", "connect" and the like should be understood in a broad sense, for example, they can be directly connected or indirectly connected through an intermediate medium; they can be fixedly connected or detachably connected or integrally formed; they can be mechanically connected or electrically connected or able to communicate with each other; they can be the internal connection of two elements or the interaction relationship between two elements. Those skilled in the art can reasonably determine the specific meanings of the above words in the present invention in combination with the specific content of the technical solution.

[0048] Example 1

[0049] Reference Figure 1 As shown, a robot grinding allowance multiple planning and force adjustment method of the present invention comprises:

[0050] S1. Monitor the changes of weld allowance in real time to obtain real-time actual weld allowance data.

[0051] It can be understood that the weld allowance refers to the excess material thickness on the weld surface relative to the target weld morphology (or ideal profile).

[0052] Specifically, by deploying a visual sensor at an appropriate position of the robot grinding system, the visual sensor includes at least one high-resolution camera to ensure that the entire processing area of ​​the weld can be covered. The camera has a high frame rate and high resolution to capture subtle allowance changes.

[0053] The real-time image of the weld area is collected by the visual sensor, and the real-time image is preprocessed, including denoising, contrast enhancement and brightness adjustment, so as to improve the image quality and reduce the impact of ambient light changes on monitoring.

[0054] In addition, image processing technologies such as edge detection, image segmentation (such as CannyEdge, threshold segmentation, etc.), or convolutional neural networks (CNN) based on deep learning can be used to extract the geometric features of the weld to obtain the margin distribution in the weld area. Using a high-resolution camera combined with a deep learning algorithm, high recognition accuracy can be maintained in the case of complex weld shapes or partial occlusion. It should be noted that the visual sensor can be adjusted according to the size of the workpiece and the size of the grinding area, as long as the camera can cover the corresponding processing area.

[0055] S2. Establishing a material removal rate model based on historical grinding data and material properties; wherein the historical grinding data includes the material removal amount of materials with different material properties under different grinding parameters; the material removal rate model is used to predict the material removal amount according to the actual grinding force and material properties; the grinding parameters include the grinding speed, grinding path, the magnitude and direction of the grinding force and / or the inclination angle of the grinding tool.

[0056] Specifically, a material removal rate model is established based on historical grinding data and material properties, including:

[0057] Collect data on the amount of material removed from grinding materials with different material properties under different grinding parameters;

[0058] The material properties include hardness H, brittleness B, elastic modulus E, and thermal conductivity λ.

[0059] The material removal amount is expressed as:

[0060] R removal = k·F·t,

[0061] Among them, R removal represents the amount of material removal, k represents the material removal rate coefficient, F represents the grinding force, and t represents the grinding time.

[0062] It should be noted that when establishing the material removal rate model, multiple linear regression and neural network are used to establish the mapping relationship between the material removal rate coefficient k and the material properties (hardness H, brittleness B, elastic modulus E, thermal conductivity λ, etc.) and grinding parameters. During actual grinding, the expected removal amount (target margin) can be estimated in real time based on the known properties of the current material and the grinding force.

[0063] For example, actual grinding test data under different materials and different grinding parameters are collected. For common materials (such as carbon steel, stainless steel, aluminum alloy, etc.), grinding experiments can be performed under several groups of grinding parameters (different grinding speeds, grinding paths, magnitudes and directions of grinding forces, and / or inclination angles of grinding tools, etc.). Before and after each group of experiments, the changes in material mass or thickness are measured, and the hardness H, brittleness B, elastic modulus E, thermal conductivity λ, etc. of the material properties are recorded, and the grinding time t and applied force F are recorded at the same time.

[0064] In addition, the change in material mass or thickness before and after grinding is measured by weighing, 3D measurement or laser thickness measurement; based on experience or literature, appropriate quantitative indicators are taken for material properties (for example, hardness can be measured by HV value or HRC value; brittleness can be measured by fracture toughness and other indicators); such as measurement data that obviously does not conform to the actual situation (sensor error, operating error, etc.). If some material properties are missing, interpolation or deletion of corresponding records can be used, but it is necessary to ensure that the coverage of the remaining data is wide enough. In order to reduce the impact of dimensional differences on the model, characteristics such as hardness, brittleness, elastic modulus, thermal conductivity, etc. can be standardized (such as Z-Score standardization) or normalized (such as mapping the values ​​to the [0,1] interval).

[0065] The dataset was divided into training set, validation set, and test set in a ratio of 6:2:2, 7:2:1, etc. to ensure that the model had enough data for learning and to retain some data for independent verification and testing.

[0066] S3. When there is a deviation between the actual weld allowance data and the target allowance, dynamically adjust the grinding parameters based on the material removal rate model.

[0067] Specifically, an interpolation algorithm (such as B-spline) is used to smoothly adjust the grinding trajectory and parameters to avoid sudden changes during the grinding process and ensure the continuity and stability of the processing. In industrial grinding, the continuity of the trajectory and force parameters is very important. If the change is too abrupt, it will cause unstable processing or lead to vibration, over-grinding and other problems. B-spline uses a series of control points to smoothly interpolate the curve, which can smoothly adjust the local area while ensuring the overall shape and avoid drastic jumps.

[0068] When the deviation exceeds the tolerance range, the global path replanning is triggered, and the grinding path is recalculated according to the actual situation of the current weld to ensure the continuity and stability of grinding;

[0069] During the dynamic adjustment process, the posture of the grinding tool, including the tilt angle and feed depth, is adjusted in real time to ensure the best fit between the tool and the weld surface to avoid over-grinding or under-grinding;

[0070] After adjusting the grinding parameters, continue to monitor the changes in weld allowance to verify whether the parameter update is effective;

[0071] If the deviation is not significantly reduced, repeat the path update process or continue to adjust the processing parameters to adapt to the changes in weld shape until the deviation is within the tolerance range.

[0072] Exemplarily, the deviation between the actual weld allowance data and the target allowance is compared. If the deviation is within the acceptable tolerance range, the existing grinding strategy is maintained; if it exceeds the threshold, dynamic adjustment is required. Thresholds can be set according to material properties, grinding accuracy requirements or quality inspection standards, such as ±0.05mm, ±0.1mm or ±0.2mm, etc.; if the deviation exceeds the threshold, it is deemed that a larger process adjustment or path replanning is required. At the same time, primary, secondary or tertiary thresholds can be set: when the deviation is within the primary threshold, the current grinding parameters are maintained, when it exceeds the secondary threshold, interpolation correction is performed, and when it exceeds the third threshold (maximum tolerance range), global path replanning is triggered.

[0073] Based on the material removal rate model and the current grinding force, grinding time and material properties, the possible material removal amount is estimated in real time. When a deviation is detected, reverse calculation is required to increase or decrease the grinding force or adjust the path within the variation range so that the weld allowance approaches the target value.

[0074] Through interpolation algorithms or global path replanning, parameters such as grinding trajectory or grinding force can be fine-tuned or significantly modified; by continuously monitoring the weld allowance and processing effect, once the new parameters take effect, it is necessary to verify whether the deviation has been reduced.

[0075] The original grinding path is discretized into several control points, and the position and posture (position and attitude) of some key points are corrected according to the actual weld contour and allowance information;

[0076] The B-spline algorithm is used to reconstruct the grinding trajectory on the updated control point sequence; key frames can also be set for interpolation of grinding force, tool inclination, etc. to ensure a smooth transition of the force from the original value to the new value.

[0077] When local adjustments still cannot control the deviation within a reasonable range, or the weld shape changes significantly (such as local weld bulges / depressions), the global path recalculation is triggered. This includes reconstructing the overall weld contour, using laser scanning or visual sensors to capture the 3D morphology of the current weld; using offline programming software, feasible domain search, or CAD / CAM-based algorithms to globally replan the grinding path on the new weld surface model; and combining the material removal rate model to allocate corresponding grinding force, feed speed, and grinding time to different parts.

[0078] When adjusting the grinding tool posture in real time, the inclination angle is adjusted to keep the grinding tool and the weld surface at a reasonable contact angle to improve the removal efficiency;

[0079] The amount of material removal can be affected by adjusting the feed depth. The multi-axis linkage of the robot end effector enables the grinding tool to achieve a composite motion of rotation and translation in three-dimensional space.

[0080] After each posture update, the removal speed of the weld residue, surface quality and grinding force uniformity under the new posture are detected by combining vision and force sensors.

[0081] If the deviation has not been significantly reduced, the process is repeated until it is within the tolerance range.

[0082] S4. Predict future grinding needs based on the current grinding status and adjust grinding parameters in advance.

[0083] Specifically, multi-dimensional data in the weld grinding process is collected in real time, and the multi-dimensional data is obtained by a visual sensor, a current and voltage sensor, a sound sensor and a force sensor; wherein the visual sensor is used to obtain the morphology and surface features of the weld, and a deep learning algorithm is used to extract geometric features, margin distribution and surface state from the weld image obtained by the visual sensor; the current and voltage sensor is used to collect current and voltage signals, and the current and voltage signals are processed by a frequency domain analysis method to identify abnormal working conditions including sudden changes in the spindle load; the sound sensor is used to collect sound signals, and Mel-frequency cepstral coefficients (MFCC) are used to extract features from the sound signals to detect the degree of wear and vibration of the tool; the force sensor is used to monitor the uniformity of the grinding force, and the smoothness and deviation of the grinding trajectory are analyzed in combination with the displacement data;

[0084] The multi-dimensional data are fused through a deep neural network to obtain a weld grinding quality prediction model, which outputs quality indicators including surface roughness, allowance consistency and defect probability in real time; based on the weld grinding quality prediction model, future grinding requirements are predicted and grinding parameters are adjusted in advance.

[0085] The deep neural network is a multi-input structure, including:

[0086] The visual sub-network is used to extract weld morphological features from images or point cloud data;

[0087] The sound sub-network is used to process audio features such as MFCC;

[0088] The current, voltage and force data sub-network is used to process the timing signals of the grinding spindle and the grinding force;

[0089] After integrating the above features at the high or middle layer of the network, the prediction results such as weld surface roughness, allowance consistency and defect probability are output.

[0090] In addition, during the grinding process, if a sharp surge in current, tool breakage, or obvious abnormal sound is detected, an emergency stop command is immediately triggered, and update instructions for parameters such as path or grinding force are sent to the robot controller through the industrial communication protocol to ensure safety.

[0091] For example, a visual sensor (high-resolution industrial camera) is installed on a fixed bracket at the end of the robot or the grinding station, with the field of view covering the weld area; a current and voltage sensor is integrated into the main shaft of the grinder or connected to the main shaft drive motor (servo system); a sound sensor (industrial microphone array or single-point microphone) is installed near the grinding station or at the end of the robot to collect grinding sounds in real time and judge tool wear, vibration or abnormal sounds; audio signals are usually collected at a sampling rate of 16kHz to 48kHz. A force sensor (six-dimensional force / torque sensor or end force sensor) is installed between the end flange of the robot and the grinder to detect the size, direction and uniformity of the grinding force; the host computer performs data collection, preprocessing, and deep learning model inference, and sends grinding parameter adjustment instructions to the robot controller.

[0092] Before and during weld grinding, the industrial camera acquires weld surface images at 10 to 30 fps (or higher); the image or point cloud data is sent to the host computer in real time for preprocessing (denoising, correction, ROI capture, etc.); when the grinder is working, the spindle current / voltage is recorded multiple times per second; if an abnormal instantaneous increase or decrease in current or voltage is detected, it is sent to the host computer for analysis (such as whether there is overload, idling, etc.) through event marking. The sound sensor continuously records, periodically (such as every 1 second or 2 seconds) intercepts a segment of audio frames, and transmits the audio data to the host computer through a dedicated interface for feature extraction (MFCC, etc.), so as to determine whether the grinding is stable and whether the tool has excessive wear or abnormal vibration. The force sensor continuously outputs the current grinding force (Fx, Fy, Fz), and each sampling period (such as 50 to 200Hz) is sent to the host computer for calculation of grinding trajectory deviation, force uniformity, etc., to assist in determining whether the clamping force needs to be adjusted or the path needs to be replanned.

[0093] A unified timestamp or industrial communication protocol (EtherCAT, PROFINET, ROS2, etc.) is used to ensure that the data of each sensor is aligned at the same time; the host computer merges multi-source data such as vision, current and voltage, sound, and force according to time series or frame numbers to form multimodal data.

[0094] A multi-input deep neural network is used, including a visual sub-network for processing image features; a sound sub-network for extracting MFCC features and then passing through a one-dimensional convolution or LSTM network; a current, voltage, and force data sub-network for processing time series signals in a fully connected layer or LSTM branch; feature fusion is performed at the high or middle layer of the network, and the quality prediction result is finally output. Among them, the surface roughness (Ra, Rz, etc.) is predicted by network regression, or classified by grades (excellent, qualified, to be improved, etc.); the margin consistency is output by outputting a score in the range of [0,1] or [0,100%] to indicate whether the current weld margin is uniform; the defect probability includes the probability of occurrence of defects such as holes, sand holes, overburning / cracks, etc., which are output through network classification.

[0095] By collecting a large amount of labeled data: each piece of data contains image clips, current and voltage waveforms, sound clips, and force sensor data, and is associated with real measured surface roughness, margin distribution, defect records, etc.; after these multimodal data are labeled, supervised learning is performed to train the deep neural network model.

[0096] When the system is grinding a certain section of the weld, the deep network comprehensively predicts the weld morphology, tool condition, force distribution, etc. of the subsequent workstations. If it is judged that "the probability of defects in the weld area 10 cm behind may be 80%, it will intervene in advance. Before entering the high-risk or thick margin area, reduce the grinding speed or change the feed path; if the margin in this area is judged to be too thick, the grinding force can be moderately increased (within the allowable range of the material); if the sound sensor + deep learning determines that the tool is severely worn, the system will be reminded to replace the grinding tool after the next working cycle; if serious abnormalities are found (such as a sharp surge in current, tool damage, etc.), an emergency stop can be triggered immediately to ensure human-machine safety. Once the model gives adjustment suggestions, the host computer issues new instructions to the robot controller through the industrial communication protocol, including updating the trajectory, adjusting the grinding force or posture parameters; after the robot executes, it continues to verify the adjustment effect through various sensors to achieve continuous closed-loop optimization.

[0097] Example 2

[0098] Based on the same inventive concept, this embodiment provides a robot grinding allowance multiple planning and force adjustment system, and its principle of solving the problem is similar to the robot grinding allowance multiple planning and force adjustment method, and the repeated parts will not be repeated.

[0099] This embodiment provides a robot grinding allowance multiple planning and force adjustment system, including: The present invention also provides a robot grinding allowance multiple planning and force adjustment system, including:

[0100] The weld allowance monitoring module is used to monitor the changes in weld allowance in real time and obtain real-time actual weld allowance data.

[0101] A material removal rate model building module, used to build a material removal rate model based on historical grinding data and material properties; wherein the historical grinding data includes material removal amounts of materials with different material properties under different grinding parameters; the material removal rate model is used to predict the material removal amount according to the actual grinding force and material properties; the grinding parameters include grinding speed, grinding path, magnitude and direction of grinding force and / or tilt angle of grinding tool;

[0102] A grinding parameter adjustment module, used for dynamically adjusting the grinding parameters based on the material removal rate model when there is a deviation between the actual weld allowance data and the target allowance;

[0103] The prediction module is used to predict future grinding needs based on the current grinding status and adjust the grinding parameters in advance;

[0104] Safety monitoring module, which is used to monitor abnormal conditions during the grinding process and automatically stop the grinding operation when potential risks are detected.

[0105] The security monitoring module uses cameras, sensors (such as infrared sensors, motion sensors and sound sensors) and other equipment (intrusion detection systems and access control devices) to monitor and record the status and activities of specific areas in real time to prevent theft and identify abnormal behavior.

[0106] In addition, it also includes a user interface module, which allows the operator to monitor the grinding process and manually adjust the grinding parameters when necessary. The user interface is connected to the robot control system through a real-time data exchange interface. The interface integrates digital input / output functions to receive user start / stop signals, emergency stop buttons and other simple switch control instructions.

[0107] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] Finally, it should be noted that the above specific implementation methods are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to examples, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A robot grinding allowance multiple planning and force adjustment method, characterized in that: include: Monitor the changes of weld allowance in real time and obtain the real-time actual weld allowance data; A material removal rate model is established based on historical grinding data and material properties; wherein the historical grinding data includes material removal amounts of materials with different material properties under different grinding parameters; the material removal rate model is used to predict the material removal amount according to the actual grinding force and material properties; the grinding parameters include grinding speed, grinding path, magnitude and direction of grinding force and / or tilt angle of grinding tool; When there is a deviation between the actual weld allowance data and the target allowance, dynamically adjusting the grinding parameters based on the material removal rate model; Predict future grinding needs based on current grinding status and adjust grinding parameters in advance.

2. A robot grinding allowance multiple planning and force adjustment method according to claim 1, characterized in that: Monitor the changes of weld allowance in real time and obtain the real-time actual weld allowance data, including: Deploy a vision sensor, wherein the vision sensor includes at least one high-resolution camera to ensure that the entire processing area of ​​the weld can be covered; The real-time image of the weld area is collected by the visual sensor, and the real-time image is preprocessed, including denoising, contrast enhancement and brightness adjustment, so as to improve the image quality and reduce the impact of ambient light changes on monitoring.

3. The method for multiple planning and force adjustment of robot grinding allowance according to claim 1, characterized in that: Build material removal rate models based on historical grinding data and material properties, including: Collect data on the amount of material removed from grinding materials with different material properties under different grinding parameters; The material properties include hardness, brittleness, elastic modulus, and thermal conductivity.

4. The method for multiple planning and force adjustment of robot grinding allowance according to claim 1, characterized in that: The material removal amount is expressed as: R removal =k·F·t, Among them, R removal represents the amount of material removal, k represents the material removal rate coefficient, F represents the grinding force, and t represents the grinding time.

5. The method for multiple planning and force adjustment of robot grinding allowance according to claim 1, characterized in that: When there is a deviation between the actual weld allowance data and the target allowance, dynamically adjusting the grinding parameters based on the material removal rate model includes: Adopt interpolation algorithm to smoothly adjust the grinding trajectory and parameters, avoid sudden changes during the grinding process, and ensure the continuity and stability of processing; When the deviation exceeds the tolerance range, the global path re-planning is triggered, and the grinding path is recalculated according to the actual situation of the current weld to ensure accurate coverage of the processing; Real-time adjustment of the grinding tool’s posture, including tilt angle and feed depth, to ensure the best fit between the tool and the weld surface, avoiding over-grinding or under-grinding; After adjusting the grinding parameters, continue to monitor the changes in weld allowance to verify whether the parameter update is effective; If the deviation is not significantly reduced, repeat the path update process or continue to adjust the processing parameters to adapt to the changes in weld shape until the deviation is within the tolerance range.

6. The method for multiple planning and force adjustment of robot grinding allowance according to claim 1, characterized in that: Predict future grinding needs based on current grinding status and adjust grinding parameters in advance, including: Real-time collection of multi-dimensional data during the weld grinding process, the multi-dimensional data is obtained by means of a visual sensor, a current and voltage sensor, a sound sensor and a force sensor; wherein the visual sensor is used to obtain the morphology and surface features of the weld, and a deep learning algorithm is used to extract geometric features, margin distribution and surface state from the weld image obtained by the visual sensor; the current and voltage sensor is used to collect current and voltage signals, and the current and voltage signals are processed by a frequency domain analysis method to identify abnormal working conditions including sudden changes in the spindle load; the sound sensor is used to collect sound signals, and features are extracted from the sound signals using Mel frequency cepstrum coefficients to detect tool wear and vibration problems; the force sensor is used to monitor the uniformity of the grinding force, and the smoothness and deviation of the grinding trajectory are analyzed in combination with the displacement data; The multi-dimensional data are fused through a deep neural network to obtain a weld grinding quality prediction model, which outputs quality indicators including surface roughness, allowance consistency and defect probability in real time; based on the weld grinding quality prediction model, future grinding requirements are predicted and grinding parameters are adjusted in advance.

7. The method for multiple planning and force adjustment of robot grinding allowance according to claim 1, characterized in that: Also includes: Install multiple cameras around the sanding work area to monitor the sanding process.

8. A robot grinding allowance multiple planning and force adjustment system, characterized in that: include: The weld allowance monitoring module is used to monitor the changes in weld allowance in real time and obtain real-time actual weld allowance data. A material removal rate model building module, used to build a material removal rate model based on historical grinding data and material properties; wherein the historical grinding data includes material removal amounts of materials with different material properties under different grinding parameters; the material removal rate model is used to predict the material removal amount according to the actual grinding force and material properties; the grinding parameters include grinding speed, grinding path, magnitude and direction of grinding force and / or tilt angle of grinding tool; A grinding parameter adjustment module, used for dynamically adjusting the grinding parameters based on the material removal rate model when there is a deviation between the actual weld allowance data and the target allowance; The prediction module is used to predict future grinding needs based on the current grinding status and adjust the grinding parameters in advance.

9. The robot grinding allowance multiple planning and force adjustment system according to claim 8, characterized in that: It also includes a safety monitoring module to monitor abnormal conditions during the grinding process and automatically stop the grinding operation when potential risks are detected.

Images