Dynamic monitoring and precision compensation system for industrial robot

Abstract

The invention discloses a dynamic monitoring and precision compensation system for an industrial robot. The dynamic monitoring and precision compensation system comprises a multi-clamping-jaw wear state monitoring module, a clamp holder fine control module and a combined wear limit judgment module. The multi-clamping-jaw abrasion state monitoring module collects abrasion state information of clamping jaws in real time through a micro-deformation monitoring unit and a frequency response analysis unit and evaluates the abrasion degree of the clamping jaws. The clamp holder fine control module calculates clamping correction parameters according to the abrasion information and the workpiece clamping data, and the clamping force and the clamping position are adjusted. And the combined wear limit judgment module monitors the wear state through a single clamping jaw threshold value judgment and overall mean value judgment unit, and outputs an early warning and provides a maintenance suggestion when the wear state exceeds a threshold value. According to the method, the wear limit threshold is corrected by inputting the clamping jaw and workpiece characteristics, the wear monitoring precision and the real-time compensation capability are improved, and the precision and the reliability of the industrial robot tail end clamp holder are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial robot control, and in particular to an industrial robot dynamic monitoring and precision compensation system. Background Art

[0002] In modern industrial production, industrial robots are widely used in automated processing, assembly, and handling tasks. Robot performance is particularly crucial in high-precision, repeatable operations. The gripper at the end of a robot, a key component, is responsible for precisely controlling the gripping, positioning, and placement of workpieces. To ensure efficient and stable operation, the gripper's performance must maintain a high degree of accuracy and consistency.

[0003] However, long-term use and repeated operation can cause wear in the gripper, especially when the jaws' contact surfaces frequently come into contact with the workpiece. This wear often leads to a weakening of the jaws' contact force and a shift in the gripping position, which in turn affects gripper accuracy, resulting in defective products or production accidents. Existing technologies primarily address this wear through regular inspection and maintenance, but these methods are unable to monitor and accurately compensate for gripper wear in real time, often resulting in reduced workpiece gripping accuracy and impacting production efficiency and quality.

[0004] To address this issue, existing technologies have proposed the use of wear sensors and monitoring systems to monitor the gripper's operating status. However, these technologies still have several drawbacks: existing wear monitoring methods are limited to crude wear detection and cannot accurately determine the degree and location of wear on each jaw, making it impossible to make precise compensation; existing technologies often rely on regular inspections and manual intervention, resulting in the equipment continuing to operate despite wear, making timely warnings and accurate maintenance impossible.

[0005] With the development of industrial automation, the requirements for precision and real-time performance of mechanical equipment are becoming increasingly higher. Therefore, how to monitor and compensate for the wear of the gripper in real time without affecting production has become a technical problem that needs to be solved urgently. Summary of the Invention

[0006] The object of the present invention is to provide an industrial robot dynamic monitoring and precision compensation system, which has the advantages of improving clamping precision and reliability.

[0007] The above technical objectives of the present invention are achieved through the following technical solutions:

[0008] Industrial robot dynamic monitoring and precision compensation system, including: multi-gripper wear state monitoring module, gripper fine control module and joint wear limit judgment module,

[0009] The multi-gripper wear state monitoring module is used to obtain wear state information of multiple grippers in the end gripper of the industrial robot during repeated gripping operations. The multi-gripper wear state monitoring module specifically includes:

[0010] The micro-deformation monitoring unit is set in the clamping contact area of each clamping jaw and is used to collect the normal compression deformation of each clamping jaw during the clamping action based on the capacitive micro-deformation sensor to obtain micro-deformation information to characterize the wear trend of the local contact part;

[0011] A frequency response analysis unit is provided in each jaw structure area and is used to obtain the vibration response frequency of each jaw in the clamping state based on laser excitation means to obtain frequency response information, so as to characterize the change of structural stiffness over time;

[0012] Multi-jaw wear state fusion unit, used to fuse the micro-deformation information and frequency response information of each jaw and output the wear state information of the corresponding jaw;

[0013] The clamper fine control module is used to calculate the clamping correction parameters according to the wear status information of each clamping jaw and the clamping information corresponding to the target workpiece, and adjust the clamping force and clamping position compensation of each clamping jaw according to the clamping correction parameters;

[0014] The combined wear limit judgment module judges whether the end clamp has reached the limit standard according to the wear status information, and outputs warning information and corresponding maintenance suggestions if it is judged that the limit standard has been reached.

[0015] Further configuration: the clamper fine control module specifically includes:

[0016] A target parameter input unit, the target parameter input unit is used to input or import clamping information of the target workpiece, the clamping information including clamping position, surface characteristics and structural parameters;

[0017] a deviation calculation unit, configured to calculate a deviation characteristic value of each clamping jaw based on clamping information of the target workpiece and wear state information corresponding to each clamping jaw;

[0018] A compensation control unit is used to generate corresponding clamping control parameters according to the deviation characteristic quantity, and adjust the clamping force and clamping position compensation of each clamping jaw according to the clamping control parameters.

[0019] Further setting: the deviation calculation unit includes:

[0020] A reference parameter extraction subunit is used to extract the contact position between the clamping jaw and the workpiece and the required clamping force when the clamping jaw is not worn according to the clamping information of the target workpiece, and generate a reference clamping parameter set;

[0021] The attenuation modeling subunit is used to calculate the clamping force attenuation and clamping position offset of the clamping jaws under the current wear state based on the wear state information of each clamping jaw, and generate a clamping capacity attenuation index;

[0022] The deviation calculation subunit is used to compare the reference clamping parameter set with the clamping capacity attenuation index, and calculate the deviation characteristic between the clamping performance of each clamping jaw in the current state and the target clamping performance.

[0023] Further configuration: the combined wear limit judgment module specifically includes:

[0024] A single-jaw threshold judgment unit is used to set a corresponding single-jaw wear limit threshold for each jaw, and when the wear status information of any jaw exceeds its corresponding single-jaw wear limit threshold, output a judgment result that the gripper has reached the limit standard;

[0025] The overall mean judgment unit is used to perform statistical calculations on the wear status information of all grippers to obtain the average wear level of the entire gripper. When the average level exceeds the set group tolerance upper limit, the unit outputs the judgment result that the gripper has reached the limit standard.

[0026] The judgment result output unit is used to output warning information and maintenance suggestions indicating that the wear of the clamp has reached the limit when the wear status information of any clamp exceeds the wear limit threshold of its single clamp, or the average wear level of the entire clamp exceeds the upper tolerance limit of the group.

[0027] Further configuration: the multi-gripper wear state fusion unit specifically includes:

[0028] The feature extraction subunit is used to perform multi-scale analysis on the micro-deformation information and frequency response information of each gripper to extract multi-dimensional features;

[0029] A feature fusion subunit, configured to fuse the multi-dimensional features according to a preset dimension to obtain a fused feature vector;

[0030] a wear classification subunit, configured to input the fused feature vector into a trained machine learning model, output a wear grade or continuous wear score corresponding to each jaw, and simultaneously output corresponding physical wear parameters;

[0031] The wear state information output unit is configured to output the physical wear parameter together with the wear level or the continuous score as wear state information.

[0032] Further configuration: the multi-scale analysis of the micro-deformation information and frequency response information of each gripper to extract multi-dimensional features specifically includes:

[0033] Performing wavelet transform or short-time Fourier transform on the micro-deformation information to extract micro-deformation features in the signal, wherein the micro-deformation features include maximum deformation, deformation change rate, and time-domain energy distribution;

[0034] The frequency response information is subjected to main frequency extraction and harmonic analysis to obtain frequency response characteristics, wherein the frequency response characteristics include main frequency offset and frequency bandwidth change.

[0035] Further configuration: the joint wear limit judgment module also includes a threshold correction unit, which is used to generate threshold correction parameters based on manually input clamping jaw characteristics and workpiece characteristics, and correct the single clamping jaw wear limit threshold and the group tolerance upper limit according to the threshold correction parameters to obtain a new single clamping jaw wear limit threshold and the group tolerance upper limit.

[0036] Further configuration: the threshold correction parameter generated according to the manually input gripper characteristics and workpiece characteristics specifically includes:

[0037] Calculating the wear resistance parameters of the gripper according to the input gripper characteristics, and generating a gripper correction factor based on the wear resistance parameters;

[0038] Calculating the wear sensitivity of the workpiece according to the input workpiece characteristics and generating a workpiece correction factor based on the wear sensitivity;

[0039] The clamping jaw correction factor and the workpiece correction factor are calculated according to the preset weighted values to generate the threshold correction parameter.

[0040] In summary, the present invention has the following beneficial effects: Through the multi-jaw wear status monitoring module, the system can obtain real-time wear status information for each jaw, including micro-deformation and frequency response data, accurately assessing wear conditions. Based on this real-time wear data, the gripper fine control module can immediately calculate the required clamping force correction and position compensation parameters, ensuring that the gripper's gripping accuracy is always maintained at an optimal state. By continuously monitoring and accurately compensating for wear conditions, the system effectively avoids wear-induced clamping force attenuation and position shift, thereby improving the accuracy and operational stability of the robot gripper. The system can automatically adjust the gripper's operating parameters, eliminating manual adjustments and error accumulation, and enhancing overall operational accuracy and reliability. The combined wear limit judgment module, through both single-jaw threshold judgment and overall mean judgment functions, can proactively detect the risk of wear reaching its limit. When the wear level of a particular jaw exceeds a set threshold, or the wear level of the entire gripper reaches the group tolerance limit, the system automatically issues an alert, prompting timely maintenance or replacement, and providing maintenance recommendations, helping to reduce unexpected failures, lower repair costs, and extend equipment life.

[0041] The threshold correction unit allows the wear limit threshold to be adjusted based on manually input gripper characteristics and workpiece characteristics, enabling the system to adaptively adjust according to actual usage and provide personalized precision control. The generation process of the gripper correction factor and the workpiece correction factor ensures that the system can flexibly respond to the wear characteristics under different working conditions and operating conditions, further improving the adaptability and accuracy of the system.

[0042] By reducing the clamping accuracy error caused by wear, damage to the workpiece caused by improper clamping is avoided, and production efficiency is improved. The system can adjust the clamping parameters in real time, reducing the robot's idle time and failure rate, and ensuring continuous and efficient production. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is an overall structural block diagram of the embodiment. DETAILED DESCRIPTION

[0044] The present invention will be further described in detail below with reference to the accompanying drawings.

[0045] Example:

[0046] like Figure 1 As shown in the figure, the industrial robot dynamic monitoring and precision compensation system includes: a multi-gripper wear state monitoring module, a gripper fine control module and a joint wear limit judgment module.

[0047] The multi-gripper wear state monitoring module is used to obtain wear state information of multiple grippers in the end gripper of the industrial robot during repeated gripping operations. The multi-gripper wear state monitoring module specifically includes:

[0048] The micro-deformation monitoring unit is set in the clamping contact area of each clamping jaw and is used to collect the normal compression deformation of each clamping jaw during the clamping action based on the capacitive micro-deformation sensor to obtain micro-deformation information to characterize the wear trend of the local contact part;

[0049] A frequency response analysis unit is provided in each jaw structure area and is used to obtain the vibration response frequency of each jaw in the clamping state based on laser excitation means to obtain frequency response information, so as to characterize the change of structural stiffness over time;

[0050] Multi-jaw wear state fusion unit, used to fuse the micro-deformation information and frequency response information of each jaw and output the wear state information of the corresponding jaw;

[0051] The clamper fine control module is used to calculate the clamping correction parameters according to the wear status information of each clamping jaw and the clamping information corresponding to the target workpiece, and adjust the clamping force and clamping position compensation of each clamping jaw according to the clamping correction parameters;

[0052] The combined wear limit judgment module judges whether the end clamp has reached the limit standard according to the wear status information, and outputs warning information and corresponding maintenance suggestions if it is judged that the limit standard has been reached.

[0053] The main function of this system is to ensure that the robot end gripper maintains efficient and accurate clamping force during repetitive work by monitoring the wear status of the gripper in real time and making precise clamping corrections based on the characteristics of the workpiece. This system monitors the wear of the gripper in real time through the multi-gripper wear status monitoring module, and uses frequency response analysis and micro-deformation monitoring technology to obtain wear status information. This information is transmitted to the gripper fine control module to adjust the gripper's clamping force and clamping position. At the same time, the wear limit judgment module dynamically adjusts the wear threshold through analysis of the wear status information, evaluates the wear status of the gripper, and issues an early warning when the wear approaches the limit. The main goal of this system is to ensure that the gripper can maintain optimal working condition in an environment where industrial robots operate for a long time and at high frequency through precise wear monitoring and adaptive clamping correction strategies, so as to avoid insufficient clamping force or positioning errors caused by wear.

[0054] The multi-gripper wear state fusion unit specifically includes:

[0055] The feature extraction subunit is used to perform multi-scale analysis on the micro-deformation information and frequency response information of each gripper to extract multi-dimensional features;

[0056] A feature fusion subunit, configured to fuse the multi-dimensional features according to a preset dimension to obtain a fused feature vector;

[0057] a wear classification subunit, configured to input the fused feature vector into a trained machine learning classification model, output a wear grade or continuous wear score corresponding to each jaw, and simultaneously output corresponding physical wear parameters;

[0058] The wear state information output unit is configured to output the physical wear parameter together with the wear level or the continuous score as wear state information.

[0059] The multi-scale analysis of the micro-deformation information and frequency response information of each gripper to extract multi-dimensional features specifically includes:

[0060] Performing wavelet transform or short-time Fourier transform on the micro-deformation information to extract micro-deformation features in the signal, wherein the micro-deformation features include maximum deformation, deformation change rate, and time-domain energy distribution;

[0061] The frequency response information is subjected to main frequency extraction and harmonic analysis to obtain frequency response characteristics, wherein the frequency response characteristics include main frequency offset and frequency bandwidth change.

[0062] The multi-gripper wear state monitoring module is responsible for acquiring wear state information for multiple grippers in the end-user gripper of an industrial robot. This module consists of three main components: a micro-deformation monitoring unit, a frequency response analysis unit, and a multi-gripper wear state fusion unit.

[0063] The micro-deformation monitoring unit is used to collect information on the micro-deformation of the jaws during the clamping process in order to characterize the wear trend of the jaws. Capacitive micro-deformation sensors are arranged in the clamping contact area of each jaw. The sensor measures the normal deformation of the jaw under the action of the clamping force to collect the micro-deformation of the jaws in real time. The sensor array is arranged in the clamping contact area but away from the clamping surface in contact with the workpiece to avoid affecting the clamping process. The micro-deformation data collected by the sensor is digitally converted through the analog signal acquisition system. The data acquisition module ensures that it can handle small changes in the clamping action through high-speed sampling and data caching functions.

[0064] The frequency response analysis unit obtains the vibration response frequency of the gripper through laser excitation and analyzes the changes in structural stiffness. Using a pulsed laser as the excitation source, the inherent vibration mode of the gripper is stimulated by the laser reflection method. The laser is directly irradiated on a specific force-bearing area on the surface of the gripper to stimulate its structural vibration. The laser reflection signal is received by the photodetector and converted into a frequency response signal. The excitation occurs when the gripping task is not in progress. After the gripping action is completed, the vibration response of the gripper is continuously collected, and the laser reflection signal is recorded by the photodetector. The vibration frequency of the gripper is obtained through the high-speed data acquisition module, and its frequency response characteristics are measured.

[0065] The multi-gripper wear state fusion unit is responsible for performing multi-dimensional feature extraction and fusion processing on the signals from the micro-deformation monitoring unit and the frequency response analysis unit to generate the wear state information of each gripper.

[0066] The feature extraction subunit performs multi-scale analysis on micro-deformation information and frequency response information through wavelet transform or short-time Fourier transform (STFT), thereby extracting multi-dimensional features. The specific process is as follows:

[0067] Perform wavelet transform on the collected micro-deformation signal to extract the instantaneous frequency and time domain characteristics of the signal. Wavelet transform formula:

[0068]

[0069] Among them, ψ* is the mother wavelet, a is the scale factor, b is the translation factor, and x(t) is the signal.

[0070] The following key features are extracted from the results of wavelet transform: maximum deformation: calculate the peak deformation of the signal; deformation change rate: calculate the rate of change of deformation, reflecting the wear rate of the contact point of the gripper; time domain energy distribution: obtain the time domain distribution of the deformation signal by calculating the energy spectrum density of the signal.

[0071] Perform fast Fourier transform (FFT) on the frequency response signal to extract the signal's main frequency offset and frequency bandwidth change from the frequency domain. The fast Fourier transform formula is:

[0072]

[0073] Where X(f) is the frequency response function, x(t) is the time domain signal, and f is the frequency.

[0074] The following key features are extracted from the FFT results: main frequency offset, which reflects the attenuation of the gripper stiffness and is related to the degree of gripper wear; frequency bandwidth change, which is used to characterize the degree of structural loss of the gripper.

[0075] The feature fusion subunit fuses the micro-deformation features and the frequency response features according to the preset dimensions to obtain a fused feature vector. The specific process is as follows:

[0076] Preset dimensions: Micro-deformation feature dimensions: including maximum deformation, deformation change rate, time domain energy distribution, etc. Frequency response feature dimensions: including main frequency offset, frequency bandwidth change, etc.

[0077] Different weights are assigned to each feature dimension. Common weighting methods include weighted average method and principal component analysis (PCA).

[0078] After the micro-deformation features and the frequency response features are fused according to the preset dimensions, a fused feature vector is obtained, which contains the multi-dimensional wear information of the gripper.

[0079] The wear classification subunit inputs the fused feature vector into the trained machine learning model, outputs the wear level or continuous wear score corresponding to each gripper, and simultaneously outputs the corresponding physical wear parameters.

[0080] The fused feature vector extracts multi-scale features from the gripper's micro-deformation information and frequency response information, and fuses them to obtain a feature vector containing multiple dimensions (for example, deformation change rate, main frequency offset, frequency bandwidth change, etc.). These feature vectors will be input into a trained machine learning classification model. Based on the complexity and nonlinear relationship of the feature vector, commonly used machine learning classification models include: Support Vector Machine (SVM): suitable for handling small sample and high-dimensional classification problems, and can effectively handle nonlinear problems; Random Forest (RF): classifies data by constructing multiple decision trees, and can handle classification problems of high-dimensional features; Neural Network (ANN): particularly suitable for handling complex nonlinear relationships, and can capture complex relationships between features through multiple levels of hidden layers.

[0081] Support vector machines (SVM) are a widely used machine learning method for classification and regression problems, particularly well-suited to handling nonlinear relationships. For wear grade classification, SVM can effectively separate data by constructing a hyperplane. For continuous wear scores, SVM can also be applied to support vector regression (SVR) for regression analysis.

[0082] Input feature vector (X): Features extracted through multi-scale analysis, including gripper micro-deformation information (such as maximum deformation and deformation change rate) and frequency response information (such as main frequency offset and frequency bandwidth change). These features are combined into a multi-dimensional fusion feature vector.

[0083] Training dataset: includes frequency response data and micro-deformation data of each gripper as input features, and the target variable is the wear level (such as "light wear", "moderate wear", "heavy wear") or a continuous wear score (such as a score of 0-100).

[0084] For wear grade, SVM maps feature vectors into a high-dimensional space and then searches for the optimal hyperplane within that space for accurate classification. For continuous wear scores, support vector regression (SVR) is used to predict the wear score by minimizing the regression error. The training process uses cross-validation to select the optimal kernel function (such as the Gaussian radial basis kernel (RBF)) and optimize the model parameters.

[0085] The trained SVM classification model or SVR regression model is used as input for the fused feature vector X, and the following results are output: wear level (e.g., "light wear," "moderate wear," or "heavy wear"); continuous wear score (e.g., a wear score of 0-100).

[0086] Neural networks (ANNs) are particularly well-suited to handling complex nonlinear relationships and can capture nonlinear relationships between features through multiple layers of neurons. For physical wear parameters (stiffness attenuation and contact area change), we will use a neural network regression model to predict these continuous variables.

[0087] Input feature vector (X): Similar to the SVM model, the input feature vector of the neural network is a fusion feature vector of micro-deformation information and frequency response information.

[0088] Training data set: includes frequency response data and micro-deformation data (input features) of each gripper, as well as target variables such as stiffness attenuation (△K) and contact area change (△A).

[0089] Structure: The neural network consists of an input layer, one or more hidden layers (using ReLU activation function), and an output layer (outputting stiffness attenuation and contact area change).

[0090] Regression model: The output of the neural network is two continuous values: stiffness attenuation (△K) and contact area change (△A).

[0091] Training process: Using mean squared error (MSE) as the loss function, the network weights are optimized to minimize the prediction error. During training, the weights are updated through backpropagation, and parameters are optimized using optimizers such as Adam.

[0092] Through the trained neural network regression model, given the input fusion feature vector X, the network outputs: stiffness attenuation (△K), which indicates the degree of attenuation of the gripper stiffness; contact area change (△A), which indicates the change in the contact area between the gripper and the workpiece.

[0093] Using these two models, the wear classification subunit can simultaneously output: wear grade or continuous wear score (using support vector machines); stiffness attenuation and contact area change, i.e., physical wear parameters (using artificial neural networks). This multi-model combination enables simultaneous classification and regression tasks, providing a more comprehensive assessment of wear status.

[0094] In this implementation, the multi-jaw wear state fusion unit effectively integrates micro-deformation information and frequency response data through multi-scale analysis and machine learning methods to generate jaw wear state information. This method extracts features using techniques such as wavelet transform, short-time Fourier transform, and fast Fourier transform, and uses machine learning models to classify wear and calculate physical wear parameters. Ultimately, the system outputs a wear grade or continuous wear score, providing accurate physical wear parameters.

[0095] The gripper fine control module specifically includes:

[0096] A target parameter input unit, the target parameter input unit is used to input or import clamping information of the target workpiece, the clamping information including clamping position, surface characteristics and structural parameters;

[0097] a deviation calculation unit, configured to calculate a deviation characteristic value of each clamping jaw based on clamping information of the target workpiece and wear state information corresponding to each clamping jaw;

[0098] A compensation control unit is used to generate corresponding clamping control parameters according to the deviation characteristic quantity, and adjust the clamping force and clamping position compensation of each clamping jaw according to the clamping control parameters.

[0099] The deviation calculation unit includes:

[0100] A reference parameter extraction subunit is used to extract the contact position between the clamping jaw and the workpiece and the required clamping force when the clamping jaw is not worn according to the clamping information of the target workpiece, and generate a reference clamping parameter set;

[0101] The attenuation modeling subunit is used to calculate the clamping force attenuation and clamping position offset of the clamping jaws under the current wear state based on the wear state information of each clamping jaw, and generate a clamping capacity attenuation index;

[0102] The deviation calculation subunit is used to compare the reference clamping parameter set with the clamping capacity attenuation index, and calculate the deviation characteristic between the clamping performance of each clamping jaw in the current state and the target clamping performance.

[0103] The gripper fine control module calculates the clamping correction parameters based on the clamping information of the target workpiece and the wear status information of each jaw, and accurately adjusts the clamping force and clamping position of each jaw.

[0104] The function of the target parameter input unit is to receive the clamping information of the target workpiece, including the clamping position, surface characteristics and structural parameters. This information is the basis for clamping correction. The clamping position represents the clamping area of the target workpiece, which is usually obtained through a visual sensor or a position sensor. For more complex workpieces, the clamping position can be further adjusted by a force sensor or a torque sensor. The surface characteristics of the workpiece include surface roughness, hardness, friction coefficient, etc. These characteristics affect the contact quality between the clamp and the workpiece and the degree of wear of the clamp. It can be obtained through surface sensors (such as laser scanning, friction force sensors, etc.). The structural parameters of the workpiece include shape, size, mass distribution, etc., which affect the clamping method of the clamp and are usually obtained through three-dimensional scanning or mechanical analysis models.

[0105] The deviation calculation unit calculates a deviation feature amount of the gripper based on gripping information of the target workpiece and wear state information of the gripper.

[0106] The reference parameter extraction subunit is used to extract the contact position and required clamping force of the clamping jaws and the workpiece when the clamping jaws are not worn, based on the clamping information of the target workpiece, and generate a reference clamping parameter set. Extraction of contact position: When the clamping jaws are not worn, the contact position is determined by the size and shape of the target workpiece and the contact area of the clamping jaws. The precise position where the clamping jaws contact the workpiece is determined by geometric modeling or mechanical analysis, and the coordinates of the position are generated in a coordinate system established based on the workpiece as the standard, and the coordinates are used as the contact position. Calculation of clamping force: The calculation of clamping force can adopt the contact mechanics model, especially the Hertz contact model, which is a classic theory that describes the contact force between the surfaces of two objects. When the clamping jaws are in contact with the workpiece, the clamping force is not only related to the deformation of the clamping jaws, but also to the geometric shape and material properties of the contact area. The clamping force calculation formula (Hertz contact theory):

[0107]

[0108] Where: F is the clamping force, R is the equivalent radius of the contact area, δ is the contact depth (deformation), that is, the compressive displacement between the clamping jaw and the workpiece surface can be obtained through experiments, and E* is the equivalent Young's modulus of the contact body, which is calculated as follows:

[0109]

[0110] Where E1 and E2 are the Young’s moduli of the gripper and workpiece, respectively.

[0111] The reference clamping parameter set includes the contact position and clamping force, and serves as the ideal clamping parameters of the jaws and workpiece in the unworn state.

[0112] The attenuation modeling subunit calculates the clamping force attenuation and clamping position offset of the clamp under the current wear state based on the stiffness attenuation and contact area change in the wear state information. Combining the contact area change, stiffness attenuation, and clamping force attenuation, a comprehensive nonlinear clamping force attenuation model can be obtained. The clamping force attenuation is affected by the dual nonlinear effects of contact area change and stiffness attenuation. We obtain:

[0113]

[0114] Among them: △A is the change in contact area, △K is the stiffness attenuation, A initial is the contact area in the unworn state, K initial is the stiffness in the unworn state, α K and α A is the weight coefficient for stiffness attenuation and contact area change, γ A is the nonlinear exponent of the change in contact area to the attenuation of the clamping force, γ Kis the nonlinear exponent of stiffness attenuation to clamping force attenuation, F base It is the reference holding force in the unworn state.

[0115] The change in contact area will cause the offset of the clamping position, and this relationship is nonlinear. The effect of the change in contact area on the offset of the clamping position follows a power law relationship:

[0116]

[0117] Where: △PA is the clamping position offset caused by the change in contact area, β A is the influence coefficient of contact area change on clamping position, μ A It is the nonlinear index of contact area change versus clamping position offset.

[0118] Stiffness degradation also affects the clamping position. Wear causes the jaws to become softer and the contact surface position to shift. We can calculate the offset of the clamping position by using stiffness degradation. This relationship follows a power law relationship:

[0119]

[0120] △P K is the clamping position offset caused by stiffness attenuation, β K is the coefficient of influence of stiffness attenuation on the clamping position, μ K is the nonlinear exponent of stiffness decay versus clamping position offset.

[0121] Combining the effects of contact area change and stiffness attenuation, the final clamping position offset is obtained:

[0122] △P=λ1·△P A +λ2·△P K

[0123] in: λ 1 and λ2 are weight coefficients, which represent the relative influence of contact area change and stiffness attenuation on the clamping position offset.

[0124] The clamping force attenuation and the clamping position offset are output as the clamping capacity attenuation indicators.

[0125] The deviation calculation subunit compares the baseline clamping parameter set and the clamping capacity attenuation index, that is, the baseline clamping parameter set represents the clamping force required by each jaw in the unworn state and the clamping coordinates on the workpiece. Now the clamping capacity attenuation index of each jaw represents the amount of clamping force attenuation and the amount of clamping position offset of each jaw under the same control parameters in the current wear state. By comparing the data of the two, the amount of clamping force increase for each jaw and the amount of adjustment of the position of each jaw relative to the workpiece in order to achieve the clamping force and clamping position in the unworn state can be obtained, that is, the deviation characteristic quantity.

[0126] The compensation control unit converts the deviation characteristic quantity into the clamping control parameters of the gripper and outputs them to the control system of the industrial robot, so that the control system adjusts the control parameters of each gripper and compensates the clamping force and clamping position to achieve the clamping effect in an unworn state, thereby improving the clamping accuracy of the industrial robot.

[0127] The combined wear limit judgment module specifically includes:

[0128] The single-jaw threshold judgment unit is used to set the corresponding single-jaw wear limit threshold for each jaw, and output the judgment result that the clamp has reached the limit standard when the wear status information of any jaw exceeds its corresponding single-jaw wear limit threshold; the wear limit threshold of each jaw is related to the service life, material properties, workload and other factors of the jaw. When the system is initially configured, the system will set the wear limit threshold for each jaw based on the characteristics of the jaw and the characteristics of the workpiece. When the system receives wear status information from the multi-jaw wear status monitoring module, the single-jaw threshold judgment unit will compare the wear status information of each jaw with the set wear limit threshold. If the wear status information of any jaw exceeds its threshold, it means that the jaw has reached the limit standard.

[0129] The overall mean judgment unit is used to perform statistical calculations on the wear status information of all jaws to obtain the average wear level of the entire clamp, and when the average level exceeds the set group tolerance upper limit, output the judgment result that the clamp has reached the limit standard; the function of the overall mean judgment unit is to obtain the overall wear level of the clamp by performing statistical calculations on the wear status information of all jaws, and judge whether the average level exceeds the group tolerance upper limit, so as to judge whether the clamp has reached the wear limit.

[0130] The judgment result output unit is used to output warning information and maintenance suggestions indicating that the wear of the clamp has reached the limit when the wear status information of any clamp exceeds the wear limit threshold of its single clamp, or the average wear level of the entire clamp exceeds the upper tolerance limit of the group, so as to guide subsequent maintenance or replacement operations.

[0131] The joint wear limit judgment module also includes a threshold correction unit, which is used to generate threshold correction parameters based on manually input clamping jaw characteristics and workpiece characteristics, and to correct the single clamping jaw wear limit threshold and the group tolerance upper limit according to the threshold correction parameters to obtain a new single clamping jaw wear limit threshold and the group tolerance upper limit.

[0132] The generation of threshold correction parameters based on manually input gripper characteristics and workpiece characteristics specifically includes:

[0133] Calculating the wear resistance parameters of the gripper according to the input gripper characteristics, and generating a gripper correction factor based on the wear resistance parameters;

[0134] Calculating the wear sensitivity of the workpiece according to the input workpiece characteristics and generating a workpiece correction factor based on the wear sensitivity;

[0135] The clamping jaw correction factor and the workpiece correction factor are calculated according to the preset weighted values to generate the threshold correction parameter.

[0136] The wear resistance parameter can be calculated by factors such as material hardness (H), friction coefficient (μ) and working temperature (T). Assuming that the wear resistance parameter M claw The relationships between these factors are:

[0137] M claw =k1·H·μ·e -α·T

[0138] Where: H is the hardness of the jaw material (unit: HV, Vickers hardness), μ is the friction coefficient between the jaw surface and the workpiece, T is the operating temperature (unit: °C), which affects the thermal expansion and fatigue of the material, k1 is an empirical coefficient determined based on experimental data, and α is the temperature-dependent wear factor. The jaw correction factor is calculated by comparing the jaw's wear resistance parameters with the preset baseline wear resistance parameters.

[0139] The wear sensitivity of a workpiece can be calculated using the following formula, which takes into account the effects of workpiece hardness and surface roughness:

[0140]

[0141] Among them: H workpiece is the hardness of the workpiece (unit: HV), R workpiece is the surface roughness of the workpiece (unit: μm), k2 is an empirical coefficient determined based on experimental data. The workpiece correction factor is calculated by comparing this wear sensitivity with a preset baseline wear sensitivity.

[0142] These correction measures ensure the high accuracy of the system in practical applications and can dynamically adjust the wear judgment criteria according to actual usage.

[0143] In summary, the present invention has the following beneficial effects: Through the multi-jaw wear status monitoring module, the system can obtain real-time wear status information for each jaw, including micro-deformation and frequency response data, accurately assessing wear conditions. Based on this real-time wear data, the gripper fine control module can immediately calculate the required clamping force correction and position compensation parameters, ensuring that the gripper's gripping accuracy is always maintained at an optimal state. By continuously monitoring and accurately compensating for wear conditions, the system effectively avoids wear-induced clamping force attenuation and position shift, thereby improving the accuracy and operational stability of the robot gripper. The system can automatically adjust the gripper's operating parameters, eliminating manual adjustments and error accumulation, and enhancing overall operational accuracy and reliability. The combined wear limit judgment module, through both single-jaw threshold judgment and overall mean judgment functions, can proactively detect the risk of wear reaching its limit. When the wear level of a particular jaw exceeds a set threshold, or the wear level of the entire gripper reaches the group tolerance limit, the system automatically issues an alert, prompting timely maintenance or replacement, and providing maintenance recommendations, helping to reduce unexpected failures, lower repair costs, and extend equipment life.

[0144] The threshold correction unit allows the wear limit threshold to be adjusted based on manually input gripper characteristics and workpiece characteristics, enabling the system to adaptively adjust according to actual usage and provide personalized precision control. The generation process of the gripper correction factor and the workpiece correction factor ensures that the system can flexibly respond to the wear characteristics under different working conditions and operating conditions, further improving the adaptability and accuracy of the system.

[0145] By reducing the clamping accuracy error caused by wear, damage to the workpiece caused by improper clamping is avoided, and production efficiency is improved. The system can adjust the clamping parameters in real time, reducing the robot's idle time and failure rate, and ensuring continuous and efficient production.

[0146] The above-described embodiments do not constitute a limitation on the scope of protection of this technical solution. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the above-described embodiments shall be included in the scope of protection of this technical solution.

Claims

1. Industrial robot dynamic monitoring and precision compensation system, characterized by: include: Multi-gripper wear status monitoring module, gripper fine control module and joint wear limit judgment module, The multi-gripper wear state monitoring module is used to obtain wear state information of multiple grippers in the end gripper of the industrial robot during repeated gripping operations. The multi-gripper wear state monitoring module specifically includes: The micro-deformation monitoring unit is set in the clamping contact area of each clamping jaw and is used to collect the normal compression deformation of each clamping jaw during the clamping action based on the capacitive micro-deformation sensor to obtain micro-deformation information to characterize the wear trend of the local contact part; A frequency response analysis unit is provided in each jaw structure area and is used to obtain the vibration response frequency of each jaw in the clamping state based on laser excitation means to obtain frequency response information, so as to characterize the change of structural stiffness over time; Multi-jaw wear state fusion unit, used to fuse the micro-deformation information and frequency response information of each jaw and output the wear state information of the corresponding jaw; The clamper fine control module is used to calculate the clamping correction parameters according to the wear status information of each clamping jaw and the clamping information corresponding to the target workpiece, and adjust the clamping force and clamping position compensation of each clamping jaw according to the clamping correction parameters; The combined wear limit judgment module judges whether the end clamp has reached the limit standard according to the wear status information, and outputs warning information and corresponding maintenance suggestions if it is judged that the limit standard has been reached.

2. The industrial robot dynamic monitoring and precision compensation system according to claim 1, characterized in that: The gripper fine control module specifically includes: A target parameter input unit, the target parameter input unit is used to input or import clamping information of the target workpiece, the clamping information including clamping position, surface characteristics and structural parameters; a deviation calculation unit, configured to calculate a deviation characteristic value of each clamping jaw based on clamping information of the target workpiece and wear state information corresponding to each clamping jaw; A compensation control unit is used to generate corresponding clamping control parameters according to the deviation characteristic quantity, and adjust the clamping force and clamping position compensation of each clamping jaw according to the clamping control parameters.

3. The industrial robot dynamic monitoring and precision compensation system according to claim 2, characterized in that: The deviation calculation unit includes: A reference parameter extraction subunit is used to extract the contact position between the clamping jaw and the workpiece and the required clamping force when the clamping jaw is not worn according to the clamping information of the target workpiece, and generate a reference clamping parameter set; The attenuation modeling subunit is used to calculate the clamping force attenuation and clamping position offset of the clamping jaws under the current wear state based on the wear state information of each clamping jaw, and generate a clamping capacity attenuation index; The deviation calculation subunit is used to compare the reference clamping parameter set with the clamping capacity attenuation index, and calculate the deviation characteristic between the clamping performance of each clamping jaw in the current state and the target clamping performance.

4. The industrial robot dynamic monitoring and precision compensation system according to claim 1, characterized in that: The combined wear limit judgment module specifically includes: A single-jaw threshold judgment unit is used to set a corresponding single-jaw wear limit threshold for each jaw, and when the wear status information of any jaw exceeds its corresponding single-jaw wear limit threshold, output a judgment result that the gripper has reached the limit standard; The overall mean judgment unit is used to perform statistical calculations on the wear status information of all grippers to obtain the average wear level of the entire gripper. When the average level exceeds the set group tolerance upper limit, the unit outputs the judgment result that the gripper has reached the limit standard. The judgment result output unit is used to output warning information and maintenance suggestions indicating that the wear of the clamp has reached the limit when the wear status information of any clamp exceeds the wear limit threshold of its single clamp, or the average wear level of the entire clamp exceeds the upper tolerance limit of the group.

5. The industrial robot dynamic monitoring and precision compensation system according to claim 1, characterized in that: The multi-gripper wear state fusion unit specifically includes: The feature extraction subunit is used to perform multi-scale analysis on the micro-deformation information and frequency response information of each gripper to extract multi-dimensional features; A feature fusion subunit, configured to fuse the multi-dimensional features according to a preset dimension to obtain a fused feature vector; a wear classification subunit, configured to input the fused feature vector into a trained machine learning model, output a wear grade or continuous wear score corresponding to each jaw, and simultaneously output corresponding physical wear parameters; The wear state information output unit is configured to output the physical wear parameter together with the wear level or the continuous score as wear state information.

6. The industrial robot dynamic monitoring and precision compensation system according to claim 5, characterized in that: The multi-scale analysis of the micro-deformation information and frequency response information of each gripper to extract multi-dimensional features specifically includes: Performing wavelet transform or short-time Fourier transform on the micro-deformation information to extract micro-deformation features in the signal, wherein the micro-deformation features include maximum deformation, deformation change rate, and time-domain energy distribution; The frequency response information is subjected to main frequency extraction and harmonic analysis to obtain frequency response characteristics, wherein the frequency response characteristics include main frequency offset and frequency bandwidth change.

7. The industrial robot dynamic monitoring and precision compensation system according to claim 4, characterized in that: The joint wear limit judgment module also includes a threshold correction unit, which is used to generate threshold correction parameters based on manually input clamping jaw characteristics and workpiece characteristics, and to correct the single clamping jaw wear limit threshold and the group tolerance upper limit according to the threshold correction parameters to obtain a new single clamping jaw wear limit threshold and the group tolerance upper limit.

8. The industrial robot dynamic monitoring and precision compensation system according to claim 7, characterized in that: The generation of threshold correction parameters based on manually input gripper characteristics and workpiece characteristics specifically includes: Calculating the wear resistance parameters of the gripper according to the input gripper characteristics, and generating a gripper correction factor based on the wear resistance parameters; Calculating the wear sensitivity of the workpiece according to the input workpiece characteristics and generating a workpiece correction factor based on the wear sensitivity; The clamping jaw correction factor and the workpiece correction factor are calculated according to the preset weighted values to generate the threshold correction parameter.

Images