Industrial Internet of Things system for collaborative robot monitoring

Abstract

The invention relates to the technical field of industrial Internet of Things, in particular to an industrial Internet of Things system for collaborative robot monitoring, which comprises the following steps: a sensor calibration module, a running state modeling module, a working performance analysis module, an input parameter analysis module, a movement track detection module and a fault type analysis module. According to the method, the accuracy and reliability of collected data are ensured by calibrating the reading of the sensor, the accuracy of robot state evaluation is optimized, the ideal motion trail of the robot is predicted in real time, the actual position is monitored, the position deviation and the abnormal trail are recognized, and the accuracy of robot state evaluation is improved by combining the calibration of abnormal points and the matching of fault modes. Fault types are quickly identified, fault positions are positioned, fault detection efficiency and accuracy are improved, adaptability of the robot in a complex production environment is improved, operation efficiency and maintenance precision of the robot are enhanced, downtime is shortened, maintenance cost is reduced, and accurate production monitoring and decision support are provided for enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things, and in particular to an industrial Internet of Things system for collaborative robot monitoring. Background Art

[0002] The field of industrial Internet of Things technology embeds network connection and data transmission modules in production equipment, machinery, sensors and various intelligent devices to achieve interconnection between devices, collect, transmit and analyze data in real time, enable industrial equipment to autonomously perceive, make intelligent decisions and collaborate with each other, optimize production processes, improve the efficiency of equipment management, support predictive maintenance and fault detection, help enterprises achieve intelligent production monitoring, remote control, real-time data analysis and decision-making, improve the automation level of production lines, reduce operating costs, and is applied to manufacturing, energy, transportation, logistics and other fields, aiming to improve production flexibility, safety and efficiency.

[0003] Among them, the Industrial Internet of Things system for collaborative robot monitoring is a monitoring system that combines Industrial Internet of Things technology with collaborative robot applications. It collects data on collaborative robots in real time during operation, including temperature, torque, and position, and transmits the target data to the central analysis platform for processing and monitoring through Internet of Things technology. It tracks the operating status of collaborative robots in real time, detects anomalies or failures in a timely manner, and provides predictive maintenance and health management suggestions to ensure the efficient and safe operation of robots in production environments. It aims to improve the work efficiency of robots, reduce equipment failure time, and optimize the production process.

[0004] Traditional collaborative robot monitoring technology has shortcomings in the accuracy, real-time performance and intelligence level of data collection and analysis. It relies on traditional monitoring methods and static models, and lacks the ability to respond to environmental changes and dynamic equipment status in real time. As a result, it is difficult to capture subtle anomalies in robot operation in real time under complex operating conditions. When the working environment changes significantly, it cannot fully compensate for the impact of environmental factors on sensor data, resulting in sensor reading deviations, affecting the overall monitoring and analysis accuracy. The lack of real-time analysis based on robot operation status data leads to low fault detection efficiency and can only respond after a fault occurs, resulting in reduced production efficiency or equipment damage. Summary of the Invention

[0005] In order to solve the technical problem of poor action execution accuracy in the existing technology, an embodiment of the present invention provides an industrial Internet of Things system for collaborative robot monitoring. The technical solution is as follows:

[0006] In one aspect, an industrial Internet of Things system for collaborative robot monitoring is provided, the system comprising:

[0007] The sensor calibration module uses IoT sensors to analyze the impact of environmental conditions on various sensor readings, calculate compensation parameters, and collect various operating data of collaborative robots to generate robot operation monitoring data;

[0008] The operation state modeling module constructs a robot operation state model based on the robot operation monitoring data, identifies the mutual change rules between multiple parameters, analyzes the working state of the robot under various loads and operating environments, and generates operation state evaluation information;

[0009] The working performance analysis module analyzes the performance of the robot in various operating environments based on the operating status evaluation information, identifies the operating efficiency and load carrying capacity of the robot, and generates a robot performance evaluation result;

[0010] The input parameter analysis module predicts the ideal motion trajectory of the robot based on the robot performance evaluation results, taking into account the working environment, operating conditions, load, and control objectives, and generates a motion trajectory prediction result according to the input control parameters.

[0011] The mobile trajectory detection module monitors the real-time position data of the robot based on the motion trajectory prediction result, compares it with the predicted trajectory, calculates the position offset, marks abnormal points, and outputs abnormal trajectory events;

[0012] The fault type analysis module extracts the operating status and location data of the abnormal point based on the abnormal trajectory event, identifies the cause and type of the fault by calculating the similarity with the known fault mode, and generates the robot fault diagnosis result.

[0013] As a further solution of the present invention, the robot operation monitoring data includes compensation parameters for the impact of changes in ambient temperature and humidity on sensor readings, a calibrated sensor data set, and real-time collected robot operation data; the operation status evaluation information includes a dynamic state model constructed based on sensor data, the health status evaluation results of the robot under various loads, and the mutual influence relationship between various parameters; the robot performance evaluation results include load response and position stability evaluation information, robot motion accuracy and operation efficiency analysis results, robot load carrying capacity and performance evaluation information; the motion trajectory prediction results include input control parameter data sets, real-time load and environmental conditions, and position prediction information at multiple time points; the abnormal trajectory events include the monitored abnormal trajectory point positions, trajectory deviation calculation results, and anomaly detection thresholds; the robot fault diagnosis results include similarity calculation results, fault cause identification information, and fault impact range prediction information.

[0014] As a further solution of the present invention, the sensor calibration module includes:

[0015] The data offset analysis submodule is based on IoT sensors and analyzes the impact of environmental changes on the readings of various sensors. It identifies the sensor data offset caused by environmental changes and obtains the environmental offset analysis results.

[0016] The compensation parameter calculation submodule calculates compensation parameters of multiple sensors based on the environmental offset analysis results, adjusts the outputs of multiple sensors, and obtains reading compensation data;

[0017] The real-time data acquisition submodule collects various data of the collaborative robot under the operating status in real time based on the reading compensation data, including temperature, torque, position, voltage, current, and vibration data, and generates robot operation monitoring data.

[0018] As a further solution of the present invention, the operating status modeling module includes:

[0019] The influence relationship analysis submodule analyzes the mutual influence relationship between multiple operating parameters based on the robot operation monitoring data, calculates the correlation coefficient, and obtains the mutual relationship analysis result;

[0020] The state model construction submodule constructs a robot operation state model based on the mutual relationship analysis results, combined with real-time monitoring data, and according to the mutual change rules among multiple parameters;

[0021] The health status analysis submodule analyzes the working status of the robot under various loads and operating environments based on the robot operating status model, and evaluates the health status of the collaborative robot in real time to obtain operating status evaluation information.

[0022] As a further solution of the present invention, the work performance analysis module includes:

[0023] The load performance analysis submodule analyzes the robot's response capabilities under various loads based on the operating status evaluation information, evaluates the impact of load changes on the robot's work efficiency, and generates a load response evaluation result;

[0024] The stability analysis submodule analyzes the position stability of the robot in various operating environments based on the load response evaluation results, evaluates the impact of operating vibration on the robot position, and generates a position stability evaluation result;

[0025] The motion accuracy analysis submodule analyzes the motion accuracy of the robot in various operating environments based on the position stability evaluation results, evaluates the impact of environmental and load changes on the robot's motion, and generates a robot performance evaluation result.

[0026] As a further solution of the present invention, the input parameter analysis module includes:

[0027] The input parameter simulation submodule predicts the motion trajectory of the robot under ideal working conditions based on the robot performance evaluation results and the input control parameters, and generates an ideal trajectory analysis result;

[0028] The deviation range evaluation submodule predicts the deviation range of the robot's motion trajectory under the influence of various factors based on the ideal trajectory analysis results, taking into account the working environment, operating conditions, load and control objectives, and generates deviation range analysis data;

[0029] The position information prediction submodule predicts the position of the robot at multiple time points based on the deviation range analysis data and generates a motion trajectory prediction result.

[0030] As a further solution of the present invention, the movement trajectory detection module includes:

[0031] The position information comparison submodule monitors the position information of the robot in real time based on the motion trajectory prediction result, and compares it with the predicted trajectory to generate real-time position data;

[0032] The offset calculation submodule calculates the offset between the robot's current position and the predicted trajectory based on the real-time position data, and generates position offset data;

[0033] The abnormal trajectory marking submodule marks abnormal trajectory points based on the position offset data and the predicted trajectory deviation range, records the operating status, position, and time information of the abnormal points, and outputs abnormal trajectory events.

[0034] As a further solution of the present invention, the specific formula for calculating the offset between the robot's current position and the predicted trajectory is:

[0035]

[0036] Among them, X r Represents the X coordinate value of the robot's current position, indicating the robot's position on the X axis at the current moment. p Represents the X coordinate value of the predicted trajectory position, which indicates the position of the robot on the X axis calculated according to the preset trajectory model. r Represents the Y coordinate value of the robot's current position, indicating the robot's position on the Y axis at the current moment. p Represents the Y coordinate value of the predicted trajectory position, which indicates the position of the robot on the Y axis calculated according to the preset trajectory model. r Represents the Z coordinate value of the robot's current position, indicating the robot's position on the Z axis at the current moment. pThe Z coordinate value represents the predicted trajectory position, indicating the robot's position on the Z axis calculated according to the preset trajectory model. w is the environmental coefficient or sensor accuracy coefficient, indicating the offset correction under different environmental conditions or according to the different accuracy of the sensor. ΔP represents the offset between the robot's current position and the predicted trajectory position, indicating the distance difference between the predicted trajectory and the actual position.

[0037] As a further solution of the present invention, the fault type analysis module includes:

[0038] The operation data extraction submodule extracts the operation status and location data of the abnormal point based on the abnormal trajectory event, including the operation current, voltage, temperature, and vibration data, and generates a fault data extraction result;

[0039] The fault type matching submodule calculates the similarity between the abnormal point data and multiple known fault modes based on the fault data extraction result, identifies the fault type, and generates a fault mode matching result;

[0040] The fault cause analysis submodule identifies the fault cause based on the fault pattern matching result, and records the fault response status, fault location and fault time information in real time to generate the robot fault diagnosis result.

[0041] As a further solution of the present invention, the specific formula for calculating the similarity between abnormal point data and multiple known failure modes is:

[0042]

[0043] Among them, S represents the similarity, which means the similarity value between the abnormal point data and the fault mode, d i Represents the i-th data value in the abnormal point data, f i Represents the i-th data value in the known fault mode data, n represents the total dimension of the data or the number of data points, and i represents the data point index used in the current calculation.

[0044] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0045] By calibrating sensor readings to ensure the accuracy and reliability of collected data, the accuracy of robot status assessment is optimized, the ideal motion trajectory of the robot is predicted in real time and the actual position is monitored, position offsets and abnormal trajectories are identified, and combined with the calibration of abnormal points and matching of fault modes, the fault type is quickly identified and the fault location is located, thereby improving the efficiency and accuracy of fault detection, enhancing the adaptability of robots in complex production environments, enhancing the operating efficiency and maintenance accuracy of robots, reducing downtime and lowering maintenance costs, and providing enterprises with accurate production monitoring and decision-making support. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 is a system flow chart of the present invention;

[0048] Figure 2 Schematic diagram of the system framework of the present invention;

[0049] Figure 3 This is a flow chart of the sensor calibration module of the present invention;

[0050] Figure 4 This is a flow chart of the operating state modeling module of the present invention;

[0051] Figure 5 This is a flow chart of the working performance analysis module of the present invention;

[0052] Figure 6 This is a flow chart of the input parameter analysis module of the present invention;

[0053] Figure 7 This is a flow chart of the movement trajectory detection module of the present invention;

[0054] Figure 8 This is a flow chart of the fault type analysis module of the present invention. DETAILED DESCRIPTION

[0055] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0056] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0057] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0058] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0059] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0060] The embodiment of the present invention provides an industrial Internet of Things system for collaborative robot monitoring, such as Figure 1 The flowchart of the industrial Internet of Things system for collaborative robot monitoring shown in the figure includes:

[0061] The sensor calibration module uses IoT sensors to analyze the impact of environmental conditions on various sensor readings, calculate compensation parameters, and collect various operating data of collaborative robots to generate robot operation monitoring data;

[0062] The operation status modeling module constructs a robot operation status model based on the robot operation monitoring data, identifies the mutual change rules between multiple parameters, analyzes the working status of the robot under various loads and operating environments, and generates operation status evaluation information;

[0063] The work performance analysis module analyzes the robot's performance in various operating environments based on the operating status evaluation information, identifies the robot's operating efficiency and load-bearing capacity, and generates robot performance evaluation results;

[0064] The input parameter analysis module is based on the robot performance evaluation results, taking into account the working environment, operating conditions, load, and control objectives. It predicts the ideal motion trajectory of the robot according to the input control parameters and generates the motion trajectory prediction results.

[0065] The mobile trajectory detection module monitors the robot's real-time position data based on the motion trajectory prediction results, compares it with the predicted trajectory, calculates the position offset, marks abnormal points, and outputs abnormal trajectory events;

[0066] The fault type analysis module extracts the operating status and location data of the abnormal point based on the abnormal trajectory events, identifies the cause and type of the fault by calculating the similarity with the known fault mode, and generates the robot fault diagnosis results.

[0067] The robot operation monitoring data includes compensation parameters for the impact of environmental temperature and humidity changes on sensor readings, calibrated sensor data sets, and real-time collected robot operation data. The operation status evaluation information includes the dynamic state model constructed based on sensor data, the health status evaluation results of the robot under various loads, and the mutual influence relationship between multiple parameters. The robot performance evaluation results include load response and position stability evaluation information, robot motion accuracy and operation efficiency analysis results, robot load carrying capacity and performance evaluation information. The motion trajectory prediction results include input control parameter data sets, real-time load and environmental conditions, and position prediction information at multiple time points. Abnormal trajectory events include the monitored abnormal trajectory point positions, trajectory deviation calculation results, and anomaly detection thresholds. The robot fault diagnosis results include similarity calculation results, fault cause identification information, and fault impact range prediction information.

[0068] See also Figure 2 and Figure 3 , the sensor calibration module includes:

[0069] The data offset analysis submodule is based on IoT sensors and analyzes the impact of environmental changes on the readings of various sensors. It identifies the sensor data offset caused by environmental changes and obtains the environmental offset analysis results.

[0070] Acquire environmental monitoring data from IoT sensors, including temperature, humidity, air pressure, and vibration. Standardize the sensor data using minimum-maximum normalization or Z-score normalization methods. Through statistical analysis, determine the normal value range of each sensor under different environmental conditions. Compare the current data with the normal range. Use a multivariate linear regression model to quantitatively analyze the correlation between environmental factors and sensor data. Calculate the environmental offset of each sensor and analyze the data deviation caused by environmental changes. Use the regression model to identify the environmental factors that have the greatest impact on sensor data and obtain the environmental offset analysis results. The result is the offset value of each sensor, which provides a basis for subsequent compensation calculations.

[0071] The compensation parameter calculation submodule calculates the compensation parameters of multiple sensors based on the environmental offset analysis results, adjusts the outputs of multiple sensors, and obtains reading compensation data;

[0072] Based on the results of the environmental offset analysis, compensation calculation is performed for the offset of each sensor. An adaptive compensation algorithm is used to calculate the compensation parameters based on the difference between the offset and the sensor output. The offset range and volatility are analyzed, and the offset is corrected using the weighted average method to obtain a compensation coefficient, which is used to adjust the sensor output data. During the calculation process, the sensor accuracy and response time are taken into consideration, and a weighted average model is used to comprehensively calculate the compensation coefficient. After the calculation is completed, the difference between the adjusted sensor output data and the original data is the compensation data. The compensation data is used as the input of the robot control system to ensure that the read data is more accurate and improve the robot's accuracy and stability.

[0073] The real-time data acquisition submodule collects various data of the collaborative robot's operating status in real time based on the reading compensation data, including temperature, torque, position, voltage, current, and vibration data, and generates robot operation monitoring data;

[0074] Using compensated sensor data, various data of the collaborative robot's operating status are collected in real time, including temperature, torque, position, voltage, current, and vibration. During the data collection process, the robot continuously monitors the data through built-in sensors and transmits it to the central control system through the Internet of Things communication protocol. The data collection adopts sliding window technology to ensure the real-time and accuracy of the data. At the same time, the data is synchronized and time-series calibrated to ensure the time consistency of each sensor data. Data fusion is performed through Kalman filtering or weighted averaging to eliminate noise and interference. The processed monitoring data is used to evaluate the robot's operating status, perform fault detection, performance optimization and real-time control.

[0075] See also Figure 2 and Figure 4 , the operating status modeling module includes:

[0076] The influence relationship analysis submodule analyzes the mutual influence relationship between various operating parameters based on the robot operation monitoring data, calculates the correlation coefficient, and obtains the mutual relationship analysis results;

[0077] Acquire robot operation monitoring data, including temperature, torque, position, voltage, current, and vibration parameters. Use the Pearson correlation coefficient method to analyze the linear correlation between multiple parameters. By calculating the degree of influence of each parameter on other parameters, obtain the correlation matrix, normalize the correlation coefficient, and eliminate the interference of external environmental factors on the calculation results. If the correlation coefficient exceeds a certain set threshold, it indicates that there is a strong mutual influence relationship between the parameters. Identify which parameters have the greatest impact on the robot's operating performance and which parameters have potential dependencies. Use stepwise regression analysis to determine the independence and synergy between parameters to ensure the accuracy and stability of the results. Generate a relationship analysis report and provide the parameter set that has the most significant impact on the robot's operating status.

[0078] The state model construction submodule builds the robot operation state model based on the mutual relationship analysis results, combined with real-time monitoring data, and according to the mutual change rules among multiple parameters;

[0079] Based on the results of the relationship analysis, multiple parameters closely related to the robot's performance, such as temperature, torque, current, and vibration, are selected to analyze the time series change characteristics of the target parameters. Time series analysis models, such as the autoregressive integral moving average model, are used to predict the future trends of each parameter. Multidimensional time series data is used to apply support vector machines or random forest algorithms to capture the nonlinear relationship between different parameters. Through regression analysis and machine learning methods, a robot operation status model containing multiple input and output dimensions is constructed to predict the robot's state changes and update it in real time based on actual input data to ensure an accurate description of the robot's health status. The constructed model is used to evaluate the robot's operation trend, predict potential failures or abnormalities, and provide a basis for subsequent health status assessments.

[0080] The health status analysis submodule analyzes the working status of the robot under various loads and operating environments based on the robot operation status model, and evaluates the health status of the collaborative robot in real time to obtain operation status evaluation information;

[0081] In the above content, the health status analysis submodule analyzes the working status of the robot under various loads and operating environments based on the robot operation status model. Calculate the health status assessment information of the robot under various loads and operating environments;

[0082] Where H represents the robot health status assessment information, X i 、Y i 、Z i They represent the monitoring parameter values of the robot under the i-th load, W1, W2, and W3 are the weight coefficients of the corresponding parameters, and n is the total number of samples of monitoring data.

[0083] Detailed explanation of the formula and the process of formula calculation and derivation:

[0084] Assume that the temperature, pressure, and current parameter data of the robot in multiple working environments have been obtained through the monitoring system. Assume that W1 = 0.4, W2 = 0.3, and W3 = 0.3, and the corresponding monitored parameter values are X1 = 75, Y1 = 150, Z1 = 1.5, X2 = 80, Y2 = 160, Z2 = 1.7, X3 = 85, Y3 = 155, and Z3 = 1.6. Substitute the above data into the formula:

[0085]

[0086] The result H=78.98 indicates that the health status assessment value of the robot under the current load and operating environment is 78.98.

[0087] See also Figure 2 and Figure 5 , the work performance analysis module includes:

[0088] The load performance analysis submodule analyzes the robot's response capabilities under various loads based on the operating status evaluation information, evaluates the impact of load changes on the robot's work efficiency, and generates load response evaluation results;

[0089] Based on the operating status evaluation information, including load, temperature, current, torque, and position parameters, the robot's response ability under different loads is evaluated. By collecting the robot's working data under different load conditions, linear regression analysis and multivariate analysis methods are used to study the impact of load changes on the robot's work efficiency. The appropriate load level range is selected, and the load changes are measured using inductive sensors. Combined with the robot's kinematic model, the impact of load changes on the robot's work efficiency is calculated. Analysis tools such as regression analysis and principal component analysis are used to extract the correlation between load and work efficiency. The response ability data under each load is compared with the preset work efficiency standard, and the load response evaluation results are calculated. The load response evaluation results can reveal the efficiency changes of the robot under different load conditions, provide a basis for optimizing robot operation, and determine the optimal workload range.

[0090] The stability analysis submodule analyzes the robot's position stability in various operating environments based on the load response evaluation results, evaluates the impact of operating vibration on the robot's position, and generates position stability evaluation results;

[0091] Based on the load response evaluation results, the vibration data of the robot in different operating environments is obtained, including vibration amplitude, frequency, and acceleration. The vibration conditions are measured by accelerometers and gyroscopes. The system identification method and Kalman filter algorithm are used to analyze the change pattern of the robot position under the influence of vibration. The vibration frequency and amplitude are analyzed in the frequency domain. The time domain data is converted into frequency domain data through Fourier transform, and the impact of different frequencies on the stability of the robot position is analyzed. Combined with the vibration data and position changes, the impact of vibration on the position error and accuracy of the robot is evaluated. By establishing a mathematical model and combining the vibration analysis results, the position stability evaluation results are calculated.

[0092] The motion accuracy analysis submodule analyzes the robot's motion accuracy in various operating environments based on the position stability evaluation results, evaluates the impact of environmental and load changes on the robot's motion, and generates robot performance evaluation results;

[0093] Based on the position stability evaluation results, the robot's motion data under different environmental conditions, including speed, displacement, path, etc., are obtained. Sensors are used to measure the robot's motion trajectory when performing tasks. Combined with the position stability evaluation results, dynamic system models and error analysis methods are used to study the impact of environmental factors and load changes on the robot's motion accuracy. Error models, such as Kalman filtering and particle filtering, are used to calculate the robot's motion errors under different loads and environmental conditions. Through simulation and actual measurement data, the impact of load and environmental changes on the accuracy of the robot's motion is evaluated. Based on the evaluation results, the robot performance evaluation results are generated.

[0094] See also Figure 2 and Figure 6 , the input parameter analysis module includes:

[0095] The input parameter simulation submodule predicts the robot's motion trajectory under ideal working conditions based on the robot performance evaluation results and the input control parameters, and generates the ideal trajectory analysis results;

[0096] According to the results of robot performance evaluation, control parameters are used in combination with the robot's dynamic model. By establishing kinematic equations and combining the influence of control parameters on robot motion, numerical integration methods are used for simulation to calculate the expected motion trajectory of the robot under ideal conditions. After the control parameters are input, inverse kinematics analysis is performed. During the motion trajectory generation process, factors such as different speeds, loads, and operating spaces are considered to simulate the maximum motion range under ideal working conditions and generate ideal trajectory analysis results, which help to conduct comparative analysis of ideal trajectories in actual work.

[0097] The deviation range assessment submodule is based on the ideal trajectory analysis results, taking into account the working environment, operating conditions, load and control objectives, to predict the robot's motion trajectory deviation range under the influence of various factors and generate deviation range analysis data;

[0098] Based on the ideal trajectory analysis results, by collecting environmental monitoring data and combining it with the control model, the Monte Carlo simulation method or particle filtering algorithm is used to predict the error range of the robot under different working conditions. The model input in the process includes the robot's working environment parameters and load data. By constructing a deviation model, the robot's motion error in a complex environment is estimated, and multi-dimensional deviation range analysis data is generated to understand the change amplitude of the robot's motion trajectory under different working conditions and its impact.

[0099] The position information prediction submodule predicts the robot's position at multiple time points based on the deviation range analysis data and generates motion trajectory prediction results;

[0100] Based on the deviation range analysis data, combined with control parameters, environmental factors and load, the robot's position at multiple time points is predicted, and the current and historical positions of the robot are estimated using the Kalman filter or particle filter algorithm. Based on the deviation range data, the dynamic state equation of the robot is established. Through the interaction between the control input and the environmental parameters, the robot's motion trajectory at future time points is calculated and its position is predicted. The time series data prediction model is used, combined with the robot's motion trajectory deviation, to predict future position changes. By continuously updating the deviation range data and the actual position measurement results, the prediction model is adjusted in real time to improve the accuracy and reliability of the position information, generate motion trajectory prediction results, and dynamically adjust them in combination with real-time monitoring data and environmental feedback to ensure the robot's operation stability and accuracy in different environments.

[0101] See also Figure 2 and Figure 7 , the mobile trajectory detection module includes:

[0102] The position information comparison submodule monitors the robot's position information in real time based on the motion trajectory prediction results, compares it with the predicted trajectory, and generates real-time position data;

[0103] The real-time monitoring system is used to obtain the current position information of the robot, and the position coordinates of the robot in the operating space. The target real-time position data is compared with the ideal trajectory data generated by the motion trajectory prediction module. The ideal trajectory data is generated by the robot motion model, control parameters, and working environment conditions. The distance measurement method is used to calculate the deviation between the real-time position and the predicted trajectory, and the degree of deviation between the current position of the robot and the ideal trajectory is obtained. The predicted trajectory is smoothed using the interpolation method to ensure the comparison accuracy between the real-time monitoring data and the predicted trajectory data. By dynamically updating the comparison results, real-time position data is generated, providing a basis for subsequent trajectory adjustment and abnormality monitoring.

[0104] The offset calculation submodule calculates the offset between the robot's current position and the predicted trajectory based on real-time position data and generates position offset data;

[0105] The specific formula for calculating the offset between the robot's current position and the predicted trajectory is:

[0106]

[0107] Among them, X r Represents the X coordinate value of the robot's current position, indicating the robot's position on the X axis at the current moment. p Represents the X coordinate value of the predicted trajectory position, which indicates the position of the robot on the X axis calculated according to the preset trajectory model. rRepresents the Y coordinate value of the robot's current position, indicating the robot's position on the Y axis at the current moment. p Represents the Y coordinate value of the predicted trajectory position, which indicates the position of the robot on the Y axis calculated according to the preset trajectory model. r Represents the Z coordinate value of the robot's current position, indicating the robot's position on the Z axis at the current moment. p The Z coordinate value represents the predicted trajectory position, indicating the robot's position on the Z axis calculated according to the preset trajectory model. w is the environmental coefficient or sensor accuracy coefficient, indicating the offset correction under different environmental conditions or according to the different accuracy of the sensor. ΔP represents the offset between the robot's current position and the predicted trajectory position, indicating the distance difference between the predicted trajectory and the actual position.

[0108] formula:

[0109]

[0110] Detailed explanation of the formula and the process of formula calculation and derivation:

[0111] This formula is used to calculate the offset between the robot's current position and the predicted trajectory position;

[0112] Parameter meaning and setting value:

[0113] Xr: The X coordinate value of the robot's current position. Assume that the robot's current position on the X axis is 1.2 cm as measured by the positioning system.

[0114] Xp: The X coordinate value of the predicted trajectory position, assuming that the predicted position calculated according to the trajectory model is 1.0 cm;

[0115] Yr: The Y coordinate value of the robot's current position. Assume that the sensor measures the robot's current position on the Y axis to be 2.5 cm.

[0116] Yp: Y coordinate value of the predicted trajectory position. Assume that the predicted position calculated according to the trajectory model is 2.3 cm;

[0117] Zr: The Z coordinate value of the robot's current position. Assume that the sensor measures the robot's current position on the Z axis to be 0.8 cm.

[0118] Zp: The Z coordinate value of the predicted trajectory position. Assume that the predicted position calculated according to the trajectory model is 0.7 cm;

[0119] w: environmental factor or sensor accuracy factor, used to correct the calculated offset result. Assume w is set to 1.05;

[0120] Substitute the parameters into the formula for calculation:

[0121]

[0122]

[0123] ΔP = 1.05 × 0.3;

[0124] ΔP = 0.315;

[0125] The result 0.315 indicates that the offset between the robot's current position and the predicted trajectory position is 0.315, which represents the degree to which the robot's position in the spatial coordinate system deviates from the predicted trajectory. The offset value is used to determine whether the robot deviates from the expected path.

[0126] The abnormal trajectory marking submodule marks abnormal trajectory points based on the position offset data and the predicted trajectory deviation range, records the operating status, location, and time information of the abnormal points, and outputs abnormal trajectory events;

[0127] Based on the deviation range between the position offset data and the predicted trajectory, the offset data is compared with the pre-set trajectory deviation tolerance to determine whether the robot's running trajectory is abnormal. The predicted trajectory deviation range is calculated in advance through environmental factors, load changes, control targets and other parameters, combined with the robot's historical motion data, error model and Kalman filter state estimation. When the offset exceeds the set threshold, it can be determined as an abnormal trajectory point. The abnormal trajectory point is recorded and attached with relevant operating status information, including the robot's precise position at the time of the abnormality, timestamp, load status, battery power, etc. Based on the target information, the abnormal trajectory event is marked to provide data support for subsequent maintenance and adjustment. During the marking process, the real-time feedback of the robot is combined to confirm whether the abnormality is caused by external environmental factors or internal faults. The abnormal trajectory points are stored and output as abnormal trajectory event data to provide a basis for subsequent analysis and adjustment.

[0128] See also Figure 2 and Figure 8 , the fault type analysis module includes:

[0129] The operation data extraction submodule extracts the operation status and location data of the abnormal point based on the abnormal trajectory event, including the operation current, voltage, temperature, and vibration data, and generates the fault data extraction result;

[0130] Based on abnormal trajectory events, the operating status and position data of the abnormal points are extracted, the abnormal points are located, and the time and location of the abnormality are identified by comparing with the normal trajectory data. The operating status data of the abnormal points include current, voltage, temperature, vibration and other parameters. The target data is collected by sensors. The current and voltage data are used to determine whether there is a power system fault. The temperature and vibration data are used to evaluate the working environment and status of the robot. During the data extraction process, the original data of all sensors are obtained and preprocessed to ensure data quality. The target data is associated with the timestamp and position information of the abnormal trajectory points to generate fault data extraction results. Through data processing, the output results include current, voltage, temperature and vibration data of each abnormal point, providing detailed input data for subsequent fault type matching and cause analysis.

[0131] The fault type matching submodule calculates the similarity between abnormal point data and multiple known fault modes based on the fault data extraction results, identifies the fault type, and generates fault mode matching results;

[0132] The specific formula for calculating the similarity between abnormal point data and multiple known failure modes is:

[0133]

[0134] Among them, S represents the similarity, which means the similarity value between the abnormal point data and the fault mode, d i Represents the i-th data value in the abnormal point data, f i Represents the i-th data value in the known fault mode data, n represents the total dimension of the data or the number of data points, and i represents the data point index used in the current calculation.

[0135] formula:

[0136]

[0137] Detailed explanation of the formula and the process of formula calculation and derivation:

[0138] The formula is used to calculate the similarity between the abnormal point data and the known failure mode data;

[0139] Parameter meaning and setting value:

[0140] S: Similarity value, indicating the degree of matching between the abnormal point data and the known fault mode;

[0141] d i : The i-th item of data in the abnormal point data, assuming that the temperature data d1 at a certain moment is 120°C, the torque data d2 is 2Nm, and the position deviation is 5;

[0142] f i: The i-th item in the fault mode data, assuming that the temperature data f1 in the target fault mode is 125°C, the torque data f2 is 2.5Nm, and the position deviation is 4.8;

[0143] n: The dimension of the data or the number of data points, which indicates the number of features of the data. Assume that the number of features of the anomaly data and the failure mode data is 3, that is, n = 3;

[0144] i: the index of the data point used in the calculation;

[0145] Substitute the parameters into the formula for calculation:

[0146] Compute the inner product:

[0147]

[0148] Compute the sum of squares:

[0149]

[0150] Calculate similarity:

[0151]

[0152] Result interpretation:

[0153] The results show that the similarity between the outlier data and the failure mode data is very high, and the outlier data and the failure mode are highly matched. The results are used to diagnose the failure mode and failure type of the collaborative robot.

[0154] The fault cause analysis submodule identifies the fault cause based on the fault pattern matching results, and records the fault response status, fault location and fault time information in real time to generate the robot fault diagnosis results;

[0155] Based on the fault pattern matching results, the fault type is determined by analyzing the fault pattern matching results, and the fault cause is inferred based on the fault type combined with the known equipment structure and working principle. If the fault mode is current overload, it may be caused by damage to the motor or circuit board. If the fault mode is too high temperature, it may be due to poor heat dissipation or overheating of the working environment. The fault cause analysis adopts a rule-based reasoning method, combined with the expert system and historical fault data, to make inferences, record the operating status when the fault occurs, record the fault location and the time of occurrence, and generate the robot fault diagnosis results, including fault type, cause, location, occurrence time and other information, and provide specific maintenance suggestions or alarms through the diagnosis results. The analysis results can be displayed through the fault diagnosis system interface and provided to operators or maintenance personnel.

[0156] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0157] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0158] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0159] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0160] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0161] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0162] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0163] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0164] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0165] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0166] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An industrial Internet of Things system for collaborative robot monitoring, characterized in that: The system comprises: The sensor calibration module uses IoT sensors to analyze the impact of environmental conditions on various sensor readings, calculate compensation parameters, and collect various operating data of collaborative robots to generate robot operation monitoring data; The operation state modeling module constructs a robot operation state model based on the robot operation monitoring data, identifies the mutual change rules between multiple parameters, analyzes the working state of the robot under various loads and operating environments, and generates operation state evaluation information; The working performance analysis module analyzes the performance of the robot in various operating environments based on the operating status evaluation information, identifies the operating efficiency and load carrying capacity of the robot, and generates a robot performance evaluation result; The input parameter analysis module predicts the ideal motion trajectory of the robot based on the robot performance evaluation results, taking into account the working environment, operating conditions, load, and control objectives, and generates a motion trajectory prediction result according to the input control parameters. The mobile trajectory detection module monitors the real-time position data of the robot based on the motion trajectory prediction result, compares it with the predicted trajectory, calculates the position offset, marks abnormal points, and outputs abnormal trajectory events; The fault type analysis module extracts the operating status and location data of the abnormal point based on the abnormal trajectory event, identifies the cause and type of the fault by calculating the similarity with the known fault mode, and generates the robot fault diagnosis result.

2. The industrial Internet of Things system for collaborative robot monitoring according to claim 1, characterized in that: The robot operation monitoring data includes compensation parameters for the impact of environmental temperature and humidity changes on sensor readings, calibrated sensor data sets, and real-time collected robot operation data. The operation status evaluation information includes a dynamic state model constructed based on sensor data, the health status evaluation results of the robot under various loads, and the mutual influence relationship between multiple parameters. The robot performance evaluation results include load response and position stability evaluation information, robot motion accuracy and operation efficiency analysis results, robot load carrying capacity and performance evaluation information. The motion trajectory prediction results include input control parameter data sets, real-time load and environmental conditions, and position prediction information at multiple time points. The abnormal trajectory events include the monitored abnormal trajectory point positions, trajectory deviation calculation results, and anomaly detection thresholds. The robot fault diagnosis results include similarity calculation results, fault cause identification information, and fault impact range prediction information.

3. The industrial Internet of Things system for collaborative robot monitoring according to claim 1, characterized in that: The sensor calibration module includes: The data offset analysis submodule is based on IoT sensors and analyzes the impact of environmental changes on the readings of various sensors. It identifies the sensor data offset caused by environmental changes and obtains the environmental offset analysis results. The compensation parameter calculation submodule calculates compensation parameters of multiple sensors based on the environmental offset analysis results, adjusts the outputs of multiple sensors, and obtains reading compensation data; The real-time data acquisition submodule collects various data of the collaborative robot under the operating status in real time based on the reading compensation data, including temperature, torque, position, voltage, current, and vibration data, and generates robot operation monitoring data.

4. The industrial Internet of Things system for collaborative robot monitoring according to claim 1, characterized in that: The operating status modeling module includes: The influence relationship analysis submodule analyzes the mutual influence relationship between multiple operating parameters based on the robot operation monitoring data, calculates the correlation coefficient, and obtains the mutual relationship analysis result; The state model construction submodule constructs a robot operation state model based on the mutual relationship analysis results, combined with real-time monitoring data, and according to the mutual change rules among multiple parameters; The health status analysis submodule analyzes the working status of the robot under various loads and operating environments based on the robot operating status model, and evaluates the health status of the collaborative robot in real time to obtain operating status evaluation information.

5. The industrial Internet of Things system for collaborative robot monitoring according to claim 1, characterized in that: The work performance analysis module includes: The load performance analysis submodule analyzes the robot's response capabilities under various loads based on the operating status evaluation information, evaluates the impact of load changes on the robot's work efficiency, and generates a load response evaluation result; The stability analysis submodule analyzes the position stability of the robot in various operating environments based on the load response evaluation results, evaluates the impact of operating vibration on the robot position, and generates a position stability evaluation result; The motion accuracy analysis submodule analyzes the motion accuracy of the robot in various operating environments based on the position stability evaluation results, evaluates the impact of environmental and load changes on the robot's motion, and generates a robot performance evaluation result.

6. The industrial Internet of Things system for collaborative robot monitoring according to claim 1, characterized in that: The input parameter analysis module includes: The input parameter simulation submodule predicts the motion trajectory of the robot under ideal working conditions based on the robot performance evaluation results and the input control parameters, and generates an ideal trajectory analysis result; The deviation range evaluation submodule predicts the deviation range of the robot's motion trajectory under the influence of various factors based on the ideal trajectory analysis results, taking into account the working environment, operating conditions, load and control objectives, and generates deviation range analysis data; The position information prediction submodule predicts the position of the robot at multiple time points based on the deviation range analysis data and generates a motion trajectory prediction result.

7. The industrial Internet of Things system for collaborative robot monitoring according to claim 1, characterized in that: The movement trajectory detection module includes: The position information comparison submodule monitors the position information of the robot in real time based on the motion trajectory prediction result, and compares it with the predicted trajectory to generate real-time position data; The offset calculation submodule calculates the offset between the robot's current position and the predicted trajectory based on the real-time position data, and generates position offset data; The abnormal trajectory marking submodule marks abnormal trajectory points based on the position offset data and the predicted trajectory deviation range, records the operating status, position, and time information of the abnormal points, and outputs abnormal trajectory events.

8. The industrial Internet of Things system for collaborative robot monitoring according to claim 7, characterized in that: The specific formula for calculating the offset between the robot's current position and the predicted trajectory is: Among them, X r Represents the X coordinate value of the robot's current position, indicating the robot's position on the X axis at the current moment. p Represents the X coordinate value of the predicted trajectory position, which indicates the position of the robot on the X axis calculated according to the preset trajectory model. r Represents the Y coordinate value of the robot's current position, indicating the robot's position on the Y axis at the current moment. p Represents the Y coordinate value of the predicted trajectory position, which indicates the position of the robot on the Y axis calculated according to the preset trajectory model. r Represents the Z coordinate value of the robot's current position, indicating the robot's position on the Z axis at the current moment. p The Z coordinate value represents the predicted trajectory position, indicating the robot's position on the Z axis calculated according to the preset trajectory model. w is the environmental coefficient or sensor accuracy coefficient, indicating the offset correction under different environmental conditions or according to the different accuracy of the sensor. ΔP represents the offset between the robot's current position and the predicted trajectory position, indicating the distance difference between the predicted trajectory and the actual position.

9. The industrial Internet of Things system for collaborative robot monitoring according to claim 1, characterized in that: The fault type analysis module includes: The operation data extraction submodule extracts the operation status and location data of the abnormal point based on the abnormal trajectory event, including the operation current, voltage, temperature, and vibration data, and generates a fault data extraction result; The fault type matching submodule calculates the similarity between the abnormal point data and multiple known fault modes based on the fault data extraction result, identifies the fault type, and generates a fault mode matching result; The fault cause analysis submodule identifies the fault cause based on the fault pattern matching result, and records the fault response status, fault location and fault time information in real time to generate the robot fault diagnosis result.

10. The industrial Internet of Things system for collaborative robot monitoring according to claim 9, characterized in that: The specific formula for calculating the similarity between abnormal point data and multiple known failure modes is: Among them, S represents the similarity, which means the similarity value between the abnormal point data and the fault mode, d i Represents the i-th data value in the abnormal point data, f i Represents the i-th data value in the known fault mode data, n represents the total dimension of the data or the number of data points, and i represents the data point index used in the current calculation.

Images