Remote monitoring and diagnosis system for industrial robot

Abstract

The invention discloses a remote monitoring and diagnosis system for an industrial robot. The system comprises an industrial robot end, a data acquisition module, a cloud server and a diagnosis terminal. Collected robot state data such as joint angles, position coordinates, torque, voltage, current, temperature, vibration and noise during working of an industrial robot system are sent to a cloud server through the Ethernet, and collected operation state data of the industrial robot are sent to the cloud server. And the diagnosis terminal obtains the operation state data of the industrial robot by accessing the cloud server, and performs training learning through an intelligent algorithm to obtain a fault diagnosis model for monitoring and diagnosing the abnormal state of the industrial robot. According to the industrial robot data monitoring method and system, the data of the industrial robot in the operation process can be better monitored, problems prone to occurring can be found in time, and the working efficiency is improved. According to the method, the loss caused by fault shutdown can be effectively reduced, most simple fault problems can be solved through data checking and remote debugging, engineers do not need to be specially arranged to the site, and fault solving is more flexible.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial robot fault diagnosis, and more specifically to an industrial robot remote monitoring and diagnosis system. Background Art

[0002] With the rapid development of industrial robot technology, industrial robots are increasingly widely used in all walks of life. During the long-term operation of industrial robots, due to sudden changes in the working environment or abnormal conditions such as wear of parts during long-term operation, the robots may not operate properly or may not complete the work on time, with high quality and quantity. The industrial robot remote monitoring and diagnosis system can monitor the operating status of industrial robots in real time, and prompt maintenance personnel to perform equipment maintenance in a timely manner when abnormal robot status is detected, which can effectively avoid the occurrence of some faults. After a fault occurs, the industrial robot remote monitoring and diagnosis system can provide the detailed operation data of the robot before and after the fault to the robot manufacturer in the first time, and assist maintenance experts to provide remote diagnosis services, greatly reducing the diagnosis and repair cycle of the robot and reducing the losses of user enterprises. Summary of the Invention

[0003] In order to achieve the above object, the present invention proposes an industrial robot remote monitoring and diagnosis system. Various sensors are used to collect robot status data, which is uploaded to a cloud server through an industrial Ethernet and stored and analyzed based on database technology. Based on database access technology, a remote PC interacts with the cloud server through a client to realize remote monitoring, historical query, and overvalue alarm of the motion status data of on-site robots, laying a foundation for functions such as remote control, online motion planning, and health assessment of robots in the later stage.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] An industrial robot remote monitoring and diagnosis system, including an industrial robot end, a data acquisition module, a cloud server, and a diagnosis terminal;

[0006] The industrial robot end is used to control the robot body to execute operation instructions according to industrial on-site or remote instructions;

[0007] The data acquisition module collects the real-time operation status data of the industrial robot and uploads it to the cloud server;

[0008] The cloud server is used to store and process the real-time operation status data collected from the industrial site; make a data set using the existing operation status data, train a monitoring and diagnosis network to obtain an optimized and trained diagnosis model; and perform diagnosis based on the currently collected real-time operation status data, and output the current operation status label of the industrial site;

[0009] A diagnostic terminal, which obtains the operation status data and the current operation status label of the current industrial robot by accessing a cloud server, and is used for monitoring and diagnosing the abnormal status of the industrial robot.

[0010] The industrial robot system includes an industrial robot body and its controller.

[0011] Communication is sequentially carried out by Ethernet among the industrial robot end, the data acquisition module, the cloud server, and the diagnostic terminal.

[0012] The real-time operation status data includes robot position parameters and environmental parameters.

[0013] The operation parameters are position parameters during the operation of the robot; including joint speed, joint angle, position coordinates, and torque; the environmental parameters include temperature, current, voltage, vibration, and noise.

[0014] The monitoring and diagnosis network model is a support vector machine model.

[0015] The steps of the training include:

[0016] Classify the real-time operation data collected on-site by experts and label the status;

[0017] Perform PCA principal component analysis to extract features; obtain a paired data set {feature vector, status label};

[0018] Input the paired data set into the support vector machine model, set the training parameters, loss function, and number of iterations for training, and stop training when the network loss converges or reaches the number of iterations to obtain an optimized and trained diagnostic model.

[0019] The diagnostic terminal device is used to download the abnormal data information from the cloud server, and perform comprehensive fault analysis and diagnosis on the abnormal signal through an intelligent diagnostic algorithm to locate the key part where the abnormality occurs and determine the cause of the fault.

[0020] The comprehensive fault analysis and diagnosis give an over-limit alarm according to whether a single or a combination of several data parameters exceed the threshold range.

[0021] It is necessary to pre-statistically classify the key parts of the abnormality and the cause of the fault manually, establish a corresponding relationship mapping table with the status label, and the mapping table stores the status label and its corresponding key part of the abnormality and the cause of occurrence.

[0022] The present invention has the following advantages and beneficial effects:

[0023] 1. The present invention can be used for online real-time monitoring of key data of robots, providing two-way services for customers and robot engineering. It can facilitate remote access to monitoring data, which is convenient and beneficial for robot fault diagnosis and analysis, and can provide data support for remote diagnosis.

[0024] 2. The present invention can provide a basis for remote diagnosis personnel to timely understand the operating status of the robot, enabling remote access without the need to organize on-site inspections by personnel, thereby improving the maintenance progress.

[0025] 3. The cloud server can analyze and perform remote cloud and local data storage, facilitating local technicians and remote technical experts to judge, maintain, monitor, etc. the working status of the robot. Moreover, the data is stored in the industrial control computer and the diagnostic terminal, which can provide data support for the automatic diagnosis algorithm of the terminal, provide a basic framework for subsequent expansion of machine automatic identification and monitoring, and has good expandability. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is the system working schematic diagram of the present invention

[0027] Figure 2 is the flowchart of the industrial robot status monitoring and diagnosis method of the present invention DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe in detail the specific implementation methods of the present invention with reference to the accompanying drawings. Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the invention. Therefore, the present invention is not limited by the specific implementations disclosed below.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0030] The object of the present invention is to provide a remote monitoring and diagnosis system for industrial robots. As shown in the attached Figure 1 figure, the system includes an industrial robot system, a data acquisition module, a cloud server, and a diagnostic terminal. The industrial robot system includes an industrial robot body and its controller. The data acquisition module includes a signal acquisition card and sensors (voltage sensors, current sensors, temperature sensors, vibration sensors, noise sensors, etc.).

[0031] The IO direct sampling module connected to the controller is used to collect the joint speed, joint angle, position coordinates, and torque data during the operation of the robot. Vibration sensors, temperature sensors, and noise sensors are installed on the outer wall of the industrial robot to collect temperature, vibration, and noise data during the operation of the robot. Voltage and current sensors are installed on the lines of the industrial robot control cabinet to collect voltage and current data during the operation of the robot.

[0032] The collected operation status data of the industrial robot, such as joint speed, joint angle, position coordinates, torque data, voltage, current, temperature, vibration, and noise, are sent to the cloud service through Ethernet for storage and processing.

[0033] The collected signals are subjected to principal component analysis. After extracting the feature vectors, different types of fault features are used to train different support vector machine models respectively to obtain multiple trained fault diagnosis models. Each of the trained support vector machine models can perform fault diagnosis on the fault features of a certain fault type; wherein, when training the support vector machine model, the fault features in the fault dataset are used as the input, and the fault mode corresponding to the fault feature is used as the fault status label.

[0034] The fault status label is the normal or fault classification of status data such as joint speed, joint angle, position coordinates, torque data, voltage, current, temperature, vibration, and noise.

[0035] The diagnosis terminal obtains the operation status data of the industrial robot by accessing the cloud server, compares the operation data with the fault diagnosis model, and monitors the health status of the robot in real time for alarm when the monitored data exceeds the preset value.

[0036] The above is only a preferred embodiment of the present invention, and does not impose any limitation on the present invention. Any simple modification, change, and equivalent structural change made to the above embodiments according to the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An industrial robot remote monitoring and diagnosis system, characterized in that, It includes an industrial robot terminal, a data acquisition module, a cloud server, and a diagnostic terminal; The industrial robot terminal is used to control the robot body to execute operation instructions according to industrial on-site or remote instructions; The data acquisition module collects the real-time operation status data of the industrial robot and uploads it to the cloud server; The cloud server is used to store and process the real-time operation status data collected from the industrial site; Use the existing operation status data to make a data set, and train the monitoring and diagnostic network to obtain an optimized and trained diagnostic model; And diagnose based on the currently collected real-time operation status data, and output the current operation status label of the industrial site; The diagnostic terminal obtains the operation status data and the current operation status label of the current industrial robot by accessing the cloud server, and is used for the monitoring and diagnosis of the abnormal status of the industrial robot.

2. The industrial robot remote monitoring and diagnosis system according to claim 1, characterized in that, The industrial robot system includes an industrial robot body and its controller.

3. An industrial robot remote monitoring and diagnosis system according to claim 1, characterized in that, The industrial robot terminal, the data acquisition module, the cloud server, and the diagnostic terminal communicate with each other in sequence via Ethernet.

4. An industrial robot remote monitoring and diagnosis system according to claim 1, characterized in that, The real-time operation status data includes robot position parameters and environmental parameters.

5. The industrial robot remote monitoring and diagnosis system according to claim 4, characterized in that The operation parameters are the position parameters during the operation of the robot; including joint speed, joint angle, position coordinates, and torque; the environmental parameters include temperature, current, voltage, vibration, and noise.

6. The remote monitoring and diagnosis system of an industrial robot according to claim 1, characterized in that, The monitoring and diagnostic network model is a support vector machine model.

7. An industrial robot remote monitoring and diagnosis system according to claim 1, characterized in that, The steps of the training include: Classify the real-time operation data collected on-site by experts and assign status labels; Perform PCA principal component analysis to extract features; obtain a paired data set {feature vector, status label}; Input the paired data set into the support vector machine model, set the training parameters, loss function, and number of iterations for training, and stop training when the network loss converges or reaches the number of iterations to obtain an optimized and trained diagnostic model.

8. The remote monitoring and diagnosis system for an industrial robot according to claim 1, characterized in that, The diagnostic terminal device is used to download the abnormal data information from the cloud server, and perform comprehensive fault analysis and diagnosis on the abnormal signal through an intelligent diagnostic algorithm to locate the key part where the abnormality occurs and determine the cause of the fault.

9. The industrial robot remote monitoring and diagnosis system according to claim 1, characterized in that, The comprehensive fault analysis and diagnosis gives an over-limit alarm according to whether a single or a combination of several data parameters exceed the threshold range.

10. An industrial robot remote monitoring and diagnosis system according to claim 1, characterized in that, It is necessary to pre-statistically classify the key parts of the abnormality and the cause of the fault manually, establish a corresponding relationship mapping table with the status label, and the mapping table stores the status label and its corresponding key parts of the abnormality and the cause of occurrence.

Images