Remote monitoring and maintenance method and system for industrial robot

Abstract

The invention belongs to the technical field of industrial robots, and particularly relates to a remote monitoring and maintenance method and system for an industrial robot, and the method comprises the steps: installing a sensor on the industrial robot, and collecting the operation data of the industrial robot in real time; carrying out data cleaning and format conversion on the real-time collected operation data of the industrial robot; after data processing is completed, the data is compared with a preset data threshold value, fault diagnosis is triggered when the operation data of the robot is abnormal, and a fault corresponding to the abnormal operation data of the industrial robot is judged through a pre-trained industrial robot fault diagnosis model; and the background maintainer remotely operates the robot for maintenance according to the diagnosis result. By combining data transmission, data processing and a fault diagnosis technology based on a deep learning algorithm, accurate and real-time remote monitoring and maintenance of the industrial robot are realized, the operation and maintenance cost is reduced, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial robots, and in particular relates to a remote monitoring and maintenance method and system for industrial robots. Background Art

[0002] Industrial robots play a vital role in modern industrial production and are widely used in many fields such as automobile manufacturing, electronics, logistics, etc. With the continuous improvement of industrial automation, the number and complexity of industrial robots are also increasing. The traditional maintenance method of industrial robots mainly relies on on-site manual inspection and on-site repair after failure, which has many disadvantages. On the one hand, on-site manual inspection requires a lot of manpower and time costs, and it is difficult to discover potential fault hazards in real time; on the other hand, when a robot fails, on-site repair often requires professional technicians to rush to the site, which not only leads to long maintenance time and affects production efficiency, but also may not be able to solve the problem quickly and accurately due to the lack of experience of technicians. Therefore, it is of great practical significance to develop an efficient remote monitoring and maintenance method for industrial robots. Summary of the invention

[0003] In view of the shortcomings of the above-mentioned existing methods, the present invention provides a remote monitoring and maintenance method and system for industrial robots, aiming to solve the core problems of low automation and low maintenance efficiency of industrial robot monitoring and maintenance methods in the prior art.

[0004] To achieve the above-mentioned purpose, the present invention is implemented by the following technical solutions:

[0005] A remote monitoring and maintenance method for an industrial robot, the method comprising the following steps:

[0006] Step S10: Install sensors at key parts of the industrial robot such as motors, joints and transmission components to collect analog signals of the industrial robot's operating data in real time, convert the analog signals into digital signals and transmit them to the data processing module via the CAN bus;

[0007] Step S20: the industrial robot operation data processing module performs data cleaning and format conversion on the industrial robot operation data collected in real time, and stores the processed data in a database;

[0008] Step S30: the industrial robot remote monitoring module reads the processed industrial robot operation data from the database, compares it with the data warning threshold preset in the remote monitoring module, and issues a warning message when the monitored data exceeds the threshold;

[0009] Step S40: After the industrial robot remote monitoring module issues a warning message, the industrial robot operation fault diagnosis unit is automatically started, and the industrial robot operation data exceeding the threshold is input into a pre-trained industrial robot fault diagnosis model to determine the fault corresponding to the industrial robot operation data exceeding the threshold. The backend maintenance personnel remotely repair the industrial robot according to the diagnosis result;

[0010] Among them, the sensors installed in step S10 include temperature sensors, pressure sensors, vibration sensors and current sensors. The temperature sensors are installed at the joints of the industrial robot to collect the temperature of each joint when the industrial robot is running in real time; the pressure sensors and vibration sensors are installed on the transmission parts of the industrial robot to collect the pressure and vibration frequency of the transmission parts when the industrial robot is running in real time; the current sensor is installed on the motor of the industrial robot to collect the current of the motor when the industrial robot is running in real time; each sensor collects the operation data of the industrial robot in real time at a time interval of 10 times per second, and the collected operation data of the industrial robot is timestamped;

[0011] In addition, in step S30, the monitoring module reads the processed industrial robot operation data from the database and updates it in real time to the industrial robot operation status display interface, presenting the temperature of each joint of the industrial robot in the form of a temperature curve; presenting the pressure and vibration frequency of the transmission parts in the form of a dynamic chart or numerical value; and presenting the current of the motor when the industrial robot is running in the form of a current curve.

[0012] Preferably, the step of converting the analog signal into a digital signal in step S10 includes:

[0013] Sampling: Based on the set time interval of 10 times per second, the continuous analog signal is discretized. At each sampling moment, the amplitude of the analog signal at that sampling moment is obtained and converted into a series of amplitude samples at discrete time points. These samples retain the basic characteristics of the analog signal.

[0014] Quantization: The amplitude samples obtained by sampling are quantized and converted into discrete digital quantities. According to the preset quantization level, the amplitude samples are divided into corresponding quantization intervals, and a fixed quantization value is used to represent all amplitudes in the interval. For example, the quantization level is set to 8 bits, and the amplitude range is divided into 256 intervals. Each interval corresponds to a quantization value. In this way, the continuous amplitude signal is converted into discrete digital quantities, which is convenient for subsequent digital processing;

[0015] Coding: Use binary complement coding to convert the quantized digital quantity into binary code to obtain a digital signal, ensuring the accuracy and compatibility of the converted digital signal in subsequent transmission and processing so that it can interact with other digital devices and systems.

[0016] Preferably, the step of the data processing module in step S20 performing data cleaning on the real-time collected industrial robot operation data includes:

[0017] Data deduplication: By comparing the timestamps of the industrial robot's operating data, check whether there are duplicate records. If there are duplicate records, keep the data checked for the first time to avoid interference with subsequent analysis by duplicate data, and ensure the simplicity and accuracy of the data;

[0018] Outlier detection and processing: Use statistical methods to identify outliers in the data, calculate the average values ​​of various types of data in the industrial robot operation data, and when the data at a certain moment is greater than 4 times the corresponding average value of the data of this type, the data at that moment is determined to be an outlier and removed;

[0019] Missing value processing: Check the missing values ​​of the industrial robot operation data according to the timestamp. If the operation data record of the industrial robot at a certain moment is 0 or blank, when the missing values ​​account for less than or equal to 10% of the total data, use the average value of the industrial robot operation data calculated in the outlier detection and processing steps to fill the missing values; when the missing values ​​account for more than 10% of the total data, re-collect the industrial robot operation data and perform data cleaning again.

[0020] Preferably, the data processing module in step S20 performs format conversion on the real-time collected industrial robot operation data, including converting the numerical data collected by the sensor into floating point type for mathematical operations; and converting the time-related data into the standard time format ISO8601 for facilitating time series analysis.

[0021] Preferably, the monitoring module in step S30 presets a data warning threshold, and issues a warning message when the monitored data exceeds the threshold, including the average value σ of the industrial robot operation data calculated according to the abnormal value detection and processing in step S20, the corresponding average value σ1 of the joint temperature, the average value σ2 of the pressure on the transmission components, the average value σ3 of the vibration frequency of the transmission components and the average value σ4 of the motor current, and the threshold of each data is set to twice the average value of each data, namely 2σ1, 2σ2, 2σ3 and 2σ4. When the industrial robot operation data is monitored to exceed the set threshold, a warning message is issued to the maintenance personnel, and the abnormal data information exceeding the set threshold is obtained from the database, including the timestamp of the abnormal data, the sensor that collects the abnormal data, and the change trend within 20 seconds before and after 20 seconds of the abnormal data. When the abnormal data is an abnormal data segment, the change trend is within 20 seconds before the first data of the abnormal data segment and within 20 seconds after the last data of the abnormal data segment; the acquired abnormal data information is sent to the maintenance personnel at the same time.

[0022] Preferably, the steps of constructing and training the industrial robot fault diagnosis model in step S40 include:

[0023] Data collection: Collect the operating data of industrial robots under different working conditions, including normal operation data and operation data under various fault conditions, including the temperature of each joint when the industrial robot is running, the pressure and vibration frequency of the transmission parts when the industrial robot is running, and the current of the motor when the industrial robot is running;

[0024] Data preprocessing and data set division: Data preprocessing is performed on the collected industrial robot operation data, including deduplication, outlier processing, and missing value processing. 70% of the preprocessed data is divided into a training set, 20% into a validation set, and 10% into a test set.

[0025] Construction of industrial robot fault diagnosis model: The model is constructed using an RNN-based algorithm, including an input layer, a hidden layer, and an output layer. The input layer is used to input the industrial robot operation data into the network; the hidden layer is used to process the long-term dependencies in the input data, receiving the current input and the hidden state of the previous moment at each time step, and updating the hidden state through the nonlinear activation function Tanh; the output layer determines the fault type of the input industrial robot operation data through linear transformation and Softmax activation function;

[0026] Industrial robot fault diagnosis model training: During the training process, the cross entropy loss function is used to calculate the gradient of the loss function with respect to the model through back propagation, and the parameters of the cross entropy loss function are updated according to the calculation results. When the calculation results converge, the model training is completed;

[0027] Evaluation and optimization of industrial robot fault diagnosis models: After model training is completed, the model is evaluated through the validation set. When overfitting occurs, L1 regularization and Dropout technology are used to optimize model training;

[0028] Confirmation and deployment of industrial robot fault diagnosis model: After completing model optimization, the model is tested using a test set. When the accuracy of the model in determining the fault type of the industrial robot operation data is greater than 90%, the model version is determined and deployed to the industrial robot operation fault diagnosis unit.

[0029] In addition, to achieve the above-mentioned purpose, the present invention also proposes a remote monitoring and maintenance system for an industrial robot, the remote monitoring and maintenance system for an industrial robot comprising:

[0030] Industrial robot operation data acquisition module: used to install sensors in key parts of the industrial robot such as motors, joints and transmission parts to collect analog signals of industrial robot operation data in real time, convert the analog signals into digital signals and transmit them to the data processing module through the CAN bus;

[0031] Industrial robot operation data preprocessing module: used to clean and convert the real-time collected industrial robot operation data, and store the processed data in the database;

[0032] Industrial robot remote monitoring module: used to read the processed industrial robot operation data from the database and update it in real time to the industrial robot operation status display interface. The monitoring module presets the data warning threshold, and issues a warning message when the monitored data exceeds the threshold;

[0033] Industrial robot maintenance module: After the industrial robot remote monitoring module issues an early warning message, the industrial robot operation fault diagnosis unit is automatically started, and the industrial robot operation data exceeding the threshold is input into the pre-trained industrial robot fault diagnosis model to determine the fault corresponding to the industrial robot operation data exceeding the threshold. The backend maintenance personnel remotely repair the industrial robot according to the diagnosis results;

[0034] The sensors installed in the industrial robot operation data acquisition module include a temperature sensor, a pressure sensor, a vibration sensor and a current sensor. The temperature sensor is installed at the joint of the industrial robot to collect the temperature of each joint when the industrial robot is running in real time; the pressure sensor and the vibration sensor are installed on the transmission component of the industrial robot to collect the pressure and vibration frequency of the transmission component when the industrial robot is running in real time; the current sensor is installed on the motor of the industrial robot to collect the current of the motor when the industrial robot is running in real time; each sensor collects the operation data of the industrial robot in real time at a time interval of 10 times per second, and the collected operation data of the industrial robot has a timestamp;

[0035] The industrial robot remote monitoring module reads the processed industrial robot operation data from the database and updates it to the industrial robot operation status display interface in real time, presenting the temperature of each joint of the industrial robot in the form of a temperature curve; presenting the pressure and vibration frequency of the transmission parts in the form of a dynamic chart or numerical value; and presenting the current of the motor when the industrial robot is running in the form of a current curve.

[0036] In addition, to achieve the above-mentioned objectives, the present invention also proposes a remote monitoring and maintenance device for an industrial robot, the device comprising: a memory, a processor, and programs such as an industrial robot fault diagnosis algorithm stored in the memory and executable on the processor, the industrial robot fault diagnosis algorithm and other programs being steps for implementing a remote monitoring and maintenance method for an industrial robot as described above.

[0037] Preferably, in order to achieve the above-mentioned purpose, the present invention also provides a computer program product, which includes programs such as an industrial robot fault diagnosis algorithm, and when the programs such as the industrial robot fault diagnosis algorithm are executed by a processor, a remote monitoring and maintenance method for an industrial robot as described above is implemented.

[0038] The advantages and effects of the present invention are:

[0039] The present invention provides a remote monitoring and maintenance method and system for industrial robots. By combining data transmission, data processing and fault diagnosis technology based on deep learning algorithms, real-time remote monitoring of industrial robots is achieved, problems are discovered in time and early warnings are issued, so as to minimize the losses caused by faults, improve the accuracy of industrial robot fault diagnosis, shorten the troubleshooting time, and improve the efficiency of industrial robot maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0041] Figure 1 The present invention is a flowchart of a remote monitoring and maintenance method for an industrial robot.

[0042] Figure 2 The figure is a schematic diagram of the structure of a remote monitoring and maintenance system for an industrial robot according to the present invention.

[0043] Figure 3 The present invention is a schematic block diagram of the structure of an electronic device for remote monitoring and maintenance of an industrial robot. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] The present invention provides a remote monitoring and maintenance method for an industrial robot. The method is as follows: Figure 1 As shown, the following steps are included:

[0046] Step S10: Install sensors at key locations such as the motor, joints, and transmission components of the industrial robot to collect analog signals of the industrial robot's operating data in real time, and convert the analog signals into digital signals and transmit them to the data processing module via the CAN bus.

[0047] The sensors installed in step S10 include temperature sensors, pressure sensors, vibration sensors and current sensors. The temperature sensors are installed at the joints of the industrial robot to collect the temperatures of the joints in real time when the industrial robot is running; the pressure sensors and vibration sensors are installed on the transmission parts of the industrial robot to collect the pressure and vibration frequency of the transmission parts in real time when the industrial robot is running; the current sensor is installed on the motor of the industrial robot to collect the current of the motor in real time when the industrial robot is running; each sensor collects the operating data of the industrial robot in real time at a time interval of 10 times per second, and the collected operating data of the industrial robot is timestamped.

[0048] Specifically, the step of converting the analog signal into a digital signal in step S10 includes:

[0049] Sampling: Based on the set time interval of 10 times per second, the continuous analog signal is discretized. At each sampling moment, the amplitude of the analog signal at that sampling moment is obtained and converted into a series of amplitude samples at discrete time points. These samples retain the basic characteristics of the analog signal.

[0050] Quantization: The amplitude samples obtained by sampling are quantized and converted into discrete digital quantities. According to the preset quantization level, the amplitude samples are divided into corresponding quantization intervals, and a fixed quantization value is used to represent all amplitudes in the interval. For example, the quantization level is set to 8 bits, and the amplitude range is divided into 256 intervals. Each interval corresponds to a quantization value. In this way, the continuous amplitude signal is converted into discrete digital quantities, which is convenient for subsequent digital processing;

[0051] Coding: Use binary complement coding to convert the quantized digital quantity into binary code to obtain a digital signal, ensuring the accuracy and compatibility of the converted digital signal in subsequent transmission and processing so that it can interact with other digital devices and systems.

[0052] Step S20: The industrial robot operation data processing module performs data cleaning and format conversion on the industrial robot operation data collected in real time, and stores the processed data in a database.

[0053] Specifically, the step of the data processing module in step S20 performing data cleaning on the real-time collected industrial robot operation data includes:

[0054] Data deduplication: By comparing the timestamps of the industrial robot's operating data, check whether there are duplicate records. If there are duplicate records, keep the data checked for the first time to avoid interference with subsequent analysis by duplicate data, and ensure the simplicity and accuracy of the data;

[0055] Outlier detection and processing: Use statistical methods to identify outliers in the data, calculate the average values ​​of various types of data in the industrial robot operation data, and when the data at a certain moment is greater than 4 times the corresponding average value of the data of this type, the data at that moment is determined to be an outlier and removed;

[0056] Missing value processing: Check the missing values ​​of the industrial robot operation data according to the timestamp. If the operation data record of the industrial robot at a certain moment is 0 or blank, when the missing values ​​account for less than or equal to 10% of the total data, use the average value of the industrial robot operation data calculated in the outlier detection and processing steps to fill the missing values; when the missing values ​​account for more than 10% of the total data, re-collect the industrial robot operation data and perform data cleaning again.

[0057] In addition, in step S20, the data processing module performs format conversion on the real-time collected industrial robot operation data, including converting the numerical data collected by the sensor into floating point type for mathematical operations; and converting the time-related data into the standard time format ISO8601 for facilitating time series analysis.

[0058] Step S30: The industrial robot remote monitoring module reads the processed industrial robot operation data from the database, compares it with the data warning threshold preset in the remote monitoring module, and issues a warning message when the monitored data exceeds the threshold.

[0059] Among them, in step S30, the monitoring module reads the processed industrial robot operation data from the database and updates it to the industrial robot operation status display interface in real time, presenting the temperature of each joint of the industrial robot in the form of a temperature curve; presenting the pressure and vibration frequency of the transmission parts in the form of a dynamic chart or numerical value; and presenting the current of the motor when the industrial robot is running in the form of a current curve.

[0060] Specifically, in step S30, the monitoring module presets a data warning threshold, and issues a warning message when the monitored data exceeds the threshold, including the average value σ of the industrial robot operation data calculated according to the abnormal value detection and processing in step S20, the corresponding average value σ1 of the joint temperature, the average value σ2 of the pressure on the transmission components, the average value σ3 of the vibration frequency of the transmission components, and the average value σ4 of the motor current. The threshold of each data is set to twice the average value of each data, which is 2σ1, 2σ2, 2σ3 and 2σ4. When the industrial robot operation data is monitored to exceed the set threshold, a warning message is issued to the maintenance personnel, and the abnormal data information exceeding the set threshold is obtained from the database, including the timestamp of the abnormal data, the sensor that collects the abnormal data, and the change trend within 20 seconds before and after 20 seconds of the abnormal data. When the abnormal data is an abnormal data segment, the change trend is within 20 seconds before the first data of the abnormal data segment and within 20 seconds after the last data of the abnormal data segment; the acquired abnormal data information is sent to the maintenance personnel at the same time.

[0061] Step S40: After the industrial robot remote monitoring module issues a warning message, the industrial robot operation fault diagnosis unit is automatically started, and the industrial robot operation data that exceeds the threshold is input into a pre-trained industrial robot fault diagnosis model to determine the fault corresponding to the industrial robot operation data that exceeds the threshold. The background maintenance personnel remotely repair the industrial robot based on the diagnosis results.

[0062] Specifically, the steps of constructing and training the industrial robot fault diagnosis model in step S40 include:

[0063] Data collection: Collect the operating data of industrial robots under different working conditions, including normal operation data and operation data under various fault conditions, including the temperature of each joint when the industrial robot is running, the pressure and vibration frequency of the transmission parts when the industrial robot is running, and the current of the motor when the industrial robot is running;

[0064] Data preprocessing and data set division: Data preprocessing is performed on the collected industrial robot operation data, including deduplication, outlier processing, and missing value processing. 70% of the preprocessed data is divided into a training set, 20% into a validation set, and 10% into a test set.

[0065] Construction of industrial robot fault diagnosis model: The model is constructed using an RNN-based algorithm, including an input layer, a hidden layer, and an output layer. The input layer is used to input the industrial robot operation data into the network; the hidden layer is used to process the long-term dependencies in the input data, receiving the current input and the hidden state of the previous moment at each time step, and updating the hidden state through the nonlinear activation function Tanh; the output layer determines the fault type of the input industrial robot operation data through linear transformation and Softmax activation function;

[0066] Industrial robot fault diagnosis model training: During the training process, the cross entropy loss function is used to calculate the gradient of the loss function with respect to the model through back propagation, and the parameters of the cross entropy loss function are updated according to the calculation results. When the calculation results converge, the model training is completed;

[0067] Evaluation and optimization of industrial robot fault diagnosis models: After model training is completed, the model is evaluated through the validation set. When overfitting occurs, L1 regularization and Dropout technology are used to optimize model training;

[0068] Confirmation and deployment of industrial robot fault diagnosis model: After completing model optimization, the model is tested using a test set. When the accuracy of the model in determining the fault type of the industrial robot operation data is greater than 90%, the model version is determined and deployed to the industrial robot operation fault diagnosis unit.

[0069] In addition, the present invention also proposes a remote monitoring and maintenance system for industrial robots, please refer to Figure 2 , the remote monitoring and maintenance system for an industrial robot comprises:

[0070] Industrial robot operation data acquisition module: used to install sensors in key parts of the industrial robot such as motors, joints and transmission parts to collect analog signals of industrial robot operation data in real time, convert the analog signals into digital signals and transmit them to the data processing module through the CAN bus;

[0071] Industrial robot operation data preprocessing module: used to clean and convert the real-time collected industrial robot operation data, and store the processed data in the database;

[0072] Industrial robot remote monitoring module: used to read the processed industrial robot operation data from the database and update it in real time to the industrial robot operation status display interface. The monitoring module presets the data warning threshold, and issues a warning message when the monitored data exceeds the threshold;

[0073] Industrial robot maintenance module: After the industrial robot remote monitoring module issues an early warning message, the industrial robot operation fault diagnosis unit is automatically started, and the industrial robot operation data exceeding the threshold is input into the pre-trained industrial robot fault diagnosis model to determine the fault corresponding to the industrial robot operation data exceeding the threshold. The backend maintenance personnel remotely repair the industrial robot according to the diagnosis results;

[0074] Among them, the sensors installed in the industrial robot operation data acquisition module include temperature sensors, pressure sensors, vibration sensors and current sensors. The temperature sensor is installed at the joints of the industrial robot to collect the temperature of each joint when the industrial robot is running in real time; the pressure sensor and vibration sensor are installed on the transmission parts of the industrial robot to collect the pressure and vibration frequency of the transmission parts when the industrial robot is running in real time; the current sensor is installed on the motor of the industrial robot to collect the current of the motor when the industrial robot is running in real time; each sensor collects the operation data of the industrial robot in real time at a time interval of 10 times per second, and the collected operation data of the industrial robot is timestamped;

[0075] Among them, the industrial robot remote monitoring module reads the processed industrial robot operation data from the database and updates it in real time to the industrial robot operation status display interface, presenting the temperature of each joint of the industrial robot in the form of a temperature curve; presenting the pressure and vibration frequency of the transmission parts in the form of dynamic graphs or numerical values; and presenting the current of the motor when the industrial robot is running in the form of a current curve.

[0076] The remote monitoring and maintenance system for industrial robots provided by the present application adopts the remote monitoring and maintenance method for industrial robots in the above-mentioned embodiment, which can solve the technical problems of low efficiency in monitoring and maintenance of industrial robots and low accuracy in fault diagnosis. Compared with the prior art, the beneficial effects of the remote monitoring and maintenance system for industrial robots provided by the present application are the same as the beneficial effects of the remote monitoring and maintenance method for industrial robots provided by the above-mentioned embodiment, and the other technical features of the remote monitoring and maintenance system for industrial robots are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0077] The present application provides a remote monitoring and maintenance device for an industrial robot, the remote monitoring and maintenance device for an industrial robot comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a remote monitoring and maintenance method for an industrial robot in the above-mentioned embodiment one.

[0078] Reference below Figure 3 , which shows a schematic diagram of the structure of a remote monitoring and maintenance device for an industrial robot suitable for implementing an embodiment of the present application. A remote monitoring and maintenance device for an industrial robot in an embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The remote monitoring and maintenance device for an industrial robot shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0079] Figure 3The remote monitoring and maintenance device for an industrial robot shown may include a processing system 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage system 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of a remote monitoring and maintenance device for an industrial robot are also stored. The processing system 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: an input system 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output system 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage system 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication system 1009. The communication system 1009 may allow a remote monitoring and maintenance device for an industrial robot to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a remote monitoring and maintenance device for an industrial robot with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0080] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication system, or installed from a storage system 1003, or installed from a ROM 1002. When the computer program is executed by the processing system 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0081] The remote monitoring and maintenance device for industrial robots provided by the present application adopts the remote monitoring and maintenance method for industrial robots in the above-mentioned embodiment, which can solve the technical problems of low efficiency in monitoring and maintenance of industrial robots and low accuracy in fault diagnosis. Compared with the prior art, the beneficial effects of the remote monitoring and maintenance device for industrial robots provided by the present application are the same as the beneficial effects of the remote monitoring and maintenance method for industrial robots provided by the above-mentioned embodiment, and the other technical features of the remote monitoring and maintenance device for industrial robots are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0082] The various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0083] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned remote monitoring and maintenance method for an industrial robot when executed by a processor.

[0084] The computer program product provided by the present application can solve the technical problems of low efficiency in monitoring and maintenance of industrial robots and low accuracy in fault diagnosis. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of a remote monitoring and maintenance method for industrial robots provided by the above embodiment, which will not be described in detail here.

[0085] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A remote monitoring and maintenance method for an industrial robot, characterized in that: The method comprises the following steps: Step S10: Install sensors on the motor, joints and transmission components of the industrial robot to collect analog signals of the industrial robot's operating data in real time, convert the analog signals into digital signals and transmit them to the data processing module through the CAN bus; Step S20: The data processing module performs data cleaning and format conversion on the real-time collected industrial robot operation data, and stores the processed data in a database; Step S30: the industrial robot remote monitoring module reads the processed industrial robot operation data from the database, compares it with the data warning threshold preset in the remote monitoring module, and issues a warning message when the monitored data exceeds the threshold; Step S40: After the industrial robot remote monitoring module issues a warning message, the industrial robot operation fault diagnosis unit is automatically started, and the industrial robot operation data exceeding the threshold is input into a pre-trained industrial robot fault diagnosis model to determine the fault corresponding to the industrial robot operation data exceeding the threshold. The backend maintenance personnel remotely repair the industrial robot according to the diagnosis result; The sensors installed in step S10 include temperature sensors, pressure sensors, vibration sensors and current sensors. The temperature sensors are installed at the joints of the industrial robot to collect the temperatures of the joints in real time when the industrial robot is running; the pressure sensors and vibration sensors are installed on the transmission components of the industrial robot to collect the pressure and vibration frequency of the transmission components in real time when the industrial robot is running; the current sensor is installed on the motor of the industrial robot to collect the current of the motor in real time when the industrial robot is running; each sensor collects the operating data of the industrial robot in real time at a time interval of 10 times per second, and the collected operating data of the industrial robot has a timestamp.

2. A remote monitoring and maintenance method for an industrial robot according to claim 1, characterized in that: The step of converting the analog signal into a digital signal in step S10 includes: Sampling: Based on the set time interval of 10 times per second, the continuous analog signal is discretized. At each sampling moment, the amplitude of the analog signal at that sampling moment is obtained and converted into a series of amplitude samples at discrete time points; Quantization: The amplitude samples obtained by sampling are quantized and converted into discrete digital quantities. According to the preset quantization level, the amplitude samples are divided into corresponding quantization intervals, and a fixed quantization value is used to represent all amplitudes in the interval. In this way, the continuous amplitude signal is converted into discrete digital quantities; Coding: Use binary complement coding to convert the quantized digital quantity into binary code to obtain a digital signal.

3. A remote monitoring and maintenance method for an industrial robot according to claim 1, characterized in that: The step of the data processing module in step S20 performing data cleaning on the real-time collected industrial robot operation data includes: Data deduplication: By comparing the timestamps of the industrial robot's operating data, check whether there are duplicate records. If there are duplicate records, keep the data checked for the first time; Outlier detection and processing: Use statistical methods to identify outliers in the data, calculate the average values ​​of various types of data in the industrial robot operation data, and when the data at a certain moment is greater than 4 times the corresponding average value of the data of this type, the data at that moment is determined to be an outlier and removed; Missing value processing: Check the missing values ​​of the industrial robot operation data according to the timestamp. If the operation data record of the industrial robot at a certain moment is 0 or blank, when the missing values ​​account for less than or equal to 10% of the total data, use the average value of the industrial robot operation data calculated in the outlier detection and processing steps to fill the missing values; when the missing values ​​account for more than 10% of the total data, re-collect the industrial robot operation data and perform data cleaning again.

4. A remote monitoring and maintenance method for an industrial robot according to claim 1, characterized in that: In step S20, the data processing module performs format conversion on the real-time collected industrial robot operation data, including converting the numerical data collected by the sensor into floating point data; and converting the time-related data into the standard time format ISO8601.

5. A remote monitoring and maintenance method for an industrial robot according to claim 1, characterized in that: In the step S30, the monitoring module presets a data warning threshold, and issues a warning message when the monitored data exceeds the threshold, including the average value σ of the industrial robot operation data calculated according to the abnormal value detection and processing in step S20, the corresponding average value σ1 of the joint temperature, the average value σ2 of the pressure on the transmission components, the average value σ3 of the vibration frequency of the transmission components and the average value σ4 of the motor current, and the threshold of each data is set to twice the average value of each data, which is 2σ1, 2σ2, 2σ3 and 2σ4. When the industrial robot operation data is monitored to exceed the set threshold, a warning message is issued to the maintenance personnel, and the abnormal data information exceeding the set threshold is obtained from the database, including the timestamp of the abnormal data, the sensor that collects the abnormal data, and the change trend within 20 seconds before and after 20 seconds of the abnormal data. When the abnormal data is an abnormal data segment, the change trend within 20 seconds before the first data of the abnormal data segment and within 20 seconds after the last data of the abnormal data segment; the acquired abnormal data information is sent to the maintenance personnel at the same time.

6. A remote monitoring and maintenance method for an industrial robot according to claim 1, characterized in that: The steps of constructing and training the industrial robot fault diagnosis model in step S40 include: Data collection: Collect the operating data of industrial robots under different working conditions, including normal operation data and operation data under various fault conditions, including the temperature of each joint when the industrial robot is running, the pressure and vibration frequency of the transmission parts when the industrial robot is running, and the current of the motor when the industrial robot is running; Data preprocessing and data set division: Data preprocessing is performed on the collected industrial robot operation data, including deduplication, outlier processing, and missing value processing. 70% of the preprocessed data is divided into a training set, 20% into a validation set, and 10% into a test set. Construction of industrial robot fault diagnosis model: The model is constructed using an RNN-based algorithm, including an input layer, a hidden layer, and an output layer. The input layer is used to input the industrial robot operation data into the network; the hidden layer is used to process the long-term dependencies in the input data, receiving the current input and the hidden state of the previous moment at each time step, and updating the hidden state through the nonlinear activation function Tanh; the output layer determines the fault type of the input industrial robot operation data through linear transformation and Softmax activation function; Industrial robot fault diagnosis model training: During the training process, the cross entropy loss function is used to calculate the gradient of the loss function with respect to the model through back propagation, and the parameters of the cross entropy loss function are updated according to the calculation results. When the calculation results converge, the model training is completed; Evaluation and optimization of industrial robot fault diagnosis models: After model training is completed, the model is evaluated through the validation set. When overfitting occurs, L1 regularization and Dropout technology are used to optimize model training; Confirmation and deployment of industrial robot fault diagnosis model: After completing model optimization, the model is tested using a test set. When the accuracy of the model in determining the fault type of the industrial robot operation data is greater than 90%, the model version is determined and deployed to the industrial robot operation fault diagnosis unit.

7. A remote monitoring and maintenance system for an industrial robot, characterized in that: The remote monitoring and maintenance system for an industrial robot comprises: Industrial robot operation data acquisition module: used to install sensors on the motors, joints and transmission parts of the industrial robot to collect analog signals of the industrial robot operation data in real time, convert the analog signals into digital signals and transmit them to the data processing module through the CAN bus; Industrial robot operation data preprocessing module: used to clean and convert the real-time collected industrial robot operation data, and store the processed data in the database; Industrial robot remote monitoring module: used to read the processed industrial robot operation data from the database and update it in real time to the industrial robot operation status display interface. The monitoring module presets the data warning threshold, and issues a warning message when the monitored data exceeds the threshold; Industrial robot maintenance module: After the industrial robot remote monitoring module issues an early warning message, the industrial robot operation fault diagnosis unit is automatically started, and the industrial robot operation data exceeding the threshold is input into the pre-trained industrial robot fault diagnosis model to determine the fault corresponding to the industrial robot operation data exceeding the threshold. The backend maintenance personnel remotely repair the industrial robot according to the diagnosis results; The sensors installed in the industrial robot operation data acquisition module include temperature sensors, pressure sensors, vibration sensors and current sensors. The temperature sensors are installed at the joints of the industrial robot to collect the temperatures of the joints in real time when the industrial robot is running; the pressure sensors and vibration sensors are installed on the transmission parts of the industrial robot to collect the pressure and vibration frequency of the transmission parts in real time when the industrial robot is running; the current sensor is installed on the motor of the industrial robot to collect the current of the motor in real time when the industrial robot is running; each sensor collects the operation data of the industrial robot in real time at a time interval of 10 times per second, and the collected operation data of the industrial robot has a timestamp.

8. A remote monitoring and maintenance device for an industrial robot, characterized in that: The remote monitoring and maintenance device for an industrial robot comprises: A memory, a processor, and a program of an industrial robot fault diagnosis algorithm stored in the memory and executable on the processor, wherein the program of the industrial robot fault diagnosis algorithm, when executed by the processor, implements a remote monitoring and maintenance method for an industrial robot as described in any one of claims 1 to 6.

9. A computer program product, characterized in that The computer program product includes a program of an industrial robot fault diagnosis algorithm, and when the program of the industrial robot fault diagnosis algorithm is executed by a processor, a remote monitoring and maintenance method for an industrial robot as described in any one of claims 1 to 6 is implemented.

Images