Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers

The complex working conditions and nonlinear characteristics of the motor drive control system of industrial robots make it difficult to detect faults.In this paper,a deep learning-based observer,which combines the convolutional neural network(CNN)and the long short-term memory network(LSTM),is employed to approximate the nonlinear driving control system.CNN layers are introduced to extract dynamic features of the data,whereas LSTM layers perform time-sequential prediction of the target system.In terms of application,normal samples are fed into the observer to build an offline prediction model for the target system.The trained CNN-LSTM-based observer is then deployed along with the target system to estimate the system outputs.Online fault detection can be realized by analyzing the residuals.Finally,an application of the proposed fault detection method to a brushless DC motor drive system is given to verify the effectiveness of the proposed scheme.Simulation results indicate the impressive fault detection capability of the presented method for driving control systems of industrial robots.

An Overview of Calibration Technology of Industrial Robots

With the continuous improvement of automation,industrial robots have become an indispensable part of automated production lines.They widely used in a number of industrial production activities,such as spraying,welding,handling,etc.,and have a great role in these sectors.Recently,the robotic technology is developing towards high precision,high intelligence.Robot calibration technology has a great significance to improve the accuracy of robot.However,it has much work to be done in the identification of robot parameters.The parameter identification work of existing serial and parallel robots is introduced.On the one hand,it summarizes the methods for parameter calibration and discusses their advantages and disadvantages.On the other hand,the application of parameter identification is introduced.This overview has a great reference value for robot manufacturers to choose proper identification method,points further research areas for researchers.Finally,this paper analyzes the existing problems in robot calibration,which may be worth researching in the future.

Variable Stiffness Identification and Configuration Optimization of Industrial Robots for Machining Tasks

Industrial robots are increasingly being used in machining tasks because of their high flexibility and intelligence.However,the low structural stiffness of a robot significantly affects its positional accuracy and the machining quality of its operation equipment.Studying robot stiffness characteristics and optimization methods is an effective method of improving the stiffness performance of a robot.Accordingly,aiming at the poor accuracy of stiffness modeling caused by approximating the stiffness of each joint as a constant,a variable stiffness identification method is proposed based on space gridding.Subsequently,a task-oriented axial stiffness evaluation index is proposed to quantitatively assess the stiffness performance in the machining direction.In addition,by analyzing the redundant kinematic characteristics of the robot machining system,a configuration optimization method is further developed to maximize the index.For numerous points or trajectory-processing tasks,a configuration smoothing strategy is proposed to rapidly acquire optimized configurations.Finally,experiments on a KR500 robot were conducted to verify the feasibility and validity of the proposed stiffness identification and configuration optimization methods.

Application of the Morphological Analysis for the Synthesis Arrangements of Industrial Robots with Parallel Structure Mechanisms

The main features of morphological model of industrial robots are discussed, such as support system, manipulator and gripping device. These features are presented with the alternatives for their realization as separate modules. The examples of synthesis of arrangements of industrial robots are resulted on module principle with writing of their morphological formulas.

Have Industrial Robots Improved Pollution Reduction?A Theoretical Approach and Empirical Analysis

To investigate whether industrial robots have improved the ecological environment,this study integrated the adoption of robot technology and pollution abatement into Melitz's heterogeneous firm model.This showed that using robots in production can lower firms'pollution intensity by increasing their abatement investments,and this reduction effect is greater for higher polluting firms and those subject to weaker local environmental regulations.These theoretical expectations were then confirmed through a series of empirical investigations based on Bartik instrument regressions,with multiple robustness checks as well as heterogeneity and mechanism analyses.This paper adds to the literature on the relationships between automation technologies and green transformation.It shows that in the pursuit of economic growth and environmental protection,it is necessary for policymakers to shift from pollution control to technical support for traditional manufacturing firms.

Technological anxiety:Analysis of the impact of industrial intelligence on employment in China

Employment is the greatest livelihood.Whether the impact of industrial robotics technology materialized in machines on employment in the digital age is an“icing on the cake”or“adding fuel to the fire”needs further study.This study aims to analyze the impact of the installation and application of industrial robots on labor demand in the context of the Chinese economy.First,from the theoretical logic and the economic development law,this study gives the prior judgment and research hypothesis that industrial intelligence will increase jobs.Then,based on the panel data of 269 cities in China from 2006 to 2021,we use the two-way fixed effect model,dynamic threshold model,and two-stage intermediary effect model.The objective is to investigate the impact of industrial intelligence on enterprise labor demand and its path mechanism.Results show that the overall effect of industrial intelligence on the labor force with the installation density index of industrial robots as the proxy variable is the“creation effect”.In other words,advanced digital technology has created additional jobs,and the overall supply of employment in the labor market has increased.The conclusion is still valid after the endogeneity identification and robustness test.In addition,the positive effect has a nonlinear effect on the network scale.When the installation density of industrial robots exceeds a particular threshold value,the division of labor continues to deepen under the combined action of the production efficiency and compensation effects,which will cause enterprises to increase labor demand further.Further research showed that industrial intelligence can increase employment by promoting synergistic agglomeration and improving labor price distortions.This study concludes that in the digital China era,the introduction and installation of industrial robots by enterprises can affect the optimal allocation of the labor market.This phenomenon has essential experience and reference significance for guiding industrial digitalization and intelligent transformation and promoting the high-quality development of people’s livelihood.

Harmonic reducer in-situ fault diagnosis for industrial robots based on deep learning

The harmonic reducer is an essential kinetic transmission component in the industrial robots.It is easy to be fatigued and resulted in physical malfunction after a long period of operation.Therefore,an accurate in-situ fault diagnosis for the harmonic reducers in an industrial robot is especially important.This paper proposes a fault diagnosis method based on deep learning for the harmonic reducer of industrial robots via consecutive time-domain vibration signals.Considering the sampling signals from industrial robots are long,narrow,and channel-independent,this method combined a 1-dimensional convolutional neural network with matrix kernels(1-D MCNN)adaptive model.By adjusting the size of the convolution kernels,it can concentrate on the contextual feature extraction of consecutive time-domain data while retaining the ability to process the multi-channel fusion data.The proposed method is examined on a physical industrial robot platform,which has achieved a prediction accuracy of99%.Its performance is appeared to be superior in comparison to the traditional 2-dimensional CNN,deep sparse automatic encoding network(DSAE),multilayer perceptual network(MLP),and support vector machine(SVM).

Online identification of time-varying dynamical systems for industrial robots based on sparse Bayesian learning

Nowadays, industrial robots have been widely used in manufacturing, healthcare, packaging, and more. Choosing robots in these applications mainly attributes to their repeatability and precision. However, prolonged and loaded operations can deteriorate the accuracy and efficiency of industrial robots due to the unavoidable accumulated kinematical and dynamical errors. This paper resolves these aforementioned issues by proposing an online time-varying sparse Bayesian learning(SBL) method to identify dynamical systems of robots in real-time. The identification of dynamical systems for industrial robots is cast as a sparse linear regression problem. By constructing the dictionary matrix, the parameters of the robot dynamics are effectively estimated via a re-weighted1-minimization algorithm. Online recursive methods are integrated into SBL to achieve real-time system identification. By including sparsity and promoting online learning, the proposed method can handle time-varying dynamical systems and therefore improve operational stability and accuracy. Experimental results on both simulated and real selective compliance assembly robot arm(SCARA) robots have demonstrated the effectiveness of the proposed method for industrial robots.

Deep adaptive control with online identification for industrial robots

Derivation of control equations from data is a critical problem in numerous scientific and engineering fields.The inverse dynamic control of robot manipulators in the field of industrial robot research is a key example.Traditionally,researchers needed to obtain the robot dynamic model through physical modeling methods before developing controllers.However,the robot dynamic model and suitable control methods are often elusive and difficult to tune,particularly when dealing with real dynamical systems.In this paper,we combine an enhanced online sparse Bayesian learning(OSBL)algorithm and a model reference adaptive control method to obtain a data-driven modeling and control strategy from data containing noise;this strategy can be applied to dynamical systems.In particular,we use a sparse Bayesian approach,relying only on some prior knowledge of its physics,to extract an accurate mechanistic model from the measured data.Unmodeled parameters are further identified from the modeling error through a deep neural network(DNN).By combining the identification model with a model reference adaptive control approach,a general deep adaptive control(DAC)method is obtained,which can tolerate unmodeled dynamics.The adaptive update law is derived from Lyapunov’s stability criterion,which guarantees the asymptotic stability of the system.Finally,the Enhanced OSBL identification method and DAC scheme are applied on a six-degree-of-freedom industrial robot,and the effectiveness of the proposed method is verified.

Customer Value Analysis in the Context of Internet Commerce of Industrial Robots

Internet commerce of industrial robots has the potential to provide higher value to customers in downstream industries. Aiming to transform the potential to a reality, customer values are systematically analyzed on basis of Value-Focused Thinking, which includes five aspects of identification, expression, organization, measurement and utilization. Nine types of heuristic questions are firstly used to identify customers＇ value statements. These statements are then transformed into a common expression. Then means-ends analysis and part- whole analysis are used to infer the relationships among statements, and result in a means-ends network and a hierarchical value tree for organizing them. To measure achievement of customer values, a decision model is used to identify and select the measurable attribute of each value statement, and a value model is then constructed from the set of measurable attributes. Finally, customer values are actively applied to support decision customer procurement, website design, creative or improved design of industrial robots. making of

Vibration Diagnosis and Optimization of Industrial Robot Based on TPA and EMD Methods

This paper proposedmethod that combined transmission path analysis(TPA)and empirical mode decomposition(EMD)envelope analysis to solve the vibration problemof an industrial robot.Firstly,the deconvolution filter timedomain TPA method is proposed to trace the source along with the time variation.Secondly,the TPA method positioned themain source of robotic vibration under typically different working conditions.Thirdly,independent vibration testing of the Rotate Vector(RV)reducer is conducted under different loads and speeds,which are key components of an industrial robot.The method of EMD and Hilbert envelope was used to extract the fault feature of the RV reducer.Finally,the structural problems of the RV reducer were summarized.The vibration performance of industrial robots was improved through the RV reducer optimization.From the whole industrial robot to the local RV Reducer and then to the internal microstructure of the reducer,the source of defect information is traced accurately.Experimental results showed that the TPA and EMD hybrid methods were more accurate and efficient than traditional time-frequency analysis methods to solve industrial robot vibration problems.

Deflection estimation of industrial robots with flexible joints

The application of industrial robots in manufacturing industries has received considerable concerns due to the high flexibility,multifunctionality,and cost-efficiency.It is well known that the robot positioning accuracy is susceptible to the load and motion of robots owing to the insufficient stiffness of robots.Therefore,the machining accuracy improvement has been a research focus in the robotic manufacturing industries in the last decade.To overcome the measurement difficulty of the joint torque and position as well as the complex dynamic coupling between rotors and links,two forward dynamics algorithms for the robot deflection estimation are proposed in this paper.The robot kinematics and dynamics algorithms considering the dynamic coupling between rotors and links are developed based on Lie theory.The forward dynamics equations of robots are solved via the proposed algorithms:the implicit numerical integration algorithm and numerical iterative estimation algorithm.When only the motor position is available,the implicit numerical integration algorithm is employed to solve the forward dynamics equations to estimate the joint torque and position.At the same time,when both the motor position and torque are available,the forward dynamics equations can be reorganized as algebraic equations and solved by the numerical iterative estimation algorithm.Simulations of a 6-DOF serial robot are performed to verify the accuracy of the proposed algorithms.

Precision measurement and compensation of kinematic errors for industrial robots using artifact and machine learning

Industrial robots are widely used in various areas owing to their greater degrees of freedom(DOFs)and larger operation space compared with traditional frame movement systems involving sliding and rotational stages.However,the geometrical transfer of joint kinematic errors and the relatively weak rigidity of industrial robots compared with frame movement systems decrease their absolute kinematic accuracy,thereby limiting their further application in ultraprecision manufacturing.This imposes a stringent requirement for improving the absolute kinematic accuracy of industrial robots in terms of the position and orientation of the robot arm end.Current measurement and compensation methods for industrial robots either require expensive measuring systems,producing positioning or orientation errors,or offer low measurement accuracy.Herein,a kinematic calibration method for an industrial robot using an artifact with a hybrid spherical and ellipsoid surface is proposed.A system with submicrometric precision for measuring the position and orientation of the robot arm end is developed using laser displacement sensors.Subsequently,a novel kinematic error compensating method involving both a residual learning algorithm and a neural network is proposed to compensate for nonlinear errors.A six-layer recurrent neural network(RNN)is designed to compensate for the kinematic nonlinear errors of a six-DOF industrial robot.The results validate the feasibility of the proposed method for measuring the kinematic errors of industrial robots,and the compensation method based on the RNN improves the accuracy via parameter fitting.Experimental studies show that the measuring system and compensation method can reduce motion errors by more than 30%.The present study provides a feasible and economic approach for measuring and improving the motion accuracy of an industrial robot at the submicrometric measurement level.

CORMAND2--针对工业机器人的欺骗攻击

Industrial robots are becoming increasingly vulnerable to cyber incidents and attacks,particularly with the dawn of the Industrial Internet-of-Things(IIoT).To gain a comprehensive understanding of these cyber risks,vulnerabilities of industrial robots were analyzed empirically,using more than three million communication packets collected with testbeds of two ABB IRB120 robots and five other robots from various original equipment manufacturers(OEMs).This analysis,guided by the confidentiality-integrity-availability(CIA)triad,uncovers robot vulnerabilities in three dimensions:confidentiality,integrity,and availability.These vulnerabilities were used to design Covering Robot Manipulation via Data Deception(CORMAND2),an automated cyber-physical attack against industrial robots.CORMAND2 manipulates robot operation while deceiving the Supervisory Control and Data Acquisition(SCADA)system that the robot is operating normally by modifying the robot’s movement data and data deception.CORMAND2 and its capability of degrading the manufacturing was validated experimentally using the aforementioned seven robots from six different OEMs.CORMAND2 unveils the limitations of existing anomaly detection systems,more specifically the assumption of the authenticity of SCADA-received movement data,to which we propose mitigations for.

The Development of Dynamic Compliant Wrist for Robots

Based on an analysis of the relative shaft-to-hole position and attiude errors, as well as of the mechanics and Kinematics in the process of automatic assembly of industrial robots, the paper studies the principle of construction of dynamic wrists. Type I-3 and Ⅱ-6 dynamic compliant wrists have been designed and made. Prblems in the production of compliant elements and the connection between compliant elements and wrists were also solved. A study on the results of tests of the function of two kinds of dynamic compliant wrists shows that the dynamic compliant wrist's compliancy function can be improved by adding metallic materials having higher longitudinal and transverse rigidity into the softer elstomer. And the design Principle is proved to be feasible and practicable. It can be expected that the use of dynamic compliant wrist will greatly lower the technical requirements of the shaft-hole assembly and the requirements in the resetting accuracy.

Data Driven Vibration Control:A Review

With the ongoing advancements in sensor networks and data acquisition technologies across various systems like manufacturing,aviation,and healthcare,the data driven vibration control(DDVC)has attracted broad interests from both the industrial and academic communities.Input shaping(IS),as a simple and effective feedforward method,is greatly demanded in DDVC methods.It convolves the desired input command with impulse sequence without requiring parametric dynamics and the closed-loop system structure,thereby suppressing the residual vibration separately.Based on a thorough investigation into the state-of-the-art DDVC methods,this survey has made the following efforts:1)Introducing the IS theory and typical input shapers;2)Categorizing recent progress of DDVC methods;3)Summarizing commonly adopted metrics for DDVC;and 4)Discussing the engineering applications and future trends of DDVC.By doing so,this study provides a systematic and comprehensive overview of existing DDVC methods from designing to optimizing perspectives,aiming at promoting future research regarding this emerging and vital issue.

Enabling Technologies for Autonomous Robotic Systems in Manufacturing

Research of autonomous manufacturing systems is motivated both by the new technical possibilities of cyber-physical systems and by the practical needs of the industry.Autonomous operation in semi-structured industrial environments can now be supported by advanced sensor technologies,digital twins,artificial intelligence and novel communication techniques.These enable real-time monitoring of production processes,situation recognition and prediction,automated and adaptive(re)planning,teamwork and performance improvement by learning.This paper summarizes the main requirements towards autonomous industrial robotics and suggests a generic workflow for realizing such systems.Application case studies will be presented from recent practice at HUN-REN SZTAKI in a broad range of domains such as assembly,welding,grinding,picking and placing,and machining.The various solutions have in common that they use a generic digital twin concept as their core.After making general recommendations for realizing autonomous robotic solutions in the industry,open issues for future research will be discussed.

The optimization method of industrial robot arm structure based on green manufacturing technology

In order to realize the optimal design of the industrial robot arm structure,an optimization method of the industrial robot arm structure based on green manufacturing technology is proposed.The stability of arm structure parameter acquisition can be controlled.The quantitative adjustment model of structural optimization parameters is constructed.The differential fusion control of the arm structure is realized.This paper analyzes the structure parameter law of the robot arm.We use dynamic parameter prediction and output torque parameter compensation method to control the arm structure.According to the adaptive iterative processing results,the arm structure parameter identification is realized.According to the identification results,the cutting parameter optimization method is adopted for the analytical control of the arm structure,and finally the optimized design of the industrial robot arm structure is realized through the green manufacturing technology.The simulation test results show that for the accuracy of the industrial robot arm structure design,this method is better,the output stability is higher,and the arm motion trajectory has a low deviation from the actual motion trajectory,which improves the optimization control and design capabilities of the industrial robot arm structure.

Design of a Two-Step Calibration Method of Kinematic Parameters for Serial Robots

Serial robots are used to handle workpieces with large dimensions, and calibrating kinematic parameters is one of the most efficient ways to upgrade their accuracy. Many models are set up to investigate how many kinematic parameters can be identified to meet the minimal principle, but the base frame and the kinematic parameter are indistinctly calibrated in a one-step way. A two-step method of calibrating kinematic parameters is proposed to improve the accuracy of the robot＇s base frame and kinematic parameters. The forward kinematics described with respect to the measuring coordinate frame are established based on the product- of-exponential （POE） formula. In the first step the robot＇s base coordinate frame is calibrated by the unit quaternion form. The errors of both the robot＇s reference configuration and the base coordinate frame＇s pose are equivalently transformed to the zero-position errors of the robot＇s joints. The simplified model of the robot＇s positioning error is established in second-power explicit expressions. Then the identification model is finished by the least square method, requiring measuring position coordinates only. The complete subtasks of calibrating the robot＇ s 39 kinematic parameters are finished in the second step. It＇s proved by a group of calibration experiments that by the proposed two-step calibration method the average absolute accuracy of industrial robots is updated to 0.23 mm. This paper presents that the robot＇s base frame should be calibrated before its kinematic parameters in order to upgrade its absolute positioning accuracy.

Uncalibrated Workpiece Positioning Method for Peg-in-hole Assembly Using an Industrial Robot

This paper proposes an uncalibrated workpiece positioning method for peg-in-hole assembly of a device using an industrial robot.Depth images are used to identify and locate the workpieces when a peg-in-hole assembly task is carried out by an industrial robot in a flexible production system.First,the depth image is thresholded according to the depth data of the workpiece surface so as to filter out the background interference.Second,a series of image processing and the feature recognition algorithms are executed to extract the outer contour features and locate the center point position.This image information,fed by the vision system,will drive the robot to achieve the positioning,approximately.Finally,the Hough circle detection algorithm is used to extract the features and the relevant parameters of the circular hole where the assembly would be done,on the color image,for accurate positioning.The experimental result shows that the positioning accuracy of this method is between 0.6-1.2 mm,in the used experimental system.The entire positioning process need not require complicated calibration,and the method is highly flexible.It is suitable for the automatic assembly tasks with multi-specification or in small batches,in a flexible production system.