Monitoring, Diagnostics, and Prognostics for Robot Tool Center Accuracy Degradation

Abstract

Over time, robots degrade because of age and wear, leading to decreased reliability and increasing potential for faults and failures; this negatively impacts robot availability. Economic factors motivate facilities and factories to improve maintenance operations to monitor robot degradation and detect faults and failures, especially to eliminate unexpected shutdowns. Since robot systems are complex, with sub-systems and components, it is challenging to determine these constituent elements’ specific influence on the overall system performance. The development of monitoring, diagnostic, and prognostic technologies (collectively known as Prognostics and Health Management (PHM)), can aid manufacturers in maintaining the performance of robot systems by providing intelligence to enhance maintenance and control strategies. This paper presents the strategy of integrating top level and component level PHM to detect robot performance degradation (including robot tool center accuracy degradation), supported by the development of a four-layer sensing and analysis structure. The top level PHM can quickly detect robot tool center accuracy degradation through advanced sensing and test methods developed at the National Institute of Standards and Technology (NIST). The component level PHM supports deep data analysis for root cause diagnostics and prognostics. A reference data set is collected and analyzed using the integration of top level PHM and component level PHM to understand the influence of temperature, speed, and payload on robot’s accuracy degradation.

Supervised Machine-Learning Methodology for Industrial Robot Positional Health Using Artificial Neural Networks, Discrete Wavelet Transform, and Nonlinear Indicators

“…In addition, combining the results of the FFNN classifiers in an expert system provides a more reliable and robust method for detecting anomalies in the robot joints’ behavior. The results for joint five, where a 100% classification accuracy is obtained, are supported by those reported in [ 24 ]. A deviation in this robot joint is shown through a review of the position and velocity graphs.…”

“…In this sense, the proposed method can identify in which part of the robot there is a deviation that directly affects the precision of the TCP due to the accumulation of the error through the kinematic chain. Besides, in [ 24 ], where the dataset was originally presented, a comparison is made between the position error and the velocity of the robot joint, to determine if there is a deviation. However, no method or model is presented to perform the analysis, although quantitative results are obtained about the deviation and in which joints it is found.…”

“…In addition, the proposed method is helpful in quickly identifying deviating joints (80 s approximately), especially in a serial robot arm, where the error accumulates along the kinematic chain. In contrast with other works that share the use of the same database, such as [ 21 ], where the residual error of the TCP is addressed, or [ 24 ], where a handmade comparison is made between the position and velocity of the joints to detect deviation; the proposed method can identify, in an automated way, in which part of the robot is the deviation, it does not require modeling of the robot or external sensors to perform measurements, and the method is applicable to robots of different degrees of freedom. The early identification of the deviating joint allows the implementation of robot calibration methodologies and the generation of diagnostic strategies for preventive maintenance of the robot, reducing maintenance times and costs, both valuable resources in the industrial field.…”

“…A smart target was designed, to be used with the vision system mentioned before, and its feasibility in performing robot accuracy assessment was verified in [ 22 , 23 ]. In [ 24 ], a methodology was presented for integrating top-level and component-level PHM (external measurement system and controller, environmental, and add-on sensing, respectively), for accuracy monitoring and diagnosis of the robot tool center. The top-level PHM allows for identifying the deviation of the TCP.…”

Measurement and Evaluation for Prognostics and Health Management (PHM) for Manufacturing Operations – Summary of an Interactive Workshop Highlighting PHM Trends

“…• Degradation Measurement of Robot Arm Accuracythis research is focused on detecting robot performance degradation by monitoring the accuracy of the robot's tool center position. This research includes the development of a four-level sensing and analysis structure along with the development of a novel six degree-of-freedom (DOF) smart target that is paired with a vision system to acquire fine resolution position information of the robot (Qiao, 2019;Qiao & Weiss, 2018). Figure 1 highlights the smart target that was developed in the scope of this work.…”