The optimum selection of wavelet transform parameters for the purpose of fault detection in an industrial robot

Jaber, Alaa Abdulhady; Bicker, Robert

doi:10.1109/iccsce.2014.7072735

Cited by 17 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• The transitory and non-stationary nature of robot data [14]. Each joint in the robot will rotate at different angles and require different currents in different robot motions.…”

Section: Related Work a Challenges Definitionmentioning

confidence: 99%

“…Another common method for anomaly detection of industrial robots is signal-analysis methods. With the use of additional sensors like current sensor [12], acoustic sensor [13], or accelerometers [14], these methods based on integral transforms like Fourier or Wavelet transform can easily extract the features of signal in the transformed domain. However, the biggest limitation of signal-analysis methods is that they can only handle one dimension signal.…”

Section: B Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Anomaly Detection of Industrial Robots Using Sliding-Window Convolutional Variational Autoencoder

et al. 2020

View full text Add to dashboard Cite

With growing dependence of industrial robots, a failure of an industrial robot may interrupt current operation or even overall manufacturing workflows in the entire production line, which can cause significant economic losses. Hence, it is very essential to maintain industrial robots to ensure high-level performance. It is widely desired to have a real-time technique to constantly monitor robots by collecting time series data from robots, which can automatically detect incipient failures before robots totally shut down. Model-based methods are typically used in anomaly detection for robots, yet explicit domain knowledge and accurate mathematical models are required. Data-driven techniques can overcome these limitations. However, a major difficulty for them is the lack of sufficient fault data of industrial robots. Besides, the used technique for anomaly detection of robots should be required to not only capture the temporal dependency in collected time series data, but also the inter-correlations between different metrics. In this paper, we introduce an unsupervised anomaly detection for industrial robots, sliding-window convolutional variational autoencoder (SWCVAE), which can realize real-time anomaly detection spatially and temporally by coping with multivariate time series data. This method has been verified by a KUKA KR6R 900SIXX industrial robot, and the results prove that the proposed model can successfully detect anomaly in the robot. Thus, this work presents a promising tool for condition-based maintenance of industrial robots.INDEX TERMS Anomaly detection, industrial robots, sliding window, variational autoencoder, convolutional neural network.

show abstract

“…• The transitory and non-stationary nature of robot data [14]. Each joint in the robot will rotate at different angles and require different currents in different robot motions.…”

Section: Related Work a Challenges Definitionmentioning

confidence: 99%

Section: B Approachesmentioning

confidence: 99%

Unsupervised Anomaly Detection of Industrial Robots Using Sliding-Window Convolutional Variational Autoencoder

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The method achieves the fault diagnosis of robot joints through the cooperation of detection and diagnosis observers, which requires a large amount of joint sensor information. Jaber and Bicker [ 7 ] collected the vibration signal of the working state of the robot, used the methods of wavelet transformation time-frequency domain analysis to analyze the fault signal of the robot under various working conditions, and realized the fault diagnosis of the robot. Capisani et al [ 8 ] established a fault diagnosis model for robots using a sliding observer and applied it to the fault diagnosis of Comau robots.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Method for Industrial Robots Based on DBN Joint Information Fusion Technology

Jiao¹,

Zheng²

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Aiming at the problems of the traditional industrial robot fault diagnosis model, such as low accuracy, low efficiency, poor stability, and real-time performance in multi-fault state diagnosis, a fault diagnosis method based on DBN joint information fusion technology is proposed. By studying the information processing method and the deep learning theory, this paper takes the fault of the joint bearing of the industrial robot as the research object. It adopts the technique of combining the deep belief network (DBN) and wavelet energy entropy, and the fault diagnosis of industrial robot is studied. The wavelet transform is used to denoise, decompose, and reconstruct the vibration signal of the joint bearing of the industrial robot. The normalized eigenvector of the reconstructed energy entropy is established, and the normalized eigenvector is used as the input of the DBN. The improved D-S evidence theory is used to solve the problem of fusion of high conflict evidence to improve the fault model’s recognition accuracy. Finally, the feasibility of the model is verified by collecting the fault sample data and creating the category sample label. The experiment shows that the fault diagnosis method designed can complete the fault diagnosis of industrial robot well, and the accuracy of the test set is 97.96%. Compared with the traditional fault diagnosis model, the method is improved obviously, and the stability of the model is good; the utility model has the advantages of short time and high diagnosis efficiency and is suitable for the diagnosis work under the condition of coexisting multiple faults. The reliability of this method in the fault diagnosis of the joint bearing of industrial robot is verified.

show abstract

“…However, its main disadvantage is that it requires multiple parameter measurements under a series of known faults to ensure its classification learning ability (Di Lello et al, 2013). In reference, a variety of vibration and sound signals in the working process of robots is collected, and the frequency domain information of signals in various working states is analyzed through wavelet transform, which can also achieve the fault detection of industrial robots (Jaber & Bicker, 2014). However, this method has strong pertinence and it is difficult to choose many parameters in the process of implementation.…”

Section: Introductionmentioning

confidence: 99%

Actuator fault detection for masonry robot manipulator arm with the interval observer

Jinbao

Zhang

Hou

et al. 2022

Journal of Field Robotics

View full text Add to dashboard Cite

The main construction method of building wall is artificial masonry, the main problem is that the process is associated with low construction efficiency and poor safety, workers are prone fall from high altitude. The research of automatic masonry robot has become an urgent need. The masonry mechanical arm system is the main executing part of the masonry robot, special attention should be paid to the robot fault. Therefore, it is necessary to establish a suitable model to detect the actuator faults of the manipulator system. In this paper, a dynamic model of manipulator fault is presented and a fault detection scheme of masonry robot manipulator arm is proposed based on the model. The model is simplified by analyzing the state parameters of each joint during robot masonry and the interval observer with more design freedom was designed based on the established mathematical model of actuator faults. In this paper, a joint method for solving S and L matrices is proposed, which avoids the limitation of the traditional method for solving L matrices by twostep. In the presence of external interference, l 1 /H ∞ performance are introduced into the generation process of residual interval, and the interval observer has better disturbance robustness and fault sensitivity. Simulation experiments verify that the scheme can effectively detect the actuator fault of the manipulator, and experiments are carried out on a 6-axis manipulator. The experimental results show that when actuator faults occur at joints 2 and 3, the residual rapidly exceeds the threshold range, which proves the effectiveness of the fault detection scheme designed in this paper.

show abstract

The optimum selection of wavelet transform parameters for the purpose of fault detection in an industrial robot

Cited by 17 publications

References 8 publications

Unsupervised Anomaly Detection of Industrial Robots Using Sliding-Window Convolutional Variational Autoencoder

Unsupervised Anomaly Detection of Industrial Robots Using Sliding-Window Convolutional Variational Autoencoder

Fault Diagnosis Method for Industrial Robots Based on DBN Joint Information Fusion Technology

Actuator fault detection for masonry robot manipulator arm with the interval observer

Contact Info

Product

Resources

About