Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot

Abstract

Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 DoF delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data are available. Due to the sequential nature of the data, nonlinearity of the system, and correlations between parameter time-series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method can calculate RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

Deep learning-based methods in structural reliability analysis: a review

“…Fathi et al [103] considered the case that run-to-failure data is not available and adopted AE to predict when maintenance is required based on the signal sequence distribution and anomaly detection. Thereafter, a sigmoid function is utilized to predict the abnormal conditional indicator, and the RUL can be calculated by GP.…”

Review of fault detection techniques for predictive maintenance

“…In all these devices, the connection of several components to the cloud allows the identification of anomalies or defect patterns (Uhlmann et al, 2017). Because the number of errors in manufacturing systems is lower than in normal operation conditions, researchers developed decision support systems that act as a benchmark to trigger alarms for failure conditions (C ozar et al, 2017;Fathi et al, 2021;Maseda et al, 2021). Dynamic dashboards designed by the researchers automatically visualises detected events using semantic reasoning, assisting experts in the revision and correction of event labels (Steenwinckel et al, 2021).…”

“…Deep learning networks guarantees better accuracies while dealing with systems like aircraft maintenance systems (Ning et al, 2021;Basora et al, 2021), delta robots (Fathi et al, 2021), wind turbines (Roelofs et al, 2021), building management systems (Mesa-Jim enez et al, 2021), air compressor systems (Gribbestad et al, 2021) and wind generators (Beretta et al, 2020). Auto-encoders and LSTMs operate well when dealing with stream data coming from manufacturing or aircraft industries.…”

“…Because the number of errors in manufacturing systems is lower than in normal operation conditions, researchers developed decision support systems that act as a benchmark to trigger alarms for failure conditions (Cózar et al. , 2017; Fathi et al. , 2021; Maseda et al.…”

Możliwości Wykorzystania Głębokich Sieci Neuronowych W Konserwacji Predykcyjnej

“…According to Fathi et al [14] research, a hybrid deep network structure with an autoencoder was provided for anomaly detection in signal sequences from sensors of the 3DOF delta robot. An integrated strategy for dynamic predictive maintenance scheduling based on a deep auto-encoder and deep forest-assisted failure prognosis method was produced by Yu et al [15].…”