Kiavash Fathi

Mr. Kiavash Fathi

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 October 2021 in Sensors
Verified
Journal Article
Open access
PDF file
KFKiavash Fathi
Kiavash Fathi
Hans Wernher van de VennHans Wernher van de Venn
Hans Wernher van de Venn
MHMarcel Honegger
Marcel Honegger
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.

6 September 2021 in Preprints.org
Verified
Preprint
Open access
PDF file
KFKiavash Fathi
Kiavash Fathi
Hans Wernher van de VennHans Wernher van de Venn
Hans Wernher van de Venn
MHMarcel Honegger
Marcel Honegger
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 is available. Due to the sequential nature of the data, non-linearity 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 is capable of calculating RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

3 June 2024
Verified
Book Chapter
Open access
PDF file
KFKiavash Fathi
Kiavash Fathi
HVHans Wernher van de Venn
Hans Wernher van de Venn
With the ever-growing complexity of different assets in a factory, the main focus of predictive maintenance solutions has shifted from model-based approaches to data-driven and hybrid approaches. This shift as a result highlights the importance and the inevitable impact of data, data quality, model maintenance, and model interpretability on the performance and acceptability of these predictive maintenance approaches in industry. In this chapter, the hurdles for developing effective predictive maintenance solutions for original equipment manufacturers (OEMs) and small and medium-sized enterprises (SMEs) with different levels of digitalization are introduced. Furthermore, it is discussed how to choose a suitable strategy for developing a predictive maintenance model, given the different constraints in the availability of data and the requirements of the customer.

Verified
Open access
PDF file
KFKiavash Fathi
Kiavash Fathi
ALAfrooz Laghaei
Afrooz Laghaei
JRJavad Rasti
Javad Rasti
MZMaryam Zekri
Maryam Zekri
Introduction: Due to sedentary postures caused by video games, many health-related issues have occurred among players. One practical solution for dealing with the aforementioned problem is to come up with game controllers which promote physical exercises. In this study, an adaptive neuro-fuzzy exergame controller was introduced. Materials and Methods: During the training stage, the parameters of the fuzzy logic’s member functions were fine-tuned. By calculating a gradient vector and by applying backpropagation, the aforementioned parameters were updated using the measured error. The controller was made of four pads, each containing a resistor and a pushbutton, which were connected to a microcontroller. In order to improve the user experience, an adaptive neuro-fuzzy logic system was used to analyze the gathered data from the controller. Results: A pure fuzzy logic system (FLS) cannot provide an acceptable playing experience for players of different ages and physical characteristics. The received signal from the controller was sent to a fine-tuned FLS. The calculated output of the previously trained FLS was one of the defined classes of “ignore”, “press”, and “hold”, which was sent as a command to the main computer. Conclusion: In the proposed method, the FLS was fine-tuned by gathering data from the user, which improved the performance of the controller due to the fact that the controller was trained to best suit the needs of the user. The gathered data was then used to change the parameters of the FLS to provide an acceptable playing experience for the user.

2 September 2026
Verified
Book Chapter
Closed access
PDF file
DKDaniyar Kakimbekov
Daniyar Kakimbekov
KFKiavash Fathi
Kiavash Fathi
MRMarko Ristin
Marko Ristin
TKTobias Kleinert
Tobias Kleinert
Hans Wernher van de VennHans Wernher van de Venn
Hans Wernher van de Venn