Novel Non-Model-Based Fault Detection and Isolation of Satellite Reaction Wheels Based on a Mixed-Learning Fusion Framework

Nozari, Hasan Abbasi; Castaldi, Paolo; Banadaki, Hamed Dehghan; Simani, Silvio

doi:10.1016/j.ifacol.2019.11.222

Cited by 14 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the performance of this FDI technique, dataset consists of 100 samples for each anomaly were simulated and checked by the FDI technique. Results obtained by the model based FDI approach presented in table (3) showed fault detection accuracy between (90-98)% and detection time between (270-318) m sec.…”

Section: Artificial Neural Network (Ann) Model-based Fdi Techniquementioning

confidence: 98%

“…In both cases, an FDI algorithm is necessary to constantly update information about the system's status and any induced changes, and to adjust the control law as needed. In this context, FDI systems provide basic information about system health status and enable subsequent tuning actions to improve system reliability, availability and conveniently [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spacecraft fault detection and identification techniques using artificial intelligence

Abdel Aziz,

Salama,

Mohamed

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The complexity of spacecraft systems and their missions is increasing, requiring higher levels of performance and innovative solutions. It is essential to have onboard autonomy with minimal faults to ensure reliability, availability, and safety. Fault Detection and Identification (FDI) is critical in identifying spacecraft faults before they cause major failures. However, FDI design and application are challenging due to the space environment and the reliance on system information. To improve accuracy, speed, and noise robustness, modern FDI methods based on Artificial Intelligence (AI) techniques have been developed. This paper investigates the latest FDI techniques in the spacecraft attitude determination and control subsystem (ADCS) and electrical power subsystem (EPS). The article discusses various FDI methodologies and frameworks, highlighting their advantages, drawbacks, and the significance of AI implementation. Additionally, the paper presents a thorough analysis and comparison of the different methods.

show abstract

Section: Artificial Neural Network (Ann) Model-based Fdi Techniquementioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Spacecraft fault detection and identification techniques using artificial intelligence

Abdel Aziz,

Salama,

Mohamed

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Quantitative FDD techniques can also be performed non-model-based, sometimes referred to as pattern-recognition-based. This strategy’s basic idea is online monitoring of any measures regarding the control system variables without requiring to define of any specific dependence laws in the time domain between them (Nozari et al, 2019). Subsequently, the operator analyzes the measured variables to make a decision about the plants’ operating mode and raise alarms.…”

Section: Fault Detection and Diagnosis Analysis For Li-ion Battery Sy...mentioning

confidence: 99%

A review on fault-tolerant control strategies for lithium-ion battery systems

Ghaeminezhad

Wang

Ouyang

2022

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

Expanding the usable life of rechargeable Lithium-ion batteries in numerous applications calls for an effective evaluation of probable faults and their diagnosis and control methods. Plenty of work has focused on Lithium-ion battery systems’ fault detection and diagnosis techniques. However, seldom of them are devoted to the comprehensive analysis and comparison of the fault-tolerant control schemes. To fill this gap, a review of the most up-to-date fault-tolerant control methods applied to the Lithium-ion battery systems is conducted in this paper. They are classified as active, passive, and integrated methods. To this end, this paper first presents a detailed description of fault types in Lithium-ion batteries, followed by a proposed classification of fault detection and diagnostic methods. Finally, the paper concludes with a comprehensive discussion of the advantages and disadvantages of the reviewed algorithms.

show abstract

“…Folami 14 applied a random forest (RF) algorithm to realise the fault isolation of a three-axis reaction wheel. Nozari et al 15 designed a satellite reaction wheel fault detection and isolation framework by combining four classical machinelearning methods: RF, SVM, partial least squares, and plain Bayes. With the increasing complexity of space missions, higher accuracy is required for satellite ACS fault diagnosis, and recently emerged deep-learning algorithms can achieve the required accuracy requirements.…”

Section: Introductionmentioning

confidence: 99%

Improved time-variable transformer-based fault diagnosis method for satellite attitude control system

Zhang,

Chen,

Gao

et al. 2024

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

This study proposes a fault diagnosis method based on a time-variable transformer network for satellite attitude control system telemetry data, which has the properties of a time series and strong multivariate correlation. First, a time-attention module was utilised to determine the correlation between the data at a specific time and before that time to effectively identify the dynamic properties of the data. A variable attention module is introduced to capture the degree of correlation between various variables to achieve multivariate decoupling. Then, the interactive attention layer combines the dynamic properties of the data with the correlations between the variables to achieve dynamic data decorrelation. Finally, a linear layer is used to implement the fault diagnosis.

show abstract

Novel Non-Model-Based Fault Detection and Isolation of Satellite Reaction Wheels Based on a Mixed-Learning Fusion Framework

Cited by 14 publications

References 4 publications

Spacecraft fault detection and identification techniques using artificial intelligence

Spacecraft fault detection and identification techniques using artificial intelligence

A review on fault-tolerant control strategies for lithium-ion battery systems

Improved time-variable transformer-based fault diagnosis method for satellite attitude control system

Contact Info

Product

Resources

About