KEYWORDS: Mathematical optimization, Detection and tracking algorithms, Data modeling, Telescopes, Large telescopes, Feature selection, Random forests, Education and training, Device simulation, Computer simulations
A method for unanticipated fault diagnosis based on IGWO-iForest (Improved Grey Wolf Optimizer-Isolation Forest) is proposed to address various unpredictable problems faced by large telescopes in extreme environments. First, the random forest feature selection algorithm is used to identify the features of the original dataset and eliminate redundant features. Secondly, the differential evolution strategy is introduced into the GWO (Grey Wolf Optimizer) to improve the local search efficiency and accuracy, and the Levy flight strategy is introduced into the GWO to improve the global search ability of the algorithm. Then, the improved IGWO is used to optimize the parameters of the iForest model. Finally, the performance of the model is verified through data collected from a fault diagnosis and self-healing hardware-in-the-loop simulation platform. The experimental results show that the IGWO-iForest algorithm achieves a fault diagnosis accuracy of 99.1%, which demonstrates its higher sensitivity to a small number of unanticipated fault data compared with other anomaly detection algorithms, proving the effectiveness of this method in accurately diagnosing unanticipated faults in telescopes
As the preliminary step of the fault injection, the way of fault sample selection has a significant influence on the testing result. In order to promote the efficiency as well as to guarantee the correctness, a theoretical framework for fault sample selection for telescope drive control system based on the SDG (Sighed Digraph) modeling and the importance of nodes in graph theory is proposed in this study. Firstly, the SDG model is developed qualitatively according to the mathematical equations of control loops utilizing classic control methods. Secondly, the compatible pathways are introduced which can depict the fault propagation completely and the importance of the model nodes based on destroying degrees relative to the components of the drive control system are introduced. Finally, a procedure of fault sample selection method is proposed to show an efficient result which only needs a few of fault samples and data information.
Aiming at the lack of effective visualization strategies for the operation and maintenance of the telescope drive system, this paper proposes to use digital twin technology to improve telescope driving system visualization. Firstly, visual modeling techniques are used to construct the digital twin model of the telescope drive system. Then, the mapping relationship between the physical and digital twin of the telescope drive system is established, and the real-time mapping of the digital twin operation status is realized through the physical parameters, historical operation data and sensor data of the drive system. Finally, the intelligent operation and maintenance strategy of the telescope is formulated using the digital twin of the drive system visualization. This research will solve the visualization problems in the telescope drive system, and has practical significance for improving the operation efficiency of the telescope and formulating efficient maintenance strategies.
Aiming at the lack of prior information and the characterization difficulties of unanticipated state detection in the drive systems of astronomical telescope, the paper proposes a Multi-layer General Process Model for the recognition of telescope drive system state. Firstly, based on the prior information of state recognition, this paper refines the classification of anticipated state and unanticipated state. Then, focusing on the comprehensive description of the state of the telescope drive system, a Multi-layer General Process Model for the recognition of unanticipated state is established. Finally, the model is evaluated by using an example of Antarctica Survey Telescope drive system and excellent results have been obtained. The study of unanticipated state is the deepening and upgrading of anticipated, and it is an extension of fault diagnosis technology.
More and more astronomical instruments have been installed in extreme environment such as Antarctica because of good seeing. However it’s not good for electromechanical system of astronomical telescope due to the harsh environment. This paper presents the study of the unanticipated states of direct drive system of extremely large telescope in extreme environment. The unanticipated states which are short of priori knowledge will degrade the reliability of monitor system significantly and put the self-diagnosis system into trouble.
This paper presents an expert system fault diagnosis and seamless self-healing scheme based on artificial intelligence, which is used for the astronomical telescope drive system. For the faults that have already occurred, the expert system inference mechanism can be used to realize quick localization of failure, and we can use the expert solution in the knowledge base to run the self-healing decision until the failure is resolved. For the failure the knowledge base doesn’t have, we can use human-machine interface to achieve real-time update of the knowledge base. For the faults that didn’t occurred, the trained adaptive BP neural network is used to fit the parameters of the telescope running status, to monitor the running status of the telescope in real time and to realize the fault warning of the telescope operation. Fault diagnosis and seamless self-healing technology is one of the key technologies to realize intelligent, its research is of great significance.
More and more astronomical instruments have been installed in Antarctica because of good seeing. Due to adverse circumstances, remote location and unattended, a high fault rate was found in these astronomical instruments in Antarctica. To ensure the reliable operation of these instruments is one of critical technology problems. This paper presents an experimental platform with semi-physical simulation technique for Antarctic Telescopes. The platform helps the research for fault detection, fault diagnosis method, fault handling and so on. It consists of fault simulation system and fault diagnosis and self-recovery system. Furthermore, the platform can be used as fault diagnosis unit for Antarctic telescope directly.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.