Assessment of Dynamic Bayesian Models for Gas Turbine Diagnostics, Part 2: Discrimination of Gradual Degradation and Rapid Faults

There are many challenges that an effective diagnostic system must overcome for successful fault diagnosis in gas turbines. Among others, it has to be robust to engine-to-engine variations in the fleet, it has to discriminate between gradual deterioration and abrupt faults, and it has to identify sensor faults correctly and be robust in case of such faults. To combine their benefits and overcome their limitations, two diagnostic methods were integrated in this work to form a multi-layer system. An adaptive performance model was used to track gradual deterioration and detect rapid or abrupt anomalies, while a series of static and dynamic Bayesian networks were integrated to identify component degradation, component abrupt faults, and sensor faults. The proposed approach was tested on synthetic data and field data from a single-shaft gas turbine of 50 MW class. The results showed that the approach could give acceptable accuracy in the isolation and identification of multiple faults, with 99% detection and isolation accuracy and 1% maximum error in the identified fault magnitude. The approach was also proven robust to sensor faults, by replacing the faulty signal with an estimated value that had only 3% error compared to the real measurement.

Passive Fault-Tolerant Control of a 2-DOF Robotic Helicopter

The presence of faults in dynamic systems causes the potential loss of some of the control objectives. For that reason, a fault-tolerant controller is required to ensure a proper operation, as well as to reduce the risk of accidents. The present work proposes a passive fault-tolerant controller that is based on robust techniques, which are utilized to adjust a proportional-derivative scheme through a linear matrix inequality. In addition, a nonlinear term is included to improve the accuracy of the control task. The proposed methodology is implemented in the control of a two degrees of a freedom robotic helicopter in a simulation environment, where abrupt faults in the actuators are considered. Finally, the proposed scheme is also tested experimentally in the Quanser® 2-DOF Helicopter, highlighting the effectiveness of the proposed controller.

A State-Domain Robust Chi-Square Test Method for GNSS/INS Integrated Navigation

Aiming at abrupt faults in GNSS/INS integrated systems in complex environments, classical fault detection algorithms are mostly developed from the measurement domain. A robust chi-square test method based on the state domain is proposed in this paper. The fault detection statistic is built based on the difference between the prior state estimation and the posterior state estimation in Kalman filtering. To improve the calculation stability, singular value decomposition (SVD) is used to factor the covariance matrix of the difference. The relevant formulas of the proposed method were theoretically derived, and the relationship between the proposed method and the existing innovation chi-square test method was revealed. The proposed method was compared with state-of-the-art chi-square test methods and verified by GNSS/INS integrated navigation experiments using simulation data and real data. The experimental results show that the proposed method (a) directly works in the state domain, (b) does not require the known real system state, (c) has computational efficiency and good robustness, and (d) accurately detects abrupt faults.

New fault detection and fault-tolerant scheme for Doppler velocity logger outage in ocean navigation systems

The inertial navigation system/Doppler velocity logger (INS/DVL) plays an important role in ocean navigation. Any DVL malfunction poses serious risks to navigation. A precise detection system is required to detect the initial moments of DVL signal malfunctions; moreover, with loss of DVL, a fault-tolerant scheme (FTS) is necessary for DVL signal reconstruction. In this paper, an evolutionary knowledge-based method, namely improved evolutionary TS-fuzzy (I-eTS), is adopted to build an artificial intelligence (AI)-based pseudo DVL to deal with long-term outage of DVL. By employing Gaussian process regression (GPR) models for fault detection, a new FTS is constructed. To verify the effectiveness of the new fault detection and fault tolerance system, navigation data is gathered by a test setup and algorithms are performed in the laboratory. In the tests, it is demonstrated that the proposed FTS leads to rapid detection of both gradual and abrupt faults, which leads to less interaction between fault detection and FTS.

Complementary Meta-Reinforcement Learning for Fault-Adaptive Control

Faults are endemic to all systems. Adaptive fault-tolerant control accepts degraded performance under faults in exchange for continued operation. In systems with abrupt faults and strict time constraints, it is imperative for control to adapt fast to system changes. We present a meta-reinforcement learning approach that quickly adapts control policy. The approach builds upon model-agnostic meta learning (MAML). The controller maintains a complement of prior policies learned under system faults. This ``library" is evaluated on a system after a new fault to initialize the new policy. This contrasts with MAML where the controller samples new policies from a distribution of similar systems at each update step to achieve the new policy. Our approach improves sample efficiency of the reinforcement learning process. We evaluate this on a model of fuel tanks under abrupt faults.

Inversion-Based Approach for Detection and Isolation of Faults in Switched Linear Systems

This paper addresses the problem of the left inversion of switched linear systems from a diagnostics perspective. The problem of left inversion is to reconstruct the input of a system with the knowledge of its output, whose differentiation is usually required. In the case of this work, the objective is to reconstruct the system’s unknown inputs, based on the knowledge of its outputs, switching sequence and known inputs. With the inverse model of the switched linear system, a real-time Fault Detection and Isolation (FDI) algorithm with an integrated Fuzzy Logic System (FLS) that is capable of detecting and isolating abrupt faults occurring in the system is developed. In order to attenuate the effects of unknown disturbances and noise at the output of the inverse model, a smoothing strategy is also used. The results are illustrated with an example. The performance of the method is validated experimentally in a dc-dc boost converter, using a low-cost microcontroller, without any additional components.

CONDITIONS AND POSSIBLE MECHANISMS OF FORMING OF LISTRIC FAULTS AND THRUST-FOLD OROGENS

В статье рассмотрен малоизученный вопрос происхождения листрических разломов, пользующихся широким распространением в покровно-надвиговых складчатых областях. Показано, что изображенные на геологических профилях этих регионов разноамплитудные перемещения отдельных покровных и тектонических пластин по типичным листрическим разломам практически невозможны в связи с возникновением в этом случае «проблемы пространства». Определено, что затруднение вызвано образованием зон приоткрывания или перекрытия при движении блоков по листрическим изогнутым поверхностям разломов в условиях горизонтального сжатия. Высказано предположение, что листрическая форма разломов вторична и образовалась путем деформации ранее существовавших разломов различной морфологии. Приведены кинематические особенности их возникновения, показывающие, что эти нарушения формируются двумя принципиально разными механизмами: в результате выкручивания фронтальных частей надвигов или вследствие искривления и выполаживания нижних частей крутых взбросов. На этом основании выделены два генетических типа листрических разломов, возникающих из разновозрастных нарушений; новообразованных пологих склонов и раннее сформированных крутых разломов. Описаны опыты, проведенные с целью экспериментального моделирования листрических разломов, которые подтвердили взгляды авторов о генезисе этих структур. Сделан вывод, что формирование листрических разломов, развитых в пределах покровно-складчатых орогенов, происходило с помощью обоих механизмов. In the article is discussed the insufficiently studied problem of an origin of the listric faults widely spread in nappe-thrust folded areas. It is shown, that represented in geological cross-sections of these regions displacement of different separate nappes and tectonic sheets with different amplitudes along of typical listric faults are practically impossible because of occurrence of «space problems». It's defined, that the difficulty is caused by formation of zones of opening or overlapping during the movement of blocks along curved surfaces of listric faults in the conditions of horizontal compression. It is assumed, that the listric form of faults is secondary and it was formed by the deformation of existed faults of various morphology. Presented kinematic features of their occurrence showing, that they are formed by two essentially different mechanisms: As a result of twisting of parts of thrusts or owing to a curvature and a flattening of lower parts of reverse faults. On this basis two genetic types of listric faults are distinguished; originating from different age disturbances of newly developed flat chopping offs and early formed abrupt faults. Experiments with the purpose of modeling of listric faults, which have confirmed the authors views on genesis of these structures are described. The conclusion is made, that listric faults within the limits of thrust-fold orogens are developed due to both mechanisms

A PDE-Based Approach for Fault Detection in Li-Ion Batteries

Despite the widespread commercialization of Li-ion batteries in various markets including portable electronics, electrified transportation, and stationary energy storage systems, their safety and reliability still poses as a concern in the eyes of industry and general public. There has been great strides in the past few decades in the development of Battery Management Systems (BMSs). The majority of the efforts, however, avoid fault occurrence by conservative designs rather than directly incorporating fault diagnostics in the BMS. Such a functionality in the BMS would enable the detection of the occurrence, type, and location of the faults and therefore, a proper reaction to them. Realizing the need for such a feature in the BMSs, the development of a model-based fault detection scheme is proposed in this paper. This method is formulated based on the original PDEs describing a single particle electrochemical battery model. The use of PDEs in the fault detection scheme reduces uncertainties arising from the model approximation. Furthermore, the convergence of this PDE-based approach is proved using Lyapunov stability theorem. Finally, the effectiveness of the proposed method in detecting various fault types ranging from incipient degradation mechanisms to abrupt faults is illustrated through simulations.