Incipient faults in electrical drives can corrupt overall performance of high-speed trains; however, they are difficult to discover because their slight fault symptoms. By sufficiently exploiting the distribution information incipient faults, this paper presents reason why cannot be detected by existing detection and diagnosis (FDD) methods. Under principal component analysis (PCA) framework, we propose a new data-driven FDD method, which is named probability-relevant PCA (PRPCA), for...

Batch-end quality modeling is used to predict the by using batch measurements and generally involves a large number of predictor variables. However, not all variables are beneficial for prediction. Conventional multiway partial least squares (PLS) may function properly batch-end because many irrelevant This paper proposes an optimized sparse PLS (OSPLS) approach simultaneous prediction relevant-variable selection. The effect on quality-prediction performance analyzed, importance selection...

Dynamics and nonlinearity may exist in the time batch directions for processes, thereby complicating monitoring of these processes. In this article, we propose a two-dimensional deep correlated representation learning (2D-DCRL) method to achieve efficient fault detection isolation nonlinear Three-way historical data are first unfolded as two-way time-slice data. Second, stacked autoencoder based neural network is constructed characterize correlation among process variables. Considering that...

A modern batch process can be characterized by a large scale and multiple operation units, local fault detection for the key units of such is imperative. time-slice canonical correlation analysis (CCA)-based multivariate statistical monitoring scheme processes proposed. First, three-way data are unfolded into data. Second, CCA modeling performed at each time instant to explore between entire process. Then, residual generated statistics constructed. The discriminate both status type detected...

Hot spots are common abnormalities in photovoltaic (PV) energy systems. Their presence can potentially cause damage to PV modules, such as performance degradation or even unexpected fire By sufficiently mining the information hidden test data collected from this paper develops a space-to-space projection method, which at its core is linear approach via preserving locally geometrical structure with respect time series. Based on nonlinear model of modules established proposed projection,...

Successive batch processes generally involve within-batch and batch-to-batch correlations, monitoring of such is imperative. This paper proposes a multiobjective two-dimensional canonical correlation analysis (M2D-CCA)-based fault detection scheme to achieve efficient successive processes. First, three-way historical process data are unfolded into two-way time-slice data. Second, for each measurement, CCA performed between the current measurement previous measurements from both time...

The distributed adaptive tracking control schemes are addressed to deal with the formation problem of multiple unmanned aerial vehicles subject input saturation, actuator fault, and external disturbance. First, a novel backstepping approach associated command filter is presented settle model uncertainty saturation problems. Second, robust fault-tolerant controller introduced tackle case disturbance, by estimating upper bounds faults disturbances. In addition, proposed controllers enable...

Online identification of a plant based on the input–output data obtained under closed-loop operation conditions is fundamental problem in many industrial applications, because it paves way for process monitoring, controller calibration, redesign, etc. This paper proposes recursive batch-to-batch method modeling batch regulated by within-batch exploiting its intrinsic repeatable pattern. To overcome severe variations parameter estimates, three kinds priori knowledge are included, namely, time...

Traction systems are an important aspect of high-speed trains, and their reliable operation is crucial. With data available from this paper proposes optimal fault detection diagnosis (FDD) strategy for dynamic traction systems. Based on the established model, using sensor measurements, a correlation-aided subspace identification technique proposed to formulate residual signals corresponding test statistics detection. Then, modified support vector machine (SVM) designed optimally solving bias...

Hot spots (HSs) in the early stage can corrupt generation efficiency of photovoltaic (PV) systems, whose evolution may cause fire hazards as time goes on. Whilst, they are difficult to detect because slight anomaly symptoms. In this paper, we propose a novel data-driven detection method HSs, named slow manifold analysis (SMA), for PV systems. SMA sufficiently extracts nonlinear information hidden monitoring data from modules HSs. The salient strengths SMA-based are: 1) algorithm is high...

The novel backstepping control schemes are proposed to deal with the formation problem of multiple unmanned aerial vehicles (UAVs) input saturation constraint and model uncertainty. trajectory tracking error UAVs is established. Then standard ideal controller, which applied address case certain no constraint, presented. After that, an adaptive controller associated designed command filter developed overcome controllers above enable asymptotical Lyapunov stability closed-loop system....

Summary In this study, a novel integrated fault tolerant control (FTC) strategy is proposed for rigid satellite attitude systems under the case of external disturbance, Lipschitz nonlinearity, and sensor faults. Different from traditional adaptive estimation method, an augmented observer designed considered faulty system, which could be used estimating both system state fault. A virtual firstly introduced, then, real derived as result unmeasurable information to design observer. On basis,...

Hot spots are easy to appear in photovoltaic (PV) systems and even cause fires severe cases. Therefore, under the framework of manifold learning, we develop a new data-driven method, named neighborhood slowest embedding (NSE), it is based on sufficiently extracting trend change information caused by anomalies monitoring data detect hot PV systems. The NSE-based spot detection method has three salient advantages: 1) sensitivity enhanced; 2) high computational efficiency ensure real-time can...

An optimal fuzzy controller design scheme is proposed to address the influence of time delay and disturbance on control performance nonlinear batch processes. First, a two-dimensional (2D) equivalent Takagi-Suguno (T-S) error model formulated. By introducing quadratic index function adopting 2D Lyapunov-Krasovskii theory, existence condition law given. Furthermore, its solvable condition, which depends time-delay bounds, constructed in terms linear matrix inequalities, gain obtained by using...

An H-infinity model predictive fault-tolerant control strategy is proposed for multi-phase batch processes with interval delay and actuator failures. First, state variables, errors output tracking are introduced to establish an extended-state-space switched system model. Then, based on this model, a law designed the set point by that satisfies requirements of optimal performance index under input constraints. The feasibility conditions solvability presented in form linear matrix...

In this work, a trajectory generation method is proposed to meet the functions of boom positioning, load elimination and obstacle avoidance for limited working space motion constraints rotary crane. The key point paper that when position static known, depth camera can obtain random starting three-dimensional coordinates ending coordinates, then an be automatically generated tracked by controller.

Abstract Research on the motion control of overhead cranes, constrained by underactuated characteristics, helps improve efficiency payload transportation. Most studies require all system state variables (trolley displacement, swing angle, and their velocities). In practice, sensors measure transmit these variables, but noise affects accuracy, reducing performance. Additionally, uncertainties in crane parameters, unmodeled friction, unknown disturbances threaten system's stability....

Abstract This paper proposes a novel data-driven approach for hot-spot fault detection in photovoltaic (PV) modules, utilizing curved Riemannian manifold (RM) to characterize the sample space. The proposed method detects hot spots PV systems by mining geometric features high-dimensional data. RM-based combines properties of manifolds detection. In addition, it also provides information about severity spots. has three main advantages:
1) is capable actively learning characteristics...

A cross-layer adaptive resource allocation algorithm of multi-user MIMO OFDM systems is proposed and simulated. The aim to maximize the transmit rate under constraints fixed power QoS. exploits fair wait time each user allocate subcarriers whose standard spatial subchannel SNR best, bits subchannels. Simulation results show that can satisfy QoS user, total be increased significantly.

Relevance Vector Machine (RVM) is one of the `state-of-the-art' approaches for classification which exploits probabilistic Bayesian learning frame work. Compared with classical Support (SVM), RVM avoids problem parameter setting while and offers outputs. These make more suitable real applications. In this paper, we have employed DDAG approach to extend into a multi-classifier enables its recognition different faulty patterns, further makes fault location feasible. conventional methods, The...